NN-adaptive predictive control for a class of discrete-time nonlinear systems with input-delay

Abstract

An adaptive neural network (NN) predictive control algorithm is proposed for a class of uncertain discrete-time nonlinear systems with input-delay. For approximate the nonlinear part of the uncertain discrete-time nonlinear system, the recurrent neural network (RNN) is employed. A version of discrete-time NN weight update rule is given. For compensate the reconstructive error of the RNN and the external disturbances, the robust control term is designed. In order to compensate the time-delay in input channel, a predictive control algorithm is proposed. Then the synchronous tracking objective can be realized. An illustrative example is provided to demonstrate the effectiveness of the proposed control strategy.