Analytical and Machine‑Learning Framework for Predicting the Impact of LPBF Parameters on the Hardness of Inconel™ 718

Analytical and Machine‑Learning Framework for Predicting the Impact of LPBF Parameters on the Hardness of Inconel™ 718 | 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 Analytical and Machine‑Learning Framework for Predicting the Impact of LPBF Parameters on the Hardness of Inconel™ 718 Mohsen Dehghanpour Abyaneh, Raffaella Sesana, Mohammad Sadegh Javadi, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7648647/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 In Laser Powder Bed Fusion, a layer-by-layer melting of metal powder takes place and is specifically suited to high-performance applications in advanced technologies using Inconel™ 718. ANOVA and hardness measurements identified relationships that cannot be predicted using conventional statistical methods. Particle Swarm Optimization and Genetic Algorithm were proposed to define the relationships between the input and output data. Although the mean accuracy was high (97% for Particle Swarm Optimization and 91% for Genetic Algorithm), the drawbacks were calculation variation and sensitivity to parameter changes. The prediction of hardness was then done using five regression models, such as Support Vector Machine, Gaussian Process Regression (GPR), Single-Layer and Deep-Layer Artificial Neural Network (ANN), and Random Tree (RT). The low R 2 values were observed in the initial implementation with a mean accuracy of 90%. The linear method of optimizing output data increased R 2 values up to and beyond 0.9 with high average accuracy. GPR and single-layer ANN performed best in terms of training results. A rollback process was implemented on the test results. GPR and ANN displayed the best results with the highest R 2 (0.99) and MAPE (1.3%) values on the testing data, which proved them as the best solutions. Mechanical Engineering Artificial Intelligence and Machine Learning Laser Powder Bed Fusion Inconel™ 718 Hardness Machine Learning Formula evaluation 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-7648647","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":517031992,"identity":"f2dcb66a-4654-4732-b332-b7696bec84f3","order_by":0,"name":"Mohsen Dehghanpour Abyaneh","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0001-7794-1509","institution":"Politecnico di Torino","correspondingAuthor":true,"prefix":"","firstName":"Mohsen","middleName":"Dehghanpour","lastName":"Abyaneh","suffix":""},{"id":517031993,"identity":"1aad6485-b09f-4a33-a2e4-ed1487a2827b","order_by":1,"name":"Raffaella Sesana","email":"","orcid":"","institution":"Politecnico di Torino","correspondingAuthor":false,"prefix":"","firstName":"Raffaella","middleName":"","lastName":"Sesana","suffix":""},{"id":517031994,"identity":"7af91ed0-4333-4b82-8f3b-4fc3bbe83f0d","order_by":2,"name":"Mohammad Sadegh Javadi","email":"","orcid":"","institution":"Amirkabir University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"Sadegh","lastName":"Javadi","suffix":""},{"id":517031995,"identity":"ed3ecfc4-cd5f-4749-87a6-3ce6660b221c","order_by":3,"name":"Parviz Narimani","email":"","orcid":"","institution":"University of Tehran","correspondingAuthor":false,"prefix":"","firstName":"Parviz","middleName":"","lastName":"Narimani","suffix":""},{"id":517031996,"identity":"a11bf73a-5584-44aa-ab8d-a4e3f38f17d5","order_by":4,"name":"Matteo Crachi","email":"","orcid":"","institution":"Politecnico di Torino","correspondingAuthor":false,"prefix":"","firstName":"Matteo","middleName":"","lastName":"Crachi","suffix":""},{"id":517031997,"identity":"90b7270f-47ef-462c-9bdf-94ac4129ab3f","order_by":5,"name":"Antonio Caraviello","email":"","orcid":"","institution":"Sophia High Tech s.r.l.","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Caraviello","suffix":""}],"badges":[],"createdAt":"2025-09-18 10:42:48","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-7648647/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7648647/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91817441,"identity":"44f454f0-9c05-4ba8-bd8b-b0c358a63122","added_by":"auto","created_at":"2025-09-22 06:56:15","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":257721,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7648647/v1/cbb97ea21c3909bae3ba97ab.jpeg"},{"id":91817560,"identity":"7b001fa1-14cb-4ae1-8e6d-edfe3165fe62","added_by":"auto","created_at":"2025-09-22 06:56:52","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189115,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7648647/v1/692a54a3ff811c51bac1f2aa.jpeg"},{"id":91818306,"identity":"8f431476-e8b1-4073-ad07-335110cebbad","added_by":"auto","created_at":"2025-09-22 07:01:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":993247,"visible":true,"origin":"","legend":"","description":"","filename":"AIinLPBFManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7648647/v1_covered_472eb6d5-b35e-48de-98bc-dba6983884d9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eAnalytical and Machine‑Learning Framework for Predicting the Impact of LPBF Parameters on the Hardness of Inconel\u003c/strong\u003e™\u003cstrong\u003e 718\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Politecnico di Torino","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":"Laser Powder Bed Fusion, Inconel™ 718, Hardness, Machine Learning, Formula evaluation","lastPublishedDoi":"10.21203/rs.3.rs-7648647/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7648647/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn Laser Powder Bed Fusion, a layer-by-layer melting of metal powder takes place and is specifically suited to high-performance applications in advanced technologies using Inconel\u0026trade; 718. ANOVA and hardness measurements identified relationships that cannot be predicted using conventional statistical methods. Particle Swarm Optimization and Genetic Algorithm were proposed to define the relationships between the input and output data. Although the mean accuracy was high (97% for Particle Swarm Optimization and 91% for Genetic Algorithm), the drawbacks were calculation variation and sensitivity to parameter changes. The prediction of hardness was then done using five regression models, such as Support Vector Machine, Gaussian Process Regression (GPR), Single-Layer and Deep-Layer Artificial Neural Network (ANN), and Random Tree (RT). The low R\u003csup\u003e2\u003c/sup\u003e values were observed in the initial implementation with a mean accuracy of 90%. The linear method of optimizing output data increased R\u003csup\u003e2\u003c/sup\u003e values up to and beyond 0.9 with high average accuracy. GPR and single-layer ANN performed best in terms of training results. A rollback process was implemented on the test results. GPR and ANN displayed the best results with the highest R\u003csup\u003e2\u003c/sup\u003e (0.99) and MAPE (1.3%) values on the testing data, which proved them as the best solutions.\u003c/p\u003e","manuscriptTitle":"Analytical and Machine‑Learning Framework for Predicting the Impact of LPBF Parameters on the Hardness of Inconel™ 718","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-19 08:20:33","doi":"10.21203/rs.3.rs-7648647/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":"229d6fda-a4a8-4d90-9a20-ea3ad683055c","owner":[],"postedDate":"September 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54939506,"name":"Mechanical Engineering"},{"id":54939507,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-09-19T08:20:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-19 08:20:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7648647","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7648647","identity":"rs-7648647","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}