A Novel Dynamic Clustering Algorithm and its Application in Fuzzy Modeling for Thermal Processes

A novel dynamic evolutionary clustering algorithm (DECA) is proposed in this paper to overcome the shortcomings of fuzzy modeling method based on general clustering algorithms that fuzzy rule number should be determined beforehand. DECA searches for the optimal cluster number by using the improved genetic techniques to optimize string lengths of chromosomes; at the same time, the convergence of clustering center parameters is expedited with the help of fuzzy c-means (FCM) algorithm. Moreover, by introducing memory function and vaccine inoculation mechanism of immune system, at the same time, DECA can converge to the optimal solution rapidly and stably. The proper fuzzy rule number and exact premise parameters are obtained simultaneously when using this efficient DECA to identify fuzzy models. The effectiveness of the proposed fuzzy modeling method based on DECA is demonstrated by simulation examples, and the accurate non-linear fuzzy models can be obtained when the method is applied to the thermal processes