Mamdani Fuzzy Systems
John H. Lilly · 2010
A fuzzy system uses fuzzy reasoning processes to convert crisp inputs into crisp outputs. The main components of the fuzzy system are a fuzzification section, an inference mechanism, and a defuzzification section. A set of rules generally in if-then modus ponens form, called a rule base, specifies how decisions are to be made based on the measured inputs. In Mamdani fuzzy systems, the consequent of each rule is a fuzzy set. There are several strategies for fuzzification, but the one most commonly used is singleton fuzzification. The inference mechanism determines the extent to which each rule in the rule base applies in the present situation, and forms a corresponding implied fuzzy set for each rule. The defuzzification section combines the implied fuzzy sets of all rules to get a crisp output. This chapter discusses two strategies of defuzzification namely, Center of Gravity (COG) defuzzification and Center Average (CA) defuzzification. Controlled Vocabulary Terms fuzzy systems; gravitation; inference mechanisms