A Novel Neuro-Wavelet-Based Self-Tuned Wavelet Controller for IPM Motor Drives

Abstract

This paper presents a hybrid neuro-wavelet scheme for online tuning of a wavelet-based multiresolution proportional integral derivative (MRPID) controller in real time for precise speed control of an interior permanent-magnet synchronous motor (IPMSM) drive system under system uncertainties. In the proposed wavelet-based MRPID controller, the discrete wavelet transform (DWT) is used to decompose the speed error between actual and command speeds into different frequency components at various scales of the DWT. The MRPID controller parameters are tuned online by the wavelet neural network (WNN) to ensure optimal performance of the drive system. The neurowavelet-based MRPID controller is trained online with adaptive learning rates in the closed-loop control of the IPMSM drive system. The adaptive learning rates are derived using the discrete Lyapunov stability theorem so that the convergence of speed tracking error could be guaranteed in the closed-loop system. The performance of the proposed hybrid controller is investigated in both simulation and experiments at different dynamic operating conditions. The complete vector control scheme incorporating the proposed self-tuning MRPID controller is successfully implemented in real time using the digital signal processor board ds1102 for the laboratory 1-hp interior permanent-magnet motor. The superior performance of the proposed WNN-based self-tuning MRPID controller is also validated over fixed-gain controllers.