A new approach to the identification of a fuzzy model

This paper presents an approach which is useful for the identification of a fuzzy model. The identification of a fuzzy model using input-output data c onsists of two parts: structure identification and parameter identification . In this paper, algorithms to identify those parameters and structures are suggested to solve the problems of conventional methods. Given a set of in put-output data, the consequent parameters are identified by the Hough tran sform and clustering method, which consider the linearity and continuity, r espectively. For the premise part identification, the input space is partit ioned by a clustering method. The gradient descent algorithm is used to fin e-tune parameters of a fuzzy model. Finally, it is shown that this method i s useful for the identification of a fuzzy model by simulation. (C) 1999 El sevier Science B.V. All rights reserved.