Hybrid ${\rm H}^{\infty}$-Based Wavelet-Neural-Network Tracking Control for Permanent-Magnet Synchronous Motor Servo Drives

Abstract

This paper proposes a hybrid H∞-based wavelet-neural-network (WNN) position tracking controller as a new robust motion-control system for permanent-magnet synchronous motor (PMSM) servo drives. The combinations of both WNN and H∞ controllers would insure the robustness and overcome the uncertainties of the servo drive. The new controller combines the merits of the H∞ control with robust performance and the WNN control (WNNC) which combines the capability of NNs for online learning ability and the capability of wavelet decomposition for identification ability. The online trained WNNC is utilized to predict the uncertain system dynamics to relax the requirement of uncertainty bound in the design of the H∞ controller. The WNNC generates an adaptive control signal to attain robust performance regardless of parameter uncertainties (PU) and load disturbances. Systematic methodology for both controllers' design is provided. A computer simulation is developed to demonstrate the effectiveness of the proposed WNN-based H∞ controller. An experimental system is established to validate the effectiveness of the drive system. All control algorithms are implemented in a TMS320C31 DSP-based control computer. The simulated and experimental results confirm that the new motion controller grants robust performance and precise dynamic response regardless of load disturbances and PMSM PU.