Model reference adaptive control for MIMO nonlinear systems using RBF neural networks

Abstract

This paper deals with the synthesis of an adaptive controller for multi-input multi-output nonlinear systems based on Radial Basis Function (RBF) neural networks. The stable controller-parameters adjustment mechanism is determined using the convergence of the synaptic weights of the RBF model. The evaluation of tracking error between the system output and that of the neural network desired reference model depends on the approximation error of the RBF model. Updating of the RBF neural network width, center, and weight characteristics is performed such that control error reduction and improved tracking accuracy are accomplished. The control signal obtained can make the real system close to the reference model.