Transformer Fault Diagnosis Based on DLH-GWO-SVM

Abstract In the field of transformer fault diagnosis, there are many diagnostic methods. These methods either not high accuracy or used too long. this paper, a dimension learning-based hunting (DLH) search strategy optimization grey wolf algorithm support vector machine (DLH-GWO-SVM) model was proposed. process initializing population, logistic chaotic mapping to improve quality initial position. Wolf screening process, DLH adopted solve problem that GWO prone fall into local optimal solution, and improved Grey (IGWO) formed. Finally, types were classified by (SVM), IGWO optimize penalty factor kernel parameter (g) SVM. Through experimental analysis, diagnosis can reach 95.83% after application DLH-GWO-SVM model.