MTL-Net: A Unified Deep Learning Architecture for Predicting Production Efficiency, Defect Rate, and Speed in Industry 4.0 Systems

MTL-Net: A Unified Deep Learning Architecture for Predicting Production Efficiency, Defect Rate, and Speed in Industry 4.0 Systems | 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 MTL-Net: A Unified Deep Learning Architecture for Predicting Production Efficiency, Defect Rate, and Speed in Industry 4.0 Systems Md Mahamudur Rahaman Shamim, Md. Nuruzzaman, Zannatul Ferdus, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7915830/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 The paper proposes a multi-task deep learning model for smart manufacturing that allows to classify efficiency and predicting two quality indicators: defect and speed. To capture dependencies in IIoT sensor stream, the model combines parallel CNN layers, BiLSTM-GRU recurrent encoders, and multi-head attention. The multi-sensor production sequences, amounting to 80,000, were employed in the training of the system through stratified balancing, adaptive loss weighting, and regularization. The experiments show that this method can predict well with accuracy above 93.3% for the classification of efficiency and R 2 = 0.924 for the defect rate and R 2 = 0.981 for the production speed. The outcomes validate that learning representations for multiple tasks is more effective than independently training each task. A scalable framework for decision support in Industry 4.0 real-time predictive maintenance resource allocation production optimization is provided in the proposed work. Industrial Engineering Artificial Intelligence and Machine Learning Smart Manufacturing Deep Multi-Task Learning Temporal Sensor Analytics Attention Mechanisms Industrial IoT Production Optimization 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-7915830","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":533044556,"identity":"cd0a3969-13f9-4787-9196-aa66fc6ae4c1","order_by":0,"name":"Md Mahamudur Rahaman Shamim","email":"","orcid":"","institution":"Western Illinois University , Macomb IL- 61455. USA , Department of Manufacturing Engineering Technology","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Mahamudur Rahaman","lastName":"Shamim","suffix":""},{"id":533044557,"identity":"7671841a-7bbb-4adc-b867-8491f0e0372a","order_by":1,"name":"Md. Nuruzzaman","email":"","orcid":"","institution":"Western Illinois University , Macomb IL- 61455. USA , Department of Manufacturing Engineering Technology","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"","lastName":"Nuruzzaman","suffix":""},{"id":533044558,"identity":"38d9a6a1-78ce-4885-b181-1f2f368c36b1","order_by":2,"name":"Zannatul Ferdus","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA60lEQVRIiWNgGAWjYDAC5gMMDDwMDPVs7M1AFoOEDGEtbAlgLQn8PMcSQFp4iNciOSPHAMQnrEW+jfnYh7dtdXkGZ858fnWjxoKHgf3w0Q34tDC2sSXPnNt2uNjgeO8265xjQIfxpKXdwKeFWb7HmJm37QDjhjNntxnnsAG1SPCY4dXCxsb/GailjnHDjZxnxjn/iNDCw8bDDNTCnDhzRg7z49w2IrRIsLEZM845d9gYGMhmzLl9EkAzCPgFGGKPGd6U1ckBo/Lx55xvdXL87IeP4dWC4i8JMEmschBg/kCK6lEwCkbBKBg5AAD70EP2OjqUyAAAAABJRU5ErkJggg==","orcid":"","institution":"Ahsanullah University Of Science And Technology, 141-142 Love Road, Tejgaon Industrial Area, Department of Mechanical And Production Engineering","correspondingAuthor":true,"prefix":"","firstName":"Zannatul","middleName":"","lastName":"Ferdus","suffix":""},{"id":533044559,"identity":"38746f03-2eae-485e-97ce-8fb5f75f0e26","order_by":3,"name":"Md Rajib Ahmed","email":"","orcid":"","institution":"Trine University, 720 Thunder Dr, Angola, IN 46703, Master’s of science in Industrial /Engineering Management","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Rajib","lastName":"Ahmed","suffix":""},{"id":533044560,"identity":"ef7914b6-d477-4d3e-8dfc-765e2d6dc351","order_by":4,"name":"ABIEER NWSHAD ANWAR","email":"","orcid":"","institution":"Sapienza University of Rome, Italy, Department of Nano-technology Engineering","correspondingAuthor":false,"prefix":"","firstName":"ABIEER","middleName":"NWSHAD","lastName":"ANWAR","suffix":""},{"id":533044561,"identity":"02d20d76-f525-4cd2-9ba7-67b4abdfc960","order_by":5,"name":"Mohammad Tooneer","email":"","orcid":"","institution":"Bangladesh University of Engineering and Technology, Industrial and Production Engineering","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Tooneer","suffix":""},{"id":533044562,"identity":"d088446b-b569-4ecf-b10b-8f3376ebfc20","order_by":6,"name":"JOHIR UDDIN KHAN","email":"","orcid":"","institution":"Chittagong University of Engineering and Technology, Raozan, Chattogram 4349, Department of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"JOHIR","middleName":"UDDIN","lastName":"KHAN","suffix":""}],"badges":[],"createdAt":"2025-10-21 22:01:02","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-7915830/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7915830/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94191773,"identity":"e34ea737-0ef5-4d68-a6bf-bf272d59b3e9","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":887012,"visible":true,"origin":"","legend":"","description":"","filename":"SmartManufacturingMTLNet.docx","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/0f7e45c67ada7dbcd818820f.docx"},{"id":94191779,"identity":"fb97bb81-23ad-43b8-9c3b-67bfd79a1630","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs7915830.json","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/b82b20be43bb5567d7fbb5ad.json"},{"id":94191776,"identity":"40d4abd7-31f0-46cf-9888-fc166402afd6","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":255801,"visible":true,"origin":"","legend":"","description":"","filename":"rs79158300enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/a667804e87b4f315c1465c6d.xml"},{"id":94193169,"identity":"d2c5cf4b-6e66-4202-aaf6-6ffb302b0f75","added_by":"auto","created_at":"2025-10-23 12:27:22","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":141825,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/0c96234194be40051714d8e1.png"},{"id":94191782,"identity":"414e7e20-11a3-485e-8f19-f4fbb0d15e5c","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109080,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/5da676e8d474b313fe040596.jpeg"},{"id":94194497,"identity":"7749c4a8-75be-4524-8f89-8e6ad9a5a678","added_by":"auto","created_at":"2025-10-23 12:43:22","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111667,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/44b9a97331035e67fe03f4a6.jpeg"},{"id":94193170,"identity":"ded4f5b6-4f4c-4f63-8b35-c79c86cb22ed","added_by":"auto","created_at":"2025-10-23 12:27:22","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33283,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/f55878e23caf0a1667451c22.png"},{"id":94193559,"identity":"bd19fb31-7dcb-4249-89cd-712557215f59","added_by":"auto","created_at":"2025-10-23 12:35:22","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":83976,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/68600264ee395cadbf8744ae.png"},{"id":94193175,"identity":"9112e016-49a1-4df8-bf97-f2dceb9efdf0","added_by":"auto","created_at":"2025-10-23 12:27:22","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148111,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/2f5c6d0e5ae34ee95a63e82d.png"},{"id":94191783,"identity":"95c2b51a-00a7-49d0-a3c9-5ff9ee2caa53","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":664761,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/8b866be74a0ee610fbc3809e.jpeg"},{"id":94191786,"identity":"38922af7-a16d-4c3d-998f-675a2af26189","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36510,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/7a79a83c41df2a47546a4451.png"},{"id":94193173,"identity":"28cb7656-9e5e-4e6e-ade2-bb02fb8b8ee9","added_by":"auto","created_at":"2025-10-23 12:27:22","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20401,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/bb8f024350b2194eb52b903b.png"},{"id":94191787,"identity":"525b57ed-8a25-4ada-8b69-3e9f8aa92b1d","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19162,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/1fc4c3b514fdb35d2b51d356.png"},{"id":94191785,"identity":"7651d70c-b513-41ca-97db-a543ddaf7418","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10396,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/ea8d4a90ecaf4aa0f6417ebc.png"},{"id":94193561,"identity":"c8248f32-1f16-4365-a67e-c265b8b1089f","added_by":"auto","created_at":"2025-10-23 12:35:22","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26299,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/f155a5d813a4bd15f4d37d22.png"},{"id":94193176,"identity":"5625c05f-cf44-4766-add2-be76f928d7a1","added_by":"auto","created_at":"2025-10-23 12:27:22","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29645,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/953db06c1f00d93a2a6d207f.png"},{"id":94191788,"identity":"15e0e95a-d6cd-4848-bf32-4a84147985fa","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116568,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/e3a2876e327f9c529948aa87.png"},{"id":94191791,"identity":"2a38b57e-0954-4b82-8eef-531da54ba55e","added_by":"auto","created_at":"2025-10-23 12:19:23","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":245557,"visible":true,"origin":"","legend":"","description":"","filename":"rs79158300structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/6d69eb59f210e6efb4cca026.xml"},{"id":94191790,"identity":"b62f978a-034a-4902-9e96-6940c004fbb8","added_by":"auto","created_at":"2025-10-23 12:19:22","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":280291,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7915830/v1/28ed9802826581b19b3042fd.html"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMTL-Net: A Unified Deep Learning Architecture for Predicting Production Efficiency, Defect Rate, and Speed in Industry 4.0 Systems\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"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":"Smart Manufacturing, Deep Multi-Task Learning, Temporal Sensor Analytics, Attention Mechanisms, Industrial IoT, Production Optimization","lastPublishedDoi":"10.21203/rs.3.rs-7915830/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7915830/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe paper proposes a multi-task deep learning model for smart manufacturing that allows to classify efficiency and predicting two quality indicators: defect and speed. To capture dependencies in IIoT sensor stream, the model combines parallel CNN layers, BiLSTM-GRU recurrent encoders, and multi-head attention. The multi-sensor production sequences, amounting to 80,000, were employed in the training of the system through stratified balancing, adaptive loss weighting, and regularization. The experiments show that this method can predict well with accuracy above 93.3% for the classification of efficiency and R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;0.924 for the defect rate and R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;0.981 for the production speed. The outcomes validate that learning representations for multiple tasks is more effective than independently training each task. A scalable framework for decision support in Industry 4.0 real-time predictive maintenance resource allocation production optimization is provided in the proposed work.\u003c/p\u003e","manuscriptTitle":"MTL-Net: A Unified Deep Learning Architecture for Predicting Production Efficiency, Defect Rate, and Speed in Industry 4.0 Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-23 12:19:17","doi":"10.21203/rs.3.rs-7915830/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":"aba09961-12fe-40c5-86f1-8aa6de1acec6","owner":[],"postedDate":"October 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56668235,"name":"Industrial Engineering"},{"id":56668236,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-10-23T12:19:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-23 12:19:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7915830","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7915830","identity":"rs-7915830","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}