Defuzzification
M. Mizumoto · 2020
The conventional fuzzy inference model consists of three basic steps: fuzzification, inference process, and defuzzification. Fuzzification is a mapping from the observed input to the fuzzy sets defined in the corresponding universe of discourse. The inference process is a decision-making logic which determines fuzzy outputs corresponding to fuzzified or crisp inputs, with respect to the fuzzy rules. Defuzzification produces a nonfuzzy output that best represents the inferred fuzzy output. Defuzzification problems emerge from the application of fuzzy control to industrial processes. The output of fuzzy controllers must be in a defuzzified form, because mechanical, electrical, phonetic, and other actuators can only accept and use deterministic signals. In existing fuzzy logic controllers, the center of gravity method is widely used as a defuzzification method which decides an actual control action from a fuzzy set of control actions inferred from fuzzy control rules. A number of defuzzification methods leading to distinct results have been proposed in the literature. We shall introduce and discuss 11 defuzzification methods which have been predominant in the literature on fuzzy control and fuzzy decision making.