Output tracking of a class of unknown nonlinear discrete-time systems using neural networks

In this paper, an adaptive controller based on neural networks is derived for controlling a class of unknown nonlinear discrete-time systems. A two-layered neural network is used to characterize the input-output behavior of the unknown systems. The Widrow-Hoff delta rule is the learning algorithm used to minimize the error signal between the actual response and that of the neural networks. The control signal is generated on-line using another two-layered neural network, so that the plant results in zero asymptotic tracking errors with respect to a desired reference signal. It is proved that the control objective is achieved by the closed-loop system and that the system remains closed-loop stability. The effectiveness of the proposed control scheme is also demonstrated by a simulation example.