One way for a systematic approach to fuzzy controller design is byapplying genetic algorithms (GAs). GAs, however, are much moreapplicable to numerical-type optimization problems. A traditional fuzzycontroller contains both linguistic-type rules and numeric-typereasoning. Hence, transforming a fuzzy controller design into aGA-applicable optimization problem becomes the first subject in thedesign approach. So, in this paper, we present an index function torepresent the linguistic control rules in terms of numeric indices. Inthis way, a GA design approach becomes feasible. The index function hasa tunable parameter which is adaptive to the controlled system and isnovel to the fuzzy rule in a TSK (Tagaki-Sugeno-Kang) type fuzzycontroller. Simulation results with a second-order damping system arepresented to show the performance of the proposed fuzzy controller
展开▼
