Fuzzy Identification of Nonlinear Systems via Orthogonal Decomposition

First of all, competitive learning takes place in the product space of systems inputs and outputs and each cluster corresponds to a fuzzy IF-THEN rule. Fuzzy relation matrix confirmed by fuzzy competitive learning is studied by orthogonal least square algorithm. The validity of fuzzy rules is obtained by means of analyzing the efforts of orthogonal vectors in fuzzy model, and subsequently removes less important ones. The structure identification and the parameter identification of fuzzy model are simultaneously confirmed in the proposed algorithm. Simulation results demonstrate that the presented approach can build the fuzzy models of nonlinear systems.