A Power Transformers Fault Diagnosis Model Based on Three DGA Ratios and PSO Optimization SVM

2017 2nd International Conference on Mechatronics and Electrical Systems

机械制造;无线电电子学

Ma, Hongzhe^1 ; Zhang, Wei^1 ; Wu, Rongrong^1 ; Yang, Chunyan^1

Electric Power Scientific Research Institute of Guangxi Power Grid, Guangxi Power Grid Corporation, Nanning, China^1

关键词: Cross validation;    Dissolved gas in oil analysis;    Fault diagnosis model;    Genetic algorithm support vector machines;    Multi-classification;    Parameter optimization;    Test method;    Transformer fault diagnosis;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/339/1/012001/pdf
DOI  :  10.1088/1757-899X/339/1/012001

来源: IOP

【 摘 要 】

In order to make up for the shortcomings of existing transformer fault diagnosis methods in dissolved gas-in-oil analysis (DGA) feature selection and parameter optimization, a transformer fault diagnosis model based on the three DGA ratios and particle swarm optimization (PSO) optimize support vector machine (SVM) is proposed. Using transforming support vector machine to the nonlinear and multi-classification SVM, establishing the particle swarm optimization to optimize the SVM multi classification model, and conducting transformer fault diagnosis combined with the cross validation principle. The fault diagnosis results show that the average accuracy of test method is better than the standard support vector machine and genetic algorithm support vector machine, and the proposed method can effectively improve the accuracy of transformer fault diagnosis is proved.