Optimizing control of sensory evaluation in the sake mashing process by decentralized learning of fuzzy inferences using a genetic algorithm

Optimal control of sensory evaluation estimated from 13 component concentrations on the basis of Dempster-Shafer's measure (DS) was attempted in the fermentation process for mashing Ginjyo-shu (sake). The control system consisted of fuzzy simulators generated by a genetic algorithm (GA) and an optimization procedure based on another GA. The fuzzy simulators simulated the dynamics of the ethanol production rate and sensory evaluation. Decentralized learning of fuzzy rules was also introduced. The fermentation period was divided into 4 phases, with a set of fuzzy rules corresponding to each phase. In order to construct an adaptive system based on the fuzzy simulators, only the set of rules corresponding to the current phase was adaptively identified, with the result that the fuzzy rules adapted to fluctuations in the relationship between the temperature and the ethanol production rate. By optimizing the control in this way, the optimal quality sake was successfully obtained.