Abstract: A fuzzy self-tuning controller based on fuzzy competitive learning is proposed in this paper. First of all, an on-line fuzzy identifying algorithm is confirmed by means of fuzzy competitive learning, and the convergence about a recursive algorithm of fuzzy competitive learning is proved. On the basis of on-line identification of subjects with the aid of the proposed method, the parameters of the adjuster are automatically adjusted. The proposed method is used to control a non-linear system to demonstrate its advantages, and the result is shown at the end of the paper.

Key words: fuzzy competitive learning, self-tuning controller, fuzzy identifying, static Kalman filtering