Research On The Modeling And Control Algorithm For Nonlinear System Based On C-R Fuzzy Model

Modern control theory has found the comparatively perfect theoretical system until now. But, it is based on the perfect model, and this condition is hard to been satisfied in real environment, so its application in industry is not ideal, and its effect often not better than PID controller. Nonlinear systems exist in the world extensively. As for nonlinear systems, it is difficult to get the accurate mathematic model. Even we can build mathematic model for those systems, it may be too complicated to design a controller with conventional means. It is the artificial intelligent control based on knowledge that takes bright future for the above problems. The study of this paper is based on the C-R fuzzy model of nonlinear system.C-R fuzzy model structure of a complex system and its identification method are studied, include Fuzzy Input Space Clustering Algorithm (FISCA) and Fuzzy Output Space Clustering Algorithm (FOSCA). Because of the blindness of choosing the initial factor in real using, we change the initial membership and make them close to the working station. The number of judgment is reduced by changing the condition of final judgment.The problem of the nonlinear modeling and the solution of nonlinear optimization is exist in the predictive control of nonlinear system. Using the C-R fuzzy model to construct the nonlinear system and combing the Fuzzy Input Space Clustering Algorithm (FISCA) with Generalized Predictive Control (GPC), a new predictive control algorithm is proposed - CR-GPC.Considered the limitation of PID control algorithm using in nonlinear system, we change the C-R fuzzy model to a C-R fuzzy step model, its structure is similar to step response model. Then we use PID control algorithm to control the nonlinear system based on the C-R fuzzy model.