A classifier fusion system for bearing fault diagnosis

作者：

Highlights：

• A multiple classifier system is proposed to detect early defects on bearings.

• Different SVMs are combined using the Iterative Boolean Combination technique.

• The BEAring Toolbox is employed to produce a high amount of bearing vibration signals.

• The proposed strategy achieves high robustness to different noise-to-signal ratio.

摘要

•A multiple classifier system is proposed to detect early defects on bearings.•Different SVMs are combined using the Iterative Boolean Combination technique.•The BEAring Toolbox is employed to produce a high amount of bearing vibration signals.•The proposed strategy achieves high robustness to different noise-to-signal ratio.

论文关键词：Bearing fault diagnosis,Vibration analysis,Machine condition monitoring,Support vector machines,Iterative Boolean Combination,ROC curves,Classifier fusion

论文评审过程：Available online 27 June 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.033