Feature Extraction for Rolling Element Bearings Prognostics Using Vibration High-Frequency Spectrum

摘要

Remaining useful life prediction of rolling element bearings with offline condition monitoring data is the purpose of this paper. A data driven algorithm based on feedforward neural network is proposed for this aim. Since, usually the number of offline measurements are not much enough, the generalized Weibull failure rated function is used for producing the auxiliary points that are employed for training. Considering the physics of the bearing degradation, level of vibration in the high-frequency bandwidth of the spectrum is used as a feature and its performance in bearing prognostic problem is compared with that of using popular recommended features in the diagnostic standard. Bearing accelerated life test data as well as two industrial bearing data are used to investigate the purpose of this study. The results show that using the high-frequency vibration level feature rather than the proposed frequency bandwidth in guidelines and standards for recording the vibration of rotating machines produces more accurate prediction of remaining useful life.