3D Convolution Lightweight Vision Transformer to Progressive Semantic Focusing for Magnetic Property Prediction of Additively Manufactured Components

3D Convolution Lightweight Vision Transformer to Progressive Semantic Focusing for Magnetic Property Prediction of Additively Manufactured Components | 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 3D Convolution Lightweight Vision Transformer to Progressive Semantic Focusing for Magnetic Property Prediction of Additively Manufactured Components Jhih‑Cheng Huang, Chia-Ho Chuang, Yin-Yang Hsiao, Mi‑Ching Tsai, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8836731/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 Objective/background: Predicting the magnetic performance of selective laser melting (SLM)-fabricated components is essential for quality assurance; however, the complex nonlinear dynamics of Fe-50Ni soft magnetic alloys under high-frequency excitation (400–800 Hz) remain poorly modeled by existing deep learning approaches. This study aims to overcome the significant accuracy degradation observed in conventional models when addressing these frequency-dependent hysteresis behaviors. Method We propose a lightweight conv-enhanced progressive sampling vision transformer (CVPSViT), which can synergize 3D spatial feature extraction with physics-informed process parameters. The architecture incorporates three methodological innovations: (1) it ingests stacked layer-wise imagery as 3D volumes to capture interlayer continuity and microdepth textures; (2) it introduces a conv-enhanced progressive sampling module (CPSM), which employs a coarse-to-fine strategy to dynamically update sampling coordinates, focusing attention on semantically discriminative regions akin to the human visual system; (3) it executes a deep cross-modal fusion by embedding critical manufacturing parameters, specifically laser power and oxygen concentration, directly into the global representation prior to inference. Results Extensive experiments on five key magnetic targets demonstrate that CVPSViT consistently outperforms conventional machine learning baselines and the standard CvT architecture. The model exhibits exceptional robustness in high-frequency scenarios: for coercivity ( \(\:{H}_{c}\) ) at 800 Hz, it achieves an \(\:\:{R}^{2}\) of 0.981, significantly surpassing the 0.876 of CvT. Furthermore, for iron loss \(\:\left({P}_{cv}\right)\) , the most frequency-sensitive indicator, CVPSViT maintains a high accuracy of 0.934 compared to 0.909 for CvT. Ablation studies confirm high efficiency, with the model requiring 24% fewer parameters (38.5M) and 12% fewer GFLOPs (22.64) than the PSViT baseline. Conclusions This work presents a robust, computationally efficient framework for the real-time quality monitoring of additively manufactured components. By effectively balancing high-frequency prediction accuracy with low model complexity, CVPSViT offers a viable solution for intelligent manufacturing systems requiring precise feedback on material properties. Selective Laser Melting Magnetic Property Prediction 3D Vision Transformer Progressive Sampling Process Parameters Full Text Additional Declarations No competing interests reported. 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-8836731","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":599257371,"identity":"ad42af64-c2a1-41ab-8edf-6ab5410a2a71","order_by":0,"name":"Jhih‑Cheng Huang","email":"","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":false,"prefix":"","firstName":"Jhih‑Cheng","middleName":"","lastName":"Huang","suffix":""},{"id":599257372,"identity":"769e7ec6-09e8-46d8-811e-0b3d5defe7ff","order_by":1,"name":"Chia-Ho Chuang","email":"","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":false,"prefix":"","firstName":"Chia-Ho","middleName":"","lastName":"Chuang","suffix":""},{"id":599257373,"identity":"367fb652-516a-4354-be1f-ef4792dac742","order_by":2,"name":"Yin-Yang Hsiao","email":"","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":false,"prefix":"","firstName":"Yin-Yang","middleName":"","lastName":"Hsiao","suffix":""},{"id":599257374,"identity":"5256d80c-6d46-47b3-b4e1-54557e6d7561","order_by":3,"name":"Mi‑Ching Tsai","email":"","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":false,"prefix":"","firstName":"Mi‑Ching","middleName":"","lastName":"Tsai","suffix":""},{"id":599257375,"identity":"877fd167-6b4f-4dd2-be89-4e99005a32a2","order_by":4,"name":"Ming‑Huwi Horng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIiWNgGAWjYBACAzBZwcDAxg7nsoEIZgJazgDVMWNoYcOjhbENxVgCWszZe589/DpvmzwfMwPjxx8FNkCRY2kSDBXWiQ3yPQbYtFj2HDc3lt1227CNmYFZmscgDSiSdkyC4Ux6YgMbD1YtBjfS2KQlt91mBGoBesfgMFCEvU2Cse0wUAvvBtxa5ty2B2lh/GHwH6rlH34tkh8bbieCtDDwGBwAirAdk2BswKPlzDE2aYZjt5PbmBmbgX5J5jE4k5ZskXAs3biNLf8DVi3H29gkf9Tctp3f3nzw448/dnIGx48Z3vhQYy3bz3wsAWsoAwEzD5hibACREDZILY5ogaj9gUdyFIyCUTAKRgEDAK6dVJhv9/dtAAAAAElFTkSuQmCC","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":true,"prefix":"","firstName":"Ming‑Huwi","middleName":"","lastName":"Horng","suffix":""}],"badges":[],"createdAt":"2026-02-10 05:39:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8836731/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8836731/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108181763,"identity":"51606b2e-aaa3-4867-a7cf-05f7f94483af","added_by":"auto","created_at":"2026-04-30 08:58:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":803845,"visible":true,"origin":"","legend":"","description":"","filename":"20260214LightweightVisionTransformerV5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8836731/v1_covered_1823fc77-de9a-4fbc-98b3-9e3b430ee35a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"3D Convolution Lightweight Vision Transformer to Progressive Semantic Focusing for Magnetic Property Prediction of Additively Manufactured Components","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Selective Laser Melting, Magnetic Property Prediction, 3D Vision Transformer, Progressive Sampling, Process Parameters","lastPublishedDoi":"10.21203/rs.3.rs-8836731/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8836731/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective/background:\u003c/h2\u003e \u003cp\u003ePredicting the magnetic performance of selective laser melting (SLM)-fabricated components is essential for quality assurance; however, the complex nonlinear dynamics of Fe-50Ni soft magnetic alloys under high-frequency excitation (400\u0026ndash;800 Hz) remain poorly modeled by existing deep learning approaches. This study aims to overcome the significant accuracy degradation observed in conventional models when addressing these frequency-dependent hysteresis behaviors.\u003c/p\u003e\u003ch2\u003eMethod\u003c/h2\u003e \u003cp\u003eWe propose a lightweight conv-enhanced progressive sampling vision transformer (CVPSViT), which can synergize 3D spatial feature extraction with physics-informed process parameters. The architecture incorporates three methodological innovations: (1) it ingests stacked layer-wise imagery as 3D volumes to capture interlayer continuity and microdepth textures; (2) it introduces a conv-enhanced progressive sampling module (CPSM), which employs a coarse-to-fine strategy to dynamically update sampling coordinates, focusing attention on semantically discriminative regions akin to the human visual system; (3) it executes a deep cross-modal fusion by embedding critical manufacturing parameters, specifically laser power and oxygen concentration, directly into the global representation prior to inference.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eExtensive experiments on five key magnetic targets demonstrate that CVPSViT consistently outperforms conventional machine learning baselines and the standard CvT architecture. The model exhibits exceptional robustness in high-frequency scenarios: for coercivity (\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{H}_{c}\\)\u003c/span\u003e\u003c/span\u003e) at 800 Hz, it achieves an\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\:{R}^{2}\\)\u003c/span\u003e\u003c/span\u003e of 0.981, significantly surpassing the 0.876 of CvT. Furthermore, for iron loss \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\left({P}_{cv}\\right)\\)\u003c/span\u003e\u003c/span\u003e, the most frequency-sensitive indicator, CVPSViT maintains a high accuracy of 0.934 compared to 0.909 for CvT. Ablation studies confirm high efficiency, with the model requiring 24% fewer parameters (38.5M) and 12% fewer GFLOPs (22.64) than the PSViT baseline.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eThis work presents a robust, computationally efficient framework for the real-time quality monitoring of additively manufactured components. By effectively balancing high-frequency prediction accuracy with low model complexity, CVPSViT offers a viable solution for intelligent manufacturing systems requiring precise feedback on material properties.\u003c/p\u003e","manuscriptTitle":"3D Convolution Lightweight Vision Transformer to Progressive Semantic Focusing for Magnetic Property Prediction of Additively Manufactured Components","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-03 10:59:54","doi":"10.21203/rs.3.rs-8836731/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":"f819a39b-1520-4ad0-bf50-ae3b8ca2ee8a","owner":[],"postedDate":"March 3rd, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-04-29T08:25:33+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-29T08:41:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-03 10:59:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8836731","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8836731","identity":"rs-8836731","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}