A Noval RUL Prediction Method for Rolling Bearing: TcLstmNet-CBAM

A Noval RUL Prediction Method for Rolling Bearing: TcLstmNet-CBAM | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A Noval RUL Prediction Method for Rolling Bearing: TcLstmNet-CBAM Qiang Liu, Zhengwei Dai, Hongxi Lai, Minghao Chen, Huiyuan Huang, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5294683/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted 14 You are reading this latest preprint version Abstract Rolling bearings are pivotal components within rotating mechanical systems, and accurately predicting their remaining service life holds significant practical importance. This paper addresses issues prevalent in common deep learning methods for predicting remaining useful life (RUL), notably inadequate feature extraction and low prediction accuracy resulting from reliance solely on short-term or long-term dependent features.In this paper, we introduce a residual useful life prediction method for bearings, named TcLstmNet-CBAM. This method integrates CBAM attention alongside parallel Temporal Convolutional Network (TCN) and Long Short-Term Memory (LSTM). Specifically, it employs a parallel network architecture for feature extraction, TCN extracts long-term temporal relationships and quickly mines deep spatial features to capture short-term time series relationships using LSTM. Additionally, the method incorporates the CBAM attention mechanism to assign weights to features across various dimensions, emphasizing the significance of important features.This approach not only achieves a more comprehensive feature distribution but also enhances the representation of crucial features, consequently leading to improved accuracy in predicting RUL. Finally, to validate the effectiveness of the proposed approach, we conducted experiments on the PHM2012 and XJTU-SY rolling bearing datasets, comparing its performance against several other prevalent deep learning prediction methods. The results demonstrate the robustness and generalization capability of the proposed method. Physical sciences/Engineering/Mechanical engineering Physical sciences/Mathematics and computing Remaining Useful Life Rolling bearings Feature extraction Parallel network CBAM TCN LSTM Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 11 Mar, 2025 Reviews received at journal 17 Feb, 2025 Reviews received at journal 07 Feb, 2025 Reviewers agreed at journal 06 Feb, 2025 Reviewers agreed at journal 06 Feb, 2025 Reviewers agreed at journal 23 Jan, 2025 Reviews received at journal 21 Jan, 2025 Reviewers agreed at journal 11 Nov, 2024 Reviewers agreed at journal 04 Nov, 2024 Reviewers invited by journal 04 Nov, 2024 Editor assigned by journal 04 Nov, 2024 Editor invited by journal 04 Nov, 2024 Submission checks completed at journal 02 Nov, 2024 First submitted to journal 19 Oct, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5294683","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":376539919,"identity":"575907e9-b6ba-4d84-b205-0ce9a425e9c7","order_by":0,"name":"Qiang Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYBACPmYgkQDE/AwMBiABxgZCWthgWiQbiNYCYxgcIFoLO4/hjQc1d+w2n1+88TEPg43shgPMzx7gdxiPsUXCsWfJ2248KzbmYUgz3nCAzdyAgBYziQS2w8lmN86YSfMwHE7ccICHTYKwln+Hk41ngLX8J1JLYtthOwP+HpCWA8RoYSu2SOw7nCBxg63YcI5BsvHMw2xmeLXw8x/eePPHt8P2/P2HNz54U2En23e8+RleLSAAUpDYIJHAAEkAzITUQ7XYM/AfIELpKBgFo2AUjEgAAEKpRBHXv9G+AAAAAElFTkSuQmCC","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":true,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Liu","suffix":""},{"id":376539920,"identity":"3d3951b4-3edd-4311-a2b0-48149bdb5d9b","order_by":1,"name":"Zhengwei Dai","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Zhengwei","middleName":"","lastName":"Dai","suffix":""},{"id":376539921,"identity":"06963eb4-98ee-4bff-8634-0defb7f1ac50","order_by":2,"name":"Hongxi Lai","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Hongxi","middleName":"","lastName":"Lai","suffix":""},{"id":376539923,"identity":"57319cd7-e183-42b3-9ccd-6d49db8e1dd6","order_by":3,"name":"Minghao Chen","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Minghao","middleName":"","lastName":"Chen","suffix":""},{"id":376539924,"identity":"6f20df88-ef39-48d2-8941-34ac0e6cc1f2","order_by":4,"name":"Huiyuan Huang","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Huiyuan","middleName":"","lastName":"Huang","suffix":""},{"id":376539925,"identity":"ace505b0-dcb1-4327-8e05-2c9debf67841","order_by":5,"name":"Jiahui Fu","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Jiahui","middleName":"","lastName":"Fu","suffix":""},{"id":376539927,"identity":"b72aceae-f4ad-4653-90a3-01204f7474f9","order_by":6,"name":"Mingxin Hou","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Mingxin","middleName":"","lastName":"Hou","suffix":""},{"id":376539928,"identity":"2087d8dd-83a3-4c4b-b7de-4a81033b8553","order_by":7,"name":"Xiaoming Xu","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Xu","suffix":""},{"id":376539929,"identity":"36727e88-324e-4d53-81a0-52017bf33f42","order_by":8,"name":"Guangbin Wang","email":"","orcid":"","institution":"Lingnan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Guangbin","middleName":"","lastName":"Wang","suffix":""},{"id":376539932,"identity":"6b4ca57b-0331-41c0-823a-2cb36f082c79","order_by":9,"name":"Jin Yan","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2024-10-19 13:08:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5294683/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5294683/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-98845-9","type":"published","date":"2025-04-23T15:57:42+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81570259,"identity":"da255003-2ede-41d3-84e4-f58beb162e4d","added_by":"auto","created_at":"2025-04-28 16:12:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1598251,"visible":true,"origin":"","legend":"","description":"","filename":"ANovalRULPredictionMethodforRollingBearingTcLstmNetCBAM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5294683/v1_covered_41ac8122-ceef-438d-8506-4514b160209e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Noval RUL Prediction Method for Rolling Bearing: TcLstmNet-CBAM","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Remaining Useful Life, Rolling bearings, Feature extraction, Parallel network, CBAM, TCN, LSTM","lastPublishedDoi":"10.21203/rs.3.rs-5294683/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5294683/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRolling bearings are pivotal components within rotating mechanical systems, and accurately predicting their remaining service life holds significant practical importance. This paper addresses issues prevalent in common deep learning methods for predicting remaining useful life (RUL), notably inadequate feature extraction and low prediction accuracy resulting from reliance solely on short-term or long-term dependent features.In this paper, we introduce a residual useful life prediction method for bearings, named TcLstmNet-CBAM. This method integrates CBAM attention alongside parallel Temporal Convolutional Network (TCN) and Long Short-Term Memory (LSTM). Specifically, it employs a parallel network architecture for feature extraction, TCN extracts long-term temporal relationships and quickly mines deep spatial features to capture short-term time series relationships using LSTM. Additionally, the method incorporates the CBAM attention mechanism to assign weights to features across various dimensions, emphasizing the significance of important features.This approach not only achieves a more comprehensive feature distribution but also enhances the representation of crucial features, consequently leading to improved accuracy in predicting RUL. Finally, to validate the effectiveness of the proposed approach, we conducted experiments on the PHM2012 and XJTU-SY rolling bearing datasets, comparing its performance against several other prevalent deep learning prediction methods. The results demonstrate the robustness and generalization capability of the proposed method.\u003c/p\u003e","manuscriptTitle":"A Noval RUL Prediction Method for Rolling Bearing: TcLstmNet-CBAM","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-15 06:17:57","doi":"10.21203/rs.3.rs-5294683/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-11T05:42:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-17T18:35:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-07T14:19:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"257072389879659199586951724717426111941","date":"2025-02-06T14:38:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267611021660300262984251096580980340535","date":"2025-02-06T11:47:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"89356693617526171202990120007385006111","date":"2025-01-23T12:03:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-21T22:21:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271121205634109804277618163263150131455","date":"2024-11-11T09:10:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"137757143647094402106079031549326932368","date":"2024-11-04T12:38:38+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-04T12:27:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-04T12:26:36+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-11-04T06:35:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-02T07:57:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-10-19T13:05:34+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f17b41bc-8b74-495a-85bb-ed2283ac204b","owner":[],"postedDate":"November 15th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":40078742,"name":"Physical sciences/Engineering/Mechanical engineering"},{"id":40078743,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-04-28T16:09:52+00:00","versionOfRecord":{"articleIdentity":"rs-5294683","link":"https://doi.org/10.1038/s41598-025-98845-9","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-04-23 15:57:42","publishedOnDateReadable":"April 23rd, 2025"},"versionCreatedAt":"2024-11-15 06:17:57","video":"","vorDoi":"10.1038/s41598-025-98845-9","vorDoiUrl":"https://doi.org/10.1038/s41598-025-98845-9","workflowStages":[]},"version":"v1","identity":"rs-5294683","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5294683","identity":"rs-5294683","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}