Information Content Analysis of Direct and Indirect Force Measurements for Machine Learning-Based Process State Classification in Multi-Stage Sheet Metal Forming

Information Content Analysis of Direct and Indirect Force Measurements for Machine Learning-Based Process State Classification in Multi-Stage Sheet Metal Forming | 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 Information Content Analysis of Direct and Indirect Force Measurements for Machine Learning-Based Process State Classification in Multi-Stage Sheet Metal Forming Markus Schumann, Jonas Moske, Felix Divo, Antonia Wüst, Kristian Kersting, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9234928/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 The predictive power of machine learning models for process monitoring in sheet metal forming depends strongly on the information content of the sensor signals. This study investigates how force signal characteristics represent process conditions in a multi-stage forming process consisting of deep drawing and ironing, in which surface roughness evolves with a downstream tendency. Indirect and direct force measurement concepts are compared: While indirect sensors are prone to noise, direct sensors often show more clarity. Neural networks are trained on datasets covering multiple roughness and process configurations. Model performance is analysed using classification metrics and explainable AI methods. The results reveal a counterintuitive finding: Visually smooth force signals with high signal-to-noise ratio can provide limited or misleading information for convolutional neural networks due to temporal misalignment, whereas noisier signals with distributed dynamics show more robust predictions. The study shows the influence of signal clarity for data-driven process monitoring in Industry 4.0-enabled forming. Mechanical Engineering Smart Tooling Force Signal Analysis Feature Extraction Explainable Machine Learning in Sheet Metal Forming Process State Classification 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-9234928","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":612720659,"identity":"15552225-a393-4b51-9f8a-0a434b405de2","order_by":0,"name":"Markus Schumann","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0002-3928-6707","institution":"Institute for Production Engineering and Forming Machines – PtU, Darmstadt","correspondingAuthor":true,"prefix":"","firstName":"Markus","middleName":"","lastName":"Schumann","suffix":""},{"id":612720660,"identity":"d9656cfc-0346-494b-af8f-33c213c86873","order_by":1,"name":"Jonas Moske","email":"","orcid":"https://orcid.org/0009-0005-7836-3447","institution":"Institute for Production Engineering and Forming Machines – PtU, Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Jonas","middleName":"","lastName":"Moske","suffix":""},{"id":612720661,"identity":"e3e198fe-fb4d-4a37-8954-cc8ef5d53fae","order_by":2,"name":"Felix Divo","email":"","orcid":"https://orcid.org/0000-0002-1916-7711","institution":"AIML Lab, Technical University, Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Felix","middleName":"","lastName":"Divo","suffix":""},{"id":612720662,"identity":"04f14dfe-7795-450c-9d44-5f0554486c76","order_by":3,"name":"Antonia Wüst","email":"","orcid":"https://orcid.org/0009-0005-8636-1337","institution":"AIML Lab, Technical University, Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Antonia","middleName":"","lastName":"Wüst","suffix":""},{"id":612720663,"identity":"9cd0fbc8-ba6e-44a3-a193-7fdc8d2c8bf6","order_by":4,"name":"Kristian Kersting","email":"","orcid":"https://orcid.org/0000-0002-2873-9152","institution":"AIML Lab, Technical University, Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Kristian","middleName":"","lastName":"Kersting","suffix":""},{"id":612720664,"identity":"d74a256e-5e14-4a96-9d4d-4a13c058f141","order_by":5,"name":"Peter Groche","email":"","orcid":"https://orcid.org/0000-0001-7927-9523","institution":"Institute for Production Engineering and Forming Machines – PtU, Darmstadt","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Groche","suffix":""}],"badges":[],"createdAt":"2026-03-26 13:44:42","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-9234928/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9234928/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105728444,"identity":"3e0b6556-4084-4a69-affb-1f4362b616ad","added_by":"auto","created_at":"2026-03-30 11:11:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2085911,"visible":true,"origin":"","legend":"","description":"","filename":"IDDRG2026InformationContentAnalysisRevision.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9234928/v1_covered_715dfadc-87b1-4547-bd51-395642048932.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eInformation Content Analysis of Direct and Indirect Force Measurements for Machine Learning-Based Process State Classification in Multi-Stage Sheet Metal Forming\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Smart Tooling, Force Signal Analysis, Feature Extraction, Explainable Machine Learning in Sheet Metal Forming, Process State Classification","lastPublishedDoi":"10.21203/rs.3.rs-9234928/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9234928/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe predictive power of machine learning models for process monitoring in sheet metal forming depends strongly on the information content of the sensor signals. This study investigates how force signal characteristics represent process conditions in a multi-stage forming process consisting of deep drawing and ironing, in which surface roughness evolves with a downstream tendency. Indirect and direct force measurement concepts are compared: While indirect sensors are prone to noise, direct sensors often show more clarity. Neural networks are trained on datasets covering multiple roughness and process configurations. Model performance is analysed using classification metrics and explainable AI methods. The results reveal a counterintuitive finding: Visually smooth force signals with high signal-to-noise ratio can provide limited or misleading information for convolutional neural networks due to temporal misalignment, whereas noisier signals with distributed dynamics show more robust predictions. The study shows the influence of signal clarity for data-driven process monitoring in Industry 4.0-enabled forming.\u003c/p\u003e","manuscriptTitle":"Information Content Analysis of Direct and Indirect Force Measurements for Machine Learning-Based Process State Classification in Multi-Stage Sheet Metal Forming","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-28 13:00:57","doi":"10.21203/rs.3.rs-9234928/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":"March 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65197970,"name":"Mechanical Engineering"}],"tags":[],"updatedAt":"2026-03-28T13:00:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-28 13:00:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9234928","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9234928","identity":"rs-9234928","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}