| Summary: | 碩士 === 國立臺灣師範大學 === 工業教育研究所 === 89 === This paper proposes a genetic algorithm (GA) approach to design a multistage fuzzy logic controller for large-scale and complex control system. The main purpose of this paper is to decrease the large number of rules by using multistage fuzzy logic controller , and adopt the genetic algorithm method to design the parameter on multistage fuzzy controller. This can get rid of trial and error approach on controller design.
There are three kinds of parameters on multistage fuzzy logic controller. It includes the rule base, input/output variables of membership function and scaling factors. The scaling factor are designed by GA , the membership function is determined by expert or regulated by GA after expert design , and the rule bases are generated by two ways：one is generated by rule generation function , the other is generated by GA . This can be found the four kinds of types in parameter design , and these four types of parameter design can be combined with two kinds of framework (Skew tree and Binary tree). Therefore there are eight kinds of multistage fuzzy logic controllers on the basis of GA , and we compared their performance in pendulum-cart system.
The results of simulation show that all of the multistage fuzzy controllers have good performance. The proposed approach provide a systematic way to design multistage fuzzy logic controller.
Keywords：Multistage Fuzzy Logic Controller、Genetic Algorithm、Inverted pendulum、Rule Generation Function
|
|---|
