Transformer Fault Diagnosis Based on Improved SVM Model

Abstract

This paper proposes an improved SVM method in order to improve the speed of classification when SVM treats with the large training set. Firstly, using RS theory to eliminate redundant information of the large original training data set, secondly, utilizing the idea of probabilities, train an initial classifier with a small training set, and prune the large training set with the initial classifier to obtain a small reduction set. Training with the reduction set, final classifier is obtained. Experiments show that this method effectively reduces the training set, and improves the classify ability.