Identification of Nonlinear System Based on ANFIS with Hybrid Fuzzy Clustering

摘要

In this study, HFCM (Hybrid fuzzy clustering method) which is proposed by Niros and Tsekouras (2012) 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, ANFIS (Adaptive neuro-fuzzy inference system) is combined to fine tune the premise parameters and consequent parameters by means of LM (Levenberg-Marquardt) Algorithm. A simulation to a dynamic nonlinear system demonstrates the effective of this method.