A Hybrid Generative and Transformer-Based Framework for Anomaly Detection in Industrial Sensor Time-Series for Predictive Maintenance

A Hybrid Generative and Transformer-Based Framework for Anomaly Detection in Industrial Sensor Time-Series for 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 Article A Hybrid Generative and Transformer-Based Framework for Anomaly Detection in Industrial Sensor Time-Series for Predictive Maintenance Nayab Asim, Irum Matloob, Zaid Khan, Rukaiya Rukaiya, Shoab Khan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9226417/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 18 You are reading this latest preprint version Abstract The hybrid anomaly detection framework presented in this paper is a development in the field of predictive maintenance in an industrial environment utilizing multivariate time series data gathered from multiple sensors. An anomaly detection framework solves the anomaly detection problems found in predictive maintenance applications where labeled data may not be available or is limited. In order to solve these problems, the development of a hybrid framework by combining Statistics, Attention-based models, and Deep Generative Models to learn both the distributional and temporal characteristics of sensors such as vibration and electrical current. More specifically, a state-of-the-art GAN was designed to estimate the normal distribution of vibration and electrical current data. This estimated normal distribution can be used to calculate an anomaly score through reconstruction error, Mahalanobis distance, and isolation tree reconstruction error using specific data from the GAN model. Anomaly detection was performed on long-range temporal dependencies through self-attention mechanisms using the Anomaly Transformer Architecture. Additional multi-scale anomaly patterns in industrial datasets are evaluated using the MSPG-SEN framework. The framework was evaluated on a total of four datasets (two labeled benchmark datasets: CWRU Bearing, Machine Failure, and two unlabeled real-world crane datasets). The results of the experiment indicate that the proposed framework achieves over a 98% true positive rate on the labeled benchmark datasets. The results from the unlabeled crane datasets indicate that different anomaly detection models produce partially overlapping but distinct anomaly patterns indicating different modeling paradigms demonstrate complementary aspects of anomalous behavior. These findings highlight that combining generative, attention-based and statistical methods increases the robustness of an anomaly detection system and can provide a wider array of detection patterns. The proposed hybrid method, therefore, has proven to be a useful system for predictive maintenance in real world applications, especially when there is limited ground truth or when ground truth is not available. 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 27 Apr, 2026 Reviews received at journal 19 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviews received at journal 17 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviewers agreed at journal 12 Apr, 2026 Reviewers agreed at journal 11 Apr, 2026 Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers invited by journal 09 Apr, 2026 Editor invited by journal 02 Apr, 2026 Editor assigned by journal 27 Mar, 2026 Submission checks completed at journal 27 Mar, 2026 First submitted to journal 25 Mar, 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-9226417","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":623831076,"identity":"7f52e26e-81ae-4120-9090-e17f0a7b9849","order_by":0,"name":"Nayab Asim","email":"","orcid":"","institution":"Fatima Jinnah Women University","correspondingAuthor":false,"prefix":"","firstName":"Nayab","middleName":"","lastName":"Asim","suffix":""},{"id":623831077,"identity":"096fa60a-7771-46c2-9e65-d15c7caccbe9","order_by":1,"name":"Irum Matloob","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYBAC+QYog4+BgY3hgw0bmCMBxAa4tLBBaQkgg41xRhqpWph50hiI0CJ9xnQDY45dHRt787HHNgl8iRsOMB+8zcNwxxinFr4csxuM25Il2HiOpRvnJLABtbAlW/MwPDPDqYWHB6SFWYJNIsdMOvcHW+6GAzxm0jwMh20IaKmHaLFIAGnh/0aMlsMQLQxgLTxsIC14HMZWdiNx23HJNqBfDHsS2OpnHmYztpxj8Ayn9+V7mLfd+Litmp8fGGIPfiQcM+Y73vzwxpuKO4YNuPSAQAKCeYyBgRlEGxzApwEF1MAYxGsZBaNgFIyCYQ8AnV1K7Sv9pUcAAAAASUVORK5CYII=","orcid":"","institution":"Fatima Jinnah Women University","correspondingAuthor":true,"prefix":"","firstName":"Irum","middleName":"","lastName":"Matloob","suffix":""},{"id":623831078,"identity":"e40929b8-eb12-45c3-8e04-668119700205","order_by":2,"name":"Zaid Khan","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zaid","middleName":"","lastName":"Khan","suffix":""},{"id":623831079,"identity":"217be37c-8d1d-4408-a5f8-d9c6284533d9","order_by":3,"name":"Rukaiya Rukaiya","email":"","orcid":"","institution":"Sir Syed University of Engineering and Technology","correspondingAuthor":false,"prefix":"","firstName":"Rukaiya","middleName":"","lastName":"Rukaiya","suffix":""},{"id":623831080,"identity":"5aca20a2-46d5-4b4f-a666-d8c297e42bd5","order_by":4,"name":"Shoab Khan","email":"","orcid":"","institution":"Center for Advanced Research in Engineering (CARE) Pvt. Ltd","correspondingAuthor":false,"prefix":"","firstName":"Shoab","middleName":"","lastName":"Khan","suffix":""},{"id":623831081,"identity":"3831bd1d-8246-4a10-af9d-5c78b793f6f5","order_by":5,"name":"Hessa Alfrahi","email":"","orcid":"","institution":"College of Computer and Information Sciences","correspondingAuthor":false,"prefix":"","firstName":"Hessa","middleName":"","lastName":"Alfrahi","suffix":""}],"badges":[],"createdAt":"2026-03-25 18:39:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9226417/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9226417/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107483077,"identity":"c59b3b8f-8247-4071-9b3f-1461adc1c1d2","added_by":"auto","created_at":"2026-04-22 02:26:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1446195,"visible":true,"origin":"","legend":"","description":"","filename":"updatedprediictivemaintaincespringer1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9226417/v1_covered_b0a2dd1c-95df-4671-b658-fb61cf6bfb20.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Hybrid Generative and Transformer-Based Framework for Anomaly Detection in Industrial Sensor Time-Series for Predictive Maintenance","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-9226417/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9226417/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The hybrid anomaly detection framework presented in this paper is a development in the field of predictive maintenance in an industrial environment utilizing multivariate time series data gathered from multiple sensors. An anomaly detection framework solves the anomaly detection problems found in predictive maintenance applications where labeled data may not be available or is limited. In order to solve these problems, the development of a hybrid framework by combining Statistics, Attention-based models, and Deep Generative Models to learn both the distributional and temporal characteristics of sensors such as vibration and electrical current. More specifically, a state-of-the-art GAN was designed to estimate the normal distribution of vibration and electrical current data. This estimated normal distribution can be used to calculate an anomaly score through reconstruction error, Mahalanobis distance, and isolation tree reconstruction error using specific data from the GAN model. Anomaly detection was performed on long-range temporal dependencies through self-attention mechanisms using the Anomaly Transformer Architecture. Additional multi-scale anomaly patterns in industrial datasets are evaluated using the MSPG-SEN framework. The framework was evaluated on a total of four datasets (two labeled benchmark datasets: CWRU Bearing, Machine Failure, and two unlabeled real-world crane datasets). The results of the experiment indicate that the proposed framework achieves over a 98% true positive rate on the labeled benchmark datasets. The results from the unlabeled crane datasets indicate that different anomaly detection models produce partially overlapping but distinct anomaly patterns indicating different modeling paradigms demonstrate complementary aspects of anomalous behavior. These findings highlight that combining generative, attention-based and statistical methods increases the robustness of an anomaly detection system and can provide a wider array of detection patterns. The proposed hybrid method, therefore, has proven to be a useful system for predictive maintenance in real world applications, especially when there is limited ground truth or when ground truth is not available.","manuscriptTitle":"A Hybrid Generative and Transformer-Based Framework for Anomaly Detection in Industrial Sensor Time-Series for Predictive Maintenance","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 17:14:02","doi":"10.21203/rs.3.rs-9226417/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-27T07:02:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-20T02:56:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"246863448012899161597148640975979672647","date":"2026-04-19T02:01:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-17T14:31:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T17:58:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T11:55:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"120886221461693418361537935548358468931","date":"2026-04-12T16:02:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"151127803450256212057442473054010396152","date":"2026-04-11T12:16:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-10T13:15:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271254851334936496991482188895694781332","date":"2026-04-10T10:02:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"163316338101207486566189243785922464257","date":"2026-04-10T05:41:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"63444218376997002730805839945346522741","date":"2026-04-10T01:09:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"336830137101069324875802917832287594696","date":"2026-04-10T00:46:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-10T00:05:09+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-02T16:29:36+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-27T11:47:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-27T11:47:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-25T18:27:22+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":"0e847839-d323-4d34-893c-573a5b956a7e","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66393410,"name":"Physical sciences/Engineering"},{"id":66393411,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-19T03:23:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 17:14:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9226417","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9226417","identity":"rs-9226417","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}