Fault Diagnosis Method of Transformer Based on ANOVA and SVM

To improve the diagnostic accuracy of transformer fault diagnosis model, this paper proposes a transformer fault diagnosis method based on analysis of variance (ANOVA) and support vector machine (SVM). Firstly, the characteristics of dissolved gas in transformer oil are screened and dimensionality reduced by analysis of variance. Secondly, the filtered features are put into the SVM model. Finally, the simulation results of using the method proposed in this paper to diagnose the fault of a transformer show that, compared with IEC and Rogers methods, ANOVA dimensionality reduction screening method for model input can better improve model performance, and the diagnostic accuracy of SVM based on ANOVA, IEC, and Rogers are 90.54%, 74.32% and 77.03% respectively, and the superiority of the proposed method is verified.