Fractional Feature Extraction and Pattern Recognition of Transformer Partial Discharge Sources

摘要：

　　The recognition of transformer partial discharge patterns is helpful for evaluating insulation condition of transformers.Six typical kinds of partial discharge patterns are tested in the study.Based on the characteristics of the data,the partial discharge patterns were divided into several classes.Thus the pattern recognition can be translated into a two category process,in which the recognition can be realized gradually.By analyzing the data,the characteristic parameters are found for recognizing the classes.Then use the confidence interval method to realize the recognition process,and the accuracy of this method was verified.The results show that the method is reliable for the partial discharge pattern recognition.

关键词： transformer partial discharge feature extraction recognition

作者: WANG Guo-qiang ZHU Yong-li LIU Li-peng

作者单位: Department of Electrical Engineering North China Electric Power University Baoding,China

会议类型: 国际会议

会议名称: 2013 2nd International Conference on Computer Science and Electronics Engineering(ICCSEE2013)(2013年第二届计算机科学与电子工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 657-661

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）