1.College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;2.State Grid Liaoning Electric Power Limited Company, Shenyang 110006, China

Online intelligent fault diagnosis is the development trend of transformer fault diagnosis. In order to make use of the performance advantages of different symptom subsets and diagnosis algorithms, and realize the complementary decision-making of multiple diagnosis models, this paper conducts multi-dimensional comparative analysis on the performance of intelligent diagnosis algorithms, and selects the diagnosis algorithms with excellent comprehensive performance for the selection of the symptom subset. The selecteded subsets and diagnosis algorithms are used to train multiple diagnosis models, and the models are selectively fused and used for final decision-making through analysis of differences between models.The example verification results show that the generalization performance and balance diagnosis ability of the fusion model are improved.