Synthesis of the sliding-mode neural network controller for unknown nonlinear discrete-time systems

This paper develops a sliding-mode neural network controller for a class of unknown nonlinear discrete-time systems using a recurrent neural network ( RNN). The control scheme is based on a linearized expression of the nonline ar system using a linear neural network (LNN). The cont, ol law is proposed according to the discrete Lyapunov theory. With a modified real-time recur rent learning algorithm, the RNN as an estimator is used to estimate the un known part in the control law in on-line fashion. The stability of the cont rol system is guaranteed owing to the on-line learning ability of the RNN a lgorithm. The proposed control scheme is applied to numerical problems and simulation results that it is very effective.