Abstract: Aiming at the problems that the accuracy of traditional wind turbine fault identification methods is difficult to guarantee and lacks interpretability,a scheme for wind turbine fault identification and explanatory analysis based on the fuzzy rule classification system is proposed. In the offline stage,representative fault rules are generated through heuristic learning,and the multi-population quantum evolutionary algorithm is used to optimize fault rules and improve the accuracy of fault identification. In the online stage,a competition strategy for neighbor rules is defined,and a post-processing strategy based on fault rules is constructed. On this basis,the fault interpretive analysis scheme realizes the ranking of potential fault probabilities and the explanatory expression of key abnormal symptoms. The simulation analysis is carried out with the data of 10 common faults of megawatt wind turbines. The results show that the proposed method can effectively improve the fault identification accuracy while provide reliable fault interpretability results.