Transformer fault diagnosis strategy considering parameter optimization of oversampler and classifier

The imbalance of transformer fault samples makes the accuracy of fault diagnosis and classifica⁃ tion low，and it is easy to weaken the classification effect of a few types of fault samples. Therefore，the oversampling method is used to realize the equalization of fault samples，and a transformer fault diagnosis strategy considering the parameter optimization of oversampler and classifier is proposed. Firstly，the overall structure of transformer fault diagnosis model is built，and the implementation process of fault diagnosis is described. On this basis，the algorithm implementation of three main links of oversampler，classifier and parameter optimizer in the diagnosis model is proposed. For the oversampler，an improved synthetic minority oversampling technique based on nearest neighbor distribution（SMOTE-NND） algorithm is proposed to realize the equalization of fault samples. For the classifier，the hierarchical directed acyclic graph support vector machine（HDAG-SVM） algorithm is used to realize the multi-label classification of fault samples. For the parameter optimizer，a double-layer parameter optimization method is proposed. The upper layer uses the hierarchical search（HS） algorithm to optimize the oversampling ratio，and the lower layer uses modified harris hawks optimization（MHHO） algorithm to optimize the parameters of support vector machine. Finally，an example is given to analyze the proposed strategy. The results show that the proposed strategy can syn⁃ thesize a few fault samples with higher quality and realize the accurate classification of fault samples. © 2023 Electric Power Automation Equipment Press. All rights reserved.