Title :
Rolling element bearings fault classification based on SVM and feature evaluation
Author :
Sui, Wen-tao ; Zhang, Dan
Author_Institution :
Sch. of Mech. Eng., Shandong Univ. of Technol., Zibo, China
Abstract :
A new method of fault diagnosis based on support vector machine (SVM) and feature evaluation is presented. Feature evaluation based on class separability criterion is discussed in this paper. A multi-fault SVM classifier based on binary classifier is constructed for bearing faults. Compared with the artificial neural network based method, the SVM based method has desirable advantages. Experiment shows that the algorithm is able to reliably recognize different fault categories. Therefore, it is a promising approach to fault diagnosis of rotating machinery.
Keywords :
fault diagnosis; inspection; machine bearings; maintenance engineering; mechanical engineering computing; support vector machines; turbomachinery; artificial neural network based method; class separability criterion; fault diagnosis; feature evaluation; multifault SVM classifier; rolling element bearings fault classification; rotating machinery; support vector machine; Artificial neural networks; Cybernetics; Fault diagnosis; Machine learning; Machinery; Risk management; Rolling bearings; Support vector machine classification; Support vector machines; Voting; Fault diagnosis; Feature evaluation; Support vector machine;
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Conference_Location :
Baoding
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
DOI :
10.1109/ICMLC.2009.5212574
