Predictive Control Of Hammerstein Model Based On T-S Fuzzy Neural Network

Model Predictive Control(MPC)as a kind of produced in industrial process control algorithm,after decades of development,both in theoretical research and in industrial applications,the linear model predictive control has been mature,but still widespread nonlinear in the process of actual production,makes the effect of the linear model predictive control,so we think the study of nonlinear model predictive control has the necessity very much.The nonlinear predictive control mainly includes mechanism model-based nonlinear model predictive control,experimental model-based nonlinear model predictive control,intelligent model-based nonlinear model predictive control and special model-based nonlinear model predictive control.With the deepening of scientific and technological research,the combination of T-S fuzzy neural network modeling and model predictive control,as well as the control method of Hammerstein model structure,has become an important control method to study typical nonlinear systems.The T-S fuzzy neural network not only has the function of local approximation,but also has the advantages of neural network and fuzzy logic.This paper mainly studies the predictive control based on T-S fuzzy neural network for Hammerstein model-based nonlinear systems.First,the least square support vector machine(LSSVM)is applied to identify the nonlinear system to obtain the Hammerstein model of the nonlinear system,and the inverse model of the static nonlinear part is identified by the T-S fuzzy neural network.The nonlinear control separation strategy is adopted,and the dynamic matrix control algorithm is used to calculate the intermediate variable of the dynamic linear part of Hammerstein model,which is taken as the input of t-s fuzzy neural network,and then the control quantity is mapped out by T-S fuzzy neural network,so as to realize the predictive control of Hammerstein model based on T-S fuzzy neural network.Finally,the control method proposed in this paper is applied to the control of p H neutralization process.The simulation results show that the control effect of the method proposed in this paper is good,with good feasibility and implementation.