Knowledge Graph based Visual Reasoning Method for Cabinets Connecting Defect Detection

preprint OA: closed
Full text JSON View at publisher
Full text 20,243 characters · extracted from preprint-html · click to expand
Knowledge Graph based Visual Reasoning Method for Cabinets Connecting Defect Detection | 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 Knowledge Graph based Visual Reasoning Method for Cabinets Connecting Defect Detection Yizihe Lang, Chunchao Chen, Qiancheng Cai, Shuangzhu Tao, Baoxing Ju, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7392974/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 Existing visual inspection algorithms for wiring defect detection in substation protection panels exhibit limited robustness when handling real-world conditions such as partial character occlusion and ambiguous symbols, achieving field accuracy rates of merely 60%. This paper proposes a novel defect detection algorithm that integrates knowledge graphs with visual reasoning. By constructing a dedicated knowledge graph for substation protection panel wiring systems and synergistically combining Yolov8's rotated object detection with Qwen-2.5 foundation vision model's image reasoning capabilities, the proposed method enables intelligent inference of missing or blurred characters while detecting and correcting ambiguous character recognition. Logical wiring rules are rigorously embedded throughout the process. The approach was validated through defect detection on over 5,000 panel images, with comparative analysis against conventional optical character recognition (OCR) algorithms. Statistical results demonstrate approximately 95% parsing accuracy for wiring images with incomplete local information elements. Compared to traditional PaddleOCR, our method achieves a 29.18% improvement in recognition accuracy for cable markings and significantly mitigates confusion between visually similar characters (e.g., "0" and "O"). This breakthrough substantially enhances the reliability of visual recognition for wiring defects in protection panels. Knowledge Graph Foundation Vision Model Rotated Object Detection Protection Panels Wiring Defect Detection 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-7392974","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":524855085,"identity":"ac045cb2-fb07-40a9-83a6-f4957c4e3d5d","order_by":0,"name":"Yizihe Lang","email":"","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Yizihe","middleName":"","lastName":"Lang","suffix":""},{"id":524855086,"identity":"6aadd59f-09bb-4b48-8d9d-8a91a23a13c7","order_by":1,"name":"Chunchao Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAv0lEQVRIiWNgGAWjYBACPmYeBoaECgk5fmbmww+I0sIG0vLgjIWxZDtbmgFxWhh4GBgftlQkGpznUZAgTgs77zGJxAaJBOPDPAwGDDU20UQ4jC/ZIHGHRJ7ZYd4DDxiOpeU2ENbCY/gg8YxEsdlhvgQDxobDRGkxOJDYJpG4uZnHQIJYLUBbgFo2MJOgxdgg4YyEscRhYCAnEOMXfv4zZpI/Kurk+PsPH37wocaGsBZUkECa8lEwCkbBKBgFuAAAaIM3H8yFIx0AAAAASUVORK5CYII=","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":true,"prefix":"","firstName":"Chunchao","middleName":"","lastName":"Chen","suffix":""},{"id":524855088,"identity":"cc0bdc59-2beb-4bb5-8a68-f32541f8087b","order_by":2,"name":"Qiancheng Cai","email":"","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Qiancheng","middleName":"","lastName":"Cai","suffix":""},{"id":524855089,"identity":"88d85fec-07a1-4bf8-a7a6-099e33320991","order_by":3,"name":"Shuangzhu Tao","email":"","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Shuangzhu","middleName":"","lastName":"Tao","suffix":""},{"id":524855091,"identity":"5fcb3f8c-0a2d-4044-86ee-e5641333b55e","order_by":4,"name":"Baoxing Ju","email":"","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Baoxing","middleName":"","lastName":"Ju","suffix":""},{"id":524855092,"identity":"14113ba5-cccc-436b-8739-e41ec22daec5","order_by":5,"name":"Haiyan Yu","email":"","orcid":"","institution":"JiangSu Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Haiyan","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2025-08-17 14:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7392974/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7392974/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92997155,"identity":"4b506ac7-b1c3-4ede-95f3-aa23b0490610","added_by":"auto","created_at":"2025-10-08 03:42:16","extension":"doc","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1707008,"visible":true,"origin":"","legend":"","description":"","filename":"KnowledgeGraphbasedVisualReasoningMethodforCabinetsConnectingDefectDetection.doc","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/d1a46b7ec0a39fb873648749.doc"},{"id":92996192,"identity":"fac67b67-3b96-4181-9aa9-d5bf85adf8e8","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7213,"visible":true,"origin":"","legend":"","description":"","filename":"ab0d048cf7874db9b8ff16ec14974198.json","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/ad62dc96a53c43ec4a99852d.json"},{"id":92996193,"identity":"300f1647-f5d0-4a01-a9c9-e1d24501ef35","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69019,"visible":true,"origin":"","legend":"","description":"","filename":"ab0d048cf7874db9b8ff16ec149741981enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/6d9796a77b434deaf2427539.xml"},{"id":92996493,"identity":"29016a0f-8797-41ed-ae54-d47b2a26c3dc","added_by":"auto","created_at":"2025-10-08 03:34:16","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":225454,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/5f65517852094d289a1d51e7.png"},{"id":92996194,"identity":"aef6c45e-ada2-4ef2-8898-ce2ba7f48f8d","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125139,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/77c7a9cd96123307c34721f7.png"},{"id":92996195,"identity":"34cefd16-a3dd-44aa-825e-5cff542e2318","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":187799,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/07c3d0c04f50a87feae9fc6f.png"},{"id":92997263,"identity":"ff0ba8be-5502-4110-838a-0ce481534fe0","added_by":"auto","created_at":"2025-10-08 03:50:16","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":325738,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/39a82d9fb4e316200b1ab058.png"},{"id":92996200,"identity":"f76f9f8f-6e99-451c-a51d-42a42f12635a","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":253704,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/57ad4486ad9c41bedc45cd3b.png"},{"id":92996496,"identity":"549e76a6-4c26-4a88-9e40-3ae0183e4879","added_by":"auto","created_at":"2025-10-08 03:34:16","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":297395,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/05217706778cecd1b186c5cb.png"},{"id":92996202,"identity":"613eebe9-da53-43c2-9590-2ced5c65d2ae","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69100,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/3cd3602c949e005c3cc53541.png"},{"id":92996498,"identity":"6784616b-ec7b-4089-9580-5ac91f358aff","added_by":"auto","created_at":"2025-10-08 03:34:16","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47924,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/cb3f463b3bdb9fc589498a31.png"},{"id":92996207,"identity":"1be9639b-2de8-4493-bbfc-a0e25223bbd4","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46889,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/f5bbbe2a506402279489190a.png"},{"id":92996197,"identity":"f698dc8c-be3f-40e1-873d-e888387f2e57","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53514,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/3e9084181e62be615bd3049f.png"},{"id":92996211,"identity":"a156032e-941c-4748-8617-9f68794bc106","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40733,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/14c2f9fce4dc5d7c0b846fc7.png"},{"id":92996203,"identity":"7109454b-3a47-41a4-bc90-d6930ddd2b9f","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":65284,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/255f6b8e5c3f6d2ccf7dc9b6.png"},{"id":92996497,"identity":"0d03c96a-c390-4858-aea4-dd17c4b349a6","added_by":"auto","created_at":"2025-10-08 03:34:16","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90436,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/a93cb4a035fd84575b2eccf9.png"},{"id":92996205,"identity":"709441f4-d9a1-4c01-93d2-cdcb508bfd6e","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54253,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/0c5065b8824214cfb2a6785b.png"},{"id":92996210,"identity":"cf918989-9d30-459c-a10b-d4985d306327","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29199,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/0c43723186d9d3a8f38872c7.png"},{"id":92996208,"identity":"a833caa0-f404-47a6-a7d1-d5fd7060c91f","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21039,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/630f7c1c0591106f31fda621.png"},{"id":92996499,"identity":"2eef0cfd-fe06-44d8-890b-220019b1c73d","added_by":"auto","created_at":"2025-10-08 03:34:16","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67467,"visible":true,"origin":"","legend":"","description":"","filename":"ab0d048cf7874db9b8ff16ec149741981structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/18cf8f50f68288fbae4c039e.xml"},{"id":92996213,"identity":"1d773520-65da-4a43-97b5-f092eea0d5c9","added_by":"auto","created_at":"2025-10-08 03:26:16","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76292,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1/96c166ce65d066c53f8ba2ba.html"},{"id":93591704,"identity":"cce8a01e-730d-4ed1-a3d0-61fe0b9a53de","added_by":"auto","created_at":"2025-10-15 12:47:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":787446,"visible":true,"origin":"","legend":"","description":"","filename":"KnowledgeGraphbasedVisualReasoningMethodforCabinetsConnectingDefectDetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7392974/v1_covered_9bae408b-e268-4aa0-af15-33162a0a2da8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Knowledge Graph based Visual Reasoning Method for Cabinets Connecting Defect Detection","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":"Knowledge Graph, Foundation Vision Model, Rotated Object Detection, Protection Panels, Wiring Defect Detection","lastPublishedDoi":"10.21203/rs.3.rs-7392974/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7392974/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eExisting visual inspection algorithms for wiring defect detection in substation protection panels exhibit limited robustness when handling real-world conditions such as partial character occlusion and ambiguous symbols, achieving field accuracy rates of merely 60%. This paper proposes a novel defect detection algorithm that integrates knowledge graphs with visual reasoning. By constructing a dedicated knowledge graph for substation protection panel wiring systems and synergistically combining Yolov8's rotated object detection with Qwen-2.5 foundation vision model's image reasoning capabilities, the proposed method enables intelligent inference of missing or blurred characters while detecting and correcting ambiguous character recognition. Logical wiring rules are rigorously embedded throughout the process. The approach was validated through defect detection on over 5,000 panel images, with comparative analysis against conventional optical character recognition (OCR) algorithms. Statistical results demonstrate approximately 95% parsing accuracy for wiring images with incomplete local information elements. Compared to traditional PaddleOCR, our method achieves a 29.18% improvement in recognition accuracy for cable markings and significantly mitigates confusion between visually similar characters (e.g., \"0\" and \"O\"). This breakthrough substantially enhances the reliability of visual recognition for wiring defects in protection panels.\u003c/p\u003e","manuscriptTitle":"Knowledge Graph based Visual Reasoning Method for Cabinets Connecting Defect Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-08 03:26:11","doi":"10.21203/rs.3.rs-7392974/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":"92306710-6ba9-42f0-ac2d-e17df2387b3d","owner":[],"postedDate":"October 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-15T12:39:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-08 03:26:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7392974","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7392974","identity":"rs-7392974","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00