LMS-RTDETR: A Lightweight Weld Defect Detection Method Based on X-Ray

LMS-RTDETR: A Lightweight Weld Defect Detection Method Based on X-Ray | 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 LMS-RTDETR: A Lightweight Weld Defect Detection Method Based on X-Ray Xipeng Zhang, Heng Chen, Ziyang Liu, Shang Anli This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6521999/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract In the field of nondestructive testing, especially in X-ray weld defect detection where computational resources and storage space are limited, traditional target detection models face great challenges in dealing with low-contrast, multi-scale, and morphologically complex weld defects. In this paper, a Lightweight Multi-Scale Real-Time non-convolution detection TRansformer (LMS-RTDETR) is proposed with the aim of improving the detection of weld defects in resource-limited environments. First, a Multi-Scale Feature Aggregation (MSFA) module is used for parallel convolution and feature reorganization. Secondly, an Efficient Additive Attention Feature Interaction module reduces computational complexity from quadratic to linear while maintaining contextual awareness. Then, a Multi-Scale Feature Pyramid Network (MSFPN) implements multi-branch pathways for effective feature fusion. Finally, bounding box regression is optimized using the NWD-Inner GIoU loss function. The experiments show that LMS-RTDETR reduces the model parameters and floating point operations on the X-ray weld defect dataset by 38.34% and 29.30%. mAP50:95 improves by 3.10 percentage points. This study provides a high-precision solution for industrial non-destructive testing. Physical sciences/Engineering Physical sciences/Mathematics and computing Non-Destructive Testing 1 Multi-Scale 2 Efficient Additive 3 X-ray weld defect 4 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 27 May, 2025 Reviews received at journal 24 May, 2025 Reviewers agreed at journal 24 May, 2025 Reviews received at journal 21 May, 2025 Reviewers agreed at journal 15 May, 2025 Reviewers invited by journal 15 May, 2025 Editor assigned by journal 10 May, 2025 Editor invited by journal 07 May, 2025 Submission checks completed at journal 06 May, 2025 First submitted to journal 24 Apr, 2025 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-6521999","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":457184285,"identity":"12411948-eeb9-485d-bece-89ffc291730e","order_by":0,"name":"Xipeng Zhang","email":"","orcid":"","institution":"University of Shaanxi Province, Xijing University, Xi'an, 710123","correspondingAuthor":false,"prefix":"","firstName":"Xipeng","middleName":"","lastName":"Zhang","suffix":""},{"id":457184286,"identity":"8cad6048-4710-420f-a96f-90bd40b0a2be","order_by":1,"name":"Heng Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACeWbmAwYfDNjk7I83HyBOi2F7W0LhjAo+Y4YzxxKItObMGYPPPGfkEhlu5BgQp4NxRo7hBt42swTGnjMfb7xhsJPTbSCghV0irdhAsi0tj5m9d7PlHIZkY7MDBG1J3mZg2HasmI3n7DZpHoYDidsIaWG4kWD+I7Htf2KPRM4zIrWcOWJgcOAMW+IMiRw24rSAAtmwoYLN2IDnmLHlHAMi/AKKSuM/wKg0YG9+eONNhZ0cQS0oQIKHyKhB1kKqjlEwCkbBKBgRAABnh0YAmuRazwAAAABJRU5ErkJggg==","orcid":"","institution":"University of Shaanxi Province, Xijing University, Xi'an, 710123","correspondingAuthor":true,"prefix":"","firstName":"Heng","middleName":"","lastName":"Chen","suffix":""},{"id":457184287,"identity":"b904a7e1-26e9-431a-954c-88bd33ba79f6","order_by":2,"name":"Ziyang Liu","email":"","orcid":"","institution":"University of Shaanxi Province, Xijing University, Xi'an, 710123","correspondingAuthor":false,"prefix":"","firstName":"Ziyang","middleName":"","lastName":"Liu","suffix":""},{"id":457184289,"identity":"c2a16b06-c00a-47dc-b354-6ce4eee9e8ad","order_by":3,"name":"Shang Anli","email":"","orcid":"","institution":"Engineering Research Center of Hydrogen Energy Equipment \u0026 Safety Detection, University of Shaanxi Province, Xijing University, Xi'an, 710123","correspondingAuthor":false,"prefix":"","firstName":"Shang","middleName":"","lastName":"Anli","suffix":""}],"badges":[],"createdAt":"2025-04-24 15:08:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6521999/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6521999/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-25916-2","type":"published","date":"2025-11-25T15:57:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97179890,"identity":"c3fb1e5f-1b08-4dae-91ed-e85f43b1dbe2","added_by":"auto","created_at":"2025-12-01 16:17:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":942603,"visible":true,"origin":"","legend":"","description":"","filename":"LMSRTDETRALightweightWeldDefectDetectionMethodBasedonXRay.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6521999/v1_covered_e503e412-7345-41d6-9138-64f8025a0251.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LMS-RTDETR: A Lightweight Weld Defect Detection Method Based on X-Ray","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":"Non-Destructive Testing 1, Multi-Scale 2, Efficient Additive 3, X-ray weld defect 4","lastPublishedDoi":"10.21203/rs.3.rs-6521999/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6521999/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn the field of nondestructive testing, especially in X-ray weld defect detection where computational resources and storage space are limited, traditional target detection models face great challenges in dealing with low-contrast, multi-scale, and morphologically complex weld defects. In this paper, a Lightweight Multi-Scale Real-Time non-convolution detection TRansformer (LMS-RTDETR) is proposed with the aim of improving the detection of weld defects in resource-limited environments. First, a Multi-Scale Feature Aggregation (MSFA) module is used for parallel convolution and feature reorganization. Secondly, an Efficient Additive Attention Feature Interaction module reduces computational complexity from quadratic to linear while maintaining contextual awareness. Then, a Multi-Scale Feature Pyramid Network (MSFPN) implements multi-branch pathways for effective feature fusion. Finally, bounding box regression is optimized using the NWD-Inner GIoU loss function. The experiments show that LMS-RTDETR reduces the model parameters and floating point operations on the X-ray weld defect dataset by 38.34% and 29.30%. mAP50:95 improves by 3.10 percentage points. This study provides a high-precision solution for industrial non-destructive testing.\u003c/p\u003e","manuscriptTitle":"LMS-RTDETR: A Lightweight Weld Defect Detection Method Based on X-Ray","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-19 03:03:50","doi":"10.21203/rs.3.rs-6521999/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-27T06:51:36+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-25T01:32:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"29779018846744340788481449795882449088","date":"2025-05-25T01:28:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-22T03:04:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"83106641486217331566959546056890472155","date":"2025-05-15T15:08:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-15T14:54:56+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-10T13:49:24+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-07T13:27:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-06T09:18:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-24T14:56:33+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":"908de710-6736-401c-864c-8004eef25e13","owner":[],"postedDate":"May 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48591257,"name":"Physical sciences/Engineering"},{"id":48591258,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-12-01T16:15:52+00:00","versionOfRecord":{"articleIdentity":"rs-6521999","link":"https://doi.org/10.1038/s41598-025-25916-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-25 15:57:23","publishedOnDateReadable":"November 25th, 2025"},"versionCreatedAt":"2025-05-19 03:03:50","video":"","vorDoi":"10.1038/s41598-025-25916-2","vorDoiUrl":"https://doi.org/10.1038/s41598-025-25916-2","workflowStages":[]},"version":"v1","identity":"rs-6521999","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6521999","identity":"rs-6521999","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}