Data-driven soft sensing for raw milk ethanol stability prediction

Data-driven soft sensing for raw milk ethanol stability prediction | 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 Data-driven soft sensing for raw milk ethanol stability prediction Song Shen, Xiaodong Song, Haohan Ding, Xiaohui Cui, Yicheng Di, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7396515/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 To address the destructive limitations of conventional ethanol stability testing methods for raw milk and their declining applicability in industrial contexts, this study proposes a TabNet-based soft sensing model. By leveraging autoencoder-based feature reconstruction and a multimodal feature selection strategy, eight highly relevant attributes were systematically identified as model inputs: protein content, total solids, solids-not-fat (SNF), fat content, titratable acidity, lactose content, relative density, and raw milk temperature. A diffusion model was innovatively employed to overcome the constraint of class imbalance, enabling the development of a non-destructive model that predicts ethanol stability based on routinely monitored indicators. Validated on a three-year industrial-scale raw milk intake dataset, the proposed model achieved an accuracy of 92.57% and a recall of 90.26% in identifying ethanol-unstable samples, demonstrating substantial potential for real-world engineering applications. Physical sciences/Chemistry Physical sciences/Engineering Physical sciences/Mathematics and computing ethanol stability soft sensing raw milk diffusion model unbalanced data 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-7396515","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":512861426,"identity":"efc1f3e7-b310-4f66-8314-8ac52d5e4076","order_by":0,"name":"Song Shen","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Shen","suffix":""},{"id":512861427,"identity":"7a79eeca-db29-40a0-80c7-81012e413fc5","order_by":1,"name":"Xiaodong Song","email":"","orcid":"","institution":"Key Laboratory of Dairy Quality Digital Intelligence Monitoring Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaodong","middleName":"","lastName":"Song","suffix":""},{"id":512861428,"identity":"c4be9a12-ab9a-472d-8392-57669997061a","order_by":2,"name":"Haohan Ding","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Haohan","middleName":"","lastName":"Ding","suffix":""},{"id":512861429,"identity":"87b5d026-9ed5-413d-9eaa-bfa45584cab0","order_by":3,"name":"Xiaohui Cui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIie2RMWsCMRTHcwTSJXJruvQzPOeKfpWEA11ECgUnhxPhuojzSb+EW+mW8qBdWm+9wSFdbnJwklta+rRQHK7XGwvmR/L4J+/9yBDGPJ5/SRAzzWhxbkH/3IpGitBNlW9oWMLJuUYJ0yhRbtIZwYvc3bjJpvtw8WbZbowsvI8rFZWbGejn/i1ga0WhiB7nIx2ka2RqYysVUGbqtECzOioCI7BD4K0EqaV/U2KrPw+KdEAhgmwL/KNemTqTHBUGFLqQ0ytBjaJe32dgFn2zRAEUUEO+haf5eiBVXq2Ed4Pistx3zCLDol3usQfZsO3K8fVVmFYrp4jDx5iYiqUt/5wnuKPSazLp8Xg858UXwCdnxbdHokkAAAAASUVORK5CYII=","orcid":"","institution":"Jiangnan University","correspondingAuthor":true,"prefix":"","firstName":"Xiaohui","middleName":"","lastName":"Cui","suffix":""},{"id":512861430,"identity":"e74b3aa7-4574-4a14-ae72-e9b050626d4b","order_by":4,"name":"Yicheng Di","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Yicheng","middleName":"","lastName":"Di","suffix":""},{"id":512861431,"identity":"7994ae64-e704-454e-9c3b-0930ee1cf896","order_by":5,"name":"Zhenqi Xie","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Zhenqi","middleName":"","lastName":"Xie","suffix":""},{"id":512861432,"identity":"66dded72-ab65-4afe-8bf4-d7b7ef0211a3","order_by":6,"name":"Huadi Huang","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Huadi","middleName":"","lastName":"Huang","suffix":""},{"id":512861433,"identity":"fd15ce2b-f84d-4b67-9d41-dd6440f6bd12","order_by":7,"name":"Guanjun Dong","email":"","orcid":"","institution":"Key Laboratory of Dairy Quality Digital Intelligence Monitoring Technology","correspondingAuthor":false,"prefix":"","firstName":"Guanjun","middleName":"","lastName":"Dong","suffix":""}],"badges":[],"createdAt":"2025-08-18 06:53:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7396515/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7396515/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96602766,"identity":"fcf2fcdd-3923-4b71-9598-7d99136bd9c5","added_by":"auto","created_at":"2025-11-24 09:01:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1276841,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptauthor.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7396515/v1_covered_439f4c97-fa6b-4a19-bdc1-d734bd81d93b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Data-driven soft sensing for raw milk ethanol stability prediction","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":"ethanol stability, soft sensing, raw milk, diffusion model, unbalanced, data","lastPublishedDoi":"10.21203/rs.3.rs-7396515/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7396515/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the destructive limitations of conventional ethanol stability testing methods for raw milk and their declining applicability in industrial contexts, this study proposes a TabNet-based soft sensing model. By leveraging autoencoder-based feature reconstruction and a multimodal feature selection strategy, eight highly relevant attributes were systematically identified as model inputs: protein content, total solids, solids-not-fat (SNF), fat content, titratable acidity, lactose content, relative density, and raw milk temperature. A diffusion model was innovatively employed to overcome the constraint of class imbalance, enabling the development of a non-destructive model that predicts ethanol stability based on routinely monitored indicators. Validated on a three-year industrial-scale raw milk intake dataset, the proposed model achieved an accuracy of 92.57% and a recall of 90.26% in identifying ethanol-unstable samples, demonstrating substantial potential for real-world engineering applications.\u003c/p\u003e","manuscriptTitle":"Data-driven soft sensing for raw milk ethanol stability prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-12 16:33:32","doi":"10.21203/rs.3.rs-7396515/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":"22a9ea94-5931-4ca2-9247-b6bf99caea47","owner":[],"postedDate":"September 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54475923,"name":"Physical sciences/Chemistry"},{"id":54475924,"name":"Physical sciences/Engineering"},{"id":54475925,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-11-20T18:08:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-12 16:33:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7396515","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7396515","identity":"rs-7396515","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}