论文信息 - A study on finding fuzzy rules for semi-active suspension controllers with genetic algorithm

A study on finding fuzzy rules for semi-active suspension controllers with genetic algorithm

This paper presents a new method to generate fuzzy controllers through genetic algorithm (GA). A CA with a new local improvement mechanism, which is based on genetic recombination in bacterial genetics, is applied to our method. This new algorithm is ejj-icient in improvement of local portions of chromosomes. Appropriate combinations of input variables, number of fuzzy rules and parameters for membership functions are determined automatically through the GA operations. Comparisons with other conventional GAS are also discussed. To show the effectiveness of our approach, fuzzy controllers for semi-active suspension system are generated.

T. Hashiyama | T. Furuhashi | Y. Uchikawa

[1] Dean Karnopp,et al. Vibration Control Using Semi-Active Force Generators , 1974 .

[2] Kalyanmoy Deb,et al. Don't Worry, Be Messy , 1991, ICGA.

[3] Heinz Mühlenbein,et al. Parallel Genetic Algorithms, Population Genetics, and Combinatorial Optimization , 1989, Parallelism, Learning, Evolution.

[4] Dorion Sagan,et al. Microcosmos: Four Billion Years of Evolution from Our Microbial Ancestors , 1986 .

[5] Y. Uchikawa,et al. A New Approach to Genetic Based Machine Learning and an Efficient Finding of Fuzzy Rules - Proposal of Nagoya Approach - , 1994, IEEE/Nagoya-University World Wisepersons Workshop.

[6] William J. Hagan,et al. Microcosmos: Four Billion Years of Microbial Evolution. Lynn Margulis , Dorion SaganOrigins: A Skeptic's Guide to the Creation of Life on Earth. Robert Shapiro , 1987 .