Generation of fuzzy rules using Kernel based clustering in the design of Fuzzy Controller

摘要

Fuzzy Controller design approaches are represented by TSK fuzzy models. In the conventional design, a table look up scheme is used to generate fuzzy rules. However with a predefined membership function, the number of fuzzy rules increases with increase in input variables. In this paper, a technique using kernel based hybrid c-means clustering (KPFCM) to derive fuzzy structure and fuzzy if-then rules is proposed. The proposed approach provides a mechanism to obtain the reduced rule set covering the whole input/output space as well as membership functions for each input variable. Performance of the proposed FLC is compared with that of its corresponding conventional FLC in terms of several performance measures such as rise time, peak overshoot, settling time, integral absolute error (IAE) and integral of time multiplied absolute error (ITAE) and in each case, the proposed scheme shows an identical performance over its conventional counterpart. Thus we show that the proposed scheme is able to identify the minimum rule base needed to realize the fuzzy PI,PD type controllers and its performance is found to be satisfactory. Also it is shown that the proposed controller scheme gives faster results as it reduces the computational time.