Extracting fuzzy rules for system modeling using a hybrid of genetic algorithms and Kalman filter

This paper proposes a hybrid algorithm for extracting important fuzzy rules from a given rule base to construct a "parsimonious'' fuzzy model with a h igh generalization ability. This algorithm combines the advantages of genet ic algorithms' strong search capacity and Kalman filter's fast convergence merit. Each random combination of the rules in the rule base is coded into a binary string and treated as a chromosome in genetic algorithms. The bina ry string indicates the structure of a fuzzy model. The parameters of the m odel are then estimated using the Kalman filter. In order to achieve a trad e-off between the accuracy and the complexity of a fuzzy model, the Schwarz -Rissanen Criterion is used as an evaluation function in the hybrid algorit hm. The practical applicability of the proposed algorithm is examined by co mputer simulations on a human operator modeling problem and a nonlinear sys tem modeling problem. (C) 1999 Elsevier Science B,V. All rights reserved.