Design of TS Fuzzy Model Based on Cooperative Evolutionary Algorithm

An approach to construct TS fuzzy model based on cooperative co-evolutionary algorithm is proposed.The approach is composed of two phases:(1) the initial fuzzy system is identified using the fuzzy clustering algorithm;(2) the structure and parameters of the fuzzy system are optimized by the cooperative co-evolutionary algorithm.The cooperative co-evolutionary algorithm owns two species including the fuzzy rule premise species and the parameters species.Considering both precision and interpretability,the fitness function is defined and calculated on the cooperation of individuals from the two species.In order to improve interpretability of the fuzzy model,the similarity-driven rule base simplification techniques are used to reduce the fuzzy model.The proposed approach is applied to the Mackey-Glass system,and the results show its validity.