Fault Diagnosis Method of Transformer Based on WSO and SVM

To improve the diagnostic accuracy of transformer fault diagnosis model, this paper proposes a transformer fault diagnosis method with White Shark Optimizer (WSO) and Support Vector Machine (SVM). Firstly, the uncoded ratio method is used to obtain the ratio of dissolved gases in transformer oil input to the support vector machine; secondly, the White Shark algorithm is used to optimize the two parameters (kernel parameter and penalty factor) affecting the diagnostic performance of the support vector machine; lastly, the method proposed in this paper is used to diagnose the faults of the transformer, and the results of the example simulation show that The support vector machine optimized by the WSO algorithm has higher fault diagnosis accuracy than the particle swarm optimization support vector machine and the ant colony algorithm optimization support vector machine. The average correct diagnosis rates of WSO-SVM, PSO-SVM and ACO-SVM are 91.6%, 86.7% and 87.5%, respectively, which validates the excellence of the proposed approach.