Study of Transformer Fault Diagnosis Based on Sparrow Optimization Algorithm

Abstract

To solve the problem that the accuracy of transformer fault diagnosis is seriously affected by support vector machine parameters, a transformer fault diagnosis method based on the sparrow search algorithm is proposed. First, through very sparse random projection to remove redundant features. Then use the sparrow search algorithm to dynamically optimize the kernel function parameters and penalty coefficients of the support vector machine, and obtain the fault diagnosis model of the support vector machine optimized by the SSA. Finally input the processed data into SSA-SVM for fault diagnosis, and compared it with GA-SVM and GWO-SVM. The results show that the test accuracy of the support vector machine optimized by the sparrow search algorithm (SSA-SVM) reaches 86.67%, which is 6.67% and 8.34% higher than that of GWO-SVM and GA-SVM, So it can be effectively applied to fault diagnosis.