Author(s)

Li Wan and Guobin Wan

Corresponding Author

Li Wan

ABSTRACT

In view of the different types and contents of dissolved gases in transformer oil under different working conditions of oil-immersed power transformers, detecting the types and contents of different gases in transformer oil has become an important method to determine the working status of transformers. Based on the support vector machine (SVM) model, this paper uses the support vector machine's excellent solution to non-linear problems, and presents a method to determine the working mode of the transformer. After testing, the accuracy rate is as high as 96.8%. Accuracy requirements.

KEYWORDS

DGA; support vector machine; transformer; fault diagnosis; parameter optimization; SVM model