FusionNet Lite: A Lightweight Federated Deep Learning Model for Privacy-Preserving Predictive Maintenance

FusionNet Lite: A Lightweight Federated Deep Learning Model for Privacy-Preserving Predictive Maintenance | 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 FusionNet Lite: A Lightweight Federated Deep Learning Model for Privacy-Preserving Predictive Maintenance Aman Sharma, Kwan Yong Sim, Sivachandran Chandrasekaran This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8806936/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 Federated learning (FL) offers a privacy-preserving strategy for industrial predictive maintenance (PdM), yet many existing models remain too large or energy-intensive for deployment on edge devices. This study proposes \textit{FusionNet Lite}, an ultralight hybrid convolutional architecture with fewer than 1420 parameters, designed for low-latency federated optimisation under non-IID industrial conditions. The model integrates depthwise separable convolutions, a compact ConvMixer module, and squeeze-and-excitation (SE) attention to minimise computation and communication while preserving predictive performance. Experiments on the AI4I~2020 dataset show that FusionNet~Lite matches the accuracy of larger baselines and achieves the highest energy-efficiency index across both CPU and GPU environments. The model also maintains attributional stability between centralised and federated training, with Integrated Gradients (IG) demonstrating consistent feature importance patterns. Communication overhead remains below 25~kB per round, enabling deployment in bandwidth-constrained Industrial Internet of Things (IIoT) networks. The results confirm that lightweight FL architectures can support real-time PdM while preserving data privacy in distributed industrial settings. Artificial Intelligence and Machine Learning Federated Learning Predictive Maintenance Edge AI Lightweight Deep Learning Industrial IoT Explainability 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-8806936","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":586957521,"identity":"0c3b8445-61b2-44a3-a070-f5cf23750168","order_by":0,"name":"Aman Sharma","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-8058-1276","institution":"Swinburne University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Aman","middleName":"","lastName":"Sharma","suffix":""},{"id":586958293,"identity":"93263f46-4019-4d04-be98-a41327d6c550","order_by":1,"name":"Kwan Yong Sim","email":"","orcid":"https://orcid.org/0000-0002-7291-0922","institution":"Swinburne University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kwan","middleName":"Yong","lastName":"Sim","suffix":""},{"id":586958294,"identity":"0735c86c-f2c0-45d4-a44f-ec93de9595c6","order_by":2,"name":"Sivachandran Chandrasekaran","email":"","orcid":"https://orcid.org/0000-0003-2871-880X","institution":"Swinburne University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sivachandran","middleName":"","lastName":"Chandrasekaran","suffix":""}],"badges":[],"createdAt":"2026-02-06 12:14:43","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-8806936/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8806936/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102296713,"identity":"952ca2f3-99c5-4cbb-b165-6e5e45dcd5ea","added_by":"auto","created_at":"2026-02-10 10:21:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2606501,"visible":true,"origin":"","legend":"","description":"","filename":"SNCSFusionFed.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8806936/v1_covered_2ab5d9e8-eee5-4d08-94fa-db5896c8ba2c.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eFusionNet Lite: A Lightweight Federated Deep Learning Model for Privacy-Preserving Predictive Maintenance\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Swinburne University of Technology","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":"Federated Learning, Predictive Maintenance, Edge AI, Lightweight Deep Learning, Industrial IoT, Explainability","lastPublishedDoi":"10.21203/rs.3.rs-8806936/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8806936/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated learning (FL) offers a privacy-preserving strategy for industrial predictive maintenance (PdM), yet many existing models remain too large or energy-intensive for deployment on edge devices. This study proposes \\textit{FusionNet Lite}, an ultralight hybrid convolutional architecture with fewer than 1420 parameters, designed for low-latency federated optimisation under non-IID industrial conditions. The model integrates depthwise separable convolutions, a compact ConvMixer module, and squeeze-and-excitation (SE) attention to minimise computation and communication while preserving predictive performance. Experiments on the AI4I~2020 dataset show that FusionNet~Lite matches the accuracy of larger baselines and achieves the highest energy-efficiency index across both CPU and GPU environments. The model also maintains attributional stability between centralised and federated training, with Integrated Gradients (IG) demonstrating consistent feature importance patterns. Communication overhead remains below 25~kB per round, enabling deployment in bandwidth-constrained Industrial Internet of Things (IIoT) networks. The results confirm that lightweight FL architectures can support real-time PdM while preserving data privacy in distributed industrial settings.\u003c/p\u003e","manuscriptTitle":"FusionNet Lite: A Lightweight Federated Deep Learning Model for Privacy-Preserving Predictive Maintenance","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 07:03:48","doi":"10.21203/rs.3.rs-8806936/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":"4d647ba8-15c0-4a8c-a88c-e3fa1d8ee7e0","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62452719,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-02-09T07:03:48+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 07:03:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8806936","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8806936","identity":"rs-8806936","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}