Research on Transformer Fault Diagnosis Method Based on Neighborhood Rough Set and Grey Wolf Algorithm Optimized Support Vector Machine

Abstract

In order to reduce the misdiagnosis rate of transformer fault diagnosis, a transformer fault diagnosis method based on the support vector machine (SVM) is proposed. Firstly, reducing transformer fault data using neighborhood rough set (NRS). Then, the new ratios relevant to the transformer fault as the diagnosis sample is selected. Finally, the transformer fault diagnosis model based on SVM whose parameters are optimized by the gray wolf algorithm (GWO) to diagnose the transformer fault is established. Experimental results prove, neighborhood rough set can effectively reduce transformer fault data. The diagnosis model of support vector machine optimized by the grey wolf algorithm is proved to be suitable for transformer fault diagnosis.