Research on RBF neural network adaptive control of three-point contactless measuring device for CNC roller grinder
-
Kuo Li
,
Huai-chao Wu
Abstract
In order to improve the CNC roll grinder production efficiency, a novel three-point non-contact measurement device is proposed. An adaptive back-stepping control system that combines with a radial basis function neural network (RBFNN) was designed to control the measurement device working position and also to track the periodic reference movement trajectory. In the proposed control system, the RBFNN approximation and tracking ability are used to identify the unknown measuring device dynamic information. Then, the Lyapunov stability theorem is used to derive the adaptive online learning algorithm. All control algorithms are placed in the control chip based on the TMS320F28335 archive. The simulation results show that the proposed control system has a good control effect when applied to the three-point non-contact measuring device in CNC roll grinders.
Funding source: Science and Technology Innovation Team Project in Guizhou Province
Award Identifier / Grant number: Grant No. Q.K.H.P.T.R.C[2020]5020
Funding source: Training Plan for High-level Innovative Talent in Guizhou Province
Award Identifier / Grant number: Grant No. Q.K.H.P.T.R.Cã€2016】5659
Funding source: Major Science and Technology Project in Guizhou Province
Award Identifier / Grant number: Grant No. Q.K.H.Z.D.Z.X.Z[2019]3016
Funding source: Preferred Project of Scientific and Technological Activities for Personnel Studying Abroad in Guizhou Province
Award Identifier / Grant number: Grant No. Q.R.X.M.Z.Z.H.T(2018)0001
Acknowledgments
This work was supported by Major Science and Technology Project in Guizhou Province (Grant No. Q.K.H.Z.D.Z.X.Z[2019]3016), Science and Technology Innovation Team Project in Guizhou Province (Grant No. Q.K.H.P.T.R.C[2020]5020), Preferred Project of Scientific and Technological Activities for Personnel Studying Abroad in Guizhou Province(Grant No. Q.R.X.M.Z.Z.H.T(2018)0001) and Training Plan for High-level Innovative Talent in Guizhou Province (Grant No. Q.K.H.P.T.R.C[2016]5659).
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declares that they have no conflicts of interest.
References
1. Baidya, D, Roy, R. Speed control of DC motor using fuzzy-based intelligent model reference adaptive control scheme. In: Advances in communication, devices and networking. Singapore: Springer; 2018:729–35 pp.10.1007/978-981-10-7901-6_79Search in Google Scholar
2. Bai, W, Zhou, Q, Li, T, Li, H. Adaptive reinforcement learning neural network control for uncertain nonlinear system with input saturation. IEEE Trans Cybern 2019;50:3433–43. https://doi.org/10.1109/tcyb.2019.2921057.Search in Google Scholar PubMed
3. Chen, L, Wu, R, He, Y, Chai, Y. Adaptive sliding-mode control for fractional-order uncertain linear systems with nonlinear disturbances. Nonlinear Dynam 2015;80:51–8. https://doi.org/10.1007/s11071-014-1850-y.Search in Google Scholar
4. Cho, N, Shin, H, Kim, Y, Tsourdos, A. Composite model reference adaptive control with parameter convergence under finite excitation. IEEE Trans Automat Control 2017;63:811–8. https://doi.org/10.1109/tac.2017.2737324.Search in Google Scholar
5. Srivastava, S, Singh, M, Hanmandlu, M. Control and identification of non-linear systems affected by noise using wavelet network. In: Second international workshop on Intelligent systems design and application; 2002:51–6 pp.Search in Google Scholar
6. Zaafouri, A, Regaya, CB, Azza, HB, Châari, A. DSP-based adaptive backstepping using the tracking errors for high-performance sensorless speed control of induction motor drive. ISA Trans 2016;60:333–47. https://doi.org/10.1016/j.isatra.2015.11.021.Search in Google Scholar PubMed
7. Regaya, CB, Farhani, F, Zaafouri, A, Chaari, A. High-performance control of IM using MRAS-fuzzy logic observer. Int J Tomogr Simulat 2017;30:40–52.Search in Google Scholar
8. Lin, FJ, Shen, PH. Adaptive fuzzy-neural-network control for a DSP-based permanent magnet linear synchronous motor servo drive. IEEE Trans Fuzzy Syst 2006;14:481–95. https://doi.org/10.1109/tfuzz.2006.876744.Search in Google Scholar
9. Wang, X, Lin, X, Yu, Y, Wang, Q, Sun, C. Backstepping control for quadrotor with BP neural network based thrust model. In: 2017 32nd Youth academic annual conference of chinese association of automation (YAC). IEEE; 2017:292–7 pp.10.1109/YAC.2017.7967422Search in Google Scholar
10. Wang, Y, Zhang, C, Zhang, Y. Simulation modeling of ball screw feed drive system based on MRAS. In: Applied mechanics and materials. Switzerland: Trans Tech Publications Ltd; 2012, vol 226:607–12 pp.10.4028/www.scientific.net/AMM.226-228.607Search in Google Scholar
11. Yan, L, Yu, T, Wan, M. Research of roll shape measurement methods in CNC roll grinder. In: Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence. International Society for Optics and Photonics; 2006, vol 6357:63572J p.10.1117/12.717128Search in Google Scholar
12. Yan, L, Yu, T, and Wang, M. Research and application on the measurement method of roll roundness for roll grinder NC. In: 2007 International conference on mechatronics and automation. IEEE; 2007:3020–4 pp.10.1109/ICMA.2007.4304041Search in Google Scholar
13. Zhang, H, Du, M, Bu, W, Wu, D, Wu, W, Xu, L. Sliding mode controller with RBF neural network for manipulator trajectory tracking. IAENG Int J Appl Math 2015;45:334–42. https://doi.org/10.1016/j.clae.2015.03.011.Search in Google Scholar PubMed
14. Xu, C, Li, P. Matrix measure strategies for stability of cellular neural networks with proportional delays. IAENG Int J Appl Math 2016;46:305–10.Search in Google Scholar
15. Velez-Ramirez, JS, Bueno-Lopez, M, Giraldo, E. Adaptive control approach of microgrids. IAENG Int J Appl Math 2020;50:1–9.Search in Google Scholar
16. Park, J, Kim, S, Park, TS. Approximation-free state-feedback backstepping controller for uncertain pure-feedback nonautonomous nonlinear systems based on time-derivative estimator. IEEE Access 2019;7:126634–41. https://doi.org/10.1109/access.2019.2938595.Search in Google Scholar
17. Zhang, H, Han, J, Luo, C, Wang, Y. Fault-tolerant control of a nonlinear system based on generalized fuzzy hyperbolic model and adaptive disturbance observer. IEEE Trans Syst Man Cybern Syst 2017;47:2289–300. https://doi.org/10.1109/tsmc.2017.2652499.Search in Google Scholar
18. Tian, X, Zhao, G, Yang, Z, Ge, J, Xie, H. Backstepping-based sliding mode adaptive control for fractional-order system considering saturation phenomenon. IAENG Int J Appl Math 2022;52:1–8.Search in Google Scholar
19. Singh, M, Srivastava, S, Gupta, J, Handmandlu, M. Identification and control of a nonlinear system using neural networks by extracting the system dynamics. IETE J Res 2007;53:43–50. https://doi.org/10.1080/03772063.2007.10876120.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning
- Design and development of power data service platform based on multi dimension
- Evaluation on power marketing decision evaluation based on Bayesian network
- Power monitoring data access control system based on BP neural network
- Investigation and application of key technologies of aggregated flash payment based on marketing blockchain in the context of massive distributed generation grid connection
- Research on RBF neural network adaptive control of three-point contactless measuring device for CNC roller grinder
- Measurement of surface vibration signal of 500 kV transformer and analysis of its frequency characteristics
- Evaluation on key technologies for the construction of low-carbon index of electric power based on “double carbon”
- Application scenario evaluation of modified converter for quadratic Boost high gain DC-DC: taking the constant off time control mode as an example
- Efficiency of artificial intelligence automatic control system and data processing unit based on edge computing technology
- Design of mountain fire prevention monitoring system for transmission lines based on machine vision algorithms
Articles in the same Issue
- Frontmatter
- Research Articles
- Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning
- Design and development of power data service platform based on multi dimension
- Evaluation on power marketing decision evaluation based on Bayesian network
- Power monitoring data access control system based on BP neural network
- Investigation and application of key technologies of aggregated flash payment based on marketing blockchain in the context of massive distributed generation grid connection
- Research on RBF neural network adaptive control of three-point contactless measuring device for CNC roller grinder
- Measurement of surface vibration signal of 500 kV transformer and analysis of its frequency characteristics
- Evaluation on key technologies for the construction of low-carbon index of electric power based on “double carbon”
- Application scenario evaluation of modified converter for quadratic Boost high gain DC-DC: taking the constant off time control mode as an example
- Efficiency of artificial intelligence automatic control system and data processing unit based on edge computing technology
- Design of mountain fire prevention monitoring system for transmission lines based on machine vision algorithms
