Global Sliding Mode Control Based on Recurrent Wavelet Fuzzy Neural Network Control for H-type Platform

Abstract

A recurrent wavelet fuzzy neural network (RWFNN) control method combined with global sliding mode control (GSMC) is proposed to solve the problem of dual-axis synchronous error of H-type platform system driven by permanent magnet synchronous linear motor. Firstly, global sliding mode controller is designed to eliminate the approaching mode, reduce tracking error and ensure global robustness in the single-axis of H-type platform system. Recurrent wavelet fuzzy neural network compensator is designed for the dual-axis of H-type platform system, to compensate the synchronous error. The simulation results show that the proposed method not only guarantees the global robustness of the system, but also effectively reduces the synchronous error of the system and improves the tracking accuracy.