Enhanced Lightweight Bearing Defect Detection via Frequency Domain Analysis and Model Compression

Enhanced Lightweight Bearing Defect Detection via Frequency Domain Analysis and Model Compression | 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 Research Article Enhanced Lightweight Bearing Defect Detection via Frequency Domain Analysis and Model Compression Saiqiang Wei, Bingjing lin, Hong Qiu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8630069/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 18 You are reading this latest preprint version Abstract Bearing defect detection is crucial for fault diagnosis and preventive maintenance of industrial equipment. Existing models often struggle to balance accuracy with computational efficiency. In this study, we propose an improved lightweight YOLO-FCMP model based on YOLOv7-tiny, which effectively addresses this trade-off. By proposing the FSC (FrFT-SpatialAttention-Conv) module, we enhance feature representation in the frequency domain, enabling the model to capture both local and global features of bearing surface defects with higher accuracy. Additionally, deformable convolution (DCNv2) is integrated to capture geometric deformations and complex shapes. We also present a novel CAMS attention mechanism, which improves upon the CBAM mechanism by incorporating multi-scale convolutional attention, mitigating the issue of shared weights in spatial attention. Further optimizations include the Diverse Branch Block (DBB) for re-parameterization and the lightweight VoVGSCSP module centered around GSConv convolution, which reduce computational complexity while maintaining high accuracy. We propose the Inner-MPDIoU loss function to improve bounding box regression accuracy and convergence speed. Model compression techniques, such as pruning and knowledge distillation, significantly reduce computational requirements, resulting in a model with an mAP of 99.4% and a computational cost of only 4.6 GFLOPs. This work presents an efficient and precise solution for bearing defect detection in industrial applications.The source code and dataset of our proposed method are available at:https://github.com/wudiw295/Bearing-Defect-Detection.git Bearing defect detection YOLO-FCMP Frequency domain enhancement Model pruning Knowledge distillation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 29 Apr, 2026 Reviews received at journal 22 Apr, 2026 Reviewers agreed at journal 16 Apr, 2026 Reviews received at journal 16 Apr, 2026 Reviews received at journal 12 Apr, 2026 Reviews received at journal 12 Apr, 2026 Reviews received at journal 11 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers invited by journal 13 Feb, 2026 Editor assigned by journal 28 Jan, 2026 Submission checks completed at journal 22 Jan, 2026 First submitted to journal 18 Jan, 2026 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-8630069","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":591622588,"identity":"cf8f1533-8978-4947-bae4-faca6a633563","order_by":0,"name":"Saiqiang Wei","email":"","orcid":"","institution":"Xiamen University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Saiqiang","middleName":"","lastName":"Wei","suffix":""},{"id":591622589,"identity":"a77949b1-ed5f-49c6-97fd-536d97956810","order_by":1,"name":"Bingjing lin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArElEQVRIiWNgGAWjYBACA/nGBwwJBjZybOztB4jUInEggeFDRZoxH8+ZBGK1JCQwzjhzOHGehIMB8bYw87Yxp7dJMCQw/KjYRoQW+QaQFrbcNunGA4w9Z24TbQtPbpsMkMHYRpSWBJAWiXQ2iQQDYrWkgLxvkECKlmMHgIGcYNgGDOSDRPnFfn5zAzAq/8vLt7cffPCjgggtQMD+A8Y6QJT6UTAKRsEoGAWEAQDNoTrxljyblgAAAABJRU5ErkJggg==","orcid":"","institution":"Xiamen University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Bingjing","middleName":"","lastName":"lin","suffix":""},{"id":591622590,"identity":"3745562a-e4f9-4248-bc02-387767982237","order_by":2,"name":"Hong Qiu","email":"","orcid":"","institution":"Central South University of Forestry and Technology","correspondingAuthor":false,"prefix":"","firstName":"Hong","middleName":"","lastName":"Qiu","suffix":""}],"badges":[],"createdAt":"2026-01-18 08:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8630069/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8630069/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102963690,"identity":"5a6464a7-a08f-4bc9-9a1a-39e1b3c572c3","added_by":"auto","created_at":"2026-02-19 04:20:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":11979744,"visible":true,"origin":"","legend":"","description":"","filename":"EnhancedLightweightBearingDefectDetectionviaFrequencyDomainAnalysisandModelCompression.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8630069/v1_covered_28f6ed84-6e90-4075-a396-3713c5ce3093.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Lightweight Bearing Defect Detection via Frequency Domain Analysis and Model Compression","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Bearing defect detection, YOLO-FCMP, Frequency domain enhancement, Model pruning, Knowledge distillation","lastPublishedDoi":"10.21203/rs.3.rs-8630069/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8630069/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBearing defect detection is crucial for fault diagnosis and preventive maintenance of industrial equipment. Existing models often struggle to balance accuracy with computational efficiency. In this study, we propose an improved lightweight YOLO-FCMP model based on YOLOv7-tiny, which effectively addresses this trade-off. By proposing the FSC (FrFT-SpatialAttention-Conv) module, we enhance feature representation in the frequency domain, enabling the model to capture both local and global features of bearing surface defects with higher accuracy. Additionally, deformable convolution (DCNv2) is integrated to capture geometric deformations and complex shapes. We also present a novel CAMS attention mechanism, which improves upon the CBAM mechanism by incorporating multi-scale convolutional attention, mitigating the issue of shared weights in spatial attention. Further optimizations include the Diverse Branch Block (DBB) for re-parameterization and the lightweight VoVGSCSP module centered around GSConv convolution, which reduce computational complexity while maintaining high accuracy. We propose the Inner-MPDIoU loss function to improve bounding box regression accuracy and convergence speed. Model compression techniques, such as pruning and knowledge distillation, significantly reduce computational requirements, resulting in a model with an mAP of 99.4% and a computational cost of only 4.6 GFLOPs. This work presents an efficient and precise solution for bearing defect detection in industrial applications.The source code and dataset of our proposed method are available at:https://github.com/wudiw295/Bearing-Defect-Detection.git\u003c/p\u003e","manuscriptTitle":"Enhanced Lightweight Bearing Defect Detection via Frequency Domain Analysis and Model Compression","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-18 08:03:44","doi":"10.21203/rs.3.rs-8630069/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-29T06:43:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-22T09:31:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"241837698951023648799660327971146838636","date":"2026-04-17T02:16:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-16T06:25:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-12T07:44:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-12T06:59:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-11T08:53:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"129710189954242565468303415127270914963","date":"2026-04-09T04:21:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19641665446023432235329922475130109964","date":"2026-04-07T06:26:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"188383569323196449560207314866356824222","date":"2026-04-07T04:56:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73686394458769416587100594402066655002","date":"2026-04-07T04:13:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"256886405619264831556298863854600869959","date":"2026-04-07T04:01:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"237539922895726463394947136762933391648","date":"2026-04-07T03:45:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338417574708145305898859561305462557531","date":"2026-04-07T03:45:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-13T07:41:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-29T01:49:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-22T12:06:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-01-18T08:23:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"44c066bc-30e6-4160-89d1-a645e509a99f","owner":[],"postedDate":"February 18th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-04-29T06:43:07+00:00","index":37,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-18T08:03:44+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-18 08:03:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8630069","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8630069","identity":"rs-8630069","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}