Neural Sliding Mode Control for Hysteresis Systems

Authors:	Tan Yonghong, Guilin University of Electronic Technology, China Li Chuntao, Nanjing University of Aeronautics and Astronautics, China
Topic:	2.1 Control Design
Session:	Sliding Mode Control I
Keywords:	Neural networks; hysteresis; adaptive control; sliding-mode control; modelling

Abstract

In this paper, a neural network based adaptive sliding mode control scheme for hysteretic systems is proposed. In this control scheme, a neural network model is utilized to describe the characteristic of hysteresis. Then, the adaptive neural sliding mode controller based on the proposed neural model is presented for a class of single-input nonlinear systems with unknown hysteresis. For the case where theoutput of hysteresis is unmeasurable, the neural network model is applied to estimate the effect of hysteresis. Based on the model-based estimation, the effect of hysteresis on the performance of the system is compensated.