Design of Control Structure Schemes and Simulation Research of GPC Based on NN for Nonlinear System

Abstract

Though the generalized predictive control (GPC) algorithm had been gotten well control effect to the linear or weak nonlinear systems, there are still difficulties to construct many steps predictive models and its control laws for the strong nonlinear systems. For solving the questions, based on the high nonlinear mapping property of artificial neural networks (NN), the control method which is GPC's algorithm with the NN's technologies is studied. The GPC's control structure scheme based on NN for the nonlinear system is designed. The GPC's control principle, control algorithm and setting different parameters of the GPC criterion function are analysed. Finally, simulation researches of GPC's algorithm for the nonlinear system based on the NN have done. Simulation results show, the GPC's control structure scheme based on NN for nonlinear system is feasible and effective