Identification of Nonlinear System Based on ANFIS with Hybrid Fuzzy Clustering

In this study, Hybrid fuzzy clustering method , which is proposed by Niros and Tsekouras recently, is used to generate an initial TSK fuzzy model with the appropriate cluster centers number and performance index by adjusting the radius of a cluster center. To acquire a TSK fuzzy model with perfect performance, Adaptive neuro-fuzzy inference system is combined to fine tune the premise parameters and consequent parameters by means of Levenberg-Marquardt algorithm. A simulation to a dynamic nonlinear system demonstrates the effective of this method.