Method of Bearing Fault Identification Based on SVM Decision Tree
Cheng Wei Hang, Xi Li, Zheng Bo Qin, Chao Yong Huang · Applied Mechanics and Materials · 2012
This paper has put forward one method, combining with theory of decision tree and method of voting, and established one kind of multi-failure classifier of SVM, which could finish cross training, repeated classification and accumulative voting. This classifier could accomplish classification of failure bearings and do classification experiments among failures of kinds of bearings. The results have shown that this method could identify states of breakdown equipment for the purpose of diagnosis of failures of mechanical system accurately.