Remaining Useful Life Estimation of Bearings: Meta-analysis of Experimental Procedure

Hugo M. Ferreira and Alexandre C. de Sousa
Publication Target: 
Publication Issue: 
Submission Type: 
Full Paper
Supporting Agencies (optional): 
European Regional Development Fund (FEDER)
ijphm_20_010.pdf193.67 KBOctober 19, 2020 - 4:54am

In the domain of predictive maintenance, when trying to replicate and compare research in remaining useful life estimation (RUL), several inconsistencies and errors were identified in the experimental methodology used by various researchers. This makes the replication and the comparison of results difficult, thus severely hindering both progress in this research domain and its practical application to industry. We survey the literature to evaluate the experimental procedures that were used, and identify the most common errors and omission in both experimental procedures and reporting.

A total of 70 papers on RUL were audited. From this meta-analysis we estimate that approximately 11% of the papers present work that will allow for replication and comparison. Surprisingly, only about 24.3% (17 of the 70 articles) compared their results with previous work. Of the remaining work, 41.4% generated and compared several models of their own and, somewhat unsettling, 31.4% of the researchers made no comparison whatsoever. The remaining 2.9% did not use the same data set for comparisons. The results of this study were also aggregated into 3 categories: problem class selection, model fitting best practices and evaluation best practices. We conclude that model evaluation is the most problematic one.

The main contribution of the article is a proposal of an experimental protocol and several recommendations that specifically target model evaluation. Adherence to this protocol should substantially facilitate the research and application of RUL prediction models. The goals are to promote the collaboration between scholars and practitioners alike and advance the research in this domain.

Publication Year: 
Publication Volume: 
Publication Control Number: 
Page Count: 
Submission Keywords: 
data mining and machine learning; methodology; meta-analysis; prognostics ; bearings ; remaining useful life
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Submitted by: 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed