Hybrid approach for remaining useful life prediction of ball bearings

Fu Kwun Wang*, Tadele Mamo

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

32 Scopus citations


Remaining useful life (RUL) prediction plays an important role in predictive maintenance systems to support decision-makers for arranging maintenance tasks and related resources. We propose a hybrid approach that is combined an exponential weighted moving average (EWMA) control chart for anomaly detection and machine learning models such as support vector regression (SVR) and random forest regression (RFR) with differential evolution (DE) algorithm to predict the RULs of ball bearings. Here, DE algorithm is used to find the optimal hyperparameters of SVR model. The datasets of ball bearings from the Prognostics Data Repository of NASA are used to compare the prediction performance of different methods. The degradation behavior of training data from the anomaly time to the end of life is used to transfer learning for the testing data in the SVR and RFR models. The results indicate that the proposed methods outperform the other four existing methods in terms of score. Therefore, the proposed hybrid approach is a reliable tool for the RUL prediction of ball bearings.

Original languageEnglish
Pages (from-to)2494-2505
Number of pages12
JournalQuality and Reliability Engineering International
Issue number7
StatePublished - 01 11 2019
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2019 John Wiley & Sons, Ltd.


  • EWMA control chart
  • random forest regression
  • remaining useful life
  • support vector regression


Dive into the research topics of 'Hybrid approach for remaining useful life prediction of ball bearings'. Together they form a unique fingerprint.

Cite this