Deep Learning and Generative Models for Stress–Strain Prediction of Bio-Inspired Composite Materials

Deep Learning and Generative Models for Stress–Strain Prediction of Bio-Inspired Composite Materials | 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 Deep Learning and Generative Models for Stress–Strain Prediction of Bio-Inspired Composite Materials Amol A. Chavan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9467337/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 Due to their impressive mechanical performance and structural efficiency reminiscent of natural systems, bio-inspired composite materials have garnered significant attention. The proper forecast of their stress-strain behavior is necessary to design optimally and provide structural reliability. A framework of Deep Learning (DL) based modeling and analysis of the nonlinear stress-strain response of bio-inspired composite materials is developed in this work. A 5000 sample and 247 feature high dimensional dataset is used to model complex interactions between material properties and mechanical behavior. Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks are used to predictive model whereas Generative Adversarial Networks (GAN) are used to produce synthetic stress strain curves. The models will be measured by the use of Mean Squared Error (MSE) and coefficient of determination (R 2 ). These findings indicate that both CNN and LSTM models have a high prediction accuracy with a R 2 of 0.99204 and 0.99210, respectively. Remaining analysis ensures that there is impartial forecasting and consistent model behavior. The correlation analysis of the features also confirms the physical consistency of the dataset. Even though the GAN model is effective in general capturing the stress-strain behavior trend, it is also not very stable and its outputs are noisy, which implies that the model requires additional optimization. The suggested framework is a dependable and scalable method of predicting the behaviour of materials using data and can be successfully used in the digital twin systems and intelligent material design. Physical sciences/Engineering Physical sciences/Materials science Physical sciences/Mathematics and computing Deep Learning (DL) Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) Generative Adversarial Network (GAN) Stress–Strain Prediction Bio-Inspired Composite Materials Machine Learning (ML) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 17 May, 2026 Reviews received at journal 13 May, 2026 Reviewers agreed at journal 06 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers invited by journal 01 May, 2026 Editor invited by journal 28 Apr, 2026 Editor assigned by journal 21 Apr, 2026 Submission checks completed at journal 21 Apr, 2026 First submitted to journal 20 Apr, 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-9467337","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":635403669,"identity":"f31a29c6-ffd6-4f36-a4d3-494a40f5339c","order_by":0,"name":"Amol A. Chavan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYDACCTiLufHxjwoQzdxArBbGZmOGMyAtjMRraZNmbAMz8Gvhn938TOLnDgZ53fbGZuPCebXR/O1ALT8qtuG25M4xM8neMwyG284cbHw8c9vx3BmHGRsYe87cxqnFQCLB2IC3jYFx243EZgPebcdyG4BamBnb8GlJ/2z4t43BHqilTYJ3zrHc+YS15Bg+BtqSCNIizdtQk7uBkBaJGzmFj2XbJJKBfmk2nHHsQO5GoJaD+PzCPyN9w8G3bTa22443H3zwoaYud975wwcf/KjArQVmGYxxGEweIKQeGdSRongUjIJRMApGCAAAAgpfwO27qVsAAAAASUVORK5CYII=","orcid":"","institution":"Pune Institute of Computer Technology","correspondingAuthor":true,"prefix":"","firstName":"Amol","middleName":"A.","lastName":"Chavan","suffix":""}],"badges":[],"createdAt":"2026-04-20 05:54:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9467337/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9467337/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109022335,"identity":"e41e77fc-e621-48d5-8b93-cad232e7ab80","added_by":"auto","created_at":"2026-05-11 19:35:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":588861,"visible":true,"origin":"","legend":"","description":"","filename":"DeepLearningandGenerativeModelsforStressStrainPredictionofBioInspiredCompositeMaterials.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9467337/v1_covered_c19f6918-3916-4441-a2e9-b641b664bc0e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eDeep Learning and Generative Models for Stress–Strain Prediction of Bio-Inspired Composite Materials\u003c/p\u003e","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":"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":"Deep Learning (DL), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Generative Adversarial Network (GAN), Stress–Strain Prediction, Bio-Inspired Composite Materials, Machine Learning (ML)","lastPublishedDoi":"10.21203/rs.3.rs-9467337/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9467337/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDue to their impressive mechanical performance and structural efficiency reminiscent of natural systems, bio-inspired composite materials have garnered significant attention. The proper forecast of their stress-strain behavior is necessary to design optimally and provide structural reliability. A framework of Deep Learning (DL) based modeling and analysis of the nonlinear stress-strain response of bio-inspired composite materials is developed in this work. A 5000 sample and 247 feature high dimensional dataset is used to model complex interactions between material properties and mechanical behavior. Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks are used to predictive model whereas Generative Adversarial Networks (GAN) are used to produce synthetic stress strain curves. The models will be measured by the use of Mean Squared Error (MSE) and coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e). These findings indicate that both CNN and LSTM models have a high prediction accuracy with a R 2 of 0.99204 and 0.99210, respectively. Remaining analysis ensures that there is impartial forecasting and consistent model behavior. The correlation analysis of the features also confirms the physical consistency of the dataset. Even though the GAN model is effective in general capturing the stress-strain behavior trend, it is also not very stable and its outputs are noisy, which implies that the model requires additional optimization. The suggested framework is a dependable and scalable method of predicting the behaviour of materials using data and can be successfully used in the digital twin systems and intelligent material design.\u003c/p\u003e","manuscriptTitle":"Deep Learning and Generative Models for Stress–Strain Prediction of Bio-Inspired Composite Materials","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-11 19:35:29","doi":"10.21203/rs.3.rs-9467337/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-17T20:16:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-13T22:22:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"187941948781535561279227082622228289180","date":"2026-05-06T10:09:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"56169790093116535565818078140634917337","date":"2026-05-01T15:43:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"209090044225694013211747089309946845509","date":"2026-05-01T11:28:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"156440124643929655082807271625693572190","date":"2026-05-01T09:23:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"216837951652075209828360563751455225582","date":"2026-05-01T09:14:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-01T08:40:33+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-28T07:29:31+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-21T13:24:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-21T13:23:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-20T05:50:10+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":"5660c5ad-14fa-4044-9013-f087960d90d3","owner":[],"postedDate":"May 11th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-17T20:16:25+00:00","index":42,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-13T22:22:41+00:00","index":41,"fulltext":""},{"type":"reviewerAgreed","content":"187941948781535561279227082622228289180","date":"2026-05-06T10:09:59+00:00","index":40,"fulltext":""},{"type":"reviewerAgreed","content":"56169790093116535565818078140634917337","date":"2026-05-01T15:43:18+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"209090044225694013211747089309946845509","date":"2026-05-01T11:28:09+00:00","index":38,"fulltext":""},{"type":"reviewerAgreed","content":"156440124643929655082807271625693572190","date":"2026-05-01T09:23:47+00:00","index":37,"fulltext":""},{"type":"reviewerAgreed","content":"216837951652075209828360563751455225582","date":"2026-05-01T09:14:32+00:00","index":36,"fulltext":""},{"type":"reviewersInvited","content":"11","date":"2026-05-01T08:40:33+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":67957764,"name":"Physical sciences/Engineering"},{"id":67957765,"name":"Physical sciences/Materials science"},{"id":67957766,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-11T19:35:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-11 19:35:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9467337","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9467337","identity":"rs-9467337","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}