Machine Learning for Predictive Maintenance: Evaluating Accuracy, Adaptability, and Real-Time Feasibility

Machine Learning for Predictive Maintenance: Evaluating Accuracy, Adaptability, and Real-Time Feasibility | 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 Machine Learning for Predictive Maintenance: Evaluating Accuracy, Adaptability, and Real-Time Feasibility Usman Talat, Adnan Tariq, Waseem Shahzad, Romeeza Majeed This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9527725/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract Predictive maintenance and anomaly detection in industrial machinery have significantly advanced with Industry 4.0 technologies, particularly through integration with Internet of Things (IoT) infrastructures. In this study, large-scale machine-generated datasets are leveraged to systematically evaluate and compare the effectiveness of prominent machine learning models including Decision Trees (DT), Support Vector Machines (SVM), Artificial Neural Networks (ANN), and ensemble approaches such as Random Forest (RF), Bagged Trees, and RUS Boosted Trees in accurately predicting machine failures and optimizing maintenance strategies. Results indicate that Random Forest achieves the highest recall (96.69%) alongside robust accuracy (89.54%), making it exceptionally suited for detecting rare failure events. ANN exhibits the most balanced performance between precision and recall, demonstrated by an F-measure of 82.66%. Among ensemble methods, Bagged Trees attained superior accuracy (97.33%), while RUS Boosted Trees stood out with high-speed, real-time predictive capabilities ideal for dynamic operational environments. The novel scientific contributions of this work are twofold: firstly, it provides a structured comparative framework to guide the selection of appropriate machine learning algorithms tailored specifically for predictive maintenance applications; secondly, it enhances the understanding of model performance trade-offs in varying industrial contexts, thus supporting informed and effective deployment decisions in real-world manufacturing scenarios. Predictive Maintenance Anomaly Detection Machine Learning Models Real time Prediction Rare Failure Detection Computational Efficiency Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 30 Apr, 2026 Submission checks completed at journal 30 Apr, 2026 First submitted to journal 25 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-9527725","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":632420954,"identity":"38190455-bcad-42a0-b1dd-e4bee7f8e41f","order_by":0,"name":"Usman Talat","email":"data:image/png;base64,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","orcid":"","institution":"WAH Engineering College","correspondingAuthor":true,"prefix":"","firstName":"Usman","middleName":"","lastName":"Talat","suffix":""},{"id":632420955,"identity":"a543bef9-7238-4932-96d1-2a92c362d9fb","order_by":1,"name":"Adnan Tariq","email":"","orcid":"","institution":"WAH Engineering College","correspondingAuthor":false,"prefix":"","firstName":"Adnan","middleName":"","lastName":"Tariq","suffix":""},{"id":632420956,"identity":"f40550a5-6302-44cd-9018-f140e312d15c","order_by":2,"name":"Waseem Shahzad","email":"","orcid":"","institution":"MachaDev Engineering Pvt Ltd","correspondingAuthor":false,"prefix":"","firstName":"Waseem","middleName":"","lastName":"Shahzad","suffix":""},{"id":632420957,"identity":"230a4c9f-40fb-4ce9-b846-fb7cbcf7efdc","order_by":3,"name":"Romeeza Majeed","email":"","orcid":"","institution":"WAH Engineering College","correspondingAuthor":false,"prefix":"","firstName":"Romeeza","middleName":"","lastName":"Majeed","suffix":""}],"badges":[],"createdAt":"2026-04-25 18:38:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9527725/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9527725/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108803943,"identity":"8b9697c1-c4f0-4085-b781-820cf3d1101f","added_by":"auto","created_at":"2026-05-08 15:12:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":810973,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchPaperUsmanTalatRev1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9527725/v1_covered_542448eb-a739-4330-a7f6-bbdac95d99d7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning for Predictive Maintenance: Evaluating Accuracy, Adaptability, and Real-Time Feasibility","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Predictive Maintenance, Anomaly Detection, Machine Learning Models, Real time Prediction, Rare Failure Detection, Computational Efficiency","lastPublishedDoi":"10.21203/rs.3.rs-9527725/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9527725/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Predictive maintenance and anomaly detection in industrial machinery have significantly advanced with Industry 4.0 technologies, particularly through integration with Internet of Things (IoT) infrastructures. In this study, large-scale machine-generated datasets are leveraged to systematically evaluate and compare the effectiveness of prominent machine learning models including Decision Trees (DT), Support Vector Machines (SVM), Artificial Neural Networks (ANN), and ensemble approaches such as Random Forest (RF), Bagged Trees, and RUS Boosted Trees in accurately predicting machine failures and optimizing maintenance strategies. Results indicate that Random Forest achieves the highest recall (96.69%) alongside robust accuracy (89.54%), making it exceptionally suited for detecting rare failure events. ANN exhibits the most balanced performance between precision and recall, demonstrated by an F-measure of 82.66%. Among ensemble methods, Bagged Trees attained superior accuracy (97.33%), while RUS Boosted Trees stood out with high-speed, real-time predictive capabilities ideal for dynamic operational environments. The novel scientific contributions of this work are twofold: firstly, it provides a structured comparative framework to guide the selection of appropriate machine learning algorithms tailored specifically for predictive maintenance applications; secondly, it enhances the understanding of model performance trade-offs in varying industrial contexts, thus supporting informed and effective deployment decisions in real-world manufacturing scenarios.","manuscriptTitle":"Machine Learning for Predictive Maintenance: Evaluating Accuracy, Adaptability, and Real-Time Feasibility","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-05 04:28:45","doi":"10.21203/rs.3.rs-9527725/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2026-04-30T11:49:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-30T11:49:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2026-04-25T18:20:55+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a2dc019a-25b2-44c1-ac90-a78b34b220cf","owner":[],"postedDate":"May 5th, 2026","published":true,"recentEditorialEvents":[{"type":"editorAssigned","content":"","date":"2026-04-30T11:49:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-30T11:49:06+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T16:24:06+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-05 04:28:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9527725","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9527725","identity":"rs-9527725","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}