A Comparative Study of Machine and Deep Learning Models for Time-Series-Based Bearing Fault Diagnosis of Induction Motors

A Comparative Study of Machine and Deep Learning Models for Time-Series-Based Bearing Fault Diagnosis of Induction Motors | 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 A Comparative Study of Machine and Deep Learning Models for Time-Series-Based Bearing Fault Diagnosis of Induction Motors Kamal Hamani, Kuchar Martin, Sobek Martin, Vojtech Sotola, Petr Palacky This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9292713/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 15 You are reading this latest preprint version Abstract Accurate fault detection in induction motors (IMs) under varying load conditions remains a critical challenge in industrial condition monitoring (CM). Inspired by the foundational work, which highlighted the impact of mechanical load on fault signature detectability. This study proposes a multi-modal signal analysis approach to bearing fault diagnosis using stator current, rotor speed, and flux-induced voltage signals. A custom fifteen-class dataset was collected, comprising healthy and faulty motor states at 0%, 50%, and 100% load levels. Two types of models were evaluated in this study: traditional machine learning models and deep learning models. Experimental results demonstrate significant performance gains compared to single-sensor models, highlighting the benefits of cross-domain signal fusion. Models specifically designed to process time-series data, such as the Temporal Convolutional Network (TCN) and particularly the Long Short-Term Memory (LSTM), exhibit outstanding performance. The LSTM model achieved perfect accuracy (100%) in fault detection, outperforming all other tested models. Recent architectures, such as the Transformer, also demonstrate strong potential; with careful hyperparameter tuning, their performance especially in terms of generalization can be further enhanced. Physical sciences/Energy science and technology Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 22 Apr, 2026 Reviewers agreed at journal 22 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviews received at journal 21 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviews received at journal 18 Apr, 2026 Reviewers agreed at journal 16 Apr, 2026 Reviewers agreed at journal 16 Apr, 2026 Reviewers agreed at journal 13 Apr, 2026 Reviewers agreed at journal 11 Apr, 2026 Reviewers invited by journal 10 Apr, 2026 Editor invited by journal 08 Apr, 2026 Editor assigned by journal 02 Apr, 2026 Submission checks completed at journal 02 Apr, 2026 First submitted to journal 01 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-9292713","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":624644662,"identity":"6923ffb7-2ebd-471f-bf5e-fe6772e1d945","order_by":0,"name":"Kamal Hamani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYBACCRDxgOEAmHPgAwNDAnFaEqBaDs4gWQszDzFaJNtPJ35IYLgjr9t+9uBh27a6PAb24w/wapHmyd0skcDwzHDbmbyEw7lth4sZeBLw2yTHkLsBqOUw47YDOQaHc84cSGyQgDoTpxb+t5t/ALXYbzv/xuCwxZk6oBbGBvwOk8jdBrIlcdsNoC0MFcxALcx4dTBIzni7zSLB4HDythtvDA72VBwuZuNJw69F4nzu5hsfKg7bbjufY/zhh0FdHj+hEIMAAyQ2GxHqR8EoGAWjYBQQAABF/U1T/xXm1gAAAABJRU5ErkJggg==","orcid":"","institution":"Technical University of Ostrava","correspondingAuthor":true,"prefix":"","firstName":"Kamal","middleName":"","lastName":"Hamani","suffix":""},{"id":624644666,"identity":"c336c584-058a-410e-ae38-14fb38ad06ef","order_by":1,"name":"Kuchar Martin","email":"","orcid":"","institution":"Technical University of Ostrava","correspondingAuthor":false,"prefix":"","firstName":"Kuchar","middleName":"","lastName":"Martin","suffix":""},{"id":624644667,"identity":"dec8eb31-5128-485c-ae78-a5e978ddabbe","order_by":2,"name":"Sobek Martin","email":"","orcid":"","institution":"Technical University of Ostrava","correspondingAuthor":false,"prefix":"","firstName":"Sobek","middleName":"","lastName":"Martin","suffix":""},{"id":624644668,"identity":"768b2e1a-8acc-4fd4-b7fd-8f28b8240ed5","order_by":3,"name":"Vojtech Sotola","email":"","orcid":"","institution":"Technical University of Ostrava","correspondingAuthor":false,"prefix":"","firstName":"Vojtech","middleName":"","lastName":"Sotola","suffix":""},{"id":624644669,"identity":"780da5a1-2339-4993-9204-1bfe5cb02ab1","order_by":4,"name":"Petr Palacky","email":"","orcid":"","institution":"Technical University of Ostrava","correspondingAuthor":false,"prefix":"","firstName":"Petr","middleName":"","lastName":"Palacky","suffix":""}],"badges":[],"createdAt":"2026-04-01 13:41:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9292713/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9292713/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107705294,"identity":"933e1c85-88e6-493e-be9f-2ce6a0bfaa5a","added_by":"auto","created_at":"2026-04-24 09:11:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7511718,"visible":true,"origin":"","legend":"","description":"","filename":"AComparativeStudyofMachineandDeepLearningScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9292713/v1_covered_1c881311-dc50-422e-b243-d96f18dc6584.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Comparative Study of Machine and Deep Learning Models for Time-Series-Based Bearing Fault Diagnosis of Induction Motors","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":"","lastPublishedDoi":"10.21203/rs.3.rs-9292713/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9292713/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate fault detection in induction motors (IMs) under varying load conditions remains a critical challenge in industrial condition monitoring (CM). Inspired by the foundational work, which highlighted the impact of mechanical load on fault signature detectability. This study proposes a multi-modal signal analysis approach to bearing fault diagnosis using stator current, rotor speed, and flux-induced voltage signals. A custom fifteen-class dataset was collected, comprising healthy and faulty motor states at 0%, 50%, and 100% load levels. Two types of models were evaluated in this study: traditional machine learning models and deep learning models. Experimental results demonstrate significant performance gains compared to single-sensor models, highlighting the benefits of cross-domain signal fusion. Models specifically designed to process time-series data, such as the Temporal Convolutional Network (TCN) and particularly the Long Short-Term Memory (LSTM), exhibit outstanding performance. The LSTM model achieved perfect accuracy (100%) in fault detection, outperforming all other tested models. Recent architectures, such as the Transformer, also demonstrate strong potential; with careful hyperparameter tuning, their performance especially in terms of generalization can be further enhanced.","manuscriptTitle":"A Comparative Study of Machine and Deep Learning Models for Time-Series-Based Bearing Fault Diagnosis of Induction Motors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 09:36:27","doi":"10.21203/rs.3.rs-9292713/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-23T01:57:36+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"36411038956890813911372363035232420850","date":"2026-04-22T09:17:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"97157437476986455469401908285236517982","date":"2026-04-22T03:30:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-21T21:22:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"211188214465079017109237242915301711171","date":"2026-04-19T04:55:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-18T14:55:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"39258842045518785035505423752170126187","date":"2026-04-17T03:29:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"53949724241923957900886770156495197564","date":"2026-04-17T02:41:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77197083884266275407782924343308431279","date":"2026-04-13T13:30:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"84740502994752297269939754205272815541","date":"2026-04-11T17:07:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-10T05:52:08+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-09T03:14:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-02T07:39:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-02T07:39:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-01T13:26:18+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":"7ec02b35-f73d-4fde-9c3b-e4c2288d7551","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66485386,"name":"Physical sciences/Energy science and technology"},{"id":66485387,"name":"Physical sciences/Engineering"},{"id":66485388,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-13T16:23:25+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 09:36:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9292713","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9292713","identity":"rs-9292713","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}