GENETIC LEARNING APPLIED TO FUZZY RULES AND FUZZY KNOWLEDGE BASES

This paper proposes two different approaches to apply Genetic Algorithms to Fuzzy Logic Controllers whose Rule Base is defined through a set of rules. The first one uses the knowledge base of the system as the population of the genetic system (a single rule containing the description of the corresponding fuzzy sets is an individual of the population), while the second uses the knowledge base (containing a set of fuzzy rules and a set of Membership functions) as the individual of the genetic system. Both systems have been applied to complex control problems (fossil power plants and biped robots).