Fuzzy rule-based classification system using multi-population quantum evolutionary algorithm with contradictory rule reconstruction

Fuzzy rule-based classification systems (FRBCSs) are appropriate tools for dealing with classification problems because of their interpretable models based on linguistic variables. Intelligent optimization techniques are widely used in the rule mining of FRBCSs due to their parallel processing capability for solving the combination optimization of fuzzy antecedent parameters and “don’t care” variables, however, FRBCSs suffer from misclassification because of the chain coding scheme and non-guidance of updating strategy in rule mining process. This study presents an FRBCS that uses a multi-population quantum evolutionary algorithm with contradictory rule reconstruction. The developed method utilizes fuzzy C-means clustering to heuristically generate representative initial rules, and performs multi-population quantum coding and guided updating to optimize fuzzy rules. Furthermore, contradictory rule reconstruction is introduced to adjust misclassification rules. Numerical experiment results show that the classification accuracy and noise tolerance of the proposed method are better than those of compared FRBCSs. The proposed method is verified by applying it to fault identification in a wind turbine.