Bearing Remaining Useful Life Prediction Based on CICAE and ResConv1D-LSTM
Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders and CNN-based approaches tend to assign equal weights to all feature c...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on instrumentation and measurement Jg. 74; S. 1 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
New York
IEEE
01.01.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Schlagworte: | |
| ISSN: | 0018-9456, 1557-9662 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders and CNN-based approaches tend to assign equal weights to all feature channels for degradation feature extraction, which inevitably leads to the critical degradation characteristics being obscured by noise or characteristics of other channels. Moreover, the additive operation of traditional residual connection inherently limits the inter-block coordination, leading to redundant feature learning and constrained hierarchical representation capacity. To address these limitations, a novel two-stage deep learning framework is proposed. In the first stage, a Channel-information-constrained autoencoder (CICAE) develops an information entropy-based constraint to focus on the degradation-relevant channels while suppressing irrelevant ones. In the second stage, a ResConv1D-LSTM network integrates multi-scale convolutional blocks for progressive residual learning with several LSTM layers for temporal modeling, so as to comprehensively characterize the degradation trend, and then multiple fully connected layers are designed for RUL prediction. Experimental results demonstrate that the proposed bearing RUL prediction method outperforms existing approaches and is applicable in real-world scenarios. |
|---|---|
| AbstractList | Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders (AEs) and CNN-based approaches tend to assign equal weights to all feature channels for degradation feature extraction, which inevitably leads to the critical degradation characteristics being obscured by noise or characteristics of other channels. Moreover, the additive operation of traditional residual connection inherently limits the interblock coordination, leading to redundant feature learning and constrained hierarchical representation capacity. To address these limitations, a novel two-stage deep learning framework is proposed. In the first stage, a channel-information-constrained AE (CICAE) develops an information entropy-based constraint to focus on the degradation-relevant channels while suppressing irrelevant ones. In the second stage, a ResConv1D-LSTM network integrates multiscale convolutional blocks for progressive residual learning with several long short-term memory (LSTM) layers for temporal modeling, so as to comprehensively characterize the degradation trend, and then, multiple fully connected layers are designed for RUL prediction. Experimental results demonstrate that the proposed bearing RUL prediction method outperforms the existing approaches and is applicable in real-world scenarios. Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders and CNN-based approaches tend to assign equal weights to all feature channels for degradation feature extraction, which inevitably leads to the critical degradation characteristics being obscured by noise or characteristics of other channels. Moreover, the additive operation of traditional residual connection inherently limits the inter-block coordination, leading to redundant feature learning and constrained hierarchical representation capacity. To address these limitations, a novel two-stage deep learning framework is proposed. In the first stage, a Channel-information-constrained autoencoder (CICAE) develops an information entropy-based constraint to focus on the degradation-relevant channels while suppressing irrelevant ones. In the second stage, a ResConv1D-LSTM network integrates multi-scale convolutional blocks for progressive residual learning with several LSTM layers for temporal modeling, so as to comprehensively characterize the degradation trend, and then multiple fully connected layers are designed for RUL prediction. Experimental results demonstrate that the proposed bearing RUL prediction method outperforms existing approaches and is applicable in real-world scenarios. |
| Author | Yang, Zhenli Chai, Yi Zhuo, Yi'an Qin, Yi Zhao, Yihang Mao, Yongfang |
| Author_xml | – sequence: 1 givenname: Yi orcidid: 0000-0002-2160-4300 surname: Qin fullname: Qin, Yi email: qy_808@cqu.edu.cn organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing, China – sequence: 2 givenname: Yihang orcidid: 0009-0000-5522-6013 surname: Zhao fullname: Zhao, Yihang email: zyh0805@stu.cqu.edu.cn organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing, China – sequence: 3 givenname: Yi'an orcidid: 0009-0008-1481-9603 surname: Zhuo fullname: Zhuo, Yi'an email: zhuoyian_0830@163.com organization: CAIC Electronics Co. Ltd, Chengdu, China – sequence: 4 givenname: Yi orcidid: 0000-0002-8637-8682 surname: Chai fullname: Chai, Yi email: chaiyi@cqu.edu.cn organization: College of Automation, Chongqing University, Chongqing, China – sequence: 5 givenname: Zhenli orcidid: 0000-0001-9374-7928 surname: Yang fullname: Yang, Zhenli email: 346246866@qq.com organization: Key Laboratory of Electromechanical Equipment Security in Western Complex Environment, State Administration for Market Regulation, Chongqing, China – sequence: 6 givenname: Yongfang orcidid: 0000-0003-3567-1886 surname: Mao fullname: Mao, Yongfang email: yfm@cqu.edu.cn organization: College of Automation, Chongqing University, Chongqing, China |
| BookMark | eNpFkD1PwzAURS0EEm1hZ2CIxJzy_JE4GWkpUJQKBO1sOfYzStU6xW6R-PckaiWmd4d73pXOkJz71iMhNxTGlEJ5v5wvxgxYNuZZKXMGZ2RAs0ymZZ6zczIAoEVaiiy_JMMY1wAgcyEH5HWCOjT-K_nArW58n1YR3WGTVI3D5D2gbcy-aX0y0RFt0oXpfPowS7S3HROnrf-hj2n1uVxckQunNxGvT3dEVk-z5fQlrd6eO6RKDRNyn9LaFBYNWuDMoBZOY1mYTAqQ2rLSOSFMLWsuLQenrZYFE5TrGowpcmsLPiJ3x7-70H4fMO7Vuj0E300q3i0IYLLoW3BsmdDGGNCpXWi2OvwqCqo3pjpjqjemTsY65PaINIj4X6eUcSoy_gclWGfG |
| CODEN | IEIMAO |
| Cites_doi | 10.1109/ACCESS.2020.3041735 10.1016/j.ress.2022.108610 10.1016/j.ress.2021.107946 10.1016/j.ymssp.2023.110688 10.1177/1350650119838895 10.1016/j.measurement.2023.113478 10.1016/j.ress.2025.110978 10.1016/j.aei.2021.101247 10.1016/j.ymssp.2023.110435 10.1016/j.measurement.2022.111803 10.1109/TIM.2022.3143881 10.1016/j.ress.2023.109854 10.1109/TIM.2016.2570398 10.1109/TR.2018.2882682 10.1109/JSEN.2022.3159624 10.1016/j.aei.2020.101150 10.1016/j.ress.2025.111057 10.1109/TSMC.2024.3408058 10.1109/TII.2022.3218665 10.1016/j.measurement.2023.112600 10.1016/j.ress.2021.108140 10.1016/j.ress.2023.109716 10.1016/j.isatra.2020.12.052 10.1016/j.ymssp.2022.110010 10.1162/neco.1997.9.8.1735 10.1109/JSEN.2022.3221753 10.1016/j.isatra.2021.03.045 10.1016/j.engappai.2023.106491 10.1109/TSMC.2024.3519347 10.1109/TIM.2023.3322481 10.1016/j.ress.2022.108914 10.1016/j.ress.2021.108012 10.1016/j.jmsy.2021.03.012 10.1016/j.neucom.2015.08.104 10.1016/j.measurement.2021.109166 10.1109/TIA.2005.861365 10.1109/TIM.2021.3086906 10.1109/TIM.2021.3054025 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M |
| DOI | 10.1109/TIM.2025.3597620 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Solid State and Superconductivity Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EISSN | 1557-9662 |
| EndPage | 1 |
| ExternalDocumentID | 10_1109_TIM_2025_3597620 11123145 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 52175075 funderid: 10.13039/501100001809 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI O9- OCL P2P RIA RIE RNS TN5 TWZ 5VS 8WZ A6W AAYXX AETIX AGSQL AI. AIBXA ALLEH CITATION EJD H~9 IAAWW IBMZZ ICLAB IDIHD IFJZH M43 VH1 VJK 7SP 7U5 8FD L7M |
| ID | FETCH-LOGICAL-c247t-1bc8deced032cea4fae98c57407ad29ff44cb7b37d30fada782413ab0cc86dd83 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001556060600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0018-9456 |
| IngestDate | Sat Nov 01 14:14:38 EDT 2025 Sat Nov 29 07:39:14 EST 2025 Wed Aug 27 07:37:44 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c247t-1bc8deced032cea4fae98c57407ad29ff44cb7b37d30fada782413ab0cc86dd83 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0009-0000-5522-6013 0000-0002-2160-4300 0009-0008-1481-9603 0000-0002-8637-8682 0000-0001-9374-7928 0000-0003-3567-1886 |
| PQID | 3247402788 |
| PQPubID | 85462 |
| PageCount | 1 |
| ParticipantIDs | ieee_primary_11123145 proquest_journals_3247402788 crossref_primary_10_1109_TIM_2025_3597620 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-01-01 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – month: 01 year: 2025 text: 2025-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on instrumentation and measurement |
| PublicationTitleAbbrev | TIM |
| PublicationYear | 2025 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref16 ref38 ref19 ref18 Zhang (ref35) 2022 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 Zhuo (ref39) |
| References_xml | – ident: ref5 doi: 10.1109/ACCESS.2020.3041735 – ident: ref23 doi: 10.1016/j.ress.2022.108610 – ident: ref9 doi: 10.1016/j.ress.2021.107946 – ident: ref30 doi: 10.1016/j.ymssp.2023.110688 – ident: ref11 doi: 10.1177/1350650119838895 – ident: ref15 doi: 10.1016/j.measurement.2023.113478 – ident: ref36 doi: 10.1016/j.ress.2025.110978 – ident: ref38 doi: 10.1016/j.aei.2021.101247 – ident: ref3 doi: 10.1016/j.ymssp.2023.110435 – ident: ref16 doi: 10.1016/j.measurement.2022.111803 – ident: ref20 doi: 10.1109/TIM.2022.3143881 – ident: ref28 doi: 10.1016/j.ress.2023.109854 – ident: ref7 doi: 10.1109/TIM.2016.2570398 – start-page: 1 volume-title: Proc. CAA Symp. Fault Detection, Supervision Saf. Tech. Processes (SAFEPROCESS) ident: ref39 article-title: Bearing remaining useful life prediction based on TCN-transformer model – ident: ref40 doi: 10.1109/TR.2018.2882682 – ident: ref10 doi: 10.1109/JSEN.2022.3159624 – ident: ref33 doi: 10.1016/j.aei.2020.101150 – ident: ref1 doi: 10.1016/j.ress.2025.111057 – ident: ref6 doi: 10.1109/TSMC.2024.3408058 – ident: ref12 doi: 10.1109/TII.2022.3218665 – ident: ref22 doi: 10.1016/j.measurement.2023.112600 – ident: ref2 doi: 10.1016/j.ress.2021.108140 – ident: ref19 doi: 10.1016/j.ress.2023.109716 – ident: ref18 doi: 10.1016/j.isatra.2020.12.052 – ident: ref31 doi: 10.1016/j.ymssp.2022.110010 – ident: ref34 doi: 10.1162/neco.1997.9.8.1735 – ident: ref27 doi: 10.1109/JSEN.2022.3221753 – ident: ref14 doi: 10.1016/j.isatra.2021.03.045 – ident: ref17 doi: 10.1016/j.engappai.2023.106491 – ident: ref24 doi: 10.1109/TSMC.2024.3519347 – ident: ref25 doi: 10.1109/TIM.2023.3322481 – ident: ref29 doi: 10.1016/j.ress.2022.108914 – ident: ref4 doi: 10.1016/j.ress.2021.108012 – ident: ref13 doi: 10.1016/j.jmsy.2021.03.012 – ident: ref32 doi: 10.1016/j.neucom.2015.08.104 – ident: ref37 doi: 10.1016/j.measurement.2021.109166 – ident: ref8 doi: 10.1109/TIA.2005.861365 – year: 2022 ident: ref35 article-title: First de-trend then attend: Rethinking attention for time-series forecasting publication-title: arXiv:2212.08151 – ident: ref21 doi: 10.1109/TIM.2021.3086906 – ident: ref26 doi: 10.1109/TIM.2021.3054025 |
| SSID | ssj0007647 |
| Score | 2.425629 |
| Snippet | Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Autoencoders Bearing remaining useful life Channels CICAE Computer architecture Constraints Convolution Decoding Deep learning Degradation Entropy (Information theory) Feature extraction Life prediction Logic gates Long short term memory Machine learning Predictive models ResConv1DLSTM RUL prediction Training Useful life |
| Title | Bearing Remaining Useful Life Prediction Based on CICAE and ResConv1D-LSTM |
| URI | https://ieeexplore.ieee.org/document/11123145 https://www.proquest.com/docview/3247402788 |
| Volume | 74 |
| WOSCitedRecordID | wos001556060600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UFPTgW1xf5ODFQ7WPtGmOWldUVll0F_ZW2mQCgnZlu-vvd5J2VRAP3kJpQphvnplkBuA05IZYl4KcNBSJx6VKvBRN5EljrZ-vA2lcdf2eeHxMRyPZbx-ru7cwiOgun-G5Hbpcvh6rmT0quyC5JHeEx4uwKETSPNb6Ursi4U2BzIAkmNyCeU7SlxeDuweKBMP4PCL3ObGtvX_YINdU5ZcmdublZuOfG9uE9daPZJcN8FuwgNU2rP2oLrgNK-52p6p34P6K-Jm-sSd8azpCsGGNZvbKei8GWX9iszUWIXZFRk0zGmR32WWXFZWmOXU2rj6Ca6_3PHjYheFNd5Ddem0TBU-FXEy9oFSpRoXaj0KFBTcFylTFggK5QofSGM5VKcpI6Mg3hS7IYyC7VpS-UmmidRrtwVI1rnAfWBlIjFRAeknZEjSlTGRgylhxHYVa-9iBszlZ8_emVkbuYgxf5gRBbiHIWwg6sGvJ-P1fS8EOHM2ByFtpqnNy-mi_IUXrB39MO4RVu3pzNnIES9PJDI9hWX1MX-rJiWOUT7UbuPg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT9swFH_aGBNw2BgroqwbPnDZITRxnA8foQPRkVYVFIlblNjPUqWRoqbl7-fZSQEJcdjNimLZer_36We_B3DMhSHWpSAn5UnsCaliL0UTetJY6-frQBpXXT9LxuP07k5O2sfq7i0MIrrLZ3hihy6Xr-dqZY_K-iSX5I6I6CN8ioTgfvNc61nxJrFoSmQGJMPkGKyzkr7sT4cjigV5dBKSAx3b5t6vrJBrq_JGFzsDc_H1P7e2C19aT5KdNtB_gw9Y7cHOq_qCe_DZ3e9U9Xf4e0YcTd_YNd43PSHYbY1m9Y9lM4NssrD5GosROyOzphkNBsPB6TkrKk1z6sG8egz-eNnNdNSB24vz6eDSa9soeIqLZOkFpUo1KtR-yBUWwhQoUxUlFMoVmktjhFBlUoaJDn1T6IJ8BrJsRekrlcZap-E-bFTzCg-AlYHEUAWkmZQtQlPKWAamjJTQIdfaxy78XpM1f2iqZeQuyvBlThDkFoK8haALHUvGl_9aCnahtwYib-Wpzsnto_1yitcP35l2BFuX01GWZ8Px1Q_Ytis1JyU92FguVvgTNtXjclYvfjmmeQKDTLw_ |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Bearing+Remaining+Useful+Life+Prediction+Based+on+CICAE+and+ResConv1D-LSTM&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Qin%2C+Yi&rft.au=Zhao%2C+Yihang&rft.au=Yi%27An+Zhuo&rft.au=Chai%2C+Yi&rft.date=2025-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=74&rft.spage=1&rft.epage=11&rft_id=info:doi/10.1109%2FTIM.2025.3597620&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon |