Scrap weight prediction for different scrap types based on semantic segmentation and machine learning

Scrap weight prediction for different scrap types based on semantic segmentation and machine learning | 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 Scrap weight prediction for different scrap types based on semantic segmentation and machine learning Jihu Yin, Pengcheng Xiao, Bixia Zhang, Liguang Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9139195/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Scrap steel is a high-energy-content and recyclable raw material that plays an important role in reducing carbon emissions and supporting sustainable development in the steel industry. During electric arc furnace (EAF) steelmaking, uncertainty in the weight of different scrap types can lead to inaccurate batching ratios, increased energy consumption, and reduced composition control accuracy, thereby affecting production efficiency and product quality. To this end, a weight prediction method for different scrap types based on semantic segmentation and machine learning is proposed. First, a UNet model with a VGG backbone is developed to perform semantic segmentation of scrap steel images, enabling the extraction of multidimensional visual features, including area, morphology, texture, and color. The segmentation model achieves high accuracy on a self-built dataset, with mIoU, mPA, and Acc values of 92.14%, 95.88%, and 98.26%, respectively. Subsequently, particle swarm optimization is employed to optimize a random forest regression model, establishing an effective mapping between visual features and scrap weight. The proposed PSO-RF model achieves MSE, MAE, RMSE, and \((R^2)\) values of 0.197, 0.158, 0.356, and 0.932, respectively. This method enables accurate scrap weight estimation during the EAF charging stage and provides practical support for improving batching accuracy and energy efficiency. Scrap steel Weight prediction UNet Regression model Semantic segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Apr, 2026 Reviews received at journal 12 Apr, 2026 Reviews received at journal 11 Apr, 2026 Reviewers agreed at journal 29 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviews received at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers invited by journal 23 Mar, 2026 Editor assigned by journal 17 Mar, 2026 Submission checks completed at journal 17 Mar, 2026 First submitted to journal 16 Mar, 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-9139195","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":610883204,"identity":"1d675986-afbc-439c-ab5a-95995ba4e749","order_by":0,"name":"Jihu Yin","email":"","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jihu","middleName":"","lastName":"Yin","suffix":""},{"id":610883205,"identity":"f6f1264f-66c4-42ca-94de-f61f922a6b1d","order_by":1,"name":"Pengcheng Xiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYDACZjBpA+WxEa8lDcoiSgsEHCZBi8Fx5oePC2rO5/H3nz/A8KHsMAP/7Ab8WiSb2YyNZxy7XSxxI5mBcca5wwwSdw7g18LPzGAmzdtwO3GDBDMDM2/bYQYDiQT8WtiY2b8BtZxL3MB/mIH5LzFa+Jl5QLYcSNzAkMzAzEiMFslmnmKgX5ITZ9xINjjYcy6dR+IGAS0G549vBIaYXWJ//8GHD36UWcvxzyCgBQSYYYwDQMxDWD2yllEwCkbBKBgFWAEA7Yc7s+vcDBwAAAAASUVORK5CYII=","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Pengcheng","middleName":"","lastName":"Xiao","suffix":""},{"id":610883206,"identity":"be257ed3-a0aa-46a8-80fb-641104229374","order_by":2,"name":"Bixia Zhang","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Bixia","middleName":"","lastName":"Zhang","suffix":""},{"id":610883207,"identity":"d5e4c966-6197-46e0-9e2e-4d3bba93abdc","order_by":3,"name":"Liguang Zhu","email":"","orcid":"","institution":"Hebei University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Liguang","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2026-03-16 14:39:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9139195/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9139195/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105424598,"identity":"48ac5794-8f94-4df3-9a8a-9751c9009cd0","added_by":"auto","created_at":"2026-03-25 23:22:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1469494,"visible":true,"origin":"","legend":"","description":"","filename":"MainDocument.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9139195/v1_covered_c4876ccd-77f6-4cc9-864b-f127001c4987.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Scrap weight prediction for different scrap types based on semantic segmentation and machine learning","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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Scrap steel, Weight prediction, UNet, Regression model, Semantic segmentation","lastPublishedDoi":"10.21203/rs.3.rs-9139195/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9139195/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eScrap steel is a high-energy-content and recyclable raw material that plays an important role in reducing carbon emissions and supporting sustainable development in the steel industry. During electric arc furnace (EAF) steelmaking, uncertainty in the weight of different scrap types can lead to inaccurate batching ratios, increased energy consumption, and reduced composition control accuracy, thereby affecting production efficiency and product quality. To this end, a weight prediction method for different scrap types based on semantic segmentation and machine learning is proposed. First, a UNet model with a VGG backbone is developed to perform semantic segmentation of scrap steel images, enabling the extraction of multidimensional visual features, including area, morphology, texture, and color. The segmentation model achieves high accuracy on a self-built dataset, with mIoU, mPA, and Acc values of 92.14%, 95.88%, and 98.26%, respectively. Subsequently, particle swarm optimization is employed to optimize a random forest regression model, establishing an effective mapping between visual features and scrap weight. The proposed PSO-RF model achieves MSE, MAE, RMSE, and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((R^2)\\)\u003c/span\u003e\u003c/span\u003e values of 0.197, 0.158, 0.356, and 0.932, respectively. This method enables accurate scrap weight estimation during the EAF charging stage and provides practical support for improving batching accuracy and energy efficiency.\u003c/p\u003e","manuscriptTitle":"Scrap weight prediction for different scrap types based on semantic segmentation and machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-25 23:22:08","doi":"10.21203/rs.3.rs-9139195/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-13T14:34:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T02:15:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-11T20:34:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"38135258430157444535945844269124961422","date":"2026-03-29T16:36:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19101431458311142461238249673815858361","date":"2026-03-26T05:48:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-23T17:36:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"173418353499096600302785638691989871922","date":"2026-03-23T16:50:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"216655785367222059373291480399470077094","date":"2026-03-23T16:28:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-23T15:30:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-18T01:30:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-17T05:25:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2026-03-16T14:35:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4af3a135-4575-427a-8e5e-88c86ddfbffe","owner":[],"postedDate":"March 25th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T23:53:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-25 23:22:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9139195","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9139195","identity":"rs-9139195","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}