Real-Virtual Data Fusion and YOLO11-based Segmentation for Automated Deposition Region Recognition in L-DED Repair Process

Real-Virtual Data Fusion and YOLO11-based Segmentation for Automated Deposition Region Recognition in L-DED Repair Process | 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 Real-Virtual Data Fusion and YOLO11-based Segmentation for Automated Deposition Region Recognition in L-DED Repair Process Inseong Moon, Seunghwan Lee, Hyub Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8735891/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 Reliable recognition of damaged regions is essential for automated L-DED repair, yet conventional pre-process planning often relies on costly 3D scanning and CAD/CAM alignment. We propose an on-machine, single-RGB-camera framework using YOLO11 instance segmentation with real–synthetic hybrid training data generated via physics-based rendering to address labelled data scarcity. Using a 28-image unseen-object (LOTO) test set from a blade-inspired specimen excluded from training, Hybrid-YOLO11m achieved 94.2% IoU and 97.0% F1, outperforming real-only, synthetic-only, and optimized OpenCV baselines under varying illumination and reflections. Furthermore, a bead-width-based offset compensation strategy reduced the effective risk of under-deposition by approximately 96.8%. The proposed approach enables low-cost, streamlined pre-process planning without 3D scanners for practical DED repair. Laser-Directed Energy Deposition (L-DED) Repair Vision-based Process Planning Instance Segmentation Real–Virtual Data Fusion Automated Deposition Region Recognition Full Text Supplementary Files 20260115SupplementaryMaterial.docx 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-8735891","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":589841840,"identity":"e45f8e0f-7894-4632-8587-1f392f02320a","order_by":0,"name":"Inseong Moon","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Inseong","middleName":"","lastName":"Moon","suffix":""},{"id":589841841,"identity":"35584310-6004-4c0e-b85b-aa7e23f31833","order_by":1,"name":"Seunghwan Lee","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Seunghwan","middleName":"","lastName":"Lee","suffix":""},{"id":589841842,"identity":"8921118d-0241-4727-afb8-ba7f1a5035dc","order_by":2,"name":"Hyub Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYBACPgYGNiB1QE6CGUgxNoDE2PBrYYNqMZZgZiZRS+IMBqK1sDcfe8zbdid9Zjv/wQc/dzDk8zOwpX3Aq4XnWLoxb9uz3NnMzMyGvWcYLGc2sB2egVeLRI6ZNG/b4dx5zMxs0oxtDAYGB9ib8TtM/v03kJZ0OWZm9t8gLfYEtUjwsIG0JEgDbWEG28LAdhi/Fp40M8k5554ZzmxmNpbsbZMwkDjMloxXCz/74WcSb8ruyEucP/jww882GwP+9jZjvFpAgIkHwZZgAMUPQcD4gwhFo2AUjIJRMIIBANGvPD3jQK2cAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-9108-5924","institution":"Korea Institute of Industrial Technology","correspondingAuthor":true,"prefix":"","firstName":"Hyub","middleName":"","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2026-01-30 01:25:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8735891/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8735891/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107869953,"identity":"c1c3dc86-c7e3-4934-996e-a901a7989f08","added_by":"auto","created_at":"2026-04-27 07:38:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2284839,"visible":true,"origin":"","legend":"","description":"","filename":"20260120Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8735891/v1_covered_ddd1a1d6-f5cf-4eb8-8694-5e846fb8ffb5.pdf"},{"id":102857010,"identity":"8bbc1571-3a7f-40c9-bf74-a0f399b177cf","added_by":"auto","created_at":"2026-02-17 15:15:59","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":116881,"visible":true,"origin":"","legend":"","description":"","filename":"20260115SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-8735891/v1/f1e707ef9bdab167e371906e.docx"}],"financialInterests":"","formattedTitle":"Real-Virtual Data Fusion and YOLO11-based Segmentation for Automated Deposition Region Recognition in L-DED Repair Process","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":"Laser-Directed Energy Deposition (L-DED) Repair, Vision-based Process Planning, Instance Segmentation, Real–Virtual Data Fusion, Automated Deposition Region Recognition","lastPublishedDoi":"10.21203/rs.3.rs-8735891/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8735891/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReliable recognition of damaged regions is essential for automated L-DED repair, yet conventional pre-process planning often relies on costly 3D scanning and CAD/CAM alignment. We propose an on-machine, single-RGB-camera framework using YOLO11 instance segmentation with real\u0026ndash;synthetic hybrid training data generated via physics-based rendering to address labelled data scarcity. Using a 28-image unseen-object (LOTO) test set from a blade-inspired specimen excluded from training, Hybrid-YOLO11m achieved 94.2% IoU and 97.0% F1, outperforming real-only, synthetic-only, and optimized OpenCV baselines under varying illumination and reflections. Furthermore, a bead-width-based offset compensation strategy reduced the effective risk of under-deposition by approximately 96.8%. The proposed approach enables low-cost, streamlined pre-process planning without 3D scanners for practical DED repair.\u003c/p\u003e","manuscriptTitle":"Real-Virtual Data Fusion and YOLO11-based Segmentation for Automated Deposition Region Recognition in L-DED Repair Process","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-17 15:15:54","doi":"10.21203/rs.3.rs-8735891/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":"802e4ccf-dba0-48ed-9235-32fbd16f7552","owner":[],"postedDate":"February 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-25T03:25:04+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-17 15:15:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8735891","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8735891","identity":"rs-8735891","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}