A model-based method for remaining useful life prediction of machinery

Lei Yaguo , Li Naipeng , Szymon Gontarz , Lin Jing , Stanisław Radkowski , Jacek Dybała


Remaining useful life (RUL) prediction allows for predictive maintenance of machinery, thus reducing costly unscheduled maintenance. Therefore, RUL prediction of machinery appears to be a hot issue attracting more andmore attention as well as being of great challenge. This paper proposes a model-based method for predicting RUL of machinery. The method includes two modules, i.e., indicator construction and RUL prediction. In the first module, a new health indicator named weighted minimum quantization error is constructed, which fuses mutual information from multiple features and properly correlates to the degradation processes of machinery. In the second module, model parameters are initialized using the maximum-likelihood estimation algorithm and RUL is predicted using a particle filtering-based algorithm. The proposed method is demonstrated using vibration signals from accelerated degradation tests of rolling element bearings. The prediction result identifies the effectiveness of the proposed method in predicting RUL of machinery.
Author Lei Yaguo
Lei Yaguo,,
, Li Naipeng
Li Naipeng,,
, Szymon Gontarz IP
Szymon Gontarz,,
- Institute of Automotive Engineering
, Lin Jing
Lin Jing,,
, Stanisław Radkowski IP
Stanisław Radkowski,,
- Institute of Automotive Engineering
, Jacek Dybała IP
Jacek Dybała,,
- Institute of Automotive Engineering
Journal seriesIEEE Transactions on Reliability, ISSN 0018-9529
Issue year2016
Publication size in sheets0.6
Keywords in Englishhealth indicator, parameter initialization, particle filtering, remaining useful life (RUL) prediction
URL http://ieeexplore.ieee.org/document/7501892/?reload=true
Languageen angielski
Score (nominal)40
ScoreMinisterial score [Punktacja MNiSW] = 40.0, 29-11-2017, ArticleFromJournal
Ministerial score (2013-2016) [Punktacja MNiSW (2013-2016)] = 40.0, 29-11-2017, ArticleFromJournal
Publication indicators WoS Impact Factor [Impact Factor WoS]: 2016 = 2.79 (2) - 2016=3.202 (5)
Citation count*0
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.