Weibull accelerated failure time regression model for remaining useful life prediction of bearing working under multiple operating conditions. (1st December 2019)

• Record Type: Journal Article
• Authors: Kundu, Pradeep; Darpe, Ashish K.; Kulkarni, Makarand S.
• Is Part Of: Mechanical systems and signal processing. Volume 134(2019)
• Publication Date: 2019-12-01
• Subjects: Remaining useful life -- Weibull regression -- Multiple operating conditions -- Bearing; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2019.106302
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: A Weibull Accelerated Failure Time Regression model is presented for bearing remaining useful life prediction that considers operating conditions and condition monitoring signal during model parameter estimation. The result based on the performance metrics demonstrates that the proposed method helps in systematically incorporating the operating conditions in the model and accurate RUL prediction results within error bound are observed. Very high underestimation or overestimation in RUL prediction is observed when operating conditions were not considered in the formulation of the model. Abstract: The rolling element bearings in industry applications operate at different operating conditions. The approaches for remaining useful life (RUL) prediction developed so far are limited to bearings operating under a single operating condition. Thus, separate models need to be developed for each operating condition, which is a tedious and time-consuming task. In this paper, a Weibull Accelerated Failure Time Regression (WAFTR) model is presented that considers both operating condition parameters and condition monitoring signal during model parameter estimation. Using the vibration signal, statistical time domain features such as root mean square, kurtosis, peak and crest factor and frequency domain features such as variation of % signal energy in the different spectrum bands (obtained after applying the bank of band pass filters) are extracted. Frequency domain features are used for further study since better trendability are found with these features compared to the statistical time domain features. For each bearing dataset, sixteen features are available from sixteen different frequency bands. However, all do not have better trendability and therefore principal component analysis (PCA) is used for dimensionality reduction. The best PC value and operating conditions such as speed and load are used in the WAFTR model for RUL prediction. The algorithm performance has been checked with metrics such as bias, mean square error, updated score value, % unacceptable early predictions, % unacceptable late predictions and % unacceptable predictions. The accuracy of the RUL prediction is found superior with the model that includes the effect of operating conditions and does not show significant bias as noticed in the RUL prediction when the operating conditions were not considered in the formulation of the model.