Loading...

Feature extraction for rolling element bearings prognostics using vibration high-frequency spectrum

Behzad, M ; Sharif University of Technology | 2017

902 Viewed
  1. Type of Document: Article
  2. Publisher: British Institute of Non-Destructive Testing , 2017
  3. Abstract:
  4. 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 highfrequency 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
  5. Keywords:
  6. High-frequency vibration level ; Neural network ; Offline condition monitoring ; Bandwidth ; Bearings (machine parts) ; Condition monitoring ; Feedforward neural networks ; Neural networks ; Weibull distribution ; Condition-monitoring data ; Feature ; High frequency spectrum ; High frequency vibration ; High-frequency bandwidth ; Offline ; Remaining useful life predictions ; Rolling Element Bearing ; Roller bearings
  7. Source: 1st World Congress on Condition Monitoring 2017, WCCM 2017, 13 June 2017 through 16 June 2017 ; 2017
  8. URL: http://www.proceedings.com/35374.html