Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction

The remaining useful life (RUL) of complex mechanical systems is the primary aspect of prognostics and health management, which is critical for ensuring reliability and safety. Recent developments have shifted towards a data-driven approach, emphasizing empirical insights over expert opinions. The s...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeeshan Abbas, Muhammad Sharif, Musrat Hussain, Naeem Hussain, Mehboob Hussain, Naveed Ahmad Khan
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/542
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406666983866368
author Zeeshan Abbas
Muhammad Sharif
Musrat Hussain
Naeem Hussain
Mehboob Hussain
Naveed Ahmad Khan
author_facet Zeeshan Abbas
Muhammad Sharif
Musrat Hussain
Naeem Hussain
Mehboob Hussain
Naveed Ahmad Khan
author_sort Zeeshan Abbas
collection DOAJ
description The remaining useful life (RUL) of complex mechanical systems is the primary aspect of prognostics and health management, which is critical for ensuring reliability and safety. Recent developments have shifted towards a data-driven approach, emphasizing empirical insights over expert opinions. The similarity-based data-driven approach operates on the premise that systems with similar historical behaviors will likely exhibit similar future behaviors, making it suitable for RUL estimation. Conventionally, most similarity-based approaches utilize all historical data to identify reference systems for RUL estimations. However, not all historical events within a system hold equal significance for RUL. Certain events have a substantial impact on the remaining lifespan of a system. These significant and impactful events are called degradation events (DEs) in this study. Based on the hypothesis that systems undergoing similar DEs may share the same RUL, this study presents an innovative framework for RUL estimation that leverages only the DEs of a test system to identify reference systems that have experienced similar DEs. Furthermore, the model incorporates novel strategies for adjusting the RUL of the reference system based on the initial wear and degradation rates, thereby improving estimation accuracy. The effectiveness of the proposed model, in comparison with similar state-of-the-art models, is demonstrated through experiments on widely recognized jet engine datasets provided by NASA and bearing degradation data from the XJTU-SY.
format Article
id doaj-art-ea0376ca398042a08fb16cfa76ed159f
institution Kabale University
issn 2078-2489
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-ea0376ca398042a08fb16cfa76ed159f2025-08-20T03:36:18ZengMDPI AGInformation2078-24892025-06-0116754210.3390/info16070542Leveraging Degradation Events for Enhanced Remaining Useful Life PredictionZeeshan Abbas0Muhammad Sharif1Musrat Hussain2Naeem Hussain3Mehboob Hussain4Naveed Ahmad Khan5College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, ChinaState Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing 100190, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518060, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, ChinaSchool of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Information Technology and Information Systems, University of Canberra, Canberra, ACT 2617, AustraliaThe remaining useful life (RUL) of complex mechanical systems is the primary aspect of prognostics and health management, which is critical for ensuring reliability and safety. Recent developments have shifted towards a data-driven approach, emphasizing empirical insights over expert opinions. The similarity-based data-driven approach operates on the premise that systems with similar historical behaviors will likely exhibit similar future behaviors, making it suitable for RUL estimation. Conventionally, most similarity-based approaches utilize all historical data to identify reference systems for RUL estimations. However, not all historical events within a system hold equal significance for RUL. Certain events have a substantial impact on the remaining lifespan of a system. These significant and impactful events are called degradation events (DEs) in this study. Based on the hypothesis that systems undergoing similar DEs may share the same RUL, this study presents an innovative framework for RUL estimation that leverages only the DEs of a test system to identify reference systems that have experienced similar DEs. Furthermore, the model incorporates novel strategies for adjusting the RUL of the reference system based on the initial wear and degradation rates, thereby improving estimation accuracy. The effectiveness of the proposed model, in comparison with similar state-of-the-art models, is demonstrated through experiments on widely recognized jet engine datasets provided by NASA and bearing degradation data from the XJTU-SY.https://www.mdpi.com/2078-2489/16/7/542remaining useful lifeprognostics and health managementdegradation eventsmachine learning
spellingShingle Zeeshan Abbas
Muhammad Sharif
Musrat Hussain
Naeem Hussain
Mehboob Hussain
Naveed Ahmad Khan
Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
Information
remaining useful life
prognostics and health management
degradation events
machine learning
title Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
title_full Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
title_fullStr Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
title_full_unstemmed Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
title_short Leveraging Degradation Events for Enhanced Remaining Useful Life Prediction
title_sort leveraging degradation events for enhanced remaining useful life prediction
topic remaining useful life
prognostics and health management
degradation events
machine learning
url https://www.mdpi.com/2078-2489/16/7/542
work_keys_str_mv AT zeeshanabbas leveragingdegradationeventsforenhancedremainingusefullifeprediction
AT muhammadsharif leveragingdegradationeventsforenhancedremainingusefullifeprediction
AT musrathussain leveragingdegradationeventsforenhancedremainingusefullifeprediction
AT naeemhussain leveragingdegradationeventsforenhancedremainingusefullifeprediction
AT mehboobhussain leveragingdegradationeventsforenhancedremainingusefullifeprediction
AT naveedahmadkhan leveragingdegradationeventsforenhancedremainingusefullifeprediction