A Model Reference Adaptive Control Based on Fuzzy Neural Network for Some Weapon Ac Servo System

Abstract

Abstract.This paper presents a novel model reference adaptive control algorithm based on fuzzy neural network. This widely used method is utilized to adjust the parameters on line. The fuzzy neural network sliding mode controller,which integrates the fuzzy neural network with sliding mode controller, is put forward to control some weapon servo system with model uncertainties and parameters variation. Because this proposed algorithm combines excellences of FNN and sliding mode control, it has the ability to eliminate the drawbacks of traditional SMC, i.e. the chattering in the control signal and needing knowledge of bounds of uncertainties. Simulation results verify this proposed algorithm can reduce the plant\u2019s sensitivity to parameter variation and disturbance.