Integrating design stage of fuzzy systems using genetic algorithms
- 1 April 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The authors propose an automatic fuzzy system design method that uses a genetic algorithm and integrates three design stages. The method determines membership functions, the number of fuzzy rules, and the rule-consequent parameters at the same time. Because these design stages may not be independent, it is important to consider them simultaneously to obtain optimal fuzzy systems. The method includes a genetic algorithm and a penalty strategy that favors systems with fewer rules. The method was applied to the classic inverted-pendulum control problem and has been shown to be practical through a comparison with another method.<>Keywords
This publication has 4 references indexed in Scilit:
- Fuzzy controller design without domain expertsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Self-learning fuzzy controllers based on temporal backpropagationIEEE Transactions on Neural Networks, 1992
- NN-driven fuzzy reasoningInternational Journal of Approximate Reasoning, 1991
- Fuzzy identification of systems and its applications to modeling and controlIEEE Transactions on Systems, Man, and Cybernetics, 1985