Cargando…

Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network

The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep l...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Lin, Wu, Jun, Wang, Liping, Chen, Guo, Shi, Yile, Liu, Zhigui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10217506/
https://www.ncbi.nlm.nih.gov/pubmed/37238553
http://dx.doi.org/10.3390/e25050798
_version_ 1785048553875308544
author Song, Lin
Wu, Jun
Wang, Liping
Chen, Guo
Shi, Yile
Liu, Zhigui
author_facet Song, Lin
Wu, Jun
Wang, Liping
Chen, Guo
Shi, Yile
Liu, Zhigui
author_sort Song, Lin
collection PubMed
description The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep learning methods based on the automatic extraction of feature information to replace traditional methods (such as information theory or signal processing) to obtain higher prediction accuracy. Convolutional neural networks (CNNs) based on multi-scale information extraction have demonstrated promising effectiveness. However, the existing multi-scale methods significantly increase the number of model parameters and lack efficient learning mechanisms to distinguish the importance of different scale information. To deal with the issue, the authors of this paper developed a novel feature reuse multi-scale attention residual network (FRMARNet) for the RUL prediction of rolling bearings. Firstly, a cross-channel maximum pooling layer was designed to automatically select the more important information. Secondly, a lightweight feature reuse multi-scale attention unit was developed to extract the multi-scale degradation information in the vibration signals and recalibrate the multi-scale information. Then, end-to-end mapping between the vibration signal and the RUL was established. Finally, extensive experiments were used to demonstrate that the proposed FRMARNet model can improve prediction accuracy while reducing the number of model parameters, and it outperformed other state-of-the-art methods.
format Online
Article
Text
id pubmed-10217506
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102175062023-05-27 Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network Song, Lin Wu, Jun Wang, Liping Chen, Guo Shi, Yile Liu, Zhigui Entropy (Basel) Article The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep learning methods based on the automatic extraction of feature information to replace traditional methods (such as information theory or signal processing) to obtain higher prediction accuracy. Convolutional neural networks (CNNs) based on multi-scale information extraction have demonstrated promising effectiveness. However, the existing multi-scale methods significantly increase the number of model parameters and lack efficient learning mechanisms to distinguish the importance of different scale information. To deal with the issue, the authors of this paper developed a novel feature reuse multi-scale attention residual network (FRMARNet) for the RUL prediction of rolling bearings. Firstly, a cross-channel maximum pooling layer was designed to automatically select the more important information. Secondly, a lightweight feature reuse multi-scale attention unit was developed to extract the multi-scale degradation information in the vibration signals and recalibrate the multi-scale information. Then, end-to-end mapping between the vibration signal and the RUL was established. Finally, extensive experiments were used to demonstrate that the proposed FRMARNet model can improve prediction accuracy while reducing the number of model parameters, and it outperformed other state-of-the-art methods. MDPI 2023-05-14 /pmc/articles/PMC10217506/ /pubmed/37238553 http://dx.doi.org/10.3390/e25050798 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Song, Lin
Wu, Jun
Wang, Liping
Chen, Guo
Shi, Yile
Liu, Zhigui
Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title_full Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title_fullStr Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title_full_unstemmed Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title_short Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
title_sort remaining useful life prediction of rolling bearings based on multi-scale attention residual network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10217506/
https://www.ncbi.nlm.nih.gov/pubmed/37238553
http://dx.doi.org/10.3390/e25050798
work_keys_str_mv AT songlin remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork
AT wujun remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork
AT wangliping remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork
AT chenguo remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork
AT shiyile remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork
AT liuzhigui remainingusefullifepredictionofrollingbearingsbasedonmultiscaleattentionresidualnetwork