Enhanced cryogenic distillation column identification for methane separation: a hybrid artificial neural network approach
-
Suhailam Pullanikkattil
,
Raju Yerolla
and
Chandra Shekar Besta
Abstract
Modelling the dynamics of cryogenic distillation columns is challenging due to their complex, nonlinear behaviour. This study introduces a novel identification approach using a hybrid Artificial Neural Network (ANN) optimized with Particle Swarm Optimization (PSO), applied to cryogenic distillation as a case study. The NARX-PSO-ANN model effectively captures the nonlinear dynamics of the distillation process by optimizing model parameters and avoiding local optima. The novelty of this work lies in integrating the NARX (Nonlinear Autoregressive with Exogenous Inputs) architecture with PSO, which enhances robustness and performance. To validate the model’s efficacy, realistic simulations of the cryogenic distillation column were conducted using Aspen Plus Dynamics, generated 2,000 data samples-1,400 training and 600 for validation. The NARX-PSO-ANN model was evaluated against established methods like BP-ANN and NARX-based BP-ANN, consistently outperforming them in identifying cryogenic distillation column dynamics and demonstrating superior effectiveness for complex separation processes. A user-friendly Python-based graphical user interface (GUI) was developed for real-time methane composition prediction, making the model accessible for practical applications. This innovative approach offers a reliable solution for optimizing complex, nonlinear systems in the process industry.
-
Research ethics: This study followed ethical guidelines and did not involve human participants or animal subjects. The data used in this study was entirely generated through simulations, and no ethical approval was required.
-
Informed consent: Informed consent was not applicable as this study did not involve human participants or their data.
-
Author contributions: Suhailam Pullanikkattil: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – Original Draft, Writing – review & editing, Visualization, Project administration. Raju Yerolla: Conceptualization, Methodology, Formal analysis, Investigation, Resources, Writing – review & editing, Project administration. Chandra Shekar Besta: Writing – review & editing, Supervision.
-
Use of Large Language Models, AI, and Machine Learning Tools: No large language models, AI, or machine learning tools were used in the data generation, analysis, or manuscript preparation for this study.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: This research received no specific funding or financial support from any organization.
-
Data availability: The data that support the findings of this study are generated by the Aspen Plus software. The raw data can be obtained on request from the corresponding author.
References
1. Demirbas, A. Methane hydrates as potential energy resource: Part 1 – importance, resource and recovery facilities. Energy Convers Manag 2010;51:1547–61. https://doi.org/10.1016/j.enconman.2010.02.013.Search in Google Scholar
2. Mignogna, D, Ceci, P, Cafaro, C, Corazzi, G, Avino, P. Production of biogas and biomethane as renewable energy sources: a review. Appl Sci 2023;13:10219. https://doi.org/10.3390/app131810219.Search in Google Scholar
3. Faraj, RH, Mohammed, AA, Omer, KM. Modeling the compressive strength of eco-friendly self-compacting concrete incorporating ground granulated blast furnace slag using soft computing techniques. ESPR 2022;29:71338–57. https://doi.org/10.1007/s11356-022-20889-5.Search in Google Scholar PubMed
4. Gürsan, C, de Gooyert, V. The systemic impact of a transition fuel: does natural gas help or hinder the energy transition? Renew Sustain Energy Rev 2021;138:110552. https://doi.org/10.1016/j.rser.2020.110552.Search in Google Scholar
5. Wang, C, Li, Y, Xu, C, Badawy, T, Sahu, A, Jiang, C. Methanol as an octane booster for gasoline fuels. Fuel 2019;248:76–84.10.1016/j.fuel.2019.02.128Search in Google Scholar
6. Sun, L, Wang, Y, Guan, N, Li, L. Methane activation and utilization: current status and future challenges. Energy Technol 2019;8. https://doi.org/10.1002/ente.201900826.Search in Google Scholar
7. Mueller, F, Guenthner, M, Weigel, A, Thees, M. Investigation of a second exhaust valve lift to improve combustion in a methane - diesel dual-fuel engine. SAE Tech Rep Ser 2022;2022:01–0466. https://doi.org/10.4271/2022-01-0466.Search in Google Scholar
8. Catapano, F, Di Iorio, S, Magno, A, Sementa, P, Vaglieco, BM. A comprehensive analysis of the effect of ethanol, methane and methane-hydrogen blend on the combustion process in a PFI (port fuel injection) engine. Energy 2015;88:101–10. https://doi.org/10.1016/j.energy.2015.02.051.Search in Google Scholar
9. Plakia, AS. Thermodynamic modeling and simulation of CO2 and H2S removal processes from natural gas and flue gases. Athens, Greece: National Technical University of Athens; 2021.Search in Google Scholar
10. Zainudin, A, Kurniawan, T, Bindar, Y, Irawan, A. Simulation of adsorption Coke Oven Gas (COG) from steel processing plant to produce high purity hydrogen. Melville, NY: AIP Publishing; 2023.10.1063/5.0117040Search in Google Scholar
11. Qin, Z, Zhao, Y, Yi, Q, Shi, L, Li, C, Yan, X, et al.. Methanation of coke oven gas over Ni-Ce/γ-Al2O3 catalyst using a tubular heat exchange reactor: pilot-scale test and process optimization. Energy Convers Manag 2020;204:112302. https://doi.org/10.1016/j.enconman.2019.112302.Search in Google Scholar
12. Shaker, I, El-Bagoury, M, Yaser, S, Emad, H, Hamdy, O, Abouseada, N, et al.. Process simulation and design of green ammonia production plant for carbon neutrality. Int J Innovat Sustain Dev 2024;5:79–103. https://doi.org/10.21608/ijisd.2024.247887.1041.Search in Google Scholar
13. Naquash, A, Qyyum, MA, Haider, J, Bokhari, A, Lim, H, Lee, M. State-of-the-art assessment of cryogenic technologies for biogas upgrading: energy, economic, and environmental perspectives. Renew Sustain Energy Rev 2022;154:111826. https://doi.org/10.1016/j.rser.2021.111826.Search in Google Scholar
14. Park, D, Urm, JJ, Lee, JU, Chang, MH, Lee, JM. Dynamic optimization of cryogenic distillation operation for hydrogen isotope separation in fusion power plant. Int J Hydrogen Energy 2021;46:24135–48. https://doi.org/10.1016/j.ijhydene.2021.04.199.Search in Google Scholar
15. Thomas, R, M, M, Annamalai, C, Vanishree, J, Sultana, R. Modelling of level process. Int J Innovative Technol Explor Eng 2019;8:1155–61. https://doi.org/10.35940/ijitee.j9078.0981119.Search in Google Scholar
16. Matias, JOA, Ebrahimpour, M, Le Roux, GAC. Development and validation of a reduced-index dynamic model of an industrial high-purity column. Ind Eng Chem Res 2018;57:1531–46. https://doi.org/10.1021/acs.iecr.7b02789.Search in Google Scholar
17. Ratrout, NT, Gazder, U. Factors affecting performance of parametric and non-parametric models for daily traffic forecasting. Procedia Comput Sci 2014;32:285–92. https://doi.org/10.1016/j.procs.2014.05.426.Search in Google Scholar
18. Gheytanzadeh, M, Baghban, A, Habibzadeh, S, Mohaddespour, A, Abida, O. Insights into the estimation of capacitance for carbon-based supercapacitors. RSC Adv 2021;11:5479–86. https://doi.org/10.1039/d0ra09837j.Search in Google Scholar PubMed PubMed Central
19. Haratipour, P, Baghban, A, Mohammadi, A, Hosseini nazhad ghazani, SH, Bahadori, A. On the estimation of viscosities and densities of CO 2 -loaded MDEA, MDEA + AMP, MDEA + DIPA, MDEA + MEA, and MDEA + DEA aqueous solutions. J Mol Liq 2017;242:146–59. https://doi.org/10.1016/j.molliq.2017.06.123.Search in Google Scholar
20. Baghban, A, Khoshkharam, A. Application of LSSVM strategy to estimate asphaltene precipitation during different production processes. Petrol Sci Technol 2016;34:1855–60. https://doi.org/10.1080/10916466.2016.1237966.Search in Google Scholar
21. Baghban, A, Abbasi, P, Rostami, P. Modeling of viscosity for mixtures of Athabasca bitumen and heavy n-alkane with LSSVM algorithm. Petrol Sci Technol 2016;34:1698–704. https://doi.org/10.1080/10916466.2016.1219748.Search in Google Scholar
22. Yuan, Y, Zhou, X, Man, J, Jiao, H, Jiang, Q, Xu, Q, et al.. The safety evaluation of management in chemical enterprise with generalized regression neural network. IOP Conf Ser Earth Environ Sci 2019;295:042010. https://doi.org/10.1088/1755-1315/295/4/042010.Search in Google Scholar
23. Argatov, I. Artificial neural networks (ANNs) as a novel modeling technique in tribology. Front Mech Eng 2019;5. https://doi.org/10.3389/fmech.2019.00030.Search in Google Scholar
24. Pirdashti, M, Curteanu, S, Kamangar, M, Hassim, M, Khatami, M. Artificial neural networks: applications in chemical engineering. Rev Chem Eng 2013;24:205–39. https://doi.org/10.1515/revce-2013-0013.Search in Google Scholar
25. Arumugasamy, SK, Ahmad, Z. Elevating model predictive control using feedforward artificial neural networks: a review. Chem Prod Process Model 2009;4. https://doi.org/10.2202/1934-2659.1424.Search in Google Scholar
26. Baghban, A, Kashiwao, T, Bahadori, M, Ahmad, Z, Bahadori, A. Estimation of natural gases water content using adaptive neuro-fuzzy inference system. Petrol Sci. Technol 2016;34:891–7. https://doi.org/10.1080/10916466.2016.1176039.Search in Google Scholar
27. Baghban, A, Adelizadeh, M. On the determination of cetane number of hydrocarbons and oxygenates using Adaptive Neuro Fuzzy Inference System optimized with evolutionary algorithms. Fuel 2018;230:344–54. https://doi.org/10.1016/j.fuel.2018.05.032.Search in Google Scholar
28. Ghanbari, A, Kardani, MN, Moazami Goodarzi, A, Janghorban Lariche, M, Baghban, A. Neural computing approach for estimation of natural gas dew point temperature in glycol dehydration plant. Int J Ambient Energy 2020;41:775–82. https://doi.org/10.1080/01430750.2018.1492441.Search in Google Scholar
29. Chandra, K, Xie, A, Ragan-Kelley, J, Meijer, E. Gradient descent: the ultimate optimizer. Adv Neural Inf Process Syst 2022;35:8214–25.Search in Google Scholar
30. Dogo, EM, Afolabi, O, Nwulu, N, Twala, B, Aigbavboa, C. A comparative analysis of gradient descent-based optimization algorithms on convolutional neural networks. IEEE 2018:92–9. https://doi.org/10.1109/ctems.2018.8769211.Search in Google Scholar
31. Lu, T, Lu, Z, Gao, Y, Shi, L, Wang, H, Wang, T. Investigation on suitable swirl ratio and spray angle of a large-bore marine diesel engine using genetic algorithm. Fuel 2023;345:128187. https://doi.org/10.1016/j.fuel.2023.128187.Search in Google Scholar
32. Mahadeva, R, Kumar, M, Goel, A, Patole, SP, Manik, G. A novel AGPSO3-based ANN prediction approach: application to the RO desalination plant. Arabian J Sci Eng 2023:1–12. https://doi.org/10.1007/s13369-023-07631-0.Search in Google Scholar
33. Bhavya, R, Sivaraj, K, Elango, L. Ant Colony based artificial neural network for predicting spatial and temporal variation in groundwater quality. Water 2023;15:2222. https://doi.org/10.3390/w15122222.Search in Google Scholar
34. Kachitvichyanukul, V. Comparison of three evolutionary algorithms: GA, PSO, and DE. Ind Eng Manag Syst 2012;11:215–23. https://doi.org/10.7232/iems.2012.11.3.215.Search in Google Scholar
35. Soltani, H, Karimi, A, Falahatpisheh, S. The optimization of biodiesel production from transesterification of sesame oil via applying ultrasound-assisted techniques: comparison of RSM and ANN-PSO hybrid model. Chem Prod Process Model 2020;1.10.1515/cppm-2020-0076Search in Google Scholar
36. Gutiérrez, FA, García-Cuevas, LM, Sanz, W. Comparison of cryogenic and membrane oxygen production implemented in the Graz cycle. Energy Convers Manag 2022;271:116325. https://doi.org/10.1016/j.enconman.2022.116325.Search in Google Scholar
37. González, CAD, de Oliveira, DC, Yepes, DM, Pacheco, LE, Silva, EE. Aspen Plus model of a downdraft gasifier for lignocellulosic biomass adjusted by Principal Component Analysis. Energy Convers Manag 2023;296:117570. https://doi.org/10.1016/j.enconman.2023.117570.Search in Google Scholar
38. Flöter, E, de Loos, TW, de Swaan Arons, J. Improved modeling of the phase behavior of asymmetric hydrocarbon mixtures with the Peng−Robinson equation of state using a different temperature dependency of the parameter a. Ind Eng Chem Res 1998;37:1651–62. https://doi.org/10.1021/ie970644o.Search in Google Scholar
39. Peck-Schrage, SGH, Bazúa-Rueda, ER. Peng–robinson equation of state model for polycyclic aromatic hydrocarbons and long-chain hydrocarbons solubilities in supercritical fluids. Correl Based Solute Mol Prop 2018;63:4061–75. https://doi.org/10.1021/acs.jced.8b00447.Search in Google Scholar
40. Li, X, Li, J, Yang, B. Design and control of the cryogenic distillation process for purification of synthetic natural gas from methanation of coke oven gas. Ind Eng Chem Res 2014;53:19583–93. https://doi.org/10.1021/ie5024063.Search in Google Scholar
41. Luyben, WL. Distillation design and control using Aspen simulation. Hoboken, NJ: John Wiley & Sons; 2013.10.1002/9781118510193Search in Google Scholar
42. Cocchi, G, Liuzzi, G, Lucidi, S, Sciandrone, M. On the convergence of steepest descent methods for multiobjective optimization. Comput Optim Appl 2020;77:1–27. https://doi.org/10.1007/s10589-020-00192-0.Search in Google Scholar
43. Abd Elaziz, M, Dahou, A, Abualigah, L, Yu, L, Alshinwan, M, Khasawneh, AM, et al.. Advanced metaheuristic optimization techniques in applications of deep neural networks: a review. Neural Comput Appl 2021:1–21. https://doi.org/10.1007/s00521-021-05960-5.Search in Google Scholar
44. Zeng, N, Wang, Z, Liu, W, Zhang, H, Hone, K, Liu, X. A dynamic neighborhood-based switching particle swarm optimization algorithm. IEEE Trans Cybern 2020;52:9290–301. https://doi.org/10.1109/tcyb.2020.3029748.Search in Google Scholar
45. Ljung, L. Theory for the user. System identification. Upper Saddle River, NJ: Prentice Hall; 1987.Search in Google Scholar
46. Moore, AD. Python GUI programming with Tkinter: design and build functional and user-friendly GUI applications. Birmingham, UK: Packt Publishing Ltd; 2021.Search in Google Scholar
47. Rajamani, SK, Iyer, RS. Machine learning-based mobile applications using python and scikit-learn. In: Designing and developing innovative mobile applications. Hershey, PA: IGI Global; 2023:282–306 pp.10.4018/978-1-6684-8582-8.ch016Search in Google Scholar
48. Paneru, B, Poudyal, R, Paneru, B, Shah, KB, Poudyal, KN. Revolutionizing waste management: a cutting-edge pyTorch model for waste classification and prediction, coupled with a user-friendly recycling recommendation application built with tkinter. Indones J Electron Electromed Eng Med Inf 2024;6:295–304. https://doi.org/10.35882/ijeeemi.v6i1.344.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Cogeneration system’s energy performance improvement by using P-graph and advanced process control
- Numerical simulation of R134a evaporation in a cold water production system
- Implementing a radial basis function model to anticipate the outcomes of the gasification
- Sensitivity analysis and optimization of the whole process of continuous catalytic reforming for Persian gulf star oil company using an optimized data-driven model with tuned parameters
- Evaluating the therapeutic potential of 4-hydroxyflavanes diastereomers derivatives against (MetAP2) for anti-cancer therapy: a molecular docking study
- Enhanced cryogenic distillation column identification for methane separation: a hybrid artificial neural network approach
- Natural Gas and hydrogen blending: a perspective on numerical modeling and CFD analysis for transient and steady-state scenarios
- Simulation and optimization of Venturi type bubble generator to improve cavitation
Articles in the same Issue
- Frontmatter
- Research Articles
- Cogeneration system’s energy performance improvement by using P-graph and advanced process control
- Numerical simulation of R134a evaporation in a cold water production system
- Implementing a radial basis function model to anticipate the outcomes of the gasification
- Sensitivity analysis and optimization of the whole process of continuous catalytic reforming for Persian gulf star oil company using an optimized data-driven model with tuned parameters
- Evaluating the therapeutic potential of 4-hydroxyflavanes diastereomers derivatives against (MetAP2) for anti-cancer therapy: a molecular docking study
- Enhanced cryogenic distillation column identification for methane separation: a hybrid artificial neural network approach
- Natural Gas and hydrogen blending: a perspective on numerical modeling and CFD analysis for transient and steady-state scenarios
- Simulation and optimization of Venturi type bubble generator to improve cavitation
