Intelligent Optimal Recurrent Wavelet Elman Neural Network Control System for Permanent-Magnet Synchronous Motor Servo Drive

Abstract

In this paper, an intelligent control system using recurrent wavelet-based Elman neural network (RWENN) for position control of permanent-magnet synchronous motor (PMSM) servo drive is proposed to achieve high precision tracking performance and to deal with the existence of uncertainties. The proposed intelligent optimal RWENN control system (IORWENNCS) incorporating an optimal controller, a RWENN controller and a robust controller. Based on the principle of optimal control, a position tracking controller is designed to minimize a quadratic performance index. In addition, a RWENN controller with accurate approximation capability is used to approximate a nonlinear function in the optimal control law. Moreover, a robust controller with adaptive bound estimation algorithm is proposed to confront the approximation error. The online adaptive control laws are derived based on the optimal control technique and Lyapunov stability analysis, so that the stability of the IORWENNCS can be guaranteed. Using the proposed control scheme, the position tracking performance is substantially improved and the robustness to uncertainties can be obtained as well. All control algorithms are implemented in a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the proposed IORWENNCS grants robust performance and precise tracking response regardless of load disturbances and PMSM uncertainties.