Confidence-Aware Tiny Machine Learning Orchestration for Vibration-Based Predictive Maintenance in Automotive Powertrains

Confidence-Aware Tiny Machine Learning Orchestration for Vibration-Based Predictive Maintenance in Automotive Powertrains | 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 Confidence-Aware Tiny Machine Learning Orchestration for Vibration-Based Predictive Maintenance in Automotive Powertrains Yashawant Pathak, Madhukar Dubey, Trapti Sharma This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8826286/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 Tiny Machine Learning (TinyML) enables real-time diagnostics on low-cost microcontrollers deployed inside vehicles. However, aggressive model compression—especially 8-bit quantization—can introduce a reliability gap that is risky for safety critical automotive monitoring. This paper presents a confidence aware TinyML orchestration framework for vibration-based predictive maintenance in automotive powertrains. The system dynamically balances edge and cloud inference using a lightweight uncertainty signal computed from normalized SoftMax entropy. High-confidence vibration windows are processed locally on an ESP32 microcontroller, while ambiguous samples are selectively offloaded to a cloud backend for higher-fidelity analysis. The framework exploits the ESP32 dual-core architecture to keep monitoring non-blocking during communication. Experiments on benchmark bearing vibration data show that the proposed approach recovers 85.7% of the accuracy lost due to 8-bit quantization, achieving 96.8% accuracy while offloading only 12% of samples. Compared to a cloud-only baseline, wireless energy is reduced by about 88% and average end-to-end latency remains 82.8ms. These results suggest that confidence-aware orchestration is a practical pathway to deploy TinyML predictive maintenance in connected vehicles. Artificial Intelligence and Machine Learning Mechanical Engineering Tiny Machine Learning Predictive Maintenance Vibration Analysis Edge–Cloud Computing Confidence- Aware Offloading 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-8826286","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":587990775,"identity":"b0794c25-b61e-4de0-9102-d2c538213c1a","order_by":0,"name":"Yashawant Pathak","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYHACNiTGARsGxmYIj4eQFgkGBmaQljSgFmbStBwGspnxu8rg+PFnj3lq7tSZs58/9uDHmfP5zO38Bxh+1DDImOPScibH3Jjn2DMJy55kdsOeG7ctG4EOY+w5xsBj2YBDy4EcNukctsMSBgeS2SR4Ptw2APuFt4GBx+AADi3nnz+TzvkH1HL+MZvknw/nwFoY/+LTciPBTDq3DajlRjKbNM+NA2AtzPhskbzxxkz6b99hyZ0zHptJy5xJBmkxOCxzTAKnFr7z6c8kZ3w7zG/On/hM8s0xOwPD/oMPH76psbHHpUUBJm4AEzFsAEYPOKJwAPkGdC3yONWOglEwCkbBSAUAmjJabJmvcRUAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0000-4385-0281","institution":"Rustamji Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Yashawant","middleName":"","lastName":"Pathak","suffix":""},{"id":587990776,"identity":"91cddb6a-d913-4033-ac5c-06781227acdf","order_by":1,"name":"Madhukar Dubey","email":"","orcid":"https://orcid.org/0000-0002-0874-2039","institution":"Rustamji Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Madhukar","middleName":"","lastName":"Dubey","suffix":""},{"id":587990947,"identity":"90bf0e44-578e-4aac-90e0-937a875bfbb1","order_by":2,"name":"Trapti Sharma","email":"","orcid":"https://orcid.org/0009-0003-1325-3349","institution":"Rustamji Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Trapti","middleName":"","lastName":"Sharma","suffix":""}],"badges":[],"createdAt":"2026-02-09 05:57:12","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-8826286/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8826286/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102311844,"identity":"1ad30492-c737-4955-918f-f0aeef2b8969","added_by":"auto","created_at":"2026-02-10 11:59:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":379484,"visible":true,"origin":"","legend":"","description":"","filename":"tinyMlPaperAutomobile5pages.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8826286/v1_covered_28a55328-0545-4bfb-b7e7-2e7f64e8dca1.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eConfidence-Aware Tiny Machine Learning\u003c/p\u003e\n\u003cp\u003eOrchestration for Vibration-Based Predictive Maintenance in Automotive Powertrains\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Rustamji Institute 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":"Tiny Machine Learning, Predictive Maintenance, Vibration Analysis, Edge–Cloud Computing, Confidence- Aware Offloading","lastPublishedDoi":"10.21203/rs.3.rs-8826286/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8826286/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTiny Machine Learning (TinyML) enables real-time diagnostics on low-cost microcontrollers deployed inside vehicles. However, aggressive model compression\u0026mdash;especially 8-bit quantization\u0026mdash;can introduce a reliability gap that is risky for safety critical automotive monitoring. This paper presents a confidence aware TinyML orchestration framework for vibration-based predictive maintenance in automotive powertrains. The system dynamically balances edge and cloud inference using a lightweight uncertainty signal computed from normalized SoftMax entropy. High-confidence vibration windows are processed locally on an ESP32 microcontroller, while ambiguous samples are selectively offloaded to a cloud backend for higher-fidelity analysis. The framework exploits the ESP32 dual-core architecture to keep monitoring non-blocking during communication. Experiments on benchmark bearing vibration data show that the proposed approach recovers 85.7% of the accuracy lost due to 8-bit quantization, achieving 96.8% accuracy while offloading only 12% of samples. Compared to a cloud-only baseline, wireless energy is reduced by about 88% and average end-to-end latency remains 82.8ms. These results suggest that confidence-aware orchestration is a practical pathway to deploy TinyML predictive maintenance in connected vehicles.\u003c/p\u003e","manuscriptTitle":"Confidence-Aware Tiny Machine Learning\nOrchestration for Vibration-Based Predictive Maintenance in Automotive Powertrains","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-10 11:52:39","doi":"10.21203/rs.3.rs-8826286/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":"2c26bbfd-9638-4279-b23e-8ee8fb76512a","owner":[],"postedDate":"February 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62550260,"name":"Artificial Intelligence and Machine Learning"},{"id":62550261,"name":"Mechanical Engineering"}],"tags":[],"updatedAt":"2026-02-10T11:52:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-10 11:52:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8826286","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8826286","identity":"rs-8826286","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}