Research of recurrent wavelet neural network speed controller based on chaotic series adaptive PSO

Abstract

In this paper, a recurrent wavelet neural network(RWNN) control system based on chaotic series adaptive particle swarm optimization (PSO) is proposed to control the PMSM drive system. First, the RWNN control system is developed for the control of PMSM. Moreover, the on-line learning algorithms of the connective weights, translations and dilations of the RWNN are derived using back-propagation(BP) method. Furthermore, the chaotic series adaptive PSO algorithm is adopted to adapt the learning rates of the neural networks to improve the learning capability. The simulation results show that the proposed control scheme has stronger robustness.