Towards hybrid and explainable data-driven models for forming processes: addressing the gap between simulation, process data, and model validation

Towards hybrid and explainable data-driven models for forming processes: addressing the gap between simulation, process data, and model validation | 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 Method Article Towards hybrid and explainable data-driven models for forming processes: addressing the gap between simulation, process data, and model validation Daria Gelbich, Markus Schumann, Jonas Moske, Philipp Niemietz, and 18 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8589495/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 Finite element method simulations are foundational to forming process design, but their utility for machine learning is often limited by idealizations that create a gap with stochastic, real-world manufacturing conditions. This paper investigates the systematic integration of simulation-based knowledge into machine learning pipelines to bridge this gap. A structured review of 56 publications reveals systemic limitations in current research, which we classify as the reality, validation, and trust gaps. In response, this work formulates four research questions to address these gaps, examining them through use cases in forging, blanking, and deep drawing. The analysis demonstrates that the impact of simulation simplifications is highly task-dependent, requiring a tailored approach to model selection and data integration. This paper contributes to the methodological discourse by proposing a framework for simulation-informed machine learning. It argues for a shift in focus from maximizing physical realism to a “fitfor-purpose” approach, where simulation complexity is strategically aligned with the requirements of the downstream machine learning task. The paper outlines a path toward more robust, interpretable, and industrially transferable modeling strategies in forming technology. Mechanical Engineering Finite element simulation forming technology machine learning synthetic data Full Text Additional Declarations The authors declare no competing interests. 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-8589495","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":573785141,"identity":"affd1f57-5194-4546-893f-9c2976290d5d","order_by":0,"name":"Daria Gelbich","email":"data:image/png;base64,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","orcid":"","institution":"Manufacturing Technology Institute - MTI of RWTH Aachen University","correspondingAuthor":true,"prefix":"","firstName":"Daria","middleName":"","lastName":"Gelbich","suffix":""},{"id":573785142,"identity":"05b691df-134c-452c-97e9-dc546655966a","order_by":1,"name":"Markus Schumann","email":"","orcid":"","institution":"Institut für Produktionstechnik und Umformmaschinen (PTU), Technische Universität Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Markus","middleName":"","lastName":"Schumann","suffix":""},{"id":573785143,"identity":"468f3b64-42ff-444d-9b67-7b35822b4283","order_by":2,"name":"Jonas Moske","email":"","orcid":"","institution":"Institut für Produktionstechnik und Umformmaschinen (PTU), Technische Universität Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Jonas","middleName":"","lastName":"Moske","suffix":""},{"id":573785144,"identity":"0b5e1cb4-3a61-4def-a914-6a95bd702f2a","order_by":3,"name":"Philipp Niemietz","email":"","orcid":"","institution":"Manufacturing Technology Institute - MTI of RWTH Aachen University","correspondingAuthor":false,"prefix":"","firstName":"Philipp","middleName":"","lastName":"Niemietz","suffix":""},{"id":573785145,"identity":"c18d3b28-9167-42ff-b292-e5071ea7f0b5","order_by":4,"name":"Pascal Heinzelmann","email":"","orcid":"","institution":"Institute for Metal Forming Technology, University of Stuttgart","correspondingAuthor":false,"prefix":"","firstName":"Pascal","middleName":"","lastName":"Heinzelmann","suffix":""},{"id":573785146,"identity":"89f93518-1793-4cd9-843f-2868f24cc451","order_by":5,"name":"Jonas Knoche","email":"","orcid":"","institution":"Institute of Forming Technology, University of Siegen","correspondingAuthor":false,"prefix":"","firstName":"Jonas","middleName":"","lastName":"Knoche","suffix":""},{"id":573785147,"identity":"04f414d4-e372-42e8-bb3c-cde377af21fb","order_by":6,"name":"Eduard Ortlieb","email":"","orcid":"","institution":"Institute of Metal Forming and Metal Forming Machines, Leibniz University Hannover","correspondingAuthor":false,"prefix":"","firstName":"Eduard","middleName":"","lastName":"Ortlieb","suffix":""},{"id":573785148,"identity":"be426baf-239d-45ef-8a1d-bc076e5e31ca","order_by":7,"name":"Artem Alimov","email":"","orcid":"","institution":"Department of Hybrid Manufacturing","correspondingAuthor":false,"prefix":"","firstName":"Artem","middleName":"","lastName":"Alimov","suffix":""},{"id":573785149,"identity":"ceb15f27-4fea-4d7f-87d8-2f7ebf8ba37d","order_by":8,"name":"Marion Vogel","email":"","orcid":"","institution":"Institute of Manufacturing Technology, Friedrich-Alexander-Universität Erlangen-Nürnberg","correspondingAuthor":false,"prefix":"","firstName":"Marion","middleName":"","lastName":"Vogel","suffix":""},{"id":573785150,"identity":"02afbcb5-ffbf-44c6-a614-dd5acc7519b7","order_by":9,"name":"Christoph Hartmann","email":"","orcid":"","institution":"Institute of Metal Forming and Casting, Technische Universität München","correspondingAuthor":false,"prefix":"","firstName":"Christoph","middleName":"","lastName":"Hartmann","suffix":""},{"id":573785151,"identity":"09f6273e-d5ef-4d83-8531-497255ac4347","order_by":10,"name":"Christine Heinzel","email":"","orcid":"","institution":"nstitute for production technology and systems, Leuphana University of Lüneburg","correspondingAuthor":false,"prefix":"","firstName":"Christine","middleName":"","lastName":"Heinzel","suffix":""},{"id":573785152,"identity":"a2d78649-91b4-40f4-8c63-1b41f8ef56c4","order_by":11,"name":"Adili Yiming","email":"","orcid":"","institution":"Chair of MachineTools Development and Adaptive Controls, Dresden University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Adili","middleName":"","lastName":"Yiming","suffix":""},{"id":573785153,"identity":"9c86288b-bd57-4b99-930c-711d9db569f8","order_by":12,"name":"Steffen Ihlenfeldt","email":"","orcid":"","institution":"Chair of MachineTools Development and Adaptive Controls, Dresden University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Steffen","middleName":"","lastName":"Ihlenfeldt","suffix":""},{"id":573785154,"identity":"4d0fe99e-8a1a-4612-a7a2-a6215027549d","order_by":13,"name":"Noomane Ben Khalifa","email":"","orcid":"","institution":"nstitute for production technology and systems, Leuphana University of Lüneburg","correspondingAuthor":false,"prefix":"","firstName":"Noomane","middleName":"Ben","lastName":"Khalifa","suffix":""},{"id":573785155,"identity":"3d2b1555-0480-4346-b7ac-9f8332435390","order_by":14,"name":"Wolfram Volk","email":"","orcid":"","institution":"Institute of Metal Forming and Casting, Technische Universität München","correspondingAuthor":false,"prefix":"","firstName":"Wolfram","middleName":"","lastName":"Volk","suffix":""},{"id":573785156,"identity":"0b8f8eb2-faf6-45ee-8e50-398b0341cd23","order_by":15,"name":"Marion Merklein","email":"","orcid":"","institution":"Institute of Manufacturing Technology, Friedrich-Alexander-Universität Erlangen-Nürnberg","correspondingAuthor":false,"prefix":"","firstName":"Marion","middleName":"","lastName":"Merklein","suffix":""},{"id":573785157,"identity":"effd738d-1ccf-4b8b-a744-cd47842c6463","order_by":16,"name":"Sebastian Härtel","email":"","orcid":"","institution":"Department of Hybrid Manufacturing, Brandenburg University of Technology Cottbus-Senftenberg","correspondingAuthor":false,"prefix":"","firstName":"Sebastian","middleName":"","lastName":"Härtel","suffix":""},{"id":573785158,"identity":"dcc73091-442b-4063-8e94-a80bedeaf77e","order_by":17,"name":"Bernd–Arno Behrens","email":"","orcid":"","institution":"Institute of Metal Forming and Metal Forming Machines, Leibniz University Hannover","correspondingAuthor":false,"prefix":"","firstName":"Bernd–Arno","middleName":"","lastName":"Behrens","suffix":""},{"id":573785159,"identity":"00d8e9a1-5f0f-429a-8c54-346616019281","order_by":18,"name":"Bernd Engel","email":"","orcid":"","institution":"Institute of Forming Technology, University of Siegen","correspondingAuthor":false,"prefix":"","firstName":"Bernd","middleName":"","lastName":"Engel","suffix":""},{"id":573785160,"identity":"f93e112c-c4d0-47f1-a692-d19a8c7a03b7","order_by":19,"name":"Mathias Liewald","email":"","orcid":"","institution":"Institute for Metal Forming Technology, University of Stuttgart","correspondingAuthor":false,"prefix":"","firstName":"Mathias","middleName":"","lastName":"Liewald","suffix":""},{"id":573785161,"identity":"269dcd0d-4913-424b-ac46-54fe2596b051","order_by":20,"name":"Peter Groche","email":"","orcid":"","institution":"Institut für Produktionstechnik und Umformmaschinen (PTU), Technische Universität Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Groche","suffix":""},{"id":573785162,"identity":"312fc43a-d389-4281-85c0-347c7e6374dd","order_by":21,"name":"Thomas Bergs","email":"","orcid":"","institution":"Manufacturing Technology Institute - MTI of RWTH Aachen University","correspondingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"","lastName":"Bergs","suffix":""}],"badges":[],"createdAt":"2026-01-13 08:51:25","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8589495/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8589495/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100368618,"identity":"8aead018-3d79-4ed3-b1c5-677d7b4c2acb","added_by":"auto","created_at":"2026-01-16 07:58:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2513793,"visible":true,"origin":"","legend":"","description":"","filename":"AK1SPPArticleCopy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8589495/v1_covered_747812a4-0db0-4016-8ad4-44f055c3cebe.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTowards hybrid and explainable data-driven models for forming processes: addressing the gap between simulation, process data, and model validation\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Deutsche Forschungsgemeinschaft","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":"Finite element simulation, forming technology, machine learning, synthetic data","lastPublishedDoi":"10.21203/rs.3.rs-8589495/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8589495/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFinite element method simulations are foundational to forming process design, but their utility for machine learning is often limited by idealizations that create a gap with stochastic, real-world manufacturing conditions. This paper investigates the systematic integration of simulation-based knowledge into machine learning pipelines to bridge this gap. A structured review of 56 publications reveals systemic limitations in current research, which we classify as the reality, validation, and trust gaps. In response, this work formulates four research questions to address these gaps, examining them through use cases in forging, blanking, and deep drawing. The analysis demonstrates that the impact of simulation simplifications is highly task-dependent, requiring a tailored approach to model selection and data integration. This paper contributes to the methodological discourse by proposing a framework for simulation-informed machine learning. It argues for a shift in focus from maximizing physical realism to a “fitfor-purpose” approach, where simulation complexity is strategically aligned with the requirements of the downstream machine learning task. The paper outlines a path toward more robust, interpretable, and industrially transferable modeling strategies in forming technology.\u003c/p\u003e","manuscriptTitle":"Towards hybrid and explainable data-driven models for forming processes: addressing the gap between simulation, process data, and model validation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-14 04:30:33","doi":"10.21203/rs.3.rs-8589495/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":"7b3d1485-5fcf-4360-b9be-1a4fe677b81c","owner":[],"postedDate":"January 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61049036,"name":"Mechanical Engineering"}],"tags":[],"updatedAt":"2026-01-14T04:30:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-14 04:30:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8589495","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8589495","identity":"rs-8589495","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}