Title :
A new method for fuzzy models identification
Author :
Cipriano, A. ; Ramos, M. ; Montoya, F.
Author_Institution :
Fac. of Eng., Catholic Univ. of Chile, Santiago, Chile
Abstract :
In this paper a new method for fuzzy models identification is presented. The algorithm is based on an iterative procedure and determines the optimal membership functions through the minimization of the root mean square error. Using illustrative examples the new method is evaluated and compared with the identification algorithm of Sugeno and Yasukawa, and the Horikawa algorithm
Keywords :
fuzzy set theory; identification; iterative methods; Horikawa algorithm; Sugeno and Yasukawa algorithm; fuzzy models identification; identification algorithm; iterative procedure; optimal membership functions; root mean square error minimisation; Automatic control; Backpropagation algorithms; Clustering algorithms; Fuzzy sets; Input variables; Iterative algorithms; Least squares methods; Minimization methods; Neural networks; Parameter estimation;
Conference_Titel :
Industrial Electronics, Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE IECON 21st International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-3026-9
DOI :
10.1109/IECON.1995.484175
