Band 14, Heft 1

This article demonstrates the behavior of generalized ( ψ , φ \psi ,\varphi )-type contraction mappings involving expressions of rational-type in the context of super-metric spaces. In this direction, we obtained unique and common fixed point results for a pair of mappings. The obtained results are then utilized to establish some corollaries. Moreover, numerical examples and applications related to the system of integral inclusions and fractal fractional partial differential equations have been presented to validate the established results. The central objective of this research is to provide a more comprehensive framework for generalizing classical results in the context of super-metric space.

Ultrasound imaging stands as a cornerstone of modern medical diagnostics, revolutionising clinical practice with its non-invasive, real-time visualisation of internal structures. Central to this technique is the propagation of ultrasound waves and their intricate interplay with biological tissues, culminating in the generation of intricate and detailed images. This study delves into the symbiotic relationship between solitons and ultrasound imaging within the framework of the Westervelt equation, a fundamental model governing ultrasound propagation. Employing the generalised Riccati equation mapping method and the generalised exponential rational function method, a diverse array of soliton solutions is elucidated, encompassing dark, kink, combined dark–bright, combined dark-singular, periodic singular, and singular solitons. Visualisation of these solutions through 3D plots, contour plots, and 2D plots at varying time intervals offers a captivating insight into their dynamic nature. We provide a comparison of these solutions through 2D plots at different parameter values, highlighting their varying impacts. Central to this study is the exploration of how these soliton solutions can be harnessed to enhance the quality and accuracy of ultrasound images in medical imaging. Through meticulous analysis of their characteristics, this research seeks to illuminate their potential applications, paving the way for a new era of precision diagnostics in healthcare. By conducting thorough mathematical analyses and numerical simulations, we seek to elucidate the complex relationship between soliton theory and ultrasound imaging, connecting the theoretical aspects of nonlinear wave phenomena with their practical applications in medical diagnostics. An intensive literature review underscores the novelty of our work.

This research introduces a novel and robust numerical approach, the stochastic improved Simpson Method, specifically developed to solve Itô and Stratonovich stochastic nonlinear system of differential equations with fractional order. By extending the classical Simpson’s one-third rule with the explicit product integration rectangle rule, the proposed method efficiently handles fractional derivatives of orders between 0 and 1, based on the Caputo derivative. The novelty of this approach lies in its enhanced accuracy and stability in addressing the unique challenges posed by both Itô and Stratonovich systems, outperforming traditional numerical techniques. Rigorous order analysis, conducted with Mathematica 12 software, demonstrates the robustness and precision of the method. Its effectiveness is further validated through four distinct numerical case studies, highlighting its superior performance in solving stochastic nonlinear system of differential equations with fractional order.

The Akbota equation (AE), as a Heisenberg ferromagnetic-type equation, can be extremely valuable in the study of curve and surface geometry. In this study, we employ the well-known two analytical techniques, the modified Khater method and the new sub-equation approach, to construct the solitary wave solution of AE. Transform the partial differential equation into an ordinary differential equation using the wave transformation. The graphical visualization of select wave solutions is carried out using Wolfram Mathematica software. By utilizing appropriate parametric values across various wave velocities, this process unveils the intricate internal structures and provides a comprehensive understanding of wave behavior. The visual representations are rendered in 3D, 2D, and contour surfaces, capturing a range of solitonic phenomena. These include multiple kink solitons, flat kink, kink-peakon, kink solitons, and singular kink solitons, offering detailed insights into the complex dynamics of the system under study. Newly obtained soliton solutions are compared with available soliton solutions in the literature. The new results indicate that these obtained solutions can be a part of completing the family of solutions, and the considered methods are effective, simple, and easy to use. For qualitative assessment, convert the ordinary differential into a dynamical system by using the Galilean transformation to conduct the sensitivity visualization and bifurcation assessment along with phase portraits and chaos analysis of the considered model. Bifurcation analysis is crucial in soliton dynamics, as it influences the behavior and characteristics of solitons in various systems, with the results presented through phase portraits. Sensitivity visualization illustrates how parametric values affect the system’s behavior. The solutions obtained have broad applications in surface geometry and electromagnetism theory. The aim of this study is to enhance the understanding of complex nonlinear dynamics and their relevance in curve and surface geometry.

At present, the detection of surface defects of paper-plastic composite bags still mainly depends on manual visual inspection, which is very inefficient and easy to cause false detection. Based on the algorithm which combines edge detection and adaptive region growth, binary images of the surface defect areas is extracted, six types of shape features and seven types of invariant moment features are defined by calculation as the basis to complete the effective extraction of the surface features, then a paper-plastic composite bags surface defect detection platform is built to complete the defect detection experiment, the defect screening experiment was completed by the rapid screening method of its surface defect image based on gradient projection difference. At the same time, based on Genetic Algorithm (GA), Particle Swarm Optimization, and Grey Wolf Optimization, parameter optimization models of Support Vector Machine were established, respectively. Through experimental comparison, some results show that the defect detection and classification accuracy rate reach 96.83% based on the GA, and the detection speed with the screening method is 3.75 times faster than that without the screening method. Therefore, the reliability of the image classification and screening method for bags surface defects proposed in this study is verified.

Petroleum products are vital to the country’s economy and are transported by pipelines. The main goal of this article is to investigate one of the components of crude oil, sulphur, and examine the impact on carbon steel pipes (API 5L [X60, X46, and X42] and A106 pipe) and demonstrate how sulphur content affects various types of API 5L XL independently from the other significant factors present in the crude oil. The sulphur has a huge impact on the mechanical characteristics and corrosion resistance of petroleum pipelines. We found that an increase in the sulphur content led to an increase in the corrosion rate (CR) and decreased the mechanical properties. It has been shown that the safest and most economical way to transport crude oil is through pipeline networks for gas and oil. Internal and external corrosions are the primary problems with API 5L and other steel pipelines used in the transportation of oil and gas. The TR-TCXRF (X-ray Fluorescence Sulphur Tester) instrument is used in this study to determine the sulphur content of crude oil. Using weight loss and the Tafel extrapolation method, the CR, corrosion potential, and corrosion current of carbon steel pipes A106 and API 5L (X60, X46, and X42) in four immersion solutions were calculated. Using an optical microscope, scanning electron microscope, and energy dispersive spectroscopy (EDS), the products of corrosion were iron sulphate (Fe 2 SO 4 ) and iron sulphide (FeS), and iron oxide (Fe 2 O 3 ); the corrosion properties of the samples were measured morphologically. The results showed that the pipeline CR significantly increases with increasing concentration of sulphur content. X60 pipe was more resistant to corrosion than X46 and X42 in API 5L-type pipes.

In this investigation, we delve into the recovery of quiescent optical solitons amidst the onset of nonlinear chromatic dispersion (CD), employing the complex Ginzburg–Landau equation. Quiescent optical solitons, self-sustaining, locally distributed wave packets, uphold their shape and amplitude over extensive distances through a delicate equilibrium of nonlinearity and dispersion. Our scrutiny extends to four distinct forms of self-phase modulation structures, wherein we adopt the ( 1 ϑ ( ζ ) , ϑ ′ ( ζ ) ϑ ( ζ ) ) \left(\frac{1}{{\vartheta }\left(\zeta )},\frac{{{\vartheta }}^{^{\prime} }\left(\zeta )}{{\vartheta }\left(\zeta )}) method, yielding solutions in hyperbolic function forms. This research meticulously examines the specific parametric constraints influencing the soliton presence, enhancing comprehension of the erratic behaviour by nonlinear waves and dynamic systems. Through vivid graphical representations, we provide insights into solution variations and their characteristics. These findings warn electronics and telecommunication engineers that nonlinear CD could halt global internet connectivity by preventing soliton transmission across borders. Hence, the imperative lies in preserving linear CD during transmission to avert such dire consequences. Furthermore, our study propels future research prospects, as we intend to substitute nonlinear CD with nonlinear cubic–quartic dispersive terms, expecting further discoveries to disseminate subsequently.

In this article, we present an accurate semi-analytical solution for fractional-order logistic equations across a wider domain. We accomplish this by deriving successive approximate solutions using a modified perturbation iteration approach tailored for fractional nonlinear differential equations. This method is also effective in addressing the cubic fractional logistic model and the Allee fractional logistic model. We provide several numerical examples to demonstrate that the perturbation iteration approach not only yields accurate approximations but also performs well across a wider domain.

In its first part, this article develops a variational formulation for the incompressible Euler system in fluid mechanics. The results are based on standard tools of calculus of variations and constrained optimization. In a second step, we present a variational formulation for a compressible Euler system in fluid mechanics assuming an approximately constant scalar field of temperature. We emphasize to obtain both the equations of Euler and Bernoulli as a single system of necessary conditions for a stationary point for the variational formulation in question. In the subsequent sections, we also present a variational formulation for a Navier–Stokes system in fluid mechanics. Finally, in the last section, we develop a duality principle applied to a Ginzburg–Landau-type equation.

The demand of the current industrial applications to high power generation results in a further increase in the rotating machinery speed which in itself may cause unstable oscillations. Unbalanced excitation and shaft deviation represent significant challenges that are faced by the designers and operators of the rotor-bearing systems, which negatively affects the general system performance. This work investigates the rotor response to an unbalanced load for a range of bearing ratios. The influence of using a bearing with a variable profile on the characteristics of the system is also investigated. Five bearing’s length-to-diameter ratios are considered in the analysis to examine the generality of the results using different profile parameters. The finite difference method is used in the numerical solution and a 3D deviation model is incorporated in the analysis. The rotor response is obtained by using the fourth-order Runge-Kutta method. Results show that the journal-bearing performance can be improved significantly for the whole considered range of the length-to-diameter ratio by adopting the relevant combination of the design parameters for each ratio. The levels of friction and maximum pressure at deviation levels of 0.52 and L / D = 1 are reduced by 7.02 and 26.9%, respectively, and similar trends have been obtained for the other bearing ratios. More importantly, the lubricant thickness level is enhanced to a large extent as a result of using the variable bearing profile despite the presence of large shaft deviations. This important outcome maintains a safe system operation under extreme operating conditions.

The poultry industry faces numerous obstacles in maintaining the health and well-being of the chicken population due to the widespread occurrence of various diseases. Early detection and timely intervention are crucial to prevent diseases and minimize losses. The advocate solution is the need of the hour to cater to the discussed challenges. Therefore, the authors proposed a novel method called “DeepFowl.” A modified DenseNet169 deep learning-based model has been utilized by DeepFowl to diagnose diseases by analyzing the images of chicken excreta. The DeepFowl method, enhanced by a proposed data oversampling algorithm, has improved disease recognition accuracy in chickens from 96.3 to 98.4%. The model’s performance was evaluated across metrics such as accuracy, recall, precision, and F 1-score, consistently achieving a high value of 98.4%. This demonstrates its effectiveness in early disease detection among chickens. Additionally, DeepFowl supports several sustainable development goals (SDGs): SDG2 (food security and sustainable agriculture), SDG3 (public health), and SDG9 (innovation).

In this report, a theoretical study is directed at the cilia motion of the Ellis fluid model due to the propagation of an infinite metachronal wave train traveling along the walls of the channel due to the continuous beating of the cilia. The governing equations of continuity and equation of motion for the well-known Ellis fluid model are carried out by taking long-wavelength approximations. The equations were solved with the help of the computational software Mathematica 13.0, and the results were obtained. The influence of physical parameters on pressure rise ( ∆ p \triangle p ), axial velocity u ( x , y ) u(x\left,y) , and stream function ψ ( x , y ) \psi (x,y) are exhibited graphically and discussed briefly. It is observed from graphical results that the velocity field shows a parabolic nature, achieves its highest magnitudes at the mid of the channel, and then reduces drastically at the walls of the channel. Velocity reduces with increasing material constant α and rises with increasing material constant β . It is also noted that pressure increases with rising α \alpha and β \beta . The present inquiry is also valid in the treatment of different symptomatic problems and different medicament delivery methods in pharmacological and biomedical engineering.

The purpose of this work is to construct and evaluate a dynamical susceptible–vaccinated–infected–recovered model for the propagation of the varicella virus in Jordan using existing epidemiological data. We use the fractal–fractional derivative in the Caputo sense to investigate the dynamical aspects of the suggested model. We investigate the model’s equilibria and evaluate the threshold parameter known as the reproductive number. A sensitivity analysis is also performed to detect the uncertainty of infection. Fixed point theorems and Arzela–Ascoli concepts are used to prove positivity, boundedness, existence, and uniqueness. The stability of the fractal–fractional model is examined in terms of Ulam–Hyers and generalized Ulam–Hyers types. Finally, using a two-step Newton polynomial technique, numerical simulations of the effects of various parameters on infection are used to explore the impact of the fractional operator on different conditions and population data. Chaos analysis and error analysis revealed the accuracy and precessions of solutions in the viable range. Several findings have been discussed by considering various fractal dimensions and arbitrary order. Overall, this study advances our understanding of disease progression and recurrence by establishing a mathematical model that can be used to replicate and evaluate varicella virus model behavior.

In robotic welding systems, weldment recognition and pose estimation play crucial roles in achieving precision and efficiency. Weldment recognition involves identifying and classifying different types of weld joints and components with high accuracy, often employing computer vision techniques and machine learning algorithms trained on diverse datasets. Concurrently, pose estimation determines the precise position and orientation of the welding torch relative to the weldment, which is crucial for ensuring proper alignment and execution of welding tasks. Hence, this study proposed a multi-point entropy estimation (MPEE) model for the pose estimation. The proposed MPEE model computes the multi-point in the weldment design with the data-driven model for the estimation of the welding points. The MPEE model estimates the multi-point in the weldment design and the estimation of the features. With the estimated points in the Weldmart, entropy points are tracked and estimated for fault estimation and fault detection. Through the data-driven approach, machine learning model is employed for the recognition and estimation of weldment with the robotics. The proposed MPEE model specifically addresses the challenge of pose estimation in welding tasks. The MPEE model focuses on estimating the position and orientation of multiple points within the weldment design. By leveraging a data-driven approach, which integrates machine learning models, the MPEE model enhances the accuracy and reliability of welding point estimation. The results stated that in a dataset comprising diverse weld joint variations, the system achieves a recognition accuracy of over 95% in real-time applications. Concurrently, employing geometric hashing and iterative closest point algorithms enables precise pose estimation of the welding torch with an average error margin of less than 1 mm.

In this study, we discussed the effect of Hall current and electric field on heat transfer and fluid flow between non-uniformly heated parallel vertical plates when fluid is presumed in transverse magnetic and electric fields. A numerical solution of dimensionless partial differential equations governing the flow is derived via the implicit Crank–Nicolson technique. The numerically calculated solutions are presented graphically and these graphical results examine the primary velocity, secondary velocity, and the temperature profiles for various physical parameters. The average values of skin friction and the Nusselt number are provided in tabular form. A significant result of our findings is that the rising values of E 1 {E}_{1} boost flow velocities and raises the temperature profile. These effects are important for fluid flow and heat transfer, making effective control and regulation essential.

In the present era of cutting-edge technologies powering electronic devices, energy systems, and modern telecommunication, a mathematical model called the telegraph equation plays a major role. It describes the wave propagation and diffusion processes in a variety of scientific and engineering areas. This work investigates, applies, and compares two semi analytical methods, namely, reduced fractional differential transform method and the Laplace-transformed residual power series method, toward solving the two-dimensional time-fractional telegraph equation. In the recent past, both the methods have been used to solve various linear and non-linear, ordinary, partial, and fractional differential equations. The literature speaks highly about residual power series method being efficient, specially for the non-linear problems. This work puts forth the methodologies and numerical experiments, and it can be observed that both methods result in the same solution for the two-dimensional linear telegraph equation. However, the solutions for the non-linear telegraph equation are better with the differential transform method.

Optical solitons have practical applications in communication systems as carriers of optical information. An advantage of an optical soliton is its ability to maintain its structure unchanged when interacting with other pulses. The purpose of this article is to strive for the optical soliton solutions of the nonlinear Schrödinger–Hirota equation incorporating chromatic dispersion, which is a governing model for understanding the dynamics of dispersive pulse propagation in optical fibers. Three distinct methodologies, namely, the 1 φ ( η ) , φ ′ ( η ) φ ( η ) \left(\phantom{\rule[-0.75em]{}{0ex}},\frac{1}{\varphi \left(\eta )},\frac{\varphi ^{\prime} \left(\eta )}{\varphi \left(\eta )}\right) method, the new Kudryashov method, and the extended simple equation method, have been employed to derive solutions for this equation. Numerous optical soliton solutions including singular soliton, dark soliton, bright soliton, periodic singular soliton, dark–bright soliton, and dark-singular solution and singular periodic solutions are offered by this method. These techniques present an accurate and successful strategy for deriving exact solutions to various nonlinear partial differential equations. Graphical representations of some of the extracted solutions are shown to demonstrate the behavior of solitons. We also presented the eye diagram for the depiction of the signal to provide a clear visualization of the pulse shapes and their characteristics. The optical solitons produced in respect to this form have never been explored by the proposed techniques before, and the results have never been published. In this study, we perform a comprehensive perturbation analysis to explore the stability and dynamics of soliton solutions within the Schrödinger–Hirota equation.

The study examines the laminar two-dimensional flow with heat and mass transfer of Jeffrey fluid having thermal radiation and heat source–sink effects past a linearly inclined vertical stretched sheet under Stefan blowing. The impact of a magnetic dipole is also examined on two different thermal processes: prescribed surface temperature (PST) and prescribed heat flux (PHF). Furthermore, the Darcy–Forchheimer model, mixed convection, Buongiorno fluid model, and slip conditions are incorporated to enhance these thermal and concentration characteristics. With their unique combination of liquid and magnetic properties, ferromagnetic fluids are useful in a variety of scientific and industrial fields. The purpose of this study is to investigate how viscous dissipation, Soret and Dufour effects, and a magnetic dipole affect fluid flow, heat transfer, and concentration transfers in Jeffrey fluid over an inclined vertical stretching surface. For the concentration profile, the rheological model (a system of partial differential equations) incorporates partial slip effects, thermophoresis, and Brownian motion effects. Using similarity transformations, the model equations are transformed into coupled nonlinear ordinary differential equations. The BVP4C method is employed to obtain solutions to the fluid’s velocity, temperature, and concentration profiles. Various parameters are analyzed to determine their influence, with effects represented in tables and graphs for both PST and PHF thermal processes. Results for specific cases are compared with previously published results, showing good agreement. Thermal radiation increases the temperature for PHF processes, while the magnetic dipole reduces the fluid’s velocity and increases the temperature for PST.

The Konopelchenko–Dubrovsky–Kaup–Kupershmidt system has significant implications in various fields, including fluid mechanics, ocean dynamics, and plasma physics. This system includes various widely recognized nonlinear evolution equations as special cases. In this study, we present a systematic approach to identifying novel wave solutions to the system, examining various combinations of interactions between lumps, stripes, double stripes, and periodic waves. By strategically selecting the arbitrary free parameters, we incorporate various 2D and 3D profiles to clearly demonstrate the dynamic behaviors of the mixed localized wave structures. These graphical representations indicate that some of the identified solutions exhibit periodic wave propagation along a straight line at specific angles to the spatial axes, maintaining constant wavelengths, amplitudes, and velocities. The solutions proposed in this study provide valuable insights into the mechanisms of wave propagation across diverse physical domains. Furthermore, the approach outlined herein is versatile and can be applied to various nonlinear differential equations in mathematical physics.

Tuberculosis (TB) and human immunodeficiency virus (HIV)/acquired immunodeficiency virus (AIDS) have a fatal bidirectional connection with a significant global epidemic overlap. People living with HIV-positive are over 30 times more likely than HIV-negative people to develop TB and active TB causes the chronic immunological activation, which accelerates HIV/AIDS disease development. This gives computational investigation of a TB and HIV/AIDS co-infection in fuzzy environment. The application of fuzzy theory aids in addressing the difficulties associated with measuring uncertainty in mathematical representations of the diseases. Here, the fuzzy reproduction number and fuzzy equilibrium points are obtained by using a model relevant to a specific group described by the triangular membership function. Two numerical techniques, namely, forward Euler’s method and Runge–Kutta method, are developed within a fuzzy framework to address the model. We have also employed the non-standard finite difference scheme, which ensures the preservation of the essential properties such as positivity, convergence, and consistency. Numerical simulations are also conducted to illustrate the applicability of the developed technique.

In this article, we present an algorithm to determine the authenticity of a signature with high probability. This study addresses the increasing need for robust and accurate methods of verifying offline signatures, which are crucial in various legal and financial contexts. By combining geometric properties of curves and advanced image processing techniques, our approach effectively distinguishes between genuine and forged signatures. The core of our method utilizes multiple knot B-splines in approximation theory, mean curvature analysis, and curve fitting, providing a comprehensive framework for signature verification. Our findings demonstrate a significant improvement in accuracy over existing methods, as validated by several empirical examples. This research not only contributes to the field of signature verification but also opens avenues for future studies to enhance and adapt our algorithm for broader applications in security and authentication systems.

Sensitivity evaluation of nonlinear systems to system parameters is critically important in nonlinear dynamics, though current focuses in the field are mainly on the sensitive dependence of nonlinear systems upon initial conditions. The present research intends to develop an approach for quantitatively measuring the sensitivity of nonlinear dynamic systems to system parameters. A single-value sensitivity index is created via a theoretical approach. Numerical simulations are conducted to demonstrate the reliability and applicability of the index in quantifying and analyzing the system parameter-dependent sensitivity for nonlinear systems. With the implementation of the sensitivity index, a diagram illustrating the sensitive and insensitive regions and degree of sensitivity over a large range of system parameters is constructed for a typical nonlinear dynamic system. The sensitivity index developed shows effectiveness and convenience in quantitatively evaluating and analyzing the parameter-dependent sensitivity for nonlinear systems. The results of the research show that chaos and quasi-periodicity of a nonlinear system are sensitive to the system’s parameters, independent of its sensitivities to initial conditions. Based on the proposed method, region diagrams regarding to different parameters are presented, which may help to avoid high sensitivity parameter values such as stiffness, mass and damping values in the design of mechanical systems.

This work studies the chaotic behaviors and solitary wave propagations for the M-fractional longitudinal wave equation (M-fLWE). Here, we explain some assertions of the M-fractional derivative. Initially, we employ bifurcation theory to examine the chaotic behaviors that arise from the incorporation of diverse perturbation terms. We depict the phase portraits using three-dimensional (3D) and two-dimensional (2D) representations, Poincaré diagrams, and time-series plots. Furthermore, we utilize an enhanced modified F-expansion method to examine ion acoustic waves in the fLWE. The derived solutions manifest as trigonometric, exponential, and hyperbolic functions. In the numerical discussion, we present novel phenomena not observed in previous studies. For particular values of the free parameters, we discern luminous and obscure bell-shaped waves, periodic waves, periodic bell-shaped rogue waves, periodic rogue waves featuring singular solitons, periodic rogue waves, and interactions between periodic rogue waves and kink-shaped formations. Additionally, we juxtapose our results with the current literature to emphasize unique attributes in 2D, 3D, and density-based representations. This research provides significant insights into the intricate behaviors and varied waveforms of the governing model via a thorough investigation. This study enhances the comprehension of real-world physical phenomena through the examination of waveform attributes, bifurcation analysis, chaotic dynamics, and solitary waves.

Throughout global history, the population has faced unprecedented challenges due to infectious spreads. Addressing the need to mitigate these infections requires well-directed and comprehensive efforts. Sexually transmitted infections, including syphilis, remain significant global health concerns affecting both developed and developing nations. Syphilis, resulting from the transmission of the Treponema pallidum bacterium through sexual contact, is estimated to affect around 12 million individuals annually worldwide. The objectives are achieved by launching the syphilis model, dividing the entire population into six compartments. Additionally, an ideal control plan is presented that integrates the most practicable medical measures to lower the quantity of afflicted persons encapsulate the dynamics of the prevailing degree of syphilis in a population. The devised model is validated by verifying essential features such as positivity, invariant region, and equilibrium points of the point for feasibility of solutions. This investigation focuses on examining the local stability of the syphilis model with a specific emphasis on considering limited observations a critical aspect of epidemic models. The reproductive number R 0 {R}_{0} has been calculated to evaluate its impact across various sub-compartments playing a pivotal role in determining community-wide transmission rates. A sensitivity analysis of the models parameters has been performed. To gain numerical solutions, the advanced and well-established numerical technique nonstandard finite difference is employed to provide insights into the genuine behavior of the model. Additionally, to assist in achieving the fundamental aim of this research, an optimal control strategy is induced by considering control variables, namely, an educational awareness campaign and treatment protocols intended to reduce the prevalence of infected individuals. The purposes are attained by employing the Pontryagin maximum principle through mathematically and modeling.

Examining the deflection properties while designing and analyzing structural elements offers important information about working of visco-thermoelastic plates in microelectromechanical systems, sensors, and flexible electronic systems. The aim of the current study is to increase the stability and durability in heat-sensitive situations. This study focuses on the transverse deflection in a homogeneous, isotropic, visco-thermoelastic rectangular plate under the influence of uniform loading. The edges of plate are considered at different boundary conditions. Boundary conditions can either involve all edges being simply supported or keeping them simply supported and clamped alternatively. The deflection analysis utilizes the Laplace transform and Finite Fourier sine transform. Inverse Laplace transform is resolved using residue method. MATLAB software aids numerical computation of deflection expression post-Inverse Laplace Transform. Graphical analysis explores the diverse boundary conditions across different modes. The variation in deflection has been studied in the plate under varied circumstances. The findings provide useful insights for engineering applications involving thermal and mechanical stability and advance theoretical and computational understanding of deflection dynamics in visco-thermoelastic rectangular plates under uniform loads.

This article proposes a potential-light-smoker-quit smoker smoking model by incorporating the infection and quitting behavior of occasional smokers. Theoretical analysis shows that the reproduction number R 0 {{\mathscr{R}}}_{0} serves as a threshold parameter: smoking is eradicated when R 0 ≤ 1 {{\mathscr{R}}}_{0}\le 1 , but becomes endemic when R 0 > 1 {{\mathscr{R}}}_{0}\gt 1 . Numerical simulations confirm these findings. The impact of parameters on R 0 {{\mathscr{R}}}_{0} implies that effective control measures require a reduction in transmission and conversion rates, as well as an increase in quit rates. Sensitivity analysis further demonstrates that decreasing transmission and conversion rates significantly reduce the peak of smokers, whereas increasing quit rates delay the onset of this peak. Optimal control strategies identify three key interventions: creating smoke-free environments, conducting smoking hazard education campaigns, and offering treatment for chain smokers, which can effectively curb the prevalence level of smoking behavior.

This article presents a study of a rotating hybrid nanofluid flow in a porous medium past a stretching surface using an overlapping grid multi-domain bivariate spectral simple iteration method (OMD-BSSIM). The objective is to appraise the performance of the OMD-BSSIM on a system of nonlinear partial differential equations that describe the unsteady flow of a hybrid nanofluid composed of copper and aluminum oxide nanoparticles in water. Additionally, the study aims to evaluate the impact of different fluid and surface parameters on the behavior of the hybrid nanofluid. The improved OMD-BSSIM algorithm is implemented in MATLAB and tested for its convergence and accuracy. The results are compared with previously published findings that were obtained using the overlapping spectral local linearization method and the bivariate spectral relaxation method. The study explores the use of R line graphs as a visualization tool to identify patterns and relationships among the skin friction coefficients, local Nusselt number, and local Sherwood number of the hybrid nanofluid and parameters over time. The findings reveal several key trends and patterns, such as the positive correlation between the shrinking ratio parameter and the skin friction coefficient and the positive relationship between increasing the rotation parameter and an inverse relationship between an increase in the alumina volume fraction coefficient and the local Nusselt number of the hybrid nanofluid. This article provides valuable insights into the flow behavior of hybrid nanofluids and highlights the potential of alumina nanoparticles as a tool for enhancing the thermal and mechanical properties of the fluid.

The traditional fabric colour matching process has problems such as long cycle, low efficiency, and high cost. To address these limitations and improve the accuracy of fabric brightness prediction, this research combines the theory of light and shadow reconstruction of layered images, multiple regression (MR) prediction, and a neural network to build a fabric brightness regression prediction model. The primary objectives include enhancing the visual representation of fabric colours and establishing a high-precision predictive framework. First, the layering process of the fabric image was determined by the light and shadow reconstruction method, and then a series of factors affecting the brightness value were set as independent variables and the brightness value as the dependent variable on the basis of the layered image by combining the MR model to build the brightness prediction model. Finally, the prediction model was optimised by incorporating a backpropagation neural network. This hybrid method ensures interpretability and nonlinear adaptability through MR prediction and neural networks. Testing the model performance, it is found that the final fabric brightness regression prediction model has better prediction performance, and its error performance is better than that of the traditional multivariate regression model. In practical applications, the proposed model can obtain 95.3 user satisfaction and 97.8 merchant satisfaction, and the difference between its predicted and actual brightness values is within 3°. These results demonstrate the model’s potential for industrial adoption in digital textile design. Future research will extend the model to dynamic lighting conditions and multi-material fabric interactions.

The gemini virus, a major obstacle to red chili production, is exacerbated by yellow virus propagation. This study explores the potential of an epidemic model using generalized fractal fractional operators to observe dynamics and develop prevention strategies to control infections. The fractional-ordering system is analyzed quantitatively and qualitatively, including positiveness, boundedness, unique solution, and reproductive analysis under equilibrium points to ensure bounded and positive solutions. The proposed model’s uniqueness is demonstrated through global effects analysis using Lipschitz and linear growth techniques, and local and global stability was assessed using the Lyapunov function and the first derivative test. The study utilizes a two-level Lagrange polynomial, specifically the Mittag–Leffler kernel, to explore the impact of fractional operators on plant diseases. The fractional-order model’s behavior is verified through numerical simulations at disease-free and equilibrium points, and results are compared to demonstrate its efficacy and memory effect. The study visually illustrates the impact of various proposed operators on the proposed red chilli model, providing numerical data for each operator with varying fractional parameters. By comparing non-integer orders to integer orders, we obtain a more comparable result to support its stance. The study found that the fractal fractional operator is more effective than the usual integer order for disease eradication because it efficiently reduces gemini virus infection rates by lowering the fractional-order parameter ϑ {\vartheta } . This study will allow us to develop mitigating techniques for afflicted plants and gain a better understanding of the virus’s behavior.

This study explores the qualitative analysis of D γ h ( ζ ) = ℒ ( ζ , h ( ζ ) , D γ h ( ζ ) ) , \begin{array}{r}{{\mathcal{D}}}^{\gamma }{\mathfrak{h}}\left(\zeta )={\mathcal{ {\mathcal L} }}\left(\zeta ,{\mathfrak{h}}\left(\zeta ),{{\mathcal{D}}}^{\gamma }{\mathfrak{h}}\left(\zeta )),\end{array} where D γ {{\mathcal{D}}}^{\gamma } is a Riemann–Liouville nabla ( ∇ \nabla ) fractional nabla derivative, incorporating integral boundary conditions on arbitrary time scales. We rigorously investigate the existence, uniqueness, and stability of solutions to these equations by employing Krasnoselskii’s fixed point theorem and the Banach contraction principle. The incorporation of integral boundary conditions extends the applicability of the results to more general systems. To demonstrate the validity and practicality of the theoretical results, we present an illustrative example supported by MATLAB-generated graphical representations. This work contributes to the broader understanding of fractional dynamic systems and their stability across diverse time scales, offering insights with potential applications in engineering and applied sciences.

To address the inherent nonlinearity, time-varying dynamics, and disturbance susceptibility of electro-hydraulic position servo systems in high-precision applications like aerospace actuators, this article proposes a fractional-order super-twisting sliding mode active disturbance rejection control (FOSSMC). Incorporating fractional calculus into the integral sliding surface enables the construction of smoother fractional-order sliding mode switching terms. The inherent long-memory property of these operators effectively suppresses low-frequency disturbances, thereby resolving the trade-off dilemma between persistent chattering and rapid convergence inherent to conventional sliding mode control. Crucially, the novel synthesis of fractional-order operators with super-twisting sliding mode control reaching law and active disturbance rejection control framework provides extra tuning freedom (through orders λ 1 , λ 2 ) to simultaneously accelerate convergence and eliminate high-frequency switching artifacts. Simulations demonstrate 37.25% faster rise time (0.32 s), 0.008 mm steady-state error (meeting ISO 4400 Class H precision), 18.37% lower sinusoidal tracking error, and Monte Carlo-validated robustness to ±15% parameter variations – satisfying industrial demands for aerospace actuators and hydraulic stamping machinery.

Within this study, we delve into novel optical solitons concerning the perturbed nonlinear Schrödinger equation, which governs the propagation of electromagnetic waves in magneto-optic waveguides. These components play vital roles in optical transmission lines and lasers, serving critical functions within integrated optical circuits as circulators, modulators, and isolators. Employing the simplest equation method, the 1 φ ( δ ) , φ ′ ( δ ) φ ( δ ) \left(\phantom{\rule[-0.75em]{}{0ex}},\frac{1}{\varphi \left(\delta )},\frac{\varphi ^{\prime} \left(\delta )}{\varphi \left(\delta )}\right) method, and the generalized Riccati equation mapping method, we derive single and multi-optical soliton solutions. Our analysis yields a diverse array of solutions, including multi-soliton, singular, combo bright-dark, periodic singular, bright, and dark optical solitons. Additionally, we discuss the parametric conditions crucial for both the existence and shaping of these solitons. The visual representation of our findings through three-dimensional, two-dimensional, and contour plots elucidates the dynamic phenomena and interprets the physical implications of these solutions using various parameter values. This research demonstrates the efficacy of rational analytical methods in elucidating the intricate dynamics of soliton solutions in nonlinear optical systems, thereby offering valuable insights for further exploration in the fields of physics, mathematics, sciences, and engineering.

In this article, the complex structure of optical soliton solutions of the nonlinear Schrödinger–Bopp–Podolsky system is investigated using the enhanced modified extended tanh-expansion approach. It also analyzes the system’s stability and how it changes by performing a bifurcation analysis. This system holds special importance in nonlinear optics because it describes light-wave behavior when they interact with nonlinear materials. The enhanced modified extended tanh-expansion method serves as a strong analytical method to construct numerous innovative and diverse optical solitons including dark and bright and singular types. The obtained solutions help researchers understand all aspects that influence the nonlinear Schrödinger–Bopp–Podolsky system behavior while providing tools for simulating nonlinear optical processes. The potential for discovering new types of optical soliton solutions specific to the Schrödinger–Bopp–Podolsky system, which may differ from those found in other systems, remains untapped. While the current literature demonstrates the effectiveness of the enhanced modified extended tanh-method in various contexts, its application to the nonlinear Schrödinger–Bopp–Podolsky system could provide new insights and expand the understanding of soliton dynamics in modified nonlinear systems.This study is innovative because it is the first to apply the enhanced modified extended tanh-method to the nonlinear Schrödinger–Bopp–Podolsky system. This approach enables the construction of new soliton solutions and provides a deeper understanding of the nonlinear dynamics of the system. We employed Mathematica and MATLAB together to provide comprehensive, illustrative, and high-quality visualizations of the findings for graphical representation.

In this article, Haar wavelet collocation method is applied for the solution of fourth-order integro-differential equations. Also, a fixed point approach is used to investigate the existence theory of solution to the considered problem. The fourth-order derivative is approximated using Haar function. In addition, third-, second-, and first-order derivatives together with unknown functions are obtained by the process of successive integrations. On applying the Haar collocation method, the suggested problem of IDEs is transformed to a system of algebraic equations. The Gauss elimination scheme is used for the solution of linear algebraic equations. The precision, effectiveness, and convergence of the Haar approach are checked on some test problems. Different collocation and Gauss points are used to determine the absolute and root mean square errors. To demonstrate the applicability of the proposed method, an experimental rate of convergence is calculated, which is almost equal to 2. The method is accurate, easily applicable, and efficient.

The study of silicon-based all-optical wavelength converters (SAOWCs) for on-chip optical interconnect applications holds potential research value and application horizons. The study proposes a SAOWC for on-chip optical interconnect technology. It also designs and optimizes an all-optical wavelength converter based on a quantum dot semiconductor optical amplifier and a Mach-Zönder interferometer in conjunction with photonic integrated circuit technology. The interlayer coupling efficiency is simulated by the finite-difference time-domain method, and the performance of the system is verified in conjunction with experiments. The experimental results showed that the coupling efficiency was as high as 98.44% at 1,550 nm wavelength. The bit error rate (BER) test results showed that the BER rose from 10 −17 to 10 −4 when the pulse width increased from 0.1 to 1.0 ps. Meanwhile, the temperature fluctuation and signal strength degradation tests further validated the stability of the device under different operating conditions. These results demonstrate that the converter has significant potential to enhance data transmission capability. The study provides a valuable reference for further improving and optimizing data transmission over all-optical networks, which is expected to promote scientific advancement and technological applications in this field.

The unmanned double steel wheel vibration roller enhances high-quality unmanned compaction operations by ensuring precise walking control, thus avoiding human error-related issues like under- and over-compaction. However, its complex construction technology, cooperative operation challenges, and high construction quality demands present significant difficulties for unmanned operation. This study addresses the challenges associated with compaction mechanisms and construction technology. It analyzes the interaction between the vibrating roller and the compacted material using the U-K equation to develop a dynamic force model, which leads to a method for determining optimal compaction parameters. Simulations reveal that the compaction speed of the three rollers is approximately 0.3 m/s, and the parameter optimization module performs as anticipated. The simulated pilot roller effectively executes motion planning under various compaction conditions, with an overlap distance of about 0.2 m between adjacent rolling belts after lane changes. This overlap, which is 0.5 times the width of the 0.4 m steel wheel, successfully prevents both under-compaction and over-compaction. A cluster motion planning strategy, based on a pilot-following structure, is proposed for the roller cluster in the compaction area. The strategy includes designing the following roller formation based on the compaction operation range and roller group configuration parameters.

With the rapid growth of motion data, the traditional motion recognition algorithm is faced with the problem of insufficient processing ability. To solve this problem, a method based on gradient descent optimization (GDO)–long short-term memory (LSTM) is proposed to meet the needs of sports action recognition. Based on the experiment of sports data set of students in Hainan University, the experiments of skipping rope, swimming, skating, and shotput were carried out extensively. The total number of experiments were 77, 94, 72, and 85. The experimental results show that the accuracies of GDO-LSTM in sports action recognition were 98.7, 100, 100, and 94.1%, respectively, which was superior to that of the three-axis gyroscope (80.5, 40.4, 23.6, and 100%). These results show that the algorithm can effectively improve the accuracy of sports action recognition and has wide application potential.

This study introduces an enhanced algorithm that integrates transfer convolutional neural networks (CNNs) with radial basis functions (RBFs) to solve the trajectory error problem commonly found in industrial robots. The proposed model utilizes the advanced data mining capabilities of CNNs by combining additional feature extractors and two independent classifiers to support erroneous data analysis. The inclusion of RBFs enhances global accuracy and precision, while mitigating the risk of local convergence. The performance of the proposed algorithm was benchmarked against three other prevalent methods. In 50 iterations, the average accuracy was 85.85% and the F 1 value was 74.3614, demonstrating excellent results. These findings underscore the high applicability and reliability of the proposed method in addressing industrial robot trajectory errors, significantly improving robotic navigation autonomy and intelligence. The results of this study pave the way for future advancements in robot trajectory accuracy and error compensation.

This study introduces a novel approach for forecasting network performance prediction in power grid warehouses, employing a nonlinear Genetic Algorithm (GA)-optimized backpropagation (BP) neural network model. The proposed model integrates the global search capability of GA with the learning efficiency of BP neural networks, thereby addressing the common issue of local optima encountered in traditional BP-based prediction models. The model is designed to capture the intricate dynamics of IoT networks in power grid environments by incorporating multiple critical factors that influence network performance, including signal strength, transmission delay, packet loss rate, and other vital indicators. This comprehensive approach enables the simulation of complex network behaviors, enhancing the model’s predictive accuracy and adaptability. The GA-BP model demonstrates superior performance over conventional BP and other methods, showcasing higher prediction accuracy and faster convergence. In the context of power grid warehouses, the model achieves a remarkable accuracy of 96.7%, an 8% improvement over standard BP. Notably, during peak evening hours from 18:00 to 22:00, when network loads are at their highest, the model maintains a stable prediction accuracy of over 98%, effectively supporting the intelligent management and optimal scheduling of power grid warehouses. To ensure the model’s applicability across various scenarios, the study verifies its scalability and robustness, proving its suitability for IoT systems in power grid warehouses of differing scales and complexities. This comprehensive verification, establish a grid warehouse model that accurately reflects the actual operation logic, and provide decision support for material management and allocation content.

To further enhance the effectiveness of interactive recommendation for intercity social network communication, the study proposes a novel interactive recommendation model for intercity social network communication. This model focuses on point-of-interest preference migration and recommendation modeling by integrating the self-attention mechanism, cross-attention mechanism, and graph neural network. The method effectively solves the problem of cross-city users’ interest point preference change and constructs a recommendation framework based on interest point heat. The experimental results showed that the recommendation accuracy of the new model was up to 93.52%. Compared with the existing more advanced recommendation methods, the recommendation coverage of Chengdu–Chongqing dining and food points of interest could be up to 96.72%. The recommendation coverage of Shanghai–Beijing business and residential and science, education, and culture points of interest could be up to 95.17%, and the maximum time reduction was 2.07 s. The contribution of this study is the introduction of a novel graph attention mechanism, which improves the accuracy and stability of recommendations. This provides an effective technical solution for intercity social network communication recommendations.

To improve people’s communication experience on high-speed trains, this study proposed a time-varying channel prediction (TVCP) method based on an improved polynomial basis extension model and backpropagation neural network. The improved polynomial-basis expansion model proposed in this study extracts the optimal basis function by constructing a channel correlation matrix and performing singular value decomposition to adapt to high-speed mobile channel changes. By using these basis functions and pilot signals to estimate historical basis coefficients as training data for back propagation neural network, future channel states can be predicted to improve the accuracy of TVCP in high-speed mobile communication systems. The results showed that when the training sample of the prediction method was 2,000, the maximum mean square error before improvement was close to 0.01, the maximum after improvement was 4.0 × 10 −4 . After increasing the normalized Doppler frequency shift to 0.5, the mean square error of the improved method was around 0.0001, while other methods were above 0.001. The improvement of the TVCP method effectively reduced the mean square error of TVCP, the prediction accuracy of the improved prediction method was much superior than that of traditional channel prediction methods. The designed method can greatly perfect the prediction accuracy of time-varying channels and enhance people’s communication experience on high-speed trains in high-speed mobile scenarios.

The research aims to solve the problem of data synchronization and redundancy in building information model co-design with blockchain technology. A hyper-ledger fabric federated blockchain, combined with a revolving door compression algorithm, is used for the construction of an intelligent building co-design model. Experiments showed that the method outperformed other blockchain technologies in terms of throughput and response time, with block-out time reduced by 19.31% and transaction throughput increased by 12.38%. The research proposes an innovative cycle division mechanism and utilizes a revolving door compression algorithm for data maintenance of the model, thereby enhancing the security of the design data and the efficiency of collaboration. This is of positive significance for intelligent building design. However, the limitation of the study is that only the blockchain-based model is designed, and further development and example validation are needed in the future.

In the substantial area of the Internet, some websites can be quite harmful and troublesome for both individuals and businesses. Our methods for identifying and forecasting these malicious websites are not always reliable; they can be slow and inaccurate. What if you had technology that could alert you to websites that pose a risk before issues arise? We are attempting to make that a reality. Despite the availability of online resources and additional research, there is a gap in our understanding. The existing approaches are not always the greatest; thus, we need a clear and consistent technique to use smart computers to forecast malicious websites. This makes it difficult for others attempting comparable tasks to compare our findings with theirs. Therefore, the study aims to close this disparity. With the help of an intelligent technology known as the XGBoost classifier and a set of data from the data-rich website Kaggle, we have devised a comprehensive strategy to address the issues identified with the existing methods for identifying and predicting malicious websites. The main objective of this study is to improve upon the current methods for identifying and predicting malicious websites. Our methodology includes data collection, data cleaning, and the application of the XGBoost classifier. To ensure accuracy, we validated our findings with thorough performance evaluations. Our approach achieved an impressive accuracy score of 95.5%, significantly outperforming previous methods. This study not only demonstrates the effectiveness of the XGBoost approach but also provides guidance for other researchers looking to identify and predict malicious websites more accurately, contributing to a safer internet environment.

With the widespread application of smart grids, their economic scheduling and operational decisions need to meet the requirements of large-scale network data and improve the transmission performance of communication resources. Therefore, a distributed network architecture is proposed to analyze the scheduling and management of power systems. A distributed discrete-time optimization algorithm based on communication strategies is applied to analyze the power generation allocation and economic operation of grid nodes. The simulation testing and strategy analysis showed that the distributed optimization algorithm achieved a total output power of 850 MW for the power grid and stabilized the regional electricity load. In the verification of the economic dispatch problem, the total output power of the distributed optimization algorithm reached 13594.87 MW, and the economic cost was reduced by about 23%. The designed method is feasible for economic dispatch, and its contribution lies in using the distributed discrete-time optimization algorithm to provide scientific and reasonable communication strategy solutions for smart grid operation, thereby improving information transmission efficiency and reducing the loss of communication resources. However, the scale and scheduling management of the power grid have not yet been explored. It is necessary to strengthen communication and resource allocation in practical applications.

Sports videos contain a large number of irrelevant backgrounds and static frames, which affect the efficiency and accuracy of temporal action detection. To optimize sports video data processing and temporal action detection, an improved multi-level spatiotemporal transformer network model is proposed. The model first optimizes the initial feature extraction of videos through an unsupervised video data preprocessing model based on deep residual networks. Subsequently, multi-scale features are generated through feature pyramid networks. The global spatiotemporal dependencies of actions are captured by a spatiotemporal encoder. The frame-level self-attention module further extracts keyframes and highlights temporal features, thereby improving detection accuracy. The accuracy of the proposed model was 0.6 at the beginning. After 300 iterations, the accuracy was 0.85. After 500 iterations, the highest accuracy was close to 0.9. The mAP of the improved model on the dataset reached 90.5%, which was higher than the 78.2% of the base model. The recall rate was 92.0%, the precision was 89.5%, and the calculation time was 220 ms. Meanwhile, the model shows balanced performance in detecting movements of different types of sports, especially in recognizing complex movements such as gymnastics and diving. This model effectively improves the efficiency and accuracy of time action detection through the collaborative action of multiple modules, demonstrating good applicability and robustness.

Internet of Things (IoT) and more new technologies have brought great convenience to daily life, but they have also raised more data security and privacy protection. To ensure the security of IoT data and user privacy in various scenarios, the federated learning (FL) method is optimized based on function encryption and blockchain. At the same time, using the decentralized function to encrypt the privacy of the training model, the learning model can provide more secure and reliable services, aiming to solve the problem of large difference in the quality of computing nodes and data privacy leakage in the current FL. The experimental results show that the model accuracy of the optimized system reaches 93%, which is significantly higher than 90% of the traditional centralized model. In addition, the improved approach effectively reduced the risk of data breaches by 1.5%, increased the resistance to attacks by 90%, and increased the user trust by 85%. The average response time of the optimized system is between 5 and 100 milliseconds. When the data dimension is less than 32 and the size of the data terminal group is less than 10, the terminal traffic of the improved FL data protection system is less than that of the other two systems. When the data terminal group was 50, the calculated communication traffic was 19,008 bits, which was an acceptable range for improving the data protection system of FL. Experimental results demonstrate that the improved method can improve the accuracy of the learning model and ensure the efficiency of data processing while protecting user privacy in data sharing.

With the increasing emphasis on environmental protection in various regions, reducing electricity emissions for enterprises has become a popular development trend. The research aims to design a machine learning-based power data warning method to assist enterprises in reducing emissions and controlling costs. In terms of research methods, load type analysis is first conducted for industrial enterprises, followed by the introduction of long short-term memory (LSTM) networks to build a basic model for power data prediction. Support vector machines are used to optimize the model’s large sample requirements, and the two models are integrated to improve accuracy. Key research has found that the proposed model performed excellently. The minimum relative prediction error was 0.20%, the maximum error fluctuation was 0.78%, the accuracy was 12.85% higher than the LSTM model, and the recall was 11.60% higher. On 220 kV, the testing time was 17.5% faster than the data prediction model and 36.0% faster than the multi-task learning model, and the accuracy was always the best. Simulation experiments showed that after data warning, carbon emissions could be reduced by up to 48.26%, and electricity costs could be reduced by up to 60.48%. The machine learning-based power data warning method proposed in this study has important practical application value and can effectively help enterprises achieve emission reduction and cost control goals.

In response to the issues of insufficient clarity and data processing capabilities in the current face model construction process, a method for constructing multi-style face models based on artistic image generation algorithms is proposed. The new method incorporates the image decomposition and normalization model to enhance the algorithm’s ability to process image data. Subsequently, receptive fields, core attention modules, multi-scale attention modules, and dynamic selection attention modules are introduced to enhance the algorithm’s handling of details and model clarity in the process of constructing face data. The research results indicated that the new algorithmic model could improve the data metrics of face models. The incorporation of distinct modules has the potential to enhance various algorithmic metrics. However, the multi-scale attention module emerged as a pivotal component, demonstrating superior stability compared to numerous alternative algorithms. When dealing with face images of different styles, the performance of the new algorithm was better compared to that of other algorithms. Therefore, the new algorithm can enhance the numerical values of face models to a certain extent, improve parameters such as facial texture clarity, and have important research significance in the direction of constructing multi-style face models.

Digital Twin is the way to realize the transformation of smart photovoltaic. According to statistics, in 2021, the annual new scale of distributed photovoltaics in China is about 29 million kilowatts, exceeding 50% of the newly installed photovoltaic power generation capacity, accounting for about 55%, with a strong development momentum. Due to the large investment and complex operational environment of photovoltaic power stations, there is an urgent need for advanced monitoring systems. Due to the consideration of land cost, power stations are usually located in remote areas, which brings a lot of inconvenience to operation and maintenance management. However, with the deep integration of modern information technologies such as Internet, cloud computing, big data, and artificial intelligence with photovoltaic industry, photovoltaic power stations will develop rapidly in the direction of digitalization, intelligence, and information technology, and smart photovoltaic power stations will become the mainstream. In this study, an interactive digital twin monitoring system based on global perception is originally proposed, and the innovation lies in realizing the all-round real-time monitoring and intelligent interactive management of photovoltaic power plants. This study takes digital twinning technology for smart energy system as the research object, focuses on combining the demand for digital twinning technology in smart energy field and then the development direction and application trend of digital twin technology in smart energy industry are prospected. This study comprehensively analyzes the research on the application of interactive digital twin monitoring system in photovoltaic (PV) power plants, and clarifies its key contributions in optimizing operation and maintenance, improving power generation efficiency, and reducing failure rate. This study further explores the adaptive learning mechanism, multi scenario applicability, and integration with other intelligent technologies of the system, which can effectively promote the sustainable development of the PV industry.

Due to the complexity and dynamism of animated scenes, frame prediction in animated videos is a challenging task. In order to improve the playback frame rate of animated videos, an innovative convolutional neural network combined with convolutional gated recursive unit method is used to refine the synthesized stream in frame prediction of animated videos. The obtained results indicated that the average prediction accuracy of the proposed model was 99.64%, and the training effect was good. The peak signal-to-noise ratios on the three datasets were 31.26, 36.63, and 22.15 dB, respectively, and the structural similarities were 0.958, 0.886, and 0.813, respectively. The maximum Learned Perceptual Image Patch Similarity of the proposed model was 0.144. This indicates that the model has achieved excellent performance in prediction accuracy and visual quality, which can successfully capture complex dynamics and fine details in animated scenes. The contribution of this study is to provide a technical support for improving the accuracy of frame prediction in animated videos, which will help promote the intelligent development of the animation production field.

Moderate martial art exercise can enhance physical fitness and promote physical and mental health, but excessive exercise intensity may cause damage to the body. To address this issue, this study adopts the forward maximum matching method and a pre-trained conditional random field model to extract semi-structured and unstructured data to construct a knowledge graph for martial arts intensity assessment. A gated graph neural network is utilized to evaluate exercise intensity and to optimize it through the use of parallel computing. The sampling-optimized model exhibited a 0.13 ms reduction in processing time compared to the second-best model, while the model with an optimized training process demonstrated a 6.7 s reduction after 100 rounds of training, outperforming the second-best model. The evaluation accuracy of the strength evaluation model in the three groups was 81.6, 86.6, and 91.6%, respectively. The average evaluation accuracy of the optimized model was 7.2 and 13.4% higher than other models, respectively. The optimized martial art exercise intensity evaluation model has the potential to significantly reduce time consumption, thereby enhancing overall efficiency. By reducing computation time, the model can improve productivity, responsiveness, and user experience. Furthermore, it can improve evaluation efficiency and accuracy, making martial art exercise intensity evaluation more precise. Ultimately, the model can effectively assist individuals in selecting suitable exercises.

The energy-saving renovation (ESR) of existing residential buildings is regarded as a pivotal strategy to reduce energy consumption and achieve energy-saving and emission-reduction goals. However, there are many difficulties in implementing these ESR projects in practice. In order to address these issues, this study is on the foundation of the characteristics of existing residential building ESR. Through in-depth analysis of functional and cost indicators for evaluating the benefits of ESR, combined with expert research and statistical analysis, a ESR benefit indicator system consisting of two subsystems: function and cost has been constructed. The study selects the best worst-case method with high reliability and simple calculation to determine the weights of various indicators and adopts a fuzzy comprehensive evaluation method to achieve quantitative integration of evaluation information. The ESR benefit evaluation model based on value engineering has been applied to the evaluation of an ESR project in Qingdao. The experimental results show that the value coefficient of the evaluation is 0.991, and the weighted evaluation value of renovation cost is 0.219, which is significantly higher than the weighted value of management cost of 0.178. This fully proves the effectiveness and accuracy of the existing evaluation index system for ESR benefits of residential buildings on the foundation of value engineering. These results have a certain value in the construction project benefit evaluation and can serve as technical references.

In recent years, the development of microgrids has driven the reform of the electricity market, breaking the monopoly of traditional power grids and promoting the healthy development of the electricity market. However, the stability of microgrids is significantly impacted by the integration of various energy sources and numerous users. This study explores the application of an intelligent dynamic programming algorithm based on the deep neural network algorithm, combined with adaptive dynamic programming. Subsequently, an intelligent real-time power generation control algorithm (IRPGC) is obtained by introducing rejection operation improvement. Finally, a real-time integrated scheduling and control framework for microgrids is constructed. The research results showed that the IRPGC algorithm had an average error of less than 10 −5 after 5,000 iterations. Compared with mainstream algorithms, this algorithm achieved favorable results in frequency deviation evaluation indicators, with a frequency deviation fluctuation range of −0.073 to 0.013 Hz, an average error integral of 51.45, an absolute error integral of 0.54, and a time-weighted absolute error integral of 1.58 × 10 5 . In the practical application of real-time microgrid power generation scheduling and control framework, the optimal rejection threshold range was found to be [0.94, 0.97]. The aforementioned results indicate that the proposed method exhibits good control performance and application effectiveness, providing a reference for real-time power generation scheduling and control in microgrids.

Vine robots represent a novel class of soft robots that achieve mobility through tip extension, a mechanism inspired by the natural growth processes of vine plants. This unique movement strategy enables effective navigation in constrained and cluttered environments, offering significant advantages over conventional robotic systems. However, the continuum nature and inherent compliance of vine robots introduce complex modeling and control challenges. Deep learning offer a powerful alternative for modeling systems with such complex dynamics. In this article, we present a data-driven dynamic model for a pressure-driven everting vine robot, utilizing a deep neural network (DNN)-based discrete-time dynamic model. This model was integrated into a model predictive control (MPC) framework, and a comparative analysis was conducted against the MPC framework using a nonlinear first-principle model of the vine robot. The results demonstrate that the DNN-MPC framework offers a better control performance and significantly improved computational efficiency compared to the MPC based on the nonlinear first-principles model. The DNN-MPC reduced computation time by a factor of 11, making it highly viable for real-time control applications.

Mechanical optimization refers to the use of advanced mechanical equipment and physical processes to optimize raw materials, products, etc. , in production, reduce energy consumption, and improve production efficiency and product quality. In the cloud manufacturing mode of manufacturing enterprises, the design of mechanical products requires server optimization based on the demand side. The existing server optimization algorithms are not intelligent enough for server discovery and optimization in this mode. A mechanical product design service and manufacturing method based on convolutional neural network and server discovery and optimization architecture is proposed, which combines deep learning and optimal path algorithm to select better mechanical product services. Research outcomes showed that the training accuracy and testing accuracy of the research network were 98.89 and 96.88%, respectively, with training loss and testing loss of 0.04619 and 0.08921, respectively. In contrast, the training accuracy and testing accuracy of the comparative network were 93.95 and 85.31%, respectively, with training loss and testing loss of 0.3556 and 0.4872. The running time of the two neural networks is 105 and 73 min, respectively. Overall, the accuracy of the research network is high, and the loss is small. The training accuracy and loss of the new activation function proposed in the study have always been superior to other functions. The path and running time of the server optimization path algorithm have better performance. It can be seen that the research proposed methods have good performance and advantages in mechanical product design services and optimization, which can provide technical references and directions for the development of manufacturing service-oriented enterprises in cloud manufacturing mode.

Ancient architecture in Tibet has attracted considerable research attention because of its historical, religious, and artistic significance. Because the design and construction of ancient buildings often do not have the same detailed documentation as modern buildings, it is difficult to accurately simulate their structural properties. To study the structural performance of ancient buildings, the Tibetan ancient architecture structural performance analysis method based on finite element analysis is proposed. To better reflect the actual situation of engineering, the genetic algorithm is introduced to fine-tune the finite element calculation. The results of the experiments showed that the column compressive strain was maximum at 700 με \text{με} . Moreover, the plastic strain occurred only when the compressive strain reached more than 1,900, so the column was in the elastic strain stage during the process. When subjected to a vertical load, the upper part of the beam was compressed and the lower part was stretched. Furthermore, the lower part of the bow wood was stressed, and the upper part was stretched. The proposed method effectively improves the accuracy of the structural performance analysis of ancient buildings, and the results can be used for reference in ancient buildings.

At present, big data and mining technology has been more and more applied to urban planning practice. Based on data mining technology and geographic information visualization, this article puts forward a study on the optimization of territorial spatial planning. This article selects the clustering algorithm and decision tree in data mining technology, combines them organically, and puts forward spatial data mining. Cluster analysis is used to conduct spatial cluster analysis of comprehensive spatial data to explore whether there is spatial correlation and large-scale contiguous data in the data; if so, it can realize the purpose of national territorial space division. According to the analysis of the relevant data of land use planning and the characteristics of the business process, the overall design of the land use planning decision support system was carried out. The preliminary effects of land use planning clustering were generated through the usage of the K -central factor clustering algorithm, and the consequences with excessive classification accuracy have been chosen as coaching samples mixed with the baseline of time series. Finally, the K nearest neighbor classification algorithm primarily based on dynamic time warping is used to classify and perceive the city's practical place again. With the useful resource of point of interest data, the remaining city characteristic identification result is obtained. Finally, the simulation analysis shows that the area under curve (AUC) value of seven types of land use is 0.9376 for cultivated land, 0.85442 for forested land, 0.81747 for grassland, 0.8708 for water area, and 0.86672 for rural residential area. The AUC value of other construction land is 0.80346, and the AUC value of urban construction land is 0.9376. In the urban expansion planning project, multi-source data such as land use status data, population distribution data, and economic development data are integrated, and the spatial agglomeration pattern of land use types is found by using the method proposed in this article, so as to provide a reference for rational planning of urban expansion direction.

The traditional fault diagnosis of agricultural sprinkler irrigation machinery and equipment has the disadvantages of low accuracy and time-consuming. To solve these problems, the study designs a machine vision (MV)-based fault diagnosis model for agricultural sprinkler irrigation machinery and equipment. The study first investigates MV in sprinkler irrigation equipment fault diagnosis, then constructs a fault diagnosis model using improved convolutional neural network, and finally compares it with other methods to verify the performance of the model. The results showed that in the Iris dataset, the accuracy of the proposed algorithm was 95.13%, the training accuracy was 0.95, and the recall rate was 89.7%, which were better than the comparison methods. In the mechanical fault diagnosis dataset, the highest accuracy of the proposed model could reach 98.45%. This indicates that the MV model constructed in the study has higher accuracy and efficiency in the fault diagnosis of agricultural sprinkler irrigation mechanical equipment, which provides convenience for maintenance and repair.

The Qingshuitang Bridge is a steel truss arch bridge with a very small side-to-mid span ratio, which cannot be constructed by traditional weight balancing methods and closure techniques. Applying vertical prestress at the edge support point can meet the anti-overturning requirements of cantilever construction. By adopting the hoisting process of each member, taking into account the impact of each member hoisting on the length of the closure section, as well as the effects of construction errors, installation errors, and temperature changes, the length of each member is corrected. Compared to using traditional closure method, this can make the internal forces and line shapes of the bridge closer to the design state.

In the wave of digital transformation, enterprises have an increasing demand for fast and accurate access to financial information. The conventional accounting service model often relies on manual operations, which are not only inefficient but also susceptible to errors. This study aims to design an intelligent accounting question-answering robot based on a large language model and knowledge graph. To build a complete knowledge graph, this study uses the attention mechanism and convolutional neural network to build a connection prediction model and completes the accounting question-answering knowledge graph. After that, the bidirectional gated loop unit is used to improve the large language model so as to further improve the correlation between knowledge and explore potential information. The results denoted that the developed method had a question-answering accuracy of 94.6%, and the answers covered 95.2% of the domain range. The response time was only 120 ms, which was faster than other models and enhanced the user experience. Moreover, the user satisfaction score of Model 1 was 9.2 points. It is expected that the designed bot will be helpful for enterprises to obtain quick financial information and improve accounting service efficiency.

The current resource recycling model has problems such as asymmetric information on recycling topics, distrust, and low efficiency of the actual recycling system. Therefore, a closed-loop supply chain model led by manufacturers is studied and constructed, and manufacturing and retailer blockchain decisions are proposed. At the same time, numerical examples are conducted to verify the model. The results show that both direct and retail sales are proportional to the sensitivity coefficient, and the prices of retail and direct sales using blockchain are lower than those without blockchain, with the former remaining between 800 and 850. When the unit cost of adopting blockchain is 3, there is no intersection between the profits of adopting and not adopting blockchain. The former is always greater than the latter and the gap is becoming larger, with a minimum of 364,655 yuan, which is much higher than the highest value of the latter. The direct and retail sales of the two models decrease as the unit cost of blockchain increases. Among them, retail sales have always been lower than direct sales sales, with the former maintained between 140 and 150 and the latter maintained between 280 and 295. The improvement of service level has led to an increasing trend in wholesale, retail, and direct sales prices. Overall, the manufacturer-led closed-loop supply chain model intuitively displays the changing trends of different variables, and the decisions proposed based on this can effectively guide manufacturers and retailers in the timing of applying blockchain technology.

In modern manufacturing workshops, there are path conflicts and collisions between automated guided vehicles (AGVs), which affect the efficient scheduling efficiency of the workshop. To address this issue, a manufacturing execution system is introduced to optimize resource management and scheduling. This system combines the shortest path algorithm with a hybrid genetic algorithm to develop collision-free driving paths for AGVs. The results showed that after 20 iterations, the adaptability of workpiece transportation remained stable at 100, with an average of 9 workpieces per day for AGV and a completion time of 2,731 min. In addition, there were no vehicle conflicts between 750 and 1,000 min. These findings indicate that the proposed system improves the scheduling flexibility and efficiency of the manufacturing workshop, while minimizing collision risks to the greatest extent possible. Future research can explore extending the system to larger scheduling requirements and consider complex scheduling constraints comprehensively.

With the advancement of technology, virtual reality (VR) offers designers innovative tools and perspectives in modern interior design, enhancing the intuitiveness and efficiency of indoor environment perception and design. This study adopts distance measurement modeling technology to accurately draw the spatial structure of an indoor environment using signal strength indicators and optimize the design solution. An interior design model based on virtual reality and particle swarm optimization backpropagation algorithm is proposed. Experimental results indicated that the proposed algorithm outperformed three other methods, including support vector machines (SVM), achieving the highest detection rate with a sliding window size of 50. Although increasing the length of the sliding window reduced accuracy, it still maintained its highest value at a length of 50. When the distance was less than 5 m, the detection rate exceeded 90%. Although the accuracy decreased with increasing distance, the designed method maintained a relatively high detection rate. Under the joint adaptive strategy, the algorithm achieved a 90% positioning error of 0.82 m, significantly outperforming the other methods and greatly enhancing indoor environmental perception accuracy and efficiency. These findings provide valuable insights for optimizing related technologies. Graphical abstract This article combines the received signal strength indication ranging technology with the particle swarm backpropagation algorithm to propose an indoor environment perception and design model based on virtual reality. The highest detection rate of 95.5% was achieved in the static state, while a detection rate of 90% was maintained in the dynamic state, demonstrating strong robustness. At different distances, the positioning error of the PSO-BP-Adaboost algorithm remains within 0.82 m, indicating its effectiveness and accuracy in real-time indoor positioning. (a) Error changes before applying filtering algorithms. (b) Error changes after applying filtering algorithms.

With the quick advancement of technology, tennis ball-picking robots have been maturely applied. However, currently, automatic tennis ball-picking robots often have low accuracy in positioning. To improve the accuracy of tennis automatic robot positioning, a weighted factor and virtual reference label improved indoor positioning algorithm is proposed, combined with radio frequency identification (RFID) technology. This method is applied to the automatic tennis ball-picking robot and constructs a tennis automatic ball-picking robot model based on improved indoor positioning algorithm and RFID technology. Comparing the effectiveness of the proposed improved algorithm, it was found that the precision and average accuracy of the algorithm were 0.983 and 94.6%, respectively, which were better than the comparison algorithms. In addition, an effectiveness comparison analysis was conducted on the tennis automatic robot model based on this algorithm, and it was found that the positioning effectiveness of the model was significantly better than the comparison model. Moreover, a positioning comparison experiment was conducted on the model, and the results showed that the positioning accuracy of the model was better than that of the comparison model. The above outcomes illustrate that the improved algorithm proposed in the study and the tennis automatic ball-picking robot model based on this algorithm have good practical value, which is conducive to improving the accuracy of the robot’s image target positioning.

To accurately color the clothing of textile enterprises, many scholars have proposed intelligent color-matching models. However, these intelligent color-matching models still have problems with incomplete color-matching functions and low color-matching accuracy. To solve the above problems, this study optimized the convolutional neural network (CNN) algorithm using the genetic algorithm (GA), extracted data through the GA, and then processed the information using the CNN algorithm. Besides, based on the optimized algorithm, an intelligent color-matching model was constructed. To verify the performance of the proposed color-matching model, the superiority of the optimization algorithm (PSO) was first tested. The results showed that the accuracy of the PSO reached 98%, and the loss value of the algorithm function was only 0.02, significantly better than other algorithms. Further analysis of the performance of the intelligent color-matching model based on PSOs showed that the accuracy of the model’s color matching reached 98%, and the matthews correlation coefficient index of the model was 1. The performance of this color-matching model was superior to other models. In practical applications, the model had an average color difference of only 0.51, 0.49, and 0.47 for the three primary colors of red, green, and blue, with small color differences and high color-matching accuracy. From the above results, it can be seen that the intelligent color-matching model proposed in the study can improve the accuracy of color matching and reduce color difference, thereby improving the efficiency of clothing color matching in textile enterprises and promoting the development of the textile industry and other color-matching industries.

In order to improve the experimental demonstration effect of computer technology, this article combines virtual reality technology and intelligent reflective surface-assisted perception and communication technology to build a general computer experiment demonstration platform. Based on sparse code division multiple access, this article proposes an intelligent reflector-assisted joint multi-user information reliable access and environmental reflector sensing scheme. Moreover, this article extracts the information about the environmental reflector in the received signal by means of computational imaging. In addition, this article iteratively optimizes the performance of multi-user information access and environment awareness through the relationship between the information of the environmental reflector and the received signal. The experimental research shows that the augmented reality-based general computer technology experimental demonstration platform proposed in this article has good effects and can effectively promote the computer technology experimental demonstration effect.

To accurately detect the abnormal behavior of business hall employees in the indoor working environment and ensure the normal operation of the store, a deep learning technology is combined to build an audio and video feature extraction network. First, a separate video and an audio feature extraction model are built by using a convolutional neural network and a long short-term memory network, and then an abnormal behavior detection model of audio and video feature fusion is built using multi-channel modules. This model can divide audio and video data into multiple different channels, and perform feature extraction and recognition on each channel. To assess the performance and robustness of the proposed model, experiments are organized on multiple datasets. The research outcomes denote that compared with some existing neural network models, the detection accuracy, recall, F1 value, and mean average precision values of the proposed model in the video audio dataset are 97.85, 96.98, 95.61, and 35.61%, respectively. The research method has a remarkable fusion effect on video and audio datasets, which improves the accuracy and robustness of abnormal behavior recognition. In addition, user and expert satisfaction with the model has also improved significantly, reaching 0.92 and 0.97, respectively. The novelty of this study lies in the comprehensive analysis of audio and video data by using multi-channel processing technology. Through effective extraction and fusion of video frames and audio signals at the same time, it significantly improves the detection ability of abnormal behaviors in indoor environments in complex scenes.

The advent of digital twin technology has precipitated a surge of interest in its implementation within the manufacturing sector, particularly with respect to enhancing productivity and mitigating the risk of equipment failure. However, due to the incomplete maturity of the technology, the manufacturing industry is prone to failures and reduced production efficiency in the production process. To reduce the frequency of failure and improve production efficiency, the optimized digital twin technology is combined with the long and short-term memory network to predict the health condition of the improved computer numerical control (CNC) machine tool. The proposed model is predicated on a convolutional neural network and a long and short-term memory network, the purpose of which is to extract the feature data of CNC machine tool parts. Second, the attention mechanism is introduced to enhance the importance weight of the model to the time feature. Finally, the Kalman filtering is employed to denoise the data and generate the final prediction result. The experimental findings of the model demonstrated that the maximum error between the predicted and true value of the convolution-long short-term memory (LSTM) model in the machine tool part health monitoring data was 0.06, and the minimum error was 0.035. The convolution-LSTM model in the anomalous point inspection displacement of the amount of positive displacement did not exceed 25 mm, and the negative displacement did not exceed −23 mm. The Kalman wave-LSTM model demonstrated an accuracy of 90.5% in monitoring the health status of the part at the minimum. The results show that the proposed method has good fitting effect and high accuracy in different monitoring cycles. This research provides a new method for monitoring and predicting the health condition of parts of CNC machine tools, which has important practical significance for optimizing and improving the production efficiency of manufacturing industries.

With the increasing demand for green and environmentally friendly building materials, the development of the building materials industry is gradually moving toward an ecological and sustainable direction. At present, there are various indicators for evaluating the greenness of wall materials, and the evaluation methods are mainly in view of personal experience. Therefore, this study designed a green degree evaluation model for wall materials. The model is first in view of the lifecycle of the wall material, considering factors that affect the greenness of the wall material. Then, an improved mathematical hierarchy process is used for modeling, and finally, indicator weights are calculated, and the model is simulated for application. The results indicate that the model can reasonably and accurately rate the greenness of wall materials with different characteristics and has high scientific and practical significance. The survey results show that the satisfaction level of the model is high, indicating that it has broad application prospects and development potential in practical applications and can provide strong support for promoting the sustainability and green development of the building materials industry.

The complexity and diversity of different music styles created by different composers make music evaluation a very difficult problem. To quantitatively evaluate the quality of music pronunciation, this work proposes a method for extracting nonlinear features of music signals. By selecting different styles of music signals, based on chaos theory, fractal theory, and Lyapunov exponent, the change in correlation dimension of different kinds of music signals is analyzed from a nonlinear perspective, so as to realize vocal music evaluation and training in music teaching. The results showed that the filter used in the study has a good noise-reduction effect. The power spectrum of the music signal was qualitatively analyzed, and the music signal was characterized by chaos. The difference between the maximum and minimum values of the Lyapunov exponent of the For Alice music signal was 0.244, which is larger than the other music signals. After the correlation dimension analysis, the correlation dimension of the Croatian Rhapsody music signal varied strongly. The average correlation dimension of the five music signals fluctuated above and below the corresponding average correlation dimension value at order 0, and the music signals had stable nonlinear features. The research method of the article is conducive to deepening the understanding of music signal patterns and has a certain promotion effect on music teaching.

New energy is widely used in power systems due to its advantages of being green and sustainable. However, it requires microgrid inverters (Mis) to connect to the power grid, and a large number of connections will cause the system to lack damping and inertia, which are not conducive to the stability of the power grid. To improve the control performance of MIs, the study first constructs a nonlinear virtual synchronous generator (VSG) control method based on differential geometry theory, and then combines multi-index nonlinear robust control to design the control method. The research results indicate that the nonlinear VSG control method can achieve frequency oscillations from 51.24 to 50.01 Hz in grid connected environments, with small fluctuations in the response of active and reactive outputs, as well as output phase currents. In off grid environments, it can quickly reach steady-state values without significant overshoot. In contrast with the traditional second-order VSG control method, the multi-index nonlinear robust VSG control method can achieve stability within the range of (49.98–50.04 Hz) and (0.1–1.0 kW) in the event of a fault in the MI system. In a parameter perturbation environment, frequency, active power, and output phase current can all quickly and smoothly reach stable values without static errors. The above outcomes indicate that the raised control method can effectively alleviate the adverse effects of external disturbances and parameter disturbances on MIs.

With the rapid development of manufacturing technology, scheduling and management of engineering production lines are becoming increasingly important. However, the current manufacturing engineering production line scheduling and management technology often has problems with low quality. To improve quality, this study proposes a scheduling management model that combines availability constraints and outsourcing. To solve this model, a hybrid algorithm based on heuristic rules and the Johnson-Bellman rule is also constructed. In comparing the performance of heuristic algorithms with other algorithms, the optimization rates of heuristic algorithms with SHPSO, QLINSGA-II, and Q-Learning-Sarsa-K-mes-GA were 96.7, 90, 78.6, and 84.7%, respectively. The average processing time was 998.7, 6287.3, 6698.9, and 6986.8 h, respectively. Among them, the proposed heuristic algorithm had the highest optimization rate and the shortest average processing time, which were significantly better than the compared algorithms. In addition, in the comparative analysis of the established scheduling management model, the average processing time of the model compared to SHPSO, QLINSGA-II, and Q-Learning-Sarsa-k-mean-GA was 196.7, 396.8, 226.7, and 498.2 h. The average processing costs were 1456.7 yuan, 3897.4 yuan, 2346.1 yuan, and 4968.6 yuan. Among them, the average processing time and average processing cost of this model were the lowest, which performed better than the comparative models. The above results indicate that the proposed model and hybrid algorithm have good performance and effectiveness, which can help improve the quality of engineering production line scheduling management.

Traditional auditing methods have difficulties in detecting various financial issues hidden in massive amounts of data. With the continuous advancement of deep learning and digital technology, new audit methods have been provided for computer auditing. Therefore, in order to achieve intelligent analysis and processing of audit reports, this study innovatively applies the convolution operation of convolutional neural networks to the forward and backward layers of bidirectional long short-term memory networks, obtaining more accurate feature recognition and prediction results. Meanwhile, by introducing radial basis functions for nonlinear mapping of the data space, the model’s ability to fit complex data is enhanced, thereby improving the analytical capability of the digital intelligent financial audit system. The experimental results show that the comprehensive average accuracy of the improved algorithm reaches 92.31%, and the F 1-score of the reconciliation function reaches 80.55, which are significantly higher than the other four algorithms. This indicates that the digital intelligent financial audit model proposed in this study can accurately analyze financial audit data, proving that it can comprehensively process various types of financial data and effectively improve the efficiency of modern enterprise audit data analysis.

The complexity of network information is on the rise, posing challenges for traditional community discovery methods when dealing with large-scale, multimodal, and dynamic networks. This research utilizes the attention mechanism (AM) to adaptively learn the association weights among nodes and constructs a community discovery model (CDM) based on the AM. The model incorporates convolutional neural networks and spectral clustering algorithms to improve the practical application of CDMs. Performance testing of the research-proposed model revealed that the accuracy of the model was 92.5 and 95.0% in the training and test sets, respectively. Subsequently, in the empirical analysis of the model, it was found that the standardized mutual information level and modularity level of the research proposed CDM were 0.917 and 0.920, respectively, which were significantly better than the conventional model. The results suggest that the proposed CDM has practical applications and provides new perspectives and methods for processing information in complex networks. This helps to reveal the relationships between nodes and the community structure in the network. The research is significant for predicting information dissemination, discovering key nodes, and evaluating network influence.

The neural collaborative filtering recommendation algorithm widely serves as personalized recommendations of users, which further applies deep learning to a recommendation system. It is a universal framework in the neural collaborative filtering recommendation algorithm; however, it does not regard the impact of important features on recommendation results, nor does it regard the issues of data sparsity and long tail distribution of items. To settle these issues, this article proposes a recommendation algorithm based on the attention mechanism and contrastive learning, which focuses on more important features through the attention mechanism and increases the quantity of samples to achieve data augmentation through contrastive learning; therefore, it enhances recommendation performance. The experimental results on two benchmark datasets show that the algorithm proposed in this article has further enhanced recommendation performance compared to other benchmark algorithms.

The development of artificial intelligence technology has also promoted the development of the field of sports rehabilitation. The existing motion matching assisted sports rehabilitation technology has poor applicability in complex environments and slow response time. A video stream matching based rehabilitation training method for motor dysfunction is developed to address the existing problems in motion matching in the field of sports rehabilitation. The research design method compares the movement posture to determine the patient’s rehabilitation level and provides rehabilitation guidance. At the same time, a keyframe comparison action similarity measurement algorithm and an unmatched keyframe action flow similarity algorithm were designed for different rehabilitation stages of patients to improve user experience. The results show that the key frame comparison action similarity metric algorithm has a matching time of about 40 ms and a matching accuracy of about 0.85. The unmatched key frame action flow similarity algorithm has no obvious advantage in the matching time of key frames, but it has an obvious advantage in the matching accuracy, which is as high as 0.9. The proposed video flow matching algorithm effectively improves the speed of patients’ rehabilitation training and the patients’ evaluation of this algorithm is higher than that of the video flow matching algorithm. And the patients’ evaluation of the algorithm is high.

This work aims to use deep learning techniques to model the thermal performance of walls in buildings located in cold regions. Upon completion of the data processing and collection steps, we theoretically train the prediction model using a neural network. In the first phases of residential building design in cold regions, decision-makers may execute performance forecasts across diverse parameter combinations. The creation of an expedited predictive model for the energy efficiency of residences in frigid areas makes this feasible. This facilitates the exclusion of building types characterized by elevated energy usage and expenses. The strategy may lower decision-making expenses and enhance decision-making efficiency during the first design phases by filtering out high-energy-consuming building kinds. This research concludes that the machine learning model enhances the building’s performance. The optimum design variable values identified in this research may serve as a reference for architects and designers aiming to meet their economic and environmental objectives in passive structures. The construction cost, thermal index, and load intensity of the building may be calculated with more accuracy by following the right procedures.

Due to the need for doctors to assist in making treatment strategies for the diagnosis results of B-ultrasound medical images, the diagnostic efficiency is relatively low. In order to improve the accuracy and efficiency of identifying lumbar muscle strain, based on the You Only Look Once version 3 algorithm, an intelligent recognition filtering algorithm combining sliding window and histogram of oriented gradient features is proposed to avoid misdiagnosis caused by artifact interference. The results show that the proposed algorithm has an accuracy of 95.2% and a recall rate of 94.7% when applied to hospital standard equipment. The proposed algorithm can effectively reduce the possibility of misdiagnosis and improve the reliability of clinical diagnosis. At the same time, this algorithm can effectively identify cases of lumbar muscle strain, reduce missed diagnosis, and ensure that patients can receive timely treatment. The proposed algorithm has an F 1 score of 94.9% for standard devices, 95.7% for high-resolution devices, and 93.4% for mobile ultrasound devices. This algorithm can maintain good recognition performance on different devices and has strong adaptability. This algorithm can be widely applied in the ultrasound diagnosis of lumbar muscle strains in hospitals, providing effective decision support for doctors and ensuring that patients can receive the necessary medical services in a timely manner. Meanwhile, it provides important support for precision medicine and personalized treatment in the medical field, which is expected to improve the health and life quality of patients.

As global climate change and urbanization accelerate, urban rainwater and flood drainage systems are facing increasingly severe challenges. Traditional drainage system design methods are no longer able to meet the complex needs of modern cities. To improve the overall performance of urban rainwater and flood drainage system, a coupling model of multiobjective optimization algorithm and rainstorm management model is constructed. This model has been used for comprehensive optimization of urban rainwater and flood drainage systems. In the comparative analysis of the proposed coupling model, the standard deviation of the total overflow of the nodes was 65 million yuan. Then, the empirical analysis of the urban stormwater drainage system proposed in the study shows that the total discharge of the drainage outlet of the study model is 4428.73 and 1386.49, respectively, with the increase in time in the recurrence period of 2 and 50-year rainfall. In addition, the research model achieved remarkable results in the reduction in peak flow and water depth, increasing the drainage efficiency by 15.7% on average. This research not only provides new theoretical basis and practical guidance for the optimization design of urban rainwater and flood drainage systems, but also has important significance for enhancing the ability of cities to respond to extreme climate events and reducing urban water-logging disasters.

The construction progress and cost management (CPCM) of construction projects are key areas that need to be focused on when formulating construction plans and conducting on-site commands. A CPCM method is proposed based on the standard genetic algorithm. During the process, a serial operation strategy is introduced, a project valuation function is defined, and a CPCM resource library is constructed. The tangent function is used to simulate the key relationships in the construction process, and finally, the construction progress and cost are compressed and optimized. The experimental results indicate that in optimal fitness tests on the construction engineering cost standards (CECS) dataset, the proposed method reaches the upper limit of 20.9 in just 23 generations, 66.67% faster than multi-stage genetic algorithm’s (MGA’s) 72 generations and 51.06% faster than quantum genetic algorithm’s (QGA’s) 47 generations. For the building engineering dataset (BED) dataset, it achieves the upper limit of 21.2 in 30 generations, 33.33% faster than MGA’s 45 generations and 49.18% faster than QGA’s 61 generations. In MSE change tests, the proposed method’s MSE fluctuates within a range of 0.04 after 22 and 23 generations for the CECS and BED datasets, respectively, which is more stable than MGA and QGA. Additionally, when the number of engineering steps increases from 5 to 25, the calculation time of the proposed method increases by less than 30 s, demonstrating higher computational efficiency than that of MGA and QGA. When conducting cost compression, the research method generates a plan that reduced construction costs by 230 k yuan. This indicates that the research method has good computational efficiency and can effectively generate the reference of project construction cost management plans.

In the construction industry, the effectiveness of project cost management directly affects the success and sustainability of the project. Traditional cost forecasting methods often rely on experience and historical data, which is difficult to adapt to the complex market environment and uncertainty. To solve this problem, this study proposes a hybrid model based on random forest and support vector machines to improve the accuracy and reliability of engineering cost prediction. Through an in-depth analysis of data from 775 residential construction projects, this study constructs a cost forecasting model with 14 key features, covering building characteristics and macroeconomic indicators. The results show that the proposed hybrid model is superior to the traditional single model in many evaluation indicators, which are reflected in the root mean square error of 251.23, the mean absolute error of 200.15, and the coefficient of determination ( R ²) of 0.6174, indicating that the model can effectively explain 61.74% of the cost variation. In addition, the feature significance analysis shows that floor area, number of floors, and Consumer Price Index are the main factors affecting project costs. This study not only improves the accuracy of the model but also overcomes the limitations of a single method by synthesizing the advantages of multiple algorithms. This study also discusses the potential applications of the model in practical engineering projects, including construction project cost forecasting, policy formulation and market analysis, real-time cost monitoring, and risk assessment and management. Through this research, this study provides a scientific and practical solution for project cost prediction, which is expected to provide strong decision support for project managers and promote the sustainable development of the construction industry.

Fire can cause significant damage to the personal safety of museum personnel and the integrity of exhibits. Many museums are choosing to install intelligent fire warning systems. In response to the low accuracy of fire prediction and recognition in most museums’ intelligent warning systems, this study proposes a museum intelligent warning system based on wireless data modules. This study first establishes an environmental monitoring system within the museum, using temperature sensors distributed throughout the museum for real-time monitoring, and transmitting the monitoring data to the upper computer for processing through a wireless data module. On this basis, a warning system based on an environmental prediction model and a fire recognition model is constructed. The results indicated that the temperature threshold range for fire was greater than 28°C, with humidity less than 48%, smoke concentration greater than 1,800 ppm, CO concentration greater than 1,830 ppm, and toxic gas concentration greater than 2,000 ppm. All the indicators tested in actual situations met the threshold range. This indicates that the proposed warning system can effectively respond to fire situations within museums, providing effective measures for the safety of museum personnel and the protection of cultural relics.

The study proposes a torque motor control method based on the improved model predictive control algorithm, aiming to solve the core problems such as insufficient dynamic adaptability, weak anti-interference ability, and difficulty in multi-objective collaborative optimization in the traditional mechatronics optimization technology. Through the improved model predictive control algorithm in the torque motor control algorithm, the load is reasonably distributed and the status of mechatronics integration is monitored in real-time, thereby optimizing mechatronics integration. The results showed that the improved control algorithm performed significantly better than the other two algorithms in optimizing mechatronics technology. Under different external interference conditions, the improved algorithm had strong anti-interference ability and could optimize mechatronics technology without being affected by external interference factors. The optimization accuracy was always maintained within the range of 1.00–1.05. At 1.0032 min, the accuracy curve of the algorithm for optimizing mechatronics technology has already flattened. When comparing the optimization effects of the three algorithms, the improved algorithm maintained an optimization error value within the range of 0.00–0.01%, significantly lower than the optimization error values of other algorithms. Overall, the algorithm achieves high-precision real-time control and multi-objective collaborative optimization through rolling time-domain optimization and dynamic load allocation, providing theoretical support and technical paths for the efficient and stable operation of complex electromechanical systems.

Based on the self-developed combined hydrodynamic cavitation device composed of a Venturi tube with variable throat length-to-diameter ratios, a triangular orifice perforated plate and nonlinear dynamic model, the influences of factors such as the throat length-to-diameter ratio, cavitation number, orifice size, orifice quantity, initial concentration of raw water, and pH value on the degradation of chemical industrial wastewater by hydrodynamic cavitation were experimentally studied. Combined with the actual situation of chemical wastewater treatment, a nonlinear dynamic model of the hydraulic cavitation process was established, and the influence of different operating parameters on degradation effect was analyzed. The results showed that the extreme conditions generated during the collapse of cavitation bubbles could cause cavitation erosion damage to the refractory pollutants in chemical industrial wastewater. When the throat length-to-diameter ratio of the Venturi tube was L / R = 20, increasing the number of orifices (49 orifices) of the downstream perforated plate and reducing the orifice diameter (4.04 mm) were beneficial to the treatment of high-concentration wastewater. When the throat length-to-diameter ratio of the Venturi tube was L / R = 40 or 60, appropriately reducing the number of orifices (16 or 25 orifices) and increasing the orifice diameter (6.73 mm) could achieve the optimal degradation of high-concentration wastewater.

The nickel-based superalloy GH4586 has been more widely used as the main material for the preparation of aerospace turbine components. However, with the development of reusable rocket engine technology, a more profound understanding of the low-cycle fatigue performance of the material under cyclic loading is required. In this study, the same specification of GH4586 used in the turbine disk of an engine is used to prepare test specimens, the fatigue performance at different strain levels of 0.5, 0.7, 0.9 and 1% is investigated, and fatigue tests are carried out at six temperatures from room temperature to 1,173 K. The fatigue σ – N curves of the material are obtained. In this study, the cyclic hardening/softening transformation mechanism of GH4586 alloy and its influence on the life of turbine components are systematically revealed through low-cycle fatigue tests with multiple temperature points (room temperature to 1,173 K) and multiple strain amplitudes (0.5–1%). The study shows that optimizing the strain amplitude below 900 K can improve the component life by more than 20%, which provides a quantitative basis for the strain–temperature coupling design of reusable rocket engine turbine.

In this article, we shall consider the solution to neutral stochastic functional operator differential equations with finite delay r > 0 : d D ( t , x t ) = f ( t , x t ) d t + g ( t , x t ) d B ( t ) , t 0 ≤ t ≤ T r\gt 0:{\rm{d}}D\left(t,{x}_{t})=f\left(t,{x}_{t}){\rm{d}}t+g\left(t,{x}_{t}){\rm{d}}B\left(t),\hspace{0.33em}{t}_{0}\le t\le T . By using Banach fixed point theorem, we obtain the existence of the solutions. We also obtain some properties of the solution.

Kuijpers’s study, published in Science under the title “Cavitation-induced reactions in high-pressure carbon dioxide,” explores the phenomenon of acoustic cavitation in high-pressure liquid CO 2 . However, an analysis of the study suggests that the vapor pressure within bubbles in high-pressure liquid CO 2 cannot remain constant or be balanced by static pressure, challenging the fundamental conditions required for acoustic cavitation. A critical prerequisite for cavitation is that the sound pressure must be proportional to the hydrostatic pressure, a condition that does not hold in Kuijpers’s experiments. This raises questions about the interpretation of the ultrasonic effects reported in the study, suggesting that they may not be caused by cavitation. The controversy surrounding acoustic cavitation in high-pressure CO 2 is of significant academic interest, as it has implications for fields such as chemical processing, materials science, and ultrasound-assisted reactions. While the physical properties of supercritical CO 2 closely resemble those of liquid CO 2 , experiments conducted with supercritical CO 2 indicate that metal corrosion and polymer formation can occur in the absence of cavitation. Moreover, computational simulations have further demonstrated the mechanical effects of ultrasound in both liquid and supercritical CO 2 , reinforcing the need for a more precise understanding of the mechanisms involved.

In this study, Inner Mongolia Chahasu Coal Mine is considered as the research object and new type of cemented filling material is developed based on gangue, fly ash, and cement. The aim is to systematically optimize its performance and investigate the influencing factors to improve the proportion of cemented filling materials used in the coal mine filling and mining process. Thus, the study seeks to reduce production costs and enhance the utilization rate of solid waste. In the literature, various studies have focused on optimizing the performance of cemented filling materials, particularly in terms of reducing environmental impact and improving cost-effectiveness. Research abroad has made significant progress in optimizing filling materials under specific geological conditions, such as varying mineral compositions and groundwater influences. However, the challenge remains in balancing the physical properties like compressive strength, flowability, and durability with the efficient use of industrial byproducts such as fly ash and gangue. Studies also indicate that while cemented filling materials have been extensively studied for their strength properties, the interaction effects of multiple factors, particularly in complex mining environments, are not well understood. In contrast, domestic studies primarily focus on the basic performance of filling materials under less variable geological conditions, with limited emphasis on how environmental complexities impact the optimization process. Furthermore, many studies do not fully address the role of gangue particle size and fly ash in improving the environmental sustainability and cost-effectiveness of filling materials. To fill this gap, this study combines the response surface methodology with optimization of the gangue particle size gradation to create a response model between cement, fly ash, solid content, and the filler body’s compressive strength. According to the test results, the filling materials’ strength and flowability were maximized when the grading factor of the gangue particle size was set at n = 0.5. A Box–Behnken experimental design was then used to examine the influence patterns of cement, fly ash, and solid content on the filling body’s strength at the early (3 days), middle (7 days), and late (28 days) stages, focusing on both single-factor and multi-factor interactions. The study found that the primary determinants of strength were the cement mass fraction and solid mass fraction, with fly ash’s contribution becoming more significant in the later stages of curing. The optimized ratios not only met the filling strength requirements but also significantly reduced cement usage and increased the utilization rate of fly ash, demonstrating the potential for both cost reduction and effective resource usage of solid waste.

The rapid growth of transportation engineering has led to significant environmental challenges due to the accumulation of building waste and tailings. A promising solution is to utilize these materials to develop high-performance tailings recycled concrete (RFAC) for highway construction, promoting a green circular economy. This study advances existing research by exploring innovative mix design strategies and performance optimization techniques to enhance RFAC’s mechanical properties and industrial applicability. Specifically, this research investigates the effects of various iron tailings admixtures on the mechanical behavior and deformation characteristics of RFAC before and after carbonation, aiming to establish an optimal composition for transportation infrastructure. The materials used include iron tailings, recycled coarse aggregate, natural river sand, and 42.5-grade ordinary silicate cement. Unlike conventional approaches, this study emphasizes the influence of particle morphology and surface characteristics of laboratory-produced recycled fine aggregate, revealing its angular shape, rough texture, and larger specific surface area, which significantly impact fluidity, bulk density, and crushing value. Experimental results demonstrate that fiber type and tailings admixture ratio play a crucial role in improving RFAC’s slump, compressive strength, split tensile strength, and failure modes. Compared to previous studies, this research provides a more refined analysis of mix proportioning and introduces tailings-based performance enhancements, offering new insights for large-scale applications in transportation engineering. By optimizing tailings incorporation and aggregate proportions, this study establishes a systematic approach to improving RFAC’s mechanical performance, durability, and construction adaptability, laying the foundation for sustainable infrastructure development.

Bridge condition assessment is a crucial component of bridge management. To better adapt to the multi-level, nonlinear, and multi-criteria decision-making problems in bridge assessments, a modified technique for order preference by similarity to ideal solution (TOPSIS)-based nonlinear method is proposed in a fuzzy environment. First, quantitative representations of three different types of bottom indices of bridge assessment models under the analytic hierarchy process framework are developed using fuzzy numbers. Subsequently, with regard to the conventional TOPSIS approach, several enhancement and optimizations are considered, including the absolutization and fuzzification of positive and negative ideal solutions, the determination of variable weights of bottom-level indexes, fuzzy assessment based on level sets, and the defuzzification and grading of the evaluation results. These measures reduce the ambiguities and uncertainties associated with the conventional TOPSIS approach and can optimally accommodate bridge performance evaluation in fuzzy logic. Finally, to illustrate the practicality and feasibility of the developing method, a real bridge assessment scenario is built. The results indicate that this approach can effectively reflect the real state of the overall bridge, providing a robust basis for bridge maintenance and rehabilitation decision-making.

The dynamic behavior of the straddle monorail pantograph system is significantly influenced by nonlinearities arising from its unique structural configuration and operational environment. This article presents a mathematical model that incorporates both nonlinear geometric and material properties of the pantograph. A finite element model is utilized to perform modal and static analyses, identifying stress concentrations and dynamic characteristics. To account for random vibration excitations, a nonlinear dynamic response framework is developed, considering vehicle-induced vibrations and network irregularities as stochastic excitation sources. The results demonstrate that these nonlinearities amplify specific resonances under random excitation, leading to increased stress and deformation at critical points. These findings provide a foundation for enhancing fault detection strategies and designing more robust pantographs, with nonlinear vibration monitoring proposed as an effective diagnostic tool. This study contributes to both theoretical understanding and practical improvements in ensuring the reliability and longevity of straddle monorail systems.

The influence of host materials on the electroluminescent (EL) properties of blue thermally activated delayed fluorescence (TADF) emitters were lacking. In this investigation, we systematically studied the effect by doping blue emitter into various host materials with differing polarities as the emitting layer (EML), and revealed the choice of host-impacted EL performance significantly. By delving deeper into the light-emission mechanisms of TADF devices, we identified that the device performance variations were predominantly governed by both energy transfer and charge trapping processes within the EML(s). Notably, stable blue TADF device exhibiting peak efficiencies and brightness values of 23.74 cd/A and 5,695 cd/m 2 , respectively, were achieved.

With the combination of Internet technology and teaching methods, the online dance teaching mode is becoming more popular. However, traditional teaching quality evaluation methods such as neural network models have low efficiency, insufficient accuracy, and are prone to ignoring individual differences, making it difficult to better adapt to the online dance teaching mode. Accordingly, this study constructs a quality evaluation index system for online dance teaching by consulting relevant online course teaching experts, considering individual student differences, and existing research, including preparation, classroom teaching implementation, classroom teaching effectiveness, and reflection on after-school teaching. On this basis, the network dance teaching quality evaluation model based on back-propagation neural network is constructed. For these shortcomings, it is optimized by the improved particle swarm. This study uses inertia weight and crossover operator strategy to optimize particle swarm optimization algorithm, achieving the collaborative work of back-propagation neural network and particle swarm optimization. This study uses statistical data from online dance teaching courses in universities for experimental analysis. According to the findings, the accuracy of the designed model reached 97.25%, which significantly exceeded other commonly used methods. Based on this evaluation model, both teachers and students can receive feedback on teaching and learning processes, thereby improving teaching methods, meeting personalized needs of students, and enhancing learning outcomes. This study combines PSO and BPNN to provide a new method for evaluating the quality of online dance teaching, providing new reference ideas for improving the quality of online education in the information society.

This study investigates a novel multi-component polymer composite method for preparing graphite/polymer composites with excellent electrical conductivity and electromagnetic shielding properties, aiming to address the challenges in achieving a balance between conductivity, mechanical stability, and thermal properties in applications like electronics, automotive, and aerospace. Expanded graphite (EG) was used as a conductive filler, and solid-state shear milling was employed to achieve uniform dispersion of graphite in a polymer matrix consisting of polyvinyl chloride (PVC), chlorinated polyethylene (CPE), and polyurethane elastomer (TPU), improving mechanical and thermal stability. X-ray diffraction, Raman spectroscopy, scanning electron microscopy, transmission electron microscopy, and conductivity tests revealed significant differences in graphite dispersion across substrates. In the EG/PVC-CPE system, graphite sheets are stripped into multiple layers, while in the EG/PVC-TPU system, they form thinner or even single layers, leading to enhanced conductivity and shielding efficiency. The results show that the EG/PVC-CPE and EG/PVC-TPU composites offer improved electrical and mechanical properties, demonstrating the potential of multi-component matrices and solid-state shear milling in developing high-performance composites for conductivity and electromagnetic interference shielding applications.

Nonlinear engineering methods improve the thermal insulation of building walls and save energy. This study proposes multiple construction forms of embedded composite phase-change energy storage walls to study heat transfer and its impact on indoor environments based on nonlinear engineering methods. The study reveals heat transfer laws and mechanisms affecting indoor environments. The results show a <10% error between measurements and numerical simulations, validating numerical methods for studying phase-change walls. Without water flow, temperature differences at the base of ordinary, S-font, U-font, and back-font phase change walls are 8.70, 8.80, 8.83, and 8.94°C, respectively. With water flow, these differences are 5.00, 5.18, and 6.51°C. Smaller coil spacing enhances heat storage. Phase-change walls reduce indoor air temperature by up to 3.2°C, improving thermal comfort. By combining nonlinear engineering methods, technical support is provided for achieving green buildings and sustainable development.

This paper proposes a Movie Recommendation System (MRS) based on big data. MRS adopts B/S architecture and uses front-end and back-end separation modes. The front-end uses the Vue progressive framework, and the back-end uses the SpringBoot back-end development framework combined with MySQL database development. First, the information about the film is crawled from the network by Python crawler technology. Second, the actual needs of the relevant movie management and recommendation system are provided, using SpringBoot, Vue, MySQL, and other technologies equipped with popular movie management, review management, user management, recharge management, and other functions. In addition, this MRS provides a personalized service, recommending films of interest to users based on their preferences. The relevant tests show that MRS has reliable technical support in the later promotion and operation, providing users with a good experience and also laying a solid foundation for system upgrading.

This study examines the impact of increasing minimum wages, focusing primarily on their effect on employment. Our research involved analyzing the statistics of panel data, testing fixed effects and stationary, conducting linear regression, and integrating the linear regression model with nonlinear model analysis. The results indicate that fluctuations in the employment rate are almost entirely explained by the selected explanatory variables, and there is a significant negative correlation between minimum wages and the employment rate. This study contributes to current research by providing more comprehensive analyses, particularly through the use of nonlinear models, resulting in better-fitting models. We employed multiple fitting methods for time series data and their differentials, combining these results with nonlinear analysis.

In the comprehensive evaluation of multiple indicators, the existence of nonlinear relationships often makes the discrimination of traditional evaluation methods unstable or difficult to accurately reflect the complex relationship between indicators. The outcome of a comprehensive evaluation is to assign a quantitative value to each evaluation object for selection or ranking. The discriminability in the evaluation results is an important measure of the effectiveness of the comprehensive evaluation. In response to the issues of uncertain discriminability or poor stability in commonly used comprehensive evaluation methods, a comprehensive evaluation method prioritizing discriminability is proposed. Based on the principle that information entropy can reflect the degree of variation in the evaluation dataset, a model for quantitatively analyzing the discriminability of evaluation indicators is provided, and the conclusion that low-discriminability indicators will reduce the overall discriminability of the comprehensive evaluation is proven. Accordingly, weighted indicators, qualification indicators, and invalid indicators are defined. By identifying and eliminating low-discriminability qualification indicators and invalid indicators, and retaining weighted indicators, the evaluation results ensure good discriminability while maintaining the comprehensiveness of the evaluation. Through empirical analysis, the scientificity and effectiveness of this method in processing multi-dimensional and nonlinear data are verified.

Pile foundation has been widely applied in modern civil engineering due to its excellent performance under complex foundation conditions. However, when subjected to dynamic loads such as waves, tides, and earthquakes, the long-term stability of pile foundations becomes a significant concern. Traditional stability analysis methods are predominantly based on static loading assumptions, which neglect the nonlinear behavior of soils and the time-varying characteristics of dynamic loads. This leads to reduced prediction accuracy and limited applicability under real-world, complex working conditions. To address these challenges, this study proposes an innovative numerical calculation method based on a two-parameter model, which integrates dynamic load effects – such as wave and tidal actions – into the pile-soil interaction framework. Compared with the conventional Winkler model, the two-parameter model incorporates both the stiffness of the subgrade and the shear interaction between adjacent soil springs, thereby capturing the nonlinear and spatially correlated behavior of foundation soils more accurately. The core innovations of this study lie in two aspects. First, it introduces a more refined numerical model by incorporating key parameters such as pile water entry depth, lateral soil resistance coefficient, and pile stiffness, offering a more realistic simulation of complex marine foundation conditions. Second, it performs a comprehensive stability analysis under dynamic loading environments, systematically investigating the influence of various factors including soil properties, pile length, and pile diameter on the critical frequency and overall structural stability. The research findings show that the proposed two-parameter model significantly improves the precision of stability analysis and effectively reveals the nonlinear dynamic responses of pile foundations. This contributes to both the theoretical development of pile-soil interaction modeling and practical engineering applications in marine and offshore structures.

Shale gas plays a crucial role in China’s energy transition and carbon peak goals, with Sichuan Province being a key development region. However, challenges such as methane (CH 4 ) emissions and inefficient carbon capture hinder its sustainable utilization. Traditional static methods for gas separation, while effective under stable and simplified conditions, often struggle to adapt to complex and fluctuating working environments typically encountered in shale gas extraction, such as variable pressure, temperature, and gas composition. These limitations reduce their efficiency and reliability in large-scale, real-world applications. In contrast, the pressure swing adsorption (PSA) process offers a dynamic and adaptable solution for CO 2 separation and CH 4 purification, performing more efficiently under varying operational conditions. This study evaluates the contribution of shale gas development in Sichuan to China’s carbon peak targets, with a focus on optimizing the PSA process. Using life cycle assessment and real-world operational data, we quantify the carbon footprint and analyze PSA parameters under different working conditions to improve CO 2 capture efficiency. Results show that optimized PSA not only significantly reduces emissions compared to static methods under variable conditions but also supports China’s carbon reduction strategy. The findings provide theoretical and practical insights for policymakers and industry stakeholders in achieving sustainable shale gas utilization.

In order to clarify the characteristics of tight oil reservoirs and their impact on seepage, we conducted a comprehensive analysis of the reservoir characteristics of the Chang-7 tight sandstone using advanced equipment such as X-ray diffractometers and high-pressure mercury injection devices from the perspective of nonlinear engineering. We studied the effect of reservoir characteristics on oil and water seepage. The results show that tight cores are mainly quartz arenite and feldspar arenite with high clay mineral content. They have abundant irregular, disconnected pore spaces and micro-fractures, leading to low permeability and poor physical properties. Tight cores are stress-sensitive, with core permeability decreasing as effective pressure increases. An exponential fitting function can effectively reflect the relationship between permeability and effective stress of tight sandstone cores in this area. As the air-measured permeability of the core increases, the start-up pressure gradient first decreases sharply and then gradually stabilizes. The oil–water two-phase start-up pressure gradient and permeability have a power relationship: G = 5.66 × 10 −4 K −1.42 . For tight cores, a slight increase in permeability can significantly reduce the start-up pressure gradient. This study provides a theoretical basis and technical support for the efficient development of tight oil reservoirs from a nonlinear engineering perspective, which helps to optimize development strategies and provide ideas to enhance tight oil reservoir recovery.

This article presents a novel method for nonlinear deformation decomposition and mode identification of plane structures based on orthogonal theory. The plane deformation of a square element is decomposed into rigid body linear displacements, rigid body rotation, tension-compression, bending, and shearing deformations. A complete orthogonal base vector set is constructed for these basic deformation modes, allowing any deformation to be expressed as a linear combination of these vectors. Compared with the traditional finite element method, the proposed approach demonstrates superior accuracy, convergence, and robustness, especially in identifying bending deformation, which is difficult to isolate using conventional techniques. The method also excels in mode identification, effectively revealing coupled modes such as shear-dominated shapes. It outperforms traditional approaches like animation and mass participation ratio methods by offering more accurate, visual, and comprehensive results. A numerical example involving a plane column validates the feasibility and effectiveness of the method, showcasing its potential in analyzing complex nonlinear deformations and identifying modal behavior in plane structures.

The pulsed water jet (PWJ) rock-breaking technology is vital in developing oil and gas resources. The presence of fractures in the rocks in the reservoir is one of the prominent features in the renovation project of the old well. However, the dynamic damage process of cracked rocks under the action of PWJ has not yet been revealed. Therefore, from the perspective of nonlinear engineering, in this study, a new PWJ coupled rock-breaking model was established by using the smooth particle fluid dynamics-finite element method (SPH-FEM) coupling algorithm to clarify the macroscopic damage mechanism of rocks with crack characteristics. From the perspective of materials science, this study verified the reliability of the model through comparative experiments and investigated the failure mechanism induced by the impact of pulsed jets on rocks containing natural fractures. The experimental and simulation results illustrate that the rock-breaking effect of the PWJ is significantly superior to that of continuous water jet, combined with the theoretical framework of nonlinear engineering and materials science. The presence of cracks hinders the propagation of the stress waves. At a crack inclination angle of 75°, the broken pit depth increased by approximately 48.5% compared to 30°. The significant improvement in rock-breaking efficiency is closely related to crack spacing, especially when the spacing is less than 2 cm.

This study uses nonlinear modeling methods to construct a complete modeling framework that integrates univariate quadratic regression, orthogonal experimental design, and multivariate polynomial regression based on 147 sets of multi-catalyst experimental data and dynamic time-series data. This study first revealed the nonlinear influence of temperature on the ethanol conversion rate and C 4 olefin selectivity using a quadratic model. Then, the main effects of factors such as the Co loading, charge ratio, and ethanol concentration were quantified using an orthogonal experimental system. Finally, a standardized multivariate interaction model was constructed to deeply analyze the physical meaning of interaction terms such as temperature, Co loading, and charge ratio. The results show that the root mean square error of the model on the test set is less than 1.14%, and the coefficient of determination ( R 2 ) is higher than 0.937, demonstrating good generalization ability and engineering applicability. This study presents a digital modeling paradigm with explanatory power, predictive power, and scalability based on nonlinear engineering for the mechanism elucidation and industrial processes of complex catalytic reaction systems.

T-node tensile specimens, including both rectangular steel pipes and rectangular steel pipe concrete configurations, were developed based on the results of tensile tests conducted on concrete-filled rectangular steel pipe T-nodes. The specimens incorporated Perfobond Leiste (PBL) stiffeners, with concrete-filled rectangular steel pipes used for the main pipes and square steel pipes as the branch (stub) pipes. The fatigue performance of the concrete-filled rectangular steel pipe T-nodes under tensile loading, in-plane bending, and out-of-plane bending was investigated using PBL stiffeners as internal reinforcement. To determine the stress concentration parameters of the branch pipes, a nonlinear finite element analysis was performed using ABAQUS (a finite element analysis software suite developed by Dassault Systèmes) software. The analysis adopted a width-to-thickness ratio of 0.4 for the branch pipe and 27 for the main pipe. The results indicate that the hot spot locations of the PBL-stiffened concrete-filled rectangular steel pipe T-nodes are consistent with those of both the unstiffened rectangular steel pipe nodes and the concrete-filled nodes. Furthermore, the stress concentration factor of the PBL-stiffened node is significantly lower than that of the unstiffened steel pipe node, indicating markedly improved fatigue resistance.

The novel cognitive blood glucose–insulin control technique presented in this work uses five layers in the controller’s structure to monitor and control the blood glucose levels of various diabetic patients’ types. The first layer is the cognitive dataset that represents the attributes of the control system. The second layer is the identifier neural network model that represents the different types of nonlinear Bergman diabetic patient models. The third layer is the feedforward neural network controller based on an identifier neural network model to find the maximum insulin-infusion level for each meal in each sample. The fourth layer is the feedback PID-RBF-NN controller based on the radial basis function neural network model to find the optimal insulin-infusion value and to keep the blood glucose level in the normal state. The fifth layer is the nonlinear patient Bergman minimal model. To train this controller, the grey wolf optimization meta-heuristic technique is employed. The results of the MATLAB simulations for three distinct patients showed the effectiveness and robustness of the suggested control algorithm in monitoring the dynamic behaviour of the diabetic patients’ blood glucose levels. Additionally, the comparison results demonstrated that the suggested cognitive glucose–insulin control algorithm improved the time to reach a normal physiological blood glucose level by 10% compared to the fuzzy logic and the fractional-order proportional integral derivative (PID) control algorithms, by 25% compared to the type-2 fuzzy control algorithm, and by 6% compared to the PID-particle swarm optimization control algorithm.

Rural revitalization policy is an important strategic measure of the country, and optimizing the design of public buildings is an important step in achieving rural revitalization. The research innovatively focuses on energy consumption in public buildings and introduces a novel multi-objective particle swarm optimization algorithm (BBMOPSO-A [backbone multi-objective particle swarm optimization algorithm]), which is designed to address the characteristics of building energy consumption (BEC, the total amount of energy consumed in the operation of a building). The new method enhanced the search capability of the algorithm by introducing new local and individual extreme points to address the multi-objective nature of the BEC problem. In addition, to reduce the computational cost, the study also innovatively employed an agent-assisted model to effectively replace the original model, ensuring that performance was not sacrificed while cost was reduced. These experiments confirmed that this new method model could effectively reduce algorithm costs. The accuracy of this method was 5.02% higher than multi-objective genetic algorithm, 3.72% higher than the multi-objective artificial ant colony algorithm, and 2.67% higher than the multi-objective particle swarm algorithm. Therefore, the backbone multi-objective particle swarm optimization algorithm has better performance and is more suitable for optimizing building energy consumption.

Unmanned aerial vehicles (UAVs) are increasingly being employed in air-to-ground communication applications due to their lightweight design, high speed, and ability to utilize low-altitude resources. Utilizing UAVs for data collection from wireless ground sensors is an efficient, convenient, and cost-effective approach. However, due to the increasing miniaturization of wireless sensors, obtaining precise locations for deploying such sensors simultaneously in large areas is challenging or costly. While sensor localization techniques have been widely explored, including collaborative localization in sensor networks and received signal strength-based positioning, previous research has not addressed scenarios where sensor positions are completely unknown. Existing work on using UAVs to collect data from ground sensors has not yet addressed the scenario where the positions of ground sensors are unknown. In this article, we design an air-to-ground cooperative communication scheme that leverages ground base stations (BS) to locate sensors with unknown positions and uses UAVs to collect data from the located ground sensors. To address this problem, we decouple it into two separate tasks: sensor localization and UAV path planning. First, we use signals from sensors captured by ground BS to determine their positions. We model the ground channel and apply trilateration techniques to overcome the impact of receiver noise, achieving precise sensor localization. Continuing from obtaining the sensor coordinates, to enhance the efficiency of multi-UAV cooperative tasks, we propose a classification algorithm based on minimum distances. This algorithm divides the regions containing sensors into multiple task areas, with each area served by a single UAV. Finally, we propose a graph-based UAV path planning algorithm to cover all sensors in the subtasks after classification. This ensures optimal data collection from all sensors within the task area. Simulation results reveal that, compared to the existing algorithms, the proposed approach adeptly tackles the data collection challenge when sensor positions remain unknown while significantly enhancing task execution efficiency across diverse environmental conditions. In addition, we have included a detailed discussion analyzing the computational efficiency and real-world deployment challenges of our method, offering valuable insights for applications such as precision agriculture, disaster response, and environmental monitoring.

With the aggravation of the global aging process, providing a suitable living environment for the elderly has become an urgent issue. Based on the theory of human-environment adaptation, this study proposes a multilevel aging-friendly design scheme, aiming to improve the adaptability of urban and rural retirement public areas and the quality of life of the elderly. Through field research and questionnaire surveys, the impact of key design elements such as spatial layout, road design, lighting configuration, and resting area setup is investigated, taking into account the needs of the elderly in urban and rural areas of Chengdu. The results of the study reveal that spatial design has the most significant impact on the adaptability of the elderly, boasting a regression coefficient of 0.34. Road design, lighting design, and seating design also contribute, with regression coefficients of 0.27, 0.22, and 0.19, respectively. These findings indicate that various design elements play a crucial role in improving the convenience of activities, safety, and social interaction for the elderly. The adjusted R 2 of the overall model is 0.72, indicating that the explanatory power of the design elements on the adaptability of the elderly is strong. The study provides a theoretical basis and practical guidance for the design of aging-friendly public areas for the elderly, which has high social value and application prospects.

In a timbre recognition system, the representation of functional sounds is the foundation of timbre frequency recognition correlation analysis and is crucial for the overall performance of the system. In order to obtain more accurate tone frequency points, this study adopts a dual tone multi frequency (DTMF) signal processing system based on A/D converter, which can effectively extract key information from audio signals. Furthermore, utilizing envelope function based electronic synthesis technology, an analog signal processing module has been developed to optimize the quality of audio signals. Next the analog signal is converted into a digital signal through an A/D converter for subsequent digital signal processing and recognition. Accurate detection of DTMF signals is a crucial step in the application of technology in signal processing, which directly affects the effectiveness of timbre recognition. With the continuous development of music signal recognition and electronic synthesis technology, the role of lossless signal transmission technology is becoming increasingly prominent. The research in this article shows that lossless signal transmission technology has achieved significant results in piano timbre recognition, with an accuracy of 89.32%, which is 22.54% higher than traditional transmission technology. This achievement not only provides new ideas for the improvement and development of musical instruments, but also provides technical support for the development of robot bands. In summary, the application of lossless signal transmission technology in piano timbre recognition has broad prospects and practical application value.

With the growth of the economy, tourism has gradually become a consumer trend in people’s lives. However, the traditional optimization method of rural tourism routes cannot optimize the routes effectively and achieve the best results. The study introduces a genetic algorithm (GA), combines it with an ant colony optimization (ACO) algorithm, and proposes an improved GA to optimize rural tourism routes. The degree of adaptation is set by collecting historical rural tourism route data, initializing the data population, and performing variant crossover operations. The ACO algorithm is used to converge the route points and shift the route according to the action probability. The experimental results show that the proposed method of the study has a minimum mean absolute error of 0.784 and a maximum mean absolute error of 0.801 in optimizing rural tourism routes, which is more accurate compared to the traditional GA and ACO algorithms. Compared with the methods proposed by other scholars, the maximum error rate of solving the proposed method of the study is only 0.56%. The results show that the improved genetic method proposed by the study can effectively enhance the effect of rural tourism route optimization, providing new ideas and perspectives for the tourism industry.

As the construction industry grows and technology advances, architectural animation (AA) plays an increasingly critical role in expressing building design and configuration. However, the generation of AA faces challenges in handling the details of architectural images and maintaining animation continuity. To this end, a new AA generation system based on the architecture learning generative adversarial network (AL-GAN) algorithm is proposed, aiming to solve the problems of insufficient detail handling, poor animation continuity, and inefficiency in traditional AA generation. The new system significantly improves the architectural image detail processing capability and animation continuity by combining the attention mechanism and the long short-term memory network. The experimental results showed that AL-GAN could get closer to the real image and process architectural colors and lines more accurately and vividly, demonstrating its superior image-processing capability. In addition, AL-GAN showed the best adaptability in different scenes, reaching 99.99% adaptability in the park scene. The research model also performed well in terms of color recognition accuracy with relatively small error values, indicating better model performance and stability. Therefore, the improved AL-GAN has better performance in the AA generation system. The study not only provides a more efficient and accurate solution for the field of AA generation but also experimentally verifies the adaptability and stability of AL-GAN in different scenes.

This study addresses the accuracy challenges in e-commerce sentiment classification and thus provides valuable insight for businesses to enrich strategies toward the interpretation of customer feedback and improvement of product development. This article elaborately contrasts long short-term memory (LSTM)-based models with traditional machine learning models, like support vector machines (SVM), random forest, and Naive Bayes classifiers. The authors have used a large dataset of customer reviews from famous e-commerce websites, pre-processed for noise reduction and standardization of the input. Our LSTM models were implemented using state-of-the-art deep learning frameworks, with special consideration while performing hyperparameter tuning. The results showed that the bidirectional LSTM model had the best performance of 92.1% in accuracy, 91.8% in precision, 92.0% in recall, and an F 1-score of 91.9%. In comparison, traditional machine learning approaches gave accuracies: 86.5% for SVM, 85.1% for random forest, and 82% for Naive Bayes. Hyperparameter tuning returned the best configurations for the LSTM models: 128 LSTM units, a dropout of 0.3, with learning rates 0.001 for LSTM and 0.0001 for bidirectional LSTM. These optimizations contributed hugely to the performance improvements observed in these models. Error analysis gave insights into the challenges that the models faced. Sarcasm and irony accounted for 22% of the classification errors, while mixed sentiment accounted for 18%, and implicit accounted for 15%. To sum up, this research has shown the efficiency of LSTM models on e-commerce user review sentiment analysis, especially bidirectional LSTM. These models show a much better result in sentiment classification compared to traditional machine learning techniques, which proves them to have huge potential for improving the accuracy of the task in real-world applications.

Introduction In order to improve the effect of intelligent recommendation of piano repertoire, this article combines the convolutional neural network (CNN) model to perform intelligent analysis of piano repertoire and combines personal preference for piano repertoire recommendation. Objectives Moreover, this article conducts research on the identification of piano waveform features in the process of piano practice by piano practitioners in complex situations. Methods In addition, this article conducts waveform extraction through hardware design, which provides a basis for piano preference identification, and theoretically analyzes the design of sealed resonant windows and the design of concentrated electric field strength resonant gaps. Results About 92.72% of the samples have a maximum ratio of more than 0.9, and the maximum ratio of the samples is greater than 0.5. That is to say, most of the errors still come from prediction and classification errors, and a small part of them are data errors. Finally, this article constructs an intelligent recommendation model for piano repertoire based on the CNN model after introducing the resonance element into the piano waveform characteristic factor limiter. Conclusion The proposed CNN-based recommendation algorithm demonstrates high accuracy and effectively enhances piano repertoire recommendations.

The prosperity of data science and the booming growth of the internet industry have made the analysis and processing of large-scale user-related feature data a particularly important issue in modern society. Traditional linear dimensionality reduction methods often fail to obtain intuitive information and discover intrinsic connections and patterns in complex high-dimensional data. This study proposes a large-scale user association feature data (LSUAFD) visualization study based on nonlinear dimensionality reduction methods to address the complexity and high-dimensional issues of data. First, a LSUAFD visualization platform based on the nonlinear dimensionality reduction method is constructed. Secondly, the nonlinear dimensionality reduction algorithm is integrated into the platform, and the functional modules and data dimensionality reduction modules of the platform are finally tested. The results indicated that by combining principal component analysis with nonlinear dimensionality reduction algorithms (t-SNE and LargeVis) to provide interactive parameter adjustment and visualization in the front end, the selected dataset exhibited excellent analytical performance. Furthermore, the method could stably and accurately detect outliers within the dataset. The errors were primarily distributed between 0.4 and −0.4, indicating a high level of precision in the interpretation of data distributions.

By optimizing energy utilization and integration, microgrids can improve the reliability of energy supply, reduce energy operating costs, and decrease energy emissions. However, there is insufficient coordination between energy interaction and low-carbon operation systems, resulting in increased carbon emissions and energy waste. Therefore, a low-carbon economic optimization method for microgrid clusters is built based on energy interaction operation strategies. This method adopts a multi-energy collaborative operation mode to construct a low-carbon optimization model for microgrid clusters. In the comparison of operating costs between microgrid clusters with and without energy interaction, for microgrids A, B, and C, when there was energy interaction, the operating costs of microgrids A and B both decreased by 25,400 RMB and 16,400 RMB, respectively, while the operating cost of microgrid C increased by 5,200 RMB. In terms of purchasing electricity costs, the purchasing electricity costs of microgrids A, B, and C all decreased in the energy interaction. In terms of purchasing gas costs, the purchasing cost of microgrid A slightly increased, while the purchasing cost of microgrids B and C decreased. Adopting energy interaction strategies has a positive effect on the economic cost of purchasing energy. After energy interaction, the purchasing demand of microgrid A was less than 4,000 kW, and most of the time, the purchasing energy demand was low. However, compared with before energy interaction, the purchasing demand of microgrids B and C significantly decreased. In the cost of carbon sales on microgrids, microgrids A, B, and C increased by $213.73, $230.02, and $415.92, respectively, in scenarios 1–3. The designed method has a promoting effect on the comprehensive operational economy and low-carbon emissions of microgrid clusters, providing technical references for the safety, stability, and environmental protection of microgrid clusters.

The swift surge of video content depicts enormous challenges for intelligent information systems in extracting and searching video data. This article explores improvements achieved by introducing a Faster-RCNN hybrid model into video data extraction and search processes. We propose a novel methodology combining Faster-RCNN with adaptive feature fusion and temporal coherence modeling to enhance object detection and tracking within video streams substantially. Using a large multi-megavideo dataset called VideoDiv-10K, which is made up of 10,000 videos from categories and others made available through public datasets like ImageNet VID and MOT16, this proposed model exhibited magnificent improvements. This model, when hybrid used with 500 h of content diversity, produced an average mean average precision of 0.891 and had an improved amount by 18.7% more than traditional Faster-RCNN. The model reduced its time for computation by 32.4% and had a massive leap in the accuracy in the search by 41.2%. Key to this performance were the temporal coherence module, which does a good job in capturing dependencies within sequential frames, and the adaptive feature fusion mechanism that dynamically integrates spatial and temporal features. Those were used to attain average F 1-score in object detection of 0.937 and 0.912 object tracking on some video resolutions and frame rates. The results of the experiment clearly prove the ability of our hybrid model to process large video data, with significant gains in both accuracy and speed. We then provide better performance within applications such as surveillance, autonomous driving, and content-based video retrieval. Our model maintains a high level of scalability and does not degrade for huge datasets.

Considering the slow convergence speed and local optima in most current swarm intelligence algorithms for image segmentation, this study combines the thresholding clustering with intelligent algorithms. The algorithm is optimized based on the characteristics of image segmentation. First, an improved differential evolution algorithm is applied to enhance the speed of threshold image segmentation. The convergence performance of the algorithm is improved by adjusting the crossover probability and mutation strategy. Second, considering the threshold difference, an improved two-dimensional Otsu threshold segmentation algorithm based on cuckoo algorithm is proposed, and fractional calculus processing and fractional enhancement filtering are introduced to improve the image segmentation quality. The loss value in image feature segmentation was less than 5 × 10 2 , the accuracy exceeded 90% in different types of image segmentation, the running time did not exceed 2 s, and the structural similarity reached 0.912, which was significantly better than other algorithms. Moreover, the pixel accuracy of the image processing algorithm exceeded 90%, with good segmentation details and edge extraction effects. The proposed image segmentation method performs well in segmentation accuracy, edge clarity, and computational efficiency, which can improve the segmentation accuracy and application effect in image processing systems and provide a method for improving the generalization ability of segmentation models in different scenarios.

To improve the performance of the adhesive layer defect detection (DD) planar array capacitor system, an adhesive layer DD method based on particle swarm optimization and fuzzy C-means (FCM) clustering algorithm is proposed. By classifying erroneous capacitance data, the experiment distinguishes the capacitance values at defect locations from those at defect-free locations. In response to the presence of artifacts in the image reconstruction results, the optimal threshold method is used to post-process the reconstructed images using the mixed regularization method. These experiments confirmed that FCM clustering reduced the mean absolute deviation (MAD) of data by about 6.1%, and the proposed clustering algorithm reduced the MAD of data by about 23.2%. Compared to the Tikhonov method, the mixed regularization method reduced the relative error of reconstructed images by about 13.1% and increased the correlation coefficient of reconstructed images by about 21.6%. Therefore, this research method had significant effects in reducing data fluctuations and errors, effectively improving the image reconstructing quality and the accuracy of DD. This study can effectively improve the accuracy of adhesive layer DD, help reduce production costs, and improve production efficiency.

The aim of this study is to solve the problem that existing instructional intervention decision-making techniques are difficult to achieve accurate interventions when optimizing students’ learning contexts. Therefore, this study combines the reinforcement learning model and the quantile tracking regression model to construct a theoretical model for instructional intervention decision-making and validate its effectiveness. The experimental results showed that the proposed model had high prediction accuracy in different student groups, and its application in practical teaching practice could obviously improve students’ learning effectiveness. Compared with the comparison method, the research model performed better in accuracy, precision, recall rate, and F 1 value, and the accuracy was as high as 96.4%. In different educational data sets, the F 1 scores of the proposed model were all above 0.89. The results show that the model can achieve accurate teaching intervention, thus optimizing students’ learning conditions. The research lays the foundation for creating a more intelligent and adaptable educational system, and promotes the intelligent development of educational technology.

With the increasing demand for automation and accuracy in industry, the control objective has been expanded from simple linear systems to complex nonlinear systems. To mitigate fluctuations in nonlinear systems due to external disturbances and enhance the accuracy of state variable estimation, this study employs fuzzy theory. The study introduces a time-delay-dependent Lyapunov asymptotic stability criterion and optimizes the affiliation function in type II fuzzy mathematics to establish a sedimentation model. A state estimation model is optimized based on the unscented Kalman filter method with an extended kernel risk-sensitive loss function and a deep residual network. The experimental results show that when μ \mu takes the value of 0.2, the maximum time-delay allowed upper bound obtained by the calming model is 2.2143, which is at the highest value. The state estimation model used in the study fits the true value curve better, and the error percentages are within 0.01%. This indicates that the model has better convergence accuracy and stability control performance.

A novel optimization framework for microgrid (MG) distribution network scheduling has been proposed, which integrates enhanced bat algorithm (BA) with probabilistic photovoltaic (PV) power prediction to address the dual challenges of renewable energy uncertainty and operational efficiency. The method combines genetic algorithm-optimized artificial neural network with Monte Carlo simulation to achieve very low PV output prediction error under variable weather conditions. In addition, the study improves the BA by using a multi-mechanism approach of Halton sequence initialization and dynamic elite retention, which enhances the convergence iteration speed of the algorithm and avoids local optima problems. The experimental results show that the maximum predicted output power (OP) of the PV generator set is 208 kW, and the predicted OP curve is more consistent with the actual OP curve. The enhanced BA has been demonstrated to enhance the optimization of operating costs of MGs. The operating costs of MGs are 125,452 yuan at low loads and 145,562 yuan at high loads. The study provides a replicable template for high-penetration renewable MGs by combining probability prediction with swarm intelligence optimization. The research provides new ideas for the scheduling strategy of MG distribution networks centered on new energy.

Tai Chi is a traditional Chinese martial art with unique movements and philosophical connotations. The research on motion segmentation and recognition in Tai Chi is of great significance for the learning and teaching of Tai Chi. To address such issues, this study introduced multi-sensor data fusion (MSDF) methods and density-based noise application spatial clustering algorithms. First, the principle and process of multi-sensor stereo matching and data fusion were introduced. Then, the principle of minimum description length was adopted to capture feature points of its trajectory and achieve trajectory cutting. Finally, clustering algorithms were used for clustering to further achieve accurate action recognition. The results showed that in the ten movements recognition experiments of Wu-style Tai Chi, under binary classification, the average action recognition accuracy of the proposed algorithm reached 98.52%, which was 5.43 and 2.94% higher than other advanced algorithms, respectively. In the scenario of multi-classification, the average accuracy of the proposed algorithm was as high as 92.33%, which was significantly better than other algorithms. This indicated that the Tai Chi action segmentation and recognition method on the grounds of the fusion of the MSDF method and a density-based noise application spatial clustering algorithm had significant performance advantages. It provided more accurate and real-time technical support for intelligent teaching, training, and competition of Tai Chi.

Fractional partial differential equations (FPDEs) are used as tools in the mathematical modeling of the natural phenomena and interpretation of many life problems in the fields of engineering and applied science. Mathematical models that include different types of partial differential equations are used in some fields of applied sciences such as biology, diffusion, electronic circuits, damping laws, and fluid mechanics. The derivation of modern analytical or numerical methods for solving FPDEs is a significant problem. In this article an efficient numerical method is proposed for solving a class of sixth-order FPDEs in which created by combining numerical Runge–Kutta–Mohammed (RKM) techniques with the method of lines. We have applied the modified approach to solve some problems involving the sixth-order FPDEs, and then, the numerical and analytical solutions for these problems have been compared. The comparisons in the implementations have proved the efficiency and accuracy of the developed RKM method. Also, the wave equation of fractional order as an application of the wave equation has been presented. Additionally, by contrasting the numerical implementations with exact answers, the effectiveness and accuracy of the suggested methodologies are shown.