Modeling and simulation of current control for permanent magnet synchronous motors based on multilayer perceptron neural networks

基于多层感知机神经网络永磁同步电机模型预测电流控制建模仿真

School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China

Received: 13 January 2025

Abstract

In the traditional finite control set model predictive current control(FCS-MPCC) for a permanent magnetic synchronous motor (PMSM), periodic delay caused by computational latency and hardware register update mechanisms leads to control commands lagging behind actual motor states, thereby impairing dynamic response and control stability of the PMSM. To address the issue, this paper introduces a two-step finite control set model predictive current control(FCS-MPCC) method. By predicting two-step current states simultaneously and generating control commands for the current time step in the previous cycle, the introduced method effectively reduces the impact of control delay and improves prediction accuracy. However, while the two-step FCS-MPCC method enhances control performance, the more complex computational logic increases the computational burden, limiting its real-time applicability. To overcome the limitation, the paper proposes a method based on the multilayer perceptron(MLP) neural network, which replaces traditional model predictive control strategies with a data-driven method. By learning the optimization rules of the two-step FCS-MPCC, the MLP neural network can replicate its control performance without requiring online computational efforts. The simulation results demonstrate that the proposed method exhibits strong robustness under secondary load disturbances, further validating its potentials for application in motor control.

摘要

永磁同步电机(PMSM)的传统有限控制集模型预测电流控制(FCS-MPCC)方法中, 由于计算延时和硬件寄存器更新机制引入的周期性延迟, 控制指令滞后于实际电机状态, 削弱了动态响应和控制稳定性。为解决这一问题, 引入两步有限集模型预测电流控制(T-FCS-MPCC), 通过同时预测两步电流状态, 在上一周期生成当前时刻的控制指令, 从而有效降低控制延时的影响, 并提升预测精度。然而, T-FCS-MPCC虽然改善了控制性能, 但更复杂的计算逻辑增加了计算负担, 降低了其实时性。为此, 提出基于多层感知机(MLP)神经网络的方法, 以数据驱动方式代替传统模型预测控制策略。MLP神经网络通过学习T-FCS-MPCC的优化规则, 能够较好地复现其控制性能, 且不需要在线控制计算。仿真研究表明, 该方法在二次负载干扰下表现出良好的鲁棒性, 进一步验证了其在电机控制中的应用潜力。

1. QUANG N K, HIEU N T, HA Q P. FPGA-based sensorless PMSM speed control using reduced-order extended Kalman filters[J]. IEEE Trans on Industrial Electronics, 2014, 61(12): 6574–6582. [Article] [Google Scholar]
2. HWANG S W, CHIN J W, LIM M S. Design process and verification of SPMSM for a wearable robot considering thermal characteristics through LPTN[J]. IEEE/ASME Trans on Mechatronics, 2021, 26(2): 1033–1042. [Article] [Google Scholar]
3. CHAN C C. The state of the art of electric and hybrid vehicles[J]. Proceedings of the IEEE, 2002, 90(2): 247–275. [Article] [Google Scholar]
4. DANG C, DOU M, YAN S, et al. An improved adaptive sliding mode speed control of PMSM drives with an extended state observer[J]. IEEE Trans on Energy Conversion, 2024, 39(4): 2349–2361. [Article] [Google Scholar]
5. TRAN H N, JEON W. Robust speed controller using dual adaptive sliding mode control(DA-SMC) method for PMSM drives[J]. IEEE Access, 2023, 11: 63261–63270. [Article] [Google Scholar]
6. MENDOZA-MONDRAGÓN F, HERNÁNDEZ-GUZMÁN V M, RODRÍGUEZ-RESÉNDIZ J. Robust speed control of permanent magnet synchronous motors using two-degrees-of-freedom control[J]. IEEE Trans on Industrial Electronics, 2018, 65(8): 6099–6108. [Article] [Google Scholar]
7. ZHANG J, REN W, SUN X M. Current-constrained adaptive robust control for uncertain PMSM drive systems: theory and experimentation[J]. IEEE Trans on Transportation Electrification, 2023, 9(3): 4158–4169. [Article] [Google Scholar]
8. ZOU W, SHI T, GUO J, et al. A novel adaptive fuzzy control scheme for a class of nonlinear planar systems under state constraints[J]. IEEE Trans on Circuits and Systems Ⅱ: Express Briefs, 2024, 71(2): 827–831 [Google Scholar]
9. ZHANG Y, WANG Q G, LIU J, et al. Command filtered fuzzy adaptive control for PMSMs with time-varying state constraints and stochastic disturbances[J]. IEEE Trans on Transportation Electrification, 2024, 10(3): 5614–5623. [Article] [Google Scholar]
10. MORARI M, LEE J H. Model predictive control: past present and future[J]. Computers & Chemical Engineering, 1999, 23: 667–682 [Google Scholar]
11. ZARBIL M S, SAEIDI M, VAHEDI A, et al. Continuous control set model predictive control(CCS-MPC) of a three-phase rectifier[J]. Zanco Journal of Pure and Applied Sciences, 2019, 31: 342–350 [Google Scholar]
12. KOURO S, CORTES P, VARGAS R, et al. Model predictive control-a simple and powerful method to control power converters[J]. IEEE Trans on Industrial Electronics, 2009, 56(6): 1826–1838. [Article] [Google Scholar]
13. GAO J, GONG C, LI W, et al. Novel compensation strategy for calculation delay of finite control set model predictive current control in PMSM[J]. IEEE Trans on Industrial Electronics, 2020, 67(7): 5816–5819. [Article] [Google Scholar]
14. YARAMASU V, RIVERA M, WU B, et al. Model predictive current control of two-level four-leg inverters-part Ⅰ: concept, algorithm, and simulation analysis[J]. IEEE Trans on Power Electronics, 2013, 28(7): 3459–3468 [Google Scholar]
15. GU M, YANG Y, FAN M, et al. Finite control set model predictive torque control with reduced computation burden for pmsm based on discrete space vector modulation[J]. IEEE Trans on Energy Conversion, 2023, 38(1): 703–712 [Google Scholar]
16. KAWAI H, ZHANG Z, KENNEL R. Finite control set-model predictive speed control with a voltage smoother[C]//IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, 2018 [Google Scholar]
17. FAVATO A, CARLET P G, TOSO F, et al. Integral model predictive current control forsynchronous motor drives[J]. IEEE Trans on Power Electronics, 2021, 36(11): 13293–13303 [Google Scholar]