OPTIMISATION OF SOFT ACTOR–CRITIC IN VECTOR CONTROL OF PERMANENT MAGNET SYNCHRONOUS MOTOR

Yiying Wang, Chen Liu, Xuedong Li, Yanhui Wu, Ying Gu, and Fei Wang.

References

  1. [1] L. M. E. Luz and W. Caarls, Comparison of reinforce-ment learning techniques for controlling a CSTR process,Brazilian Journal of Chemical Engineering, 42, 2023,1–12.
  2. [2] X. C. Liang, Z. W. Zhang, and L. Zhou, Review of controlstrategies for high-speed permanent magnet synchronousmotors, Tariffs as Environmental Protection, 19(1), 2023,60–65.
  3. [3] Z. Tang, J. Sun, H. Zhang, and X. Xie, Chaos synchronizationcontrol for stochastic nonlinear systems of interior PMSMsbased on fixed-time stability theorem, Applied Mathematicsand Computation, 430, 2022, 127115.
  4. [4] T. S. Gabbi, M. B. De Araujo, L. R. Rocha, F. P. Scalcon,H. A. Gr¨undling, and R. P. Vieira, Discrete-time sliding modecontroller based on backstepping disturbance compensationfor robust current control of PMSM drives, ISA Transactions,128, 2022, 581–592.
  5. [5] W. Abbasi, F. Rehman, I. Shah, and A. Rauf, Stabilizingcontrol algorithm for nonholonomic wheeled mobile robotusing adaptive integral sliding mode, International Journal ofRobotics and Automation, 34, 2019, 1–8.
  6. [6] L. Lin, J. P. L¨u, and M. Z. Lin, Research on vector controlsystem of permanent magnet synchronous motor based onactive disturbance rejection control, Electric Drive AutomationControl, 45(1), 2023, 6–9.
  7. [7] L. Zhang, J. Ma, Q. Wu, Z. He, T. Qin, and C. Chen, Researchon PMSM speed performance based on fractional orderadaptive fuzzy backstepping control, Energies, 16(19), 2023,6922.
  8. [8] L. Yi, M. Cong, H. Dong, and D. Liu, Reinforcementlearning and EGA-based trajectory planning for dual robots,International Journal of Robotics and Automation, 33(4), 2018,206–5084.
  9. [9] A. Sara, S. Y. Won, and S. Kim, Battery energy storage controlusing a reinforcement learning approach with cyclic time-dependent Markov process, International Journal of ElectricalPower & Energy Systems, 134, 2022, 107368.
  10. [10] Z. Song, J. Yang, X. Mei, and M. Xu, Deep reinforcementlearning for permanent magnet synchronous motor speedcontrol systems, Neural Computing and Applications, 33(10),2020, 1–10.
  11. [11] W. Wang, L. Li, F. Ye, Y. Peng, and Y. Ma, A large-scalepath planning algorithm for underwater robots based on deepreinforcement learning, International Journal of Robotics andAutomation, 39, 2024, 204–210.
  12. [12] F. L. Giraldo, F. J. Gaviria, I. M. Torres, C. Alonso,and M. Bressan, Deep reinforcement learning using deep-Q-network for global maximum power point tracking: Design andexperiments in real photovoltaic systems, Heliyon, 10(21), 2024,e37974.
  13. [13] B. Li, H. Zhang, and X. Shi, A novel path planning for AUVbased on dung beetle optimization algorithm with deep Q-network, International Journal of Robotics and Automation,40, 2024, 65–73.
  14. [14] Y. Zhao, S. Huang, X. Wang, J. Shi, and S. Yao,Energy management with adaptive moving average filterand deep deterministic policy gradient reinforcement learningfor fuel cell hybrid electric vehicles, Energy, 312, 2024,133395.
  15. [15] R. Mousavifard, K. Alipour, A. M. Najafqolian, and P.Zarafshan, Quadrotor trajectory tracking using combinedstochastic model-free position and DDPG-based attitudecontrol, ISA Transactions, 156, 2024, 240–252.
  16. [16] B. Feng, Y. J. Hu, and G. Huang, A review of deepreinforcement learning-based novel power system dispatchoptimization methods, Automated Electric Power Systems,47(17), 2023, 187–199.
  17. [17] J. Zhou, Y. Wang, Z. Yang, and D. Zhao, Research ontransition state control strategy of propfan engine based on SACalgorithm, Journal of Physics: Conference Series, 2472(1),2023, 12055.
  18. [18] S. Toufigh Bararpour, Mohammad Reza Feylizadeh, AminDelparish, Mojtaba Qanbarzadeh, Milad Raeiszadeh, andMehrzad Feilizadeh, Artificial Neural Network, Investigatorsat Shiraz University Report Findings in Artificial NeuralNetwork (Investigation of 2-nitrophenol solar degradationin the simultaneous presence of K2S2O8 and H2O2: Usingexperimental design and artificial neural network), Chemicals& Chemistry, 176, 2018, 1245.11
  19. [19] Y. Ma, A. D. Nore˜na-Caro, J. A. Adams, T. B. Brentzel,J. A. Romagnoli, and M. G. Benton, Machine-learning-basedsimulation and fed-batch control of cyanobacterial-phycocyaninproduction in Plectonema by artificial neural network and deepreinforcement learning, Computers & Chemical Engineering,142, 2020, 107016.
  20. [20] T. Zwerger and P. Mercorelli, Optimal control strategies forPMSM with a decoupling super twisting SMC and inductanceestimation in the presence of saturation, Journal of the FranklinInstitute, 361(11), 2024, 106934.
  21. [21] Q. Jiang, Y. Ma, J. Liu, and J. Yu, Full state constraints-based adaptive fuzzy finite-time command filtered controlfor permanent magnet synchronous motor stochastic systems,International Journal of Control, Automation, and Systems,20(8), 2022, 2543–2553.
  22. [22] G. D. Yang, Y. X. Chen, and C. B. Yan, Model predictive currentcontrol of permanent magnet synchronous motor based oninverter nonlinearity online compensation, Railway EngineeringScience,, 22, 2025, 1–12.
  23. [23] X. H. Wei, Q. Zhang, and T. T. Jiang, Fuzzy adaptive deepreinforcement learning method for transient optimization ofservo systems, Journal of Xi’an Jiaotong University, 55(8),2021, 68–77.
  24. [24] C. Han, Research on sensorless control of PMSM at fullspeed range, Master Thesis, Hunan University of Technology,Zhuzhou City, China, 2020.
  25. [25] J. S. Li, S. J. Pan, and J. T. Lou, Application of fuzzy PIDvariable structure adaptive algorithm in steering motor vectorcontrol for autonomous vehicles, Journal of Electrical andControl, 28(7), 2024, 152–159.
  26. [26] M. Q. Wang, J. Y. Xu, and P. F. Liu, Research on cooperativecontrol of the magnetic levitation train suspension systembased on deep reinforcement learning, Acta Mechanica, 57,2025, 1–14.
  27. [27] D. Z. Zhang, Z. H. Wang, and H. B. Zhou, Optimizationof nuclear power accident diagnosis procedure based on SACreinforcement learning, Nuclear Power Engineering, 45(S1),2024, 85–90.
  28. [28] K. Kou, G. Yang, and W. Q. Zhang, Research on autonomousnavigation method for UAV based on SAC, Journal ofNorthwestern Polytechnical University, 42(2), 2024, 310–318.
  29. [29] M. Cizmic, A. Kramer, and A. Ali, Improved identification ofhigh frequency parameters for self-sensing control of PMSMusing test current signal injection, in Proceedings of 2018IEEE 9th International Symposium on Sensorless Control forElectrical Drives (SLED), Berkeley, CA, USA, 2018, 18–23.
  30. [30] G. Kalnoor and G. Subrahmanyam, A review on applicationsof Markov decision process model and energy efficiency inwireless sensor networks, Procedia Computer Science, 167,2020, 2308–2317.

Important Links:

Go Back