Transformer Fault Diagnosis Based on Feature Selection and Parameter Optimization

摘要：

Failure of transformer is very complex, dissolved Gas in Oil Analysis (DGA) is presently the easier and simpler way for fault diagnosis of oilimmersed transformers.The correct selection of features of dissolved gas data can improve efficiency of transformer fault diagnosis.SVM is more effective than traditional mathematic model to describe the type of fault of transformer.As for the problem of difficulty of determining parameters in SVM applications, genetic algorithm (GA) was used to select SVM parameters.The test results show that this GA-SVM model is effective to detect failure of transformer.

关键词： Transformer GA-SVM Parameter optimization DGA

作者: Han Han Wang Hou-jun Dong Xiucheng

作者单位: College of Automation Engineering University of Electronic Science and Technology of China Chengdu,S Automation Engineering University of Electronic Science and Technology of China Chengdu,Sichuan,Chin Electrical Engineering Department,Xihua University Chengdu,Sichuan,China CO 610039

会议类型: 国际会议

会议名称: 2011 IEEE International Conference on Smart Grid and Clean Energy Technologies(2011 IEEE智能电网与清洁能源技术国际会议 ICSGCE2011)

会议地点: 成都

会议语种:英文

页码: 400-403

在线出版日期: 2011-09-27（万方平台首次上网日期，不代表论文的发表时间）