Title :
Fault diagnosis of transformer based on cluster analysis
Author_Institution :
Jiyuan Power Supply Co. of Henan Electr. Power Co., Jiyuan, China
Abstract :
In order to solve the problem of the imbalance between the fault data and the normal ones in the fault diagnosis of transformer, we adopt k-means algorithm to cluster the data. The result of clustering shows the existence of the boundary class that is between fault and normal ones. The separation of boundary class from the fault data and the normal ones improves the reliability and early warning ability of fault diagnosis of transformer, as well as reduces the influence from the imbalance of the two kinds of data.
Keywords :
fault diagnosis; pattern clustering; power transformers; boundary class; cluster analysis; early warning ability; fault diagnosis; k-means algorithm; power transformer; Algorithm design and analysis; Clustering algorithms; Fault diagnosis; Oil insulation; Power transformer insulation; Clustering; fault diagnosis of transformer; k-means;
Conference_Titel :
Power Engineering and Automation Conference (PEAM), 2011 IEEE
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9691-4
DOI :
10.1109/PEAM.2011.6135019
