Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings

Predicting the Remaining Useful Lifetime (RUL) of bearings is crucial for the maintenance and reliability of rotating machinery. This paper presents a novel approach utilizing PRONOSTIA and XJTU-SY datasets for RUL prediction. The proposed methodology leverages Synchrosqueezing Wavelet Transform (SS...

Full description

Saved in:
Bibliographic Details
Main Authors: Boubker Najdi, Mohammed Benbrahim, Mohammed Nabil Kabbaj
Format: Article
Language:English
Published: The Prognostics and Health Management Society 2024-12-01
Series:International Journal of Prognostics and Health Management
Subjects:
Online Access:https://papers.phmsociety.org/index.php/ijphm/article/view/4171
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314797419495424
author Boubker Najdi
Mohammed Benbrahim
Mohammed Nabil Kabbaj
author_facet Boubker Najdi
Mohammed Benbrahim
Mohammed Nabil Kabbaj
author_sort Boubker Najdi
collection DOAJ
description Predicting the Remaining Useful Lifetime (RUL) of bearings is crucial for the maintenance and reliability of rotating machinery. This paper presents a novel approach utilizing PRONOSTIA and XJTU-SY datasets for RUL prediction. The proposed methodology leverages Synchrosqueezing Wavelet Transform (SSWT) and Random Projection (RP) to extract significant features from vibration signals. These features are then fed into a Residual Network (ResNet) combined with a temporal attention layer, followed by a Long Short-Term Memory (LSTM) model, referred to as the Adaptive Residual Attention LSTM (ARAL), to assess the Health Indicator (HI) of the bearings. Notably, an exponential data labeling technique is employed instead of traditional linear labeling, enhancing the robustness of the HI assessment. Following the HI estimation, the three-sigma method is applied to identify the degradation starting point. Subsequently, Gaussian Process Regression (GPR) is utilized to predict the RUL from this point forward. The proposed method demonstrates superior performance compared to existing techniques, providing more accurate and reliable RUL predictions. Experimental results show that this integrated approach effectively captures the complex degradation patterns of bearings, making it a valuable tool for prognostics and health management in industrial applications.
format Article
id doaj-art-be6a813a4e7246b28d3be651a4a214b7
institution Kabale University
issn 2153-2648
language English
publishDate 2024-12-01
publisher The Prognostics and Health Management Society
record_format Article
series International Journal of Prognostics and Health Management
spelling doaj-art-be6a813a4e7246b28d3be651a4a214b72025-08-20T03:52:20ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482024-12-01161116https://doi.org/10.36001/ijphm.2025.v16i1.4171Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling BearingsBoubker Najdi0Mohammed Benbrahim1Mohammed Nabil Kabbaj2Systems Engineering, Modeling and Analysis Laboratory, Faculty of Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco.Systems Engineering, Modeling and Analysis Laboratory, Faculty of Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco.Systems Engineering, Modeling and Analysis Laboratory, Faculty of Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco.Predicting the Remaining Useful Lifetime (RUL) of bearings is crucial for the maintenance and reliability of rotating machinery. This paper presents a novel approach utilizing PRONOSTIA and XJTU-SY datasets for RUL prediction. The proposed methodology leverages Synchrosqueezing Wavelet Transform (SSWT) and Random Projection (RP) to extract significant features from vibration signals. These features are then fed into a Residual Network (ResNet) combined with a temporal attention layer, followed by a Long Short-Term Memory (LSTM) model, referred to as the Adaptive Residual Attention LSTM (ARAL), to assess the Health Indicator (HI) of the bearings. Notably, an exponential data labeling technique is employed instead of traditional linear labeling, enhancing the robustness of the HI assessment. Following the HI estimation, the three-sigma method is applied to identify the degradation starting point. Subsequently, Gaussian Process Regression (GPR) is utilized to predict the RUL from this point forward. The proposed method demonstrates superior performance compared to existing techniques, providing more accurate and reliable RUL predictions. Experimental results show that this integrated approach effectively captures the complex degradation patterns of bearings, making it a valuable tool for prognostics and health management in industrial applications.https://papers.phmsociety.org/index.php/ijphm/article/view/4171bearing rul prognosissignal processingdeep learningadaptive labelingpredictive maintenance
spellingShingle Boubker Najdi
Mohammed Benbrahim
Mohammed Nabil Kabbaj
Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
International Journal of Prognostics and Health Management
bearing rul prognosis
signal processing
deep learning
adaptive labeling
predictive maintenance
title Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
title_full Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
title_fullStr Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
title_full_unstemmed Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
title_short Adaptive Res-LSTM Attention-based Remaining Useful Lifetime Prognosis of Rolling Bearings
title_sort adaptive res lstm attention based remaining useful lifetime prognosis of rolling bearings
topic bearing rul prognosis
signal processing
deep learning
adaptive labeling
predictive maintenance
url https://papers.phmsociety.org/index.php/ijphm/article/view/4171
work_keys_str_mv AT boubkernajdi adaptivereslstmattentionbasedremainingusefullifetimeprognosisofrollingbearings
AT mohammedbenbrahim adaptivereslstmattentionbasedremainingusefullifetimeprognosisofrollingbearings
AT mohammednabilkabbaj adaptivereslstmattentionbasedremainingusefullifetimeprognosisofrollingbearings