Discrete-time neural network control of nonlinear systems in non-strict feedback form

Abstract

In this paper, an adaptive multilayer neural-network (NN) controller is designed to deliver a desired tracking performance for the control of a class of unknown nonlinear systems in discrete time where the system is expressed in non-strict feedback form. Three NNs are used where two NNs approximate the dynamics of the nonlinear system whereas the third critic NN generates a critic signal, which is used to tune the weights of the action generating NNs. The NN control scheme uses backstepping approach and presents a well-defined controller design. The stability analysis of the closed-loop control system is given and the uniform ultimately boundedness (UUB) of the closed-loop tracking error is shown.