Speed control of PMSM based on neural network model predictive control

Abstract

In order to optimize the control performance of permanent magnet synchronous motor (PMSM) servo system, an improved model predictive control (MPC) scheme based on neural network is investigated in this paper. First, the dynamic characteristics of the PMSM are approximated by echo state network (ESN) to predict the future speed. Particle swarm optimization (PSO) is used to train ESN output weights to solve the problem that instability of output weights caused by pseudo-inverse matrix in ESN weight solving algorithm, called PSO-ESN, which enhances the stability and the accuracy of ESN speed prediction. That provides future plant output for control optimization of the predictive control. Furthermore, in order to reduce the computational cost and improve the response performance of the controller, a fast gradient method (GM) is applied to minimize the quadratic performance index and solve the optimal control input sequences. The simulation results under three different working conditions show that the PSO-ESNMPC controller designed in this paper reduces the overshoot by 5.87% and the rise time by 0.036 s compared with the reference controllers and has better robustness under parameter changes and load disturbances.

Nonlinear speed-tracking control with overcurrent protection for uncertain permanent magnet synchronous motor systems

“…In this work, we address the issues of overcurrent protection, speed tracking, and unknown disturbances simultaneously. In this way, a balance between satisfactory control performance and reliable system safety is achieved, which however is not the case in many existing works (Chaoui et al, 2019; Ghafari-Kashani et al, 2020; Lin et al, 2021; Mao et al, 2022; Qu et al, 2021; Song et al, 2022; Sun et al, 2018; Wu et al, 2023; Xia et al, 2021; Xu et al, 2019; Zhang et al, 2019; Zhu et al, 2020).…”

“…1) In this work, we address the issues of overcurrent protection, speed tracking, and unknown disturbances simultaneously. In this way, a balance between satisfactory control performance and reliable system safety is achieved, which however is not the case in many existing works (Chaoui et al, 2019;Ghafari-Kashani et al, 2020;Lin et al, 2021;Mao et al, 2022;Qu et al, 2021;Song et al, 2022;Sun et al, 2018;Wu et al, 2023;Xia et al, 2021;Xu et al, 2019;Zhang et al, 2019;Zhu et al, 2020 et al (2019). As a result, in previous works, the conservative selection of small control gains is required to prevent the overcurrent issue, which however is not necessary for the proposed method, thereby avoiding the performance degradation.…”

“…However, the PI controller essentially belongs to linear control strategies, which could not effectively overcome the influence of multiple disturbances including parameter uncertainties and unknown load torque variations. To ensure the satisfactory control performances with respect to the disturbances, numerous efforts have been made to propose different control strategies, such as sliding mode control (SMC; Ghafari-Kashani et al, 2020; Zhu et al, 2020), adaptive control (Sun et al, 2018; Xia et al, 2021), disturbance observer based control (Qu et al, 2021; Xu et al, 2019; Zhang et al, 2019), auto disturbance rejection control (Lin et al, 2021; Wu et al, 2023), and intelligent control (Chaoui et al, 2019; Mao et al, 2022; Song et al, 2022).…”

“…The overcurrent protection is considered in this work, while was not involved in the studies by Ghafari-Kashani et al (2020); Zhu et al (2020); Xia et al (2021); Sun et al (2018); Xu et al (2019); Zhang et al (2019); Qu et al (2021); Lin et al (2021); Wu et al (2023); Mao et al (2022); Song et al (2022); Chaoui et al (2019). As a result, in previous works, the conservative selection of small control gains is required to prevent the overcurrent issue, which however is not necessary for the proposed method, thereby avoiding the performance degradation.…”