Abstract
The permanent magnet synchronous motor (PMSM) servo system is widely applied in many industrial fields due to its unique advantages. In this paper, we study the deep reinforcement learning (DRL) speed control strategy for PMSM servo system, in which exist many disturbances, i.e., load torque and rotational inertia variations. The speed control problem is formulated as a Markov decision process problem, which is computed optimal regulation scheme corresponding to each speed and error state using the deep Q-networks. Simulation results are provided to demonstrate that compared with conventional proportion integral control, the proposed DRL control can improve the robustness against load disturbances and high performance of the PMSM speed control system.
Similar content being viewed by others
References
Ramirez HS, Flores JL, Rodriguez CG, Ordaz MA (2014) On the control of the permanent magnet synchronous motor: an active disturbance rejection control approach. IEEE Trans Control Syst Technol 22(5):2056–2063
Kommuri SK, Defoort M, Karimi HR, Veluvolu KC (2016) A robust observer-based sensor fault-tolerant control for PMSM in electric vehicles. IEEE Trans Ind Electron 63(12):7671–7681
Shao XY, Sun D (2007) Development of a new robot controller architecture with FPGA-based IC design for improved high-speed performance. IEEE Trans Ind Inf 3(4):312–321
Guo H, Xu JQ, Chen YH (2015) Robust control of fault-tolerant permanent-magnet synchronous motor for aerospace application with guaranteed fault switch process. IEEE Trans Ind Electron 62(12):7309–7321
Su YX, Zheng CH, Duan BY (2005) Automatic disturbances rejection controller for precise motion control of permanent-magnet synchronous motors. IEEE Trans Ind Electron 52(3):814–823
Li SH, Liu ZG (2009) Adaptive speed control for permanent-magnet synchronous motor system with variations of load inertia. IEEE Trans Ind Electron 56(8):3050–3059
Mohamed YA-RI (2007) Design and implementation of a robust current-control scheme for a PMSM vector drive with a simple adaptive disturbance observer. IEEE Trans Ind Electron 54(4):1981–1988
Choi HH, Vu NT-T, Jung J-W (2011) Digital implementation of an adaptive speed regulator for a PMSM. IEEE Trans Power Electron 26(1):3–8
Zhang X, Sun L, Zhan K, Sun L (2013) Nonlinear speed control for PMSM system using sliding-mode control and disturbance compensation techniques. IEEE Trans Power Electron 28(3):1358–1365
Zhi DW, Xu L, Williams BW (2010) Model-based predictive direct power control of doubly fed induction generators. IEEE Trans Power Electron 25(2):341–351
Chen CS (2010) TSK-type self-organizing recurrent-neural-fuzzy control of linear microstepping motor drives. IEEE Trans Power Electron 25(9):2253–2265
Kohl N, Stone P (2004) Policy gradient reinforcement learning for fast quadrupedal locomotion. In: Proceedings of international conference on robotics and automation, pp 2619–2624
Ng AY, Coates A, Diel M, Ganapathi V, Schulte J, Tse B, Berger E, Liang E (2006) Autonomous inverted helicopter flight via reinforcement learning, In: Proceedings of international symposium on experimental robotics, pp 363–372
Singh S, Litman D, Kearns M, Walker M (2002) Optimizing dialogue management with reinforcement learning: experiments with the NJ fun system. J Artif Intell Res 16:105–133
Shi H, Sun Y, Li G, Wang F (2019) Hierarchical intermittent motor control with deterministic policy gradient. IEEE Access. 7:41799–41810
Liu K, Zhu Z (2017) Fast determination of moment of inertia of permanent magnet synchronous machine drives for design of speed loop regulator. IEEE Trans Control Syst Technol 25(5):1816–1824
Errouissi R, Al-Durra A, Muyeen SM (2018) Experimental validation of a novel PI speed controller for AC motor drives with improved transient performances. IEEE Trans Control Syst Technol 26(4):1414–1421
Apte A, Thakar U, Joshi V (2019) Disturbance observer based speed control of PMSM using fractional order PI controller. IEEE/CAA J Autom Sinica 6(1):316–326
Kim S, Ahn CK (2019) Offset-free proportional-type self-tuning speed controller for permanent magnet synchronous motors. IEEE Trans Ind Electron 66(9):7168–7176
Kim S-K (2017) Robust adaptive speed regulator with self-tuning law for surfaced-mounted permanent magnet synchronous motor. Control Eng Pract 61:55–71
Liu H, Li S (2012) Speed control for PMSM servo system using predictive functional control and extended state observer. IEEE Trans Ind Electron 59(2):1171–1183
Acknowledgements
This work was financially supported by the National Key Research and Development Program of China (2016YFB1102503), Research Project of State Key Lab of Digital Manufacturing Equipment and Technology (DMETKF2019017), and the National Natural Science Foundation of China (No. 51605375). This work was also supported in part by the Science and Technology Co-ordination and Innovation Program of Shaanxi Province, China, under Grant 2015KTZDGY-02-01.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Song, Z., Yang, J., Mei, X. et al. Deep reinforcement learning for permanent magnet synchronous motor speed control systems. Neural Comput & Applic 33, 5409–5418 (2021). https://doi.org/10.1007/s00521-020-05352-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05352-1