摘要
Abstract
The transformer fault will be discovered earlier by the analysis on the gases dissolved in transformer oil. Five characteristic gas concentration ratios with total 15 sets have been adopted to reflect the relationship between the transformer inner fault and the characteristic gas. The RFE algorithm has been used to filtrate in 15 characteristic quantities, with the obtained quantities acted as the input of the SVM model. In the SVM model, the SVM parameters will be optimized by the SA algorithm, and the GUI interface will be provided. Finally, the RFE-SA-SVM model fault diagnosis rate will be better than that of single model through data validation.关键词
特征选择/基因选择算法/支持向量机/故障诊断Key words
feature selection/recursive feature elimination/support vector machine/fault diagnosis分类
信息技术与安全科学
