Application of SVM in fault diagnosis of power electronics rectifier

Author

Wang, Rongjie ; Zhou, Haifeng

Author_Institution

Sch. of Marine Eng., Jimei Univ., Xiamen

fYear

2008

fDate

25-27 June 2008

Firstpage

1256

Lastpage

1260

Abstract

A method of fault diagnosis for power electronics rectifier based on PCA-SVM is adopted in this paper. First, the features of the fault was extracted by the method of principal component analysis (PCA), and an SVM algorithm was introduced to train the SVM for diagnosis. Experimental results show that the diagnostic method has very good diagnostic ability and efficiency, and have a good outreach capacity under small-sample. Thus, it has very good practical value and applicable prospect in the solution to fault question for power electronics rectifier.

Keywords

fault diagnosis; feature extraction; power electronics; power engineering computing; principal component analysis; rectifying circuits; support vector machines; feature extraction; power electronics rectifier fault diagnosis; principal component analysis; support vector machine algorithm; Automation; Fault diagnosis; Intelligent control; Power electronics; Power engineering and energy; Principal component analysis; Rectifiers; Support vector machines; fault diagnosis; principal component analysis; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4593104

Filename

4593104