Studying on fuzzy controller based on radial basis function network

Fuzzy reasoning and fuzzy control with ANN have been got great research interesting, but the most of researches only discussed the vector space mapping from one fuzzy set to another, not a whole fuzzy controller. A fuzzy controller based on radial basis function network is proposed in this paper, it can do fuzzy reasoning to get mapping of input/output variables in the control space with high precision, although its structure is simple and its complicated training work is avoided. Fuzzier input isn´t needed but defuzzier output can be obtained from the network. Simulating results indicate that the controller can satisfy the controlling requirement of the wine fermentation process.