Rule-base generation via symbiotic evolution for a Mamdani-type fuzzy control system

An algorithm for generating the rule-base of fuzzy systems via symbiotic evolution is proposed. Because the initially generated rules generally reflect an opaque structure with redundant membership functions, we also applied a new algorithm to merge any similar membership functions. It is shown that this algorithm leads generally to a more transparent and more interpretable rule-base with a minimum number of membership functions and a reduced number of rules. The proposed methodology has been applied successfully for the design of an active control suspension system using a non-linear bond graphs based quarter-car model with parameters that relate to a Ford Fiesta MK2