A self-organizing decentralized fuzzy neural net controller

Abstract

This paper presents a self-organizing decentralized learning controller using fuzzy control and neurocontrol for large-scale nonlinear systems. A new online unsupervised learning method which is based on a performance index of sliding mode control is used to train the fuzzy neural net controller to obtain control actions. To overcome the interactions between the subsystems, a learning algorithm is adopted to modify the control input to improve the system performance. The effectiveness and the performance of the proposed approach are illustrated by the simulation results of a two-inverted pendulum system and a two-link manipulator. The attractive features also include a smaller residual error and robustness against nonlinear interactions.