Discrete-time adaptive control of nonlinear systems using neural networks

Abstract

A neural-adaptive control system for a class of discrete-time nonlinear plants is proposed. Neural networks and adaptation are required to ensure stability and asymptotic convergence of the tracking error, in spite of the nonlinear and unknown plant dynamics. An augmented error adaptive approach is taken. The effect of the inevitable imperfect approximation accuracy of the neural network on system stability is taken into consideration by using dead-zone adaptation. Stability and convergence proofs are presented together with a simulation example.