The main function of rolling element bearings is to provide low friction conditions for supporting and guiding a rotating shaft. The rolling element bearing includes both ball bearings and roller bearings. Rolling element bearings operate with a rolling action whereas plain bearings operate with a sliding action. In various applications, these bearings are considered as critical mechanical components since defect in these components may lead to malfunction and catastrophic failure in some cases. Vibration analysis is one of the most established methods used to evaluate the condition of bearings in operating machines. In this paper, an abnormal detection structure, in which different types of abnormal detection routines can be applied, is proposed. Bearing fault modes and their effects on the bearing vibration are discussed. In order to achieve this purpose, a feature extraction method is developed to overcome the limitation of time domain features. Experimental data from bearings under different operating conditions are used to verify the proposed method.

This content is only available via PDF.
You do not currently have access to this content.