Neural network control of a class of nonlinear discrete time systems with asymptotic stability guarantees

In this paper, a single and multi-layer neural network (NN) controllers are developed for a class of nonlinear discrete time systems. Under a mild assumption on the system uncertainties, which include unmodeled dynamics and bounded disturbances, by using novel weight update laws and a robust term, local asymptotic stability of the closed-loop system is guaranteed in contrast with all other NN controllers where a uniform ultimate boundedness is normally shown. Simulation results are presented to show the effectiveness of the controller design.