Fuzzy inference device

Claim 2

A fuzzy inference device for determining an inference operational quantity in accordance with inference rules each constituted by an antecedent and a consequent, comprising: an inference rule division determiner which receives data of input variables and output variables so as to determine the number of the inference rules; an antecedent numerical processing determiner for obtaining a membership value corresponding to an antecedent of a specific inference rule from the divided data of the input variables and the output variables; a situational change processor for adaptively determining an inference quantity of a consequent of each inference rule in the case of change of an initial state or inference situations; an inference operational quantity determiner which receives outputs from said antecedent numerical processing determiner and said situational change processor and performs fuzzy inference in accordance with the inference rules so as to determine the inference operational quantity; and an evaluator for evaluating, on the basis of an evaluation reference, the inference operational quantity outputted by said inference operational quantity determiner; said situational change processor including an initialization determiner for initializing the inference quantity of the consequent by using an output value of said inference rule division determiner and a parameter searcher which begins a search from an output of said initialization determiner so as to search for an optimum parameter of the consequent in accordance with an output of said evaluator.

Claim 3

A fuzzy inference device for determining an inference operational quantity in accordance with inference rules each constituted by an antecedent and a consequent, comprising: an inference rule division determiner which receives data of input variables so as to determine the number of the inference rules; an antecedent neural element for obtaining a membership value corresponding to an antecedent of a specific inference rule from the divided data of the input variables; an output data divider which receives data of output variables so as to divide the data of the output variables by the number of the inference rules in accordance with an output of said inference rule division determiner; a situational change processor for adaptively determining an inference quantity of a consequent of each inference rule in the case of change of an initial state or inference situations; an inference operational quantity determiner which receives outputs from said antecedent neural element and said situational change processor and performs fuzzy inference in accordance with the inference rules so as to determine the inference operational quantity; and an evaluator which compares the data of the output variables with the inference operational quantity outputted by said inference operational quantity determiner so as to evaluate the inference operational quantity; said situational change processor including an initialization determiner for initializing the inference quantity of the consequent by using an output value of said output data divider and a parameter searcher which begins a search from an output of said initialization determiner so as to search for an optimum parameter of the consequent in accordance with an output of said evaluator.

Claim 4

A fuzzy inference device for determining an inference operational quantity in accordance with inference rules each constituted by an antecedent and a consequent, comprising: an inference rule division determiner which receives data of input variables so as to determine the number of the inference rules; an antecedent numerical processing determiner for obtaining a membership value corresponding to an antecedent of a specific inference rule from the divided data of the input variables; an output data divider which receives data of output variables so as to divide the data of the output variables by the number of the inference rules in accordance with an output of said inference rule division determiner; a situational change processor for adaptively determining an inference quantity of a consequent of each inference rule in the case of change of an initial state or inference situations; an inference operational quantity determiner which receives outputs from said antecedent numerical processing determiner and said situational change processor and performs fuzzy inference in accordance with the inference rules so as to determine the inference operational quantity; and an evaluator which compares the data of the output variables with the inference operational quantity outputted by said inference operational quantity determiner so as to evaluate the inference operational quantity; said situational change processor including an initialization determiner for initializing the inference quantity of the consequent by using an output value of said output data divider and a parameter searcher which begins a search from an output of said initialization determiner so as to search for an optimum parameter of the consequent in accordance with an output of said evaluator.