An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction

Zhixiong Li, Dazhong Wu, Chao Hu, Janis Terpenny

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Remaining useful life (RUL) prediction is crucial for the implementation of predictive maintenance strategies. While significant research has been conducted in model-based and data-driven prognostics, there has been little research reported on the RUL prediction using an ensemble learning method that combines prediction results from multiple learning algorithms. The objective of this research is to introduce a new ensemble prognostics method that takes into account the effects of degradation on the accuracy of RUL prediction. Specifically, this method assigns an optimized, degradation-dependent weight to each learner (i.e., learning algorithm) such that the weighted sum of the prediction results from all the learners predicts the RULs of engineered systems with better accuracy. The ensemble prognostics method is demonstrated using two case studies. One case study is to predict the RULs of aircraft bearings; the other is to predict the RULs of aircraft engines. The numerical results have shown that the predictive model trained by the ensemble learning-based prognostic approach with degradation-dependent weights is capable of outperforming the original ensemble learning-based approach and its member algorithms.

Original languageEnglish (US)
Pages (from-to)110-122
Number of pages13
JournalReliability Engineering and System Safety
Volume184
DOIs
StatePublished - Apr 2019

Fingerprint

Degradation
Learning algorithms
Bearings (structural)
Aircraft engines
Aircraft

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Industrial and Manufacturing Engineering

Cite this

@article{33e4d38e744b4f89aa61b948cdcdf30f,
title = "An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction",
abstract = "Remaining useful life (RUL) prediction is crucial for the implementation of predictive maintenance strategies. While significant research has been conducted in model-based and data-driven prognostics, there has been little research reported on the RUL prediction using an ensemble learning method that combines prediction results from multiple learning algorithms. The objective of this research is to introduce a new ensemble prognostics method that takes into account the effects of degradation on the accuracy of RUL prediction. Specifically, this method assigns an optimized, degradation-dependent weight to each learner (i.e., learning algorithm) such that the weighted sum of the prediction results from all the learners predicts the RULs of engineered systems with better accuracy. The ensemble prognostics method is demonstrated using two case studies. One case study is to predict the RULs of aircraft bearings; the other is to predict the RULs of aircraft engines. The numerical results have shown that the predictive model trained by the ensemble learning-based prognostic approach with degradation-dependent weights is capable of outperforming the original ensemble learning-based approach and its member algorithms.",
author = "Zhixiong Li and Dazhong Wu and Chao Hu and Janis Terpenny",
year = "2019",
month = "4",
doi = "10.1016/j.ress.2017.12.016",
language = "English (US)",
volume = "184",
pages = "110--122",
journal = "Reliability Engineering and System Safety",
issn = "0951-8320",
publisher = "Elsevier Limited",

}

An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction. / Li, Zhixiong; Wu, Dazhong; Hu, Chao; Terpenny, Janis.

In: Reliability Engineering and System Safety, Vol. 184, 04.2019, p. 110-122.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction

AU - Li, Zhixiong

AU - Wu, Dazhong

AU - Hu, Chao

AU - Terpenny, Janis

PY - 2019/4

Y1 - 2019/4

N2 - Remaining useful life (RUL) prediction is crucial for the implementation of predictive maintenance strategies. While significant research has been conducted in model-based and data-driven prognostics, there has been little research reported on the RUL prediction using an ensemble learning method that combines prediction results from multiple learning algorithms. The objective of this research is to introduce a new ensemble prognostics method that takes into account the effects of degradation on the accuracy of RUL prediction. Specifically, this method assigns an optimized, degradation-dependent weight to each learner (i.e., learning algorithm) such that the weighted sum of the prediction results from all the learners predicts the RULs of engineered systems with better accuracy. The ensemble prognostics method is demonstrated using two case studies. One case study is to predict the RULs of aircraft bearings; the other is to predict the RULs of aircraft engines. The numerical results have shown that the predictive model trained by the ensemble learning-based prognostic approach with degradation-dependent weights is capable of outperforming the original ensemble learning-based approach and its member algorithms.

AB - Remaining useful life (RUL) prediction is crucial for the implementation of predictive maintenance strategies. While significant research has been conducted in model-based and data-driven prognostics, there has been little research reported on the RUL prediction using an ensemble learning method that combines prediction results from multiple learning algorithms. The objective of this research is to introduce a new ensemble prognostics method that takes into account the effects of degradation on the accuracy of RUL prediction. Specifically, this method assigns an optimized, degradation-dependent weight to each learner (i.e., learning algorithm) such that the weighted sum of the prediction results from all the learners predicts the RULs of engineered systems with better accuracy. The ensemble prognostics method is demonstrated using two case studies. One case study is to predict the RULs of aircraft bearings; the other is to predict the RULs of aircraft engines. The numerical results have shown that the predictive model trained by the ensemble learning-based prognostic approach with degradation-dependent weights is capable of outperforming the original ensemble learning-based approach and its member algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85039924086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039924086&partnerID=8YFLogxK

U2 - 10.1016/j.ress.2017.12.016

DO - 10.1016/j.ress.2017.12.016

M3 - Article

AN - SCOPUS:85039924086

VL - 184

SP - 110

EP - 122

JO - Reliability Engineering and System Safety

JF - Reliability Engineering and System Safety

SN - 0951-8320

ER -