Quality Prediction using Multiscale Convolutional VAEs for Thin Plate Parts

Quality Prediction using Multiscale Convolutional VAEs for Thin Plate Parts | 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 Quality Prediction using Multiscale Convolutional VAEs for Thin Plate Parts Xin Su, Yichen Liu, Ji Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7471793/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract The machining quality of thin-walled parts is critical to the performance and reliability of high-value equipment. This study proposes a Multi-SPP-VAE model to improve the accuracy and robustness of dimensional error prediction in thin-plate machining. The model incorporates a multiscale convolutional architecture to extract both local and global features from cutting force signals, an attention mechanism to refine latent-space representations, and the fusion of static machining parameters to enhance contextual awareness.Key innovations include a novel multi-scale spatial pyramid pooling structure for improved noise suppression and temporal pattern representation, and an enhanced Grey Wolf Optimization (EGWO) algorithm with nonlinear convergence control and distance-weighted update mechanisms for automated hyperparameter tuning.Experimental evaluations demonstrate that with 108 convolutional channels and a 32-dimensional latent space, the Multi-SPP-VAE significantly outperforms conventional CNN, RNN, and LSTM-based baselines in MSE, RMSE, and MAE across multiple datasets, confirming its strong generalization and predictive performance.This work provides new insights into feature-level error prediction in thin-plate machining and offers a scalable, high-fidelity solution for real-time quality monitoring in intelligent manufacturing environments. Physical sciences/Engineering Physical sciences/Mathematics and computing thin-walled parts dimensional error prediction cutting force multiscale convolution enhanced Grey Wolf Optimizer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 15 Sep, 2025 Reviews received at journal 14 Sep, 2025 Reviews received at journal 11 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers agreed at journal 09 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 06 Sep, 2025 Reviewers agreed at journal 06 Sep, 2025 Reviewers invited by journal 06 Sep, 2025 Editor assigned by journal 06 Sep, 2025 Editor invited by journal 02 Sep, 2025 Submission checks completed at journal 29 Aug, 2025 First submitted to journal 29 Aug, 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-7471793","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":514736646,"identity":"5d41faff-7b1d-4a51-88d5-bc50802f6f7f","order_by":0,"name":"Xin Su","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYBACfv7GhgMJBjZyEC4bEVokZxw++OBDQZox8VoMDqQlG874cDixgWgtDAfOmEnzGKSl97efPcDwoewwA//sBvw6GJt7QFpscmecyUtgnHHuMIPEnQP4tTAzQGzJ3cCQY8DM23aYwUAiAb8WNoYckJbD6Qb8bwyY/xKjhYcB5H2DwwkGEkBbGInRIiEBCmSDNMMZN94lHOw5l84jcYOAFvvzoKj8YyPP35978MGPMms5/hkEtKC48QCYJAGQpHgUjIJRMApGEgAAm2ZFuAmWIv8AAAAASUVORK5CYII=","orcid":"","institution":"Chengdu Aeronautic Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Su","suffix":""},{"id":514736647,"identity":"fa72ca7a-d56d-4e53-acf7-99f63db13441","order_by":1,"name":"Yichen Liu","email":"","orcid":"","institution":"Chengdu Aeronautic Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Yichen","middleName":"","lastName":"Liu","suffix":""},{"id":514736648,"identity":"0f7f1a81-0bf4-4fe2-82f1-5c8d4f9df114","order_by":2,"name":"Ji Li","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Ji","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-08-27 12:53:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7471793/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7471793/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-35186-1","type":"published","date":"2026-01-21T15:57:41+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":101151780,"identity":"254a150f-6988-4d0e-9b08-11a2c9853bdf","added_by":"auto","created_at":"2026-01-26 16:05:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":713299,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscrip10.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7471793/v1_covered_27486b90-a56b-4fe9-ab93-c38f9c94cc92.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Quality Prediction using Multiscale Convolutional VAEs for Thin Plate Parts","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":"thin-walled parts, dimensional error prediction, cutting force, multiscale convolution, enhanced Grey Wolf Optimizer","lastPublishedDoi":"10.21203/rs.3.rs-7471793/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7471793/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe machining quality of thin-walled parts is critical to the performance and reliability of high-value equipment. This study proposes a Multi-SPP-VAE model to improve the accuracy and robustness of dimensional error prediction in thin-plate machining. The model incorporates a multiscale convolutional architecture to extract both local and global features from cutting force signals, an attention mechanism to refine latent-space representations, and the fusion of static machining parameters to enhance contextual awareness.Key innovations include a novel multi-scale spatial pyramid pooling structure for improved noise suppression and temporal pattern representation, and an enhanced Grey Wolf Optimization (EGWO) algorithm with nonlinear convergence control and distance-weighted update mechanisms for automated hyperparameter tuning.Experimental evaluations demonstrate that with 108 convolutional channels and a 32-dimensional latent space, the Multi-SPP-VAE significantly outperforms conventional CNN, RNN, and LSTM-based baselines in MSE, RMSE, and MAE across multiple datasets, confirming its strong generalization and predictive performance.This work provides new insights into feature-level error prediction in thin-plate machining and offers a scalable, high-fidelity solution for real-time quality monitoring in intelligent manufacturing environments.\u003c/p\u003e","manuscriptTitle":"Quality Prediction using Multiscale Convolutional VAEs for Thin Plate Parts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-15 12:14:26","doi":"10.21203/rs.3.rs-7471793/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-15T18:31:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-14T05:42:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-11T13:24:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"48353962902031603339181766880121202418","date":"2025-09-11T12:19:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206868631353539903864478244123557803594","date":"2025-09-09T06:36:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"127678444979312096627165335733092039640","date":"2025-09-08T17:05:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247014633705761899218762081697816275412","date":"2025-09-06T13:55:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23667432927358069298781961855078373878","date":"2025-09-06T09:41:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-06T08:11:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-06T08:07:14+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-02T11:27:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-29T12:21:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-29T12:17:56+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":"0a7bf433-1443-40e9-b498-71973cb28b17","owner":[],"postedDate":"September 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54679355,"name":"Physical sciences/Engineering"},{"id":54679356,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-01-26T16:01:37+00:00","versionOfRecord":{"articleIdentity":"rs-7471793","link":"https://doi.org/10.1038/s41598-026-35186-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-01-21 15:57:41","publishedOnDateReadable":"January 21st, 2026"},"versionCreatedAt":"2025-09-15 12:14:26","video":"","vorDoi":"10.1038/s41598-026-35186-1","vorDoiUrl":"https://doi.org/10.1038/s41598-026-35186-1","workflowStages":[]},"version":"v1","identity":"rs-7471793","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7471793","identity":"rs-7471793","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}