Study of Generalized Predictive Control Scheme and Algorithm Based on Artificial Neural Network

Predictive control algorithm had been developed rapidly and successfully used in the industrial production practice from the 20th century 70´s until now, and the generalized predictive control (GPC) algorithm had been gotten well control effect to the linear or weak nonlinear systems. But there were still difficulties to construct many steps predictive models and its control rules for the strong nonlinear systems. For solved the questions, based on the high nonlinear mapping property of artificial neural networks (ANN), the control structure scheme which was GPC´s algorithm with the ANN´s technologies was studied. The GPC´s control structure scheme and its algorithm based on ANN for the nonlinear system were designed. The GPC´s control principle, control algorithm and setting different parameters of the GPC´s criterion function were analysed. Finally, simulation studies of the GPC control structure scheme and its algorithm based on the ANN have done for the nonlinear system. Simulation results show, the GPC´s control structure scheme and its algorithm based on ANN were feasible and effective for nonlinear system.