RDD-YOLO: A study on an improved valve stem surface defect detection algorithm for YOLOv11

RDD-YOLO: A study on an improved valve stem surface defect detection algorithm for YOLOv11 | 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 RDD-YOLO: A study on an improved valve stem surface defect detection algorithm for YOLOv11 Jiadong Dong, Feihu Sang, Hao Sun, Changrong Ou, Qinghu Guo, Chunxiang Zheng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8639584/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Addressing challenges in detecting surface defects on refrigeration equipment valve stems—including difficulty in extracting small target features, low accuracy against complex backgrounds, and high computational demands—this paper proposes an improved RDD-YOLO model based on YOLOv11. First, the model replaces part of the convolutions in the backbone and all convolutions in the neck with receptive field channel attention convolutions (RFCAConv), enhancing local perception and channel attention to improve feature extraction for small target defects. Second, it constructs a depth-adaptive kernel spatial pyramid pooling factorization (DAK_SPPF) within the backbone network and designs depth-adaptive kernel convolution (DAKConv) to optimize multi-scale feature fusion, thereby improving detection accuracy in complex backgrounds. To reduce parameters and computational complexity, a lightweight deep dynamic efficient (LDDE) detection head is proposed. Combining dynamic convolution and the efficient local attention (ELA) module, a lightweight Detect_DyHead architecture is designed. Finally, the wise intersection over union version 3 (WIoU v3) loss function is introduced to optimize weight allocation for low-quality samples, enhancing recognition and generalization capabilities for such instances. Experimental results demonstrate that the improved model achieves a 5.7% and 1.6% increase in [email protected] on the NEU-DET and custom datasets, respectively, compared to the original model. Concurrently, computational complexity is reduced by 6.4%, while detection precision and recall improve by 7.9% and 5.0%, respectively. This effectively enhances the detection performance of valve stem surface defects, meeting the high-precision and real-time detection demands of industrial scenarios. Valve stem Defect detection YOLOv11n Multi-scale features Lightweight inspection head Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-8639584","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":597590186,"identity":"a3bc2253-eb0d-4d64-8fa8-a97a746f2c89","order_by":0,"name":"Jiadong Dong","email":"","orcid":"","institution":"Anqing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jiadong","middleName":"","lastName":"Dong","suffix":""},{"id":597590187,"identity":"30d067fd-f2e5-4ea5-9e0b-c699bf04e349","order_by":1,"name":"Feihu Sang","email":"","orcid":"","institution":"Anqing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Feihu","middleName":"","lastName":"Sang","suffix":""},{"id":597590189,"identity":"72f62eb1-7231-4466-b2e4-0f98e6cd1b9d","order_by":2,"name":"Hao Sun","email":"","orcid":"","institution":"Anqing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Sun","suffix":""},{"id":597590191,"identity":"575f8bb6-d168-492f-9f5f-2ff24f91b586","order_by":3,"name":"Changrong Ou","email":"","orcid":"","institution":"Anqing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Changrong","middleName":"","lastName":"Ou","suffix":""},{"id":597590192,"identity":"f1d7004d-cba7-46c1-8494-69a4cdc7afff","order_by":4,"name":"Qinghu Guo","email":"","orcid":"","institution":"Anqing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Qinghu","middleName":"","lastName":"Guo","suffix":""},{"id":597590193,"identity":"2f262577-7a00-4994-8f26-7d7e5cbfcea3","order_by":5,"name":"Chunxiang Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYDACCSD+gMQmTgvjDJK1MPOQpEV+dvMzaZsa6zyDA8wHb/Mw2OUR1MI455ixcc6x9GKDA2zJ1jwMycUEtTBL5DA+zmE7nLjhAI+ZNA/DgcQGQlrYJHIYDlv8A2nh/0acFh6QLYxtYFvYiNMiIZFmbNjbl5448zCbseUcg2TCWuRnJD+T+PHNOrHvePPDG28q7AhrgQJmMGJgMCBSPQNU/SgYBaNgFIwC7AAAvZ41zHZb4xcAAAAASUVORK5CYII=","orcid":"","institution":"Anqing Normal University","correspondingAuthor":true,"prefix":"","firstName":"Chunxiang","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2026-01-19 12:41:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8639584/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8639584/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105563767,"identity":"b2e325d2-4947-4fc3-b75d-b5931183e34a","added_by":"auto","created_at":"2026-03-27 12:47:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1092546,"visible":true,"origin":"","legend":"","description":"","filename":"RDDYOLOAstudyonanimprovedvalvestemsurfacedefectdetectionalgorithmforYOLOv11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8639584/v1_covered_4b6c9943-12a2-40b2-996a-4c3668bdb479.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"RDD-YOLO: A study on an improved valve stem surface defect detection algorithm for YOLOv11","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Valve stem, Defect detection, YOLOv11n, Multi-scale features, Lightweight inspection head","lastPublishedDoi":"10.21203/rs.3.rs-8639584/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8639584/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAddressing challenges in detecting surface defects on refrigeration equipment valve stems\u0026mdash;including difficulty in extracting small target features, low accuracy against complex backgrounds, and high computational demands\u0026mdash;this paper proposes an improved RDD-YOLO model based on YOLOv11. First, the model replaces part of the convolutions in the backbone and all convolutions in the neck with receptive field channel attention convolutions (RFCAConv), enhancing local perception and channel attention to improve feature extraction for small target defects. Second, it constructs a depth-adaptive kernel spatial pyramid pooling factorization (DAK_SPPF) within the backbone network and designs depth-adaptive kernel convolution (DAKConv) to optimize multi-scale feature fusion, thereby improving detection accuracy in complex backgrounds. To reduce parameters and computational complexity, a lightweight deep dynamic efficient (LDDE) detection head is proposed. Combining dynamic convolution and the efficient local attention (ELA) module, a lightweight Detect_DyHead architecture is designed. Finally, the wise intersection over union version 3 (WIoU v3) loss function is introduced to optimize weight allocation for low-quality samples, enhancing recognition and generalization capabilities for such instances. Experimental results demonstrate that the improved model achieves a 5.7% and 1.6% increase in [email protected] on the NEU-DET and custom datasets, respectively, compared to the original model. Concurrently, computational complexity is reduced by 6.4%, while detection precision and recall improve by 7.9% and 5.0%, respectively. This effectively enhances the detection performance of valve stem surface defects, meeting the high-precision and real-time detection demands of industrial scenarios.\u003c/p\u003e","manuscriptTitle":"RDD-YOLO: A study on an improved valve stem surface defect detection algorithm for YOLOv11","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-27 11:17:01","doi":"10.21203/rs.3.rs-8639584/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7896ba26-6ebd-4178-8370-2a5a22662747","owner":[],"postedDate":"February 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-22T08:54:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-27 11:17:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8639584","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8639584","identity":"rs-8639584","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}