A novel SVD-UKFNN algorithm for predicting current efficiency of aluminum electrolysis

A novel SVD-UKFNN algorithm for predicting current efficiency of aluminum electrolysis | 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 novel SVD-UKFNN algorithm for predicting current efficiency of aluminum electrolysis Xiaoyan Fang, Xihong Fei, Kang Wang, Tian Fang, Rui Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5297061/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract The optimal control of the aluminum electrolysis production process (AEFP) presents an enduring challenge in industrial operations, largely due to its inherent dynamic nonlinearity, multivariable complexity, and susceptibility to significant disturbances. These factors hinder the development of precise predictive models for dynamic current efficiency. To address these problems, this article proposes a novel singular value decomposition unscented Kalman filtering neural network (NSVD-UKFNN) to improve the predictive accuracy of current efficiency in aluminum electrolysis. The approach begins by constructing a dynamic prediction model within the UKFNN framework, utilizing artificial neural networks (ANNs) to capture complex system behaviors. Singular value decomposition (SVD) is then incorporated into the unscented Kalman filtering neural network (UKFNN) architecture to compute the prior matrix square root, thereby enhancing model stability. Finally, the state variable prediction variance is reformulated as an objective function and optimized through gradient descent, effectively reducing error accumulation during computations. Comparative experimental results demonstrate that the proposed SVD-UKFNN significantly outperforms several related frameworks in predicting current efficiency, showcasing its potential for broader industrial applications. Physical sciences/Engineering/Chemical engineering Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 17 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 25 Dec, 2024 Reviews received at journal 22 Dec, 2024 Reviews received at journal 15 Dec, 2024 Reviews received at journal 29 Nov, 2024 Reviewers agreed at journal 28 Nov, 2024 Reviewers agreed at journal 28 Nov, 2024 Reviewers agreed at journal 24 Nov, 2024 Reviewers invited by journal 17 Nov, 2024 Editor assigned by journal 10 Nov, 2024 Editor invited by journal 07 Nov, 2024 Submission checks completed at journal 06 Nov, 2024 First submitted to journal 20 Oct, 2024 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-5297061","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":379035985,"identity":"5ba88177-59a2-4a95-8c21-fe61b3fd86cb","order_by":0,"name":"Xiaoyan Fang","email":"","orcid":"","institution":"Chongqing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Fang","suffix":""},{"id":379035986,"identity":"3635bebe-32a7-4ff7-b65c-baf97d47e4d7","order_by":1,"name":"Xihong Fei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYBAC9gYeEGXDwMDM3AATNMCrhecAWEsaUAtjA0w1UVoOAzHRWiRyDz4u+HU+mr+dsYGZ588feQb25m0SDDV3cGvhOZdsPLPvdu6Mw0AtvG0Ghg08x8okGI49w6nFnr3HTJq353ZuA1hLg0ECg0SOmQRjw2HctjDzgLScy51/GOwwoBb5NwS0gGzh+XEgdwNYCxvIFh4CWnjOGBvzNiTnbgRqOTi3zdiwjSet2CLhGB4tEjmGj3n+2OXOO3/44IM3f+Tk+dkPb7zxoQa3FjBgbIPQB0AEG4hIwK8BCP4QVDEKRsEoGAUjGQAAgjRN5Acomp4AAAAASUVORK5CYII=","orcid":"","institution":"Anhui University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xihong","middleName":"","lastName":"Fei","suffix":""},{"id":379035987,"identity":"3a3e2bd3-e70c-4cc9-92c7-7a537b37642a","order_by":2,"name":"Kang Wang","email":"","orcid":"","institution":"Anhui University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kang","middleName":"","lastName":"Wang","suffix":""},{"id":379035988,"identity":"8ae21188-afa0-451e-9504-6bc17a92f69c","order_by":3,"name":"Tian Fang","email":"","orcid":"","institution":"Anhui University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tian","middleName":"","lastName":"Fang","suffix":""},{"id":379035989,"identity":"dd42ecfb-d79e-43b1-9fae-c2860d3036b8","order_by":4,"name":"Rui Chen","email":"","orcid":"","institution":"West Anhui University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-10-20 06:38:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5297061/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5297061/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-94210-y","type":"published","date":"2025-03-17T15:57:17+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":79120603,"identity":"a544d681-8302-45d4-b6bf-cc1118f3f089","added_by":"auto","created_at":"2025-03-24 16:10:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6667303,"visible":true,"origin":"","legend":"","description":"","filename":"scmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5297061/v1_covered_3bb29b8b-0e2c-4886-bf5b-191afe088cd1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A novel SVD-UKFNN algorithm for predicting current efficiency of aluminum electrolysis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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-5297061/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5297061/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The optimal control of the aluminum electrolysis production process (AEFP) presents an enduring challenge in industrial operations, largely due to its inherent dynamic nonlinearity, multivariable complexity, and susceptibility to significant disturbances. These factors hinder the development of precise predictive models for dynamic current efficiency. To address these problems, this article proposes a novel singular value decomposition unscented Kalman filtering neural network (NSVD-UKFNN) to improve the predictive accuracy of current efficiency in aluminum electrolysis. The approach begins by constructing a dynamic prediction model within the UKFNN framework, utilizing artificial neural networks (ANNs) to capture complex system behaviors. Singular value decomposition (SVD) is then incorporated into the unscented Kalman filtering neural network (UKFNN) architecture to compute the prior matrix square root, thereby enhancing model stability. Finally, the state variable prediction variance is reformulated as an objective function and optimized through gradient descent, effectively reducing error accumulation during computations. Comparative experimental results demonstrate that the proposed SVD-UKFNN significantly outperforms several related frameworks in predicting current efficiency, showcasing its potential for broader industrial applications.","manuscriptTitle":"A novel SVD-UKFNN algorithm for predicting current efficiency of aluminum electrolysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-21 11:30:15","doi":"10.21203/rs.3.rs-5297061/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-25T11:53:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-22T11:51:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-15T10:26:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-29T23:02:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"90549927991998266799836712958402447448","date":"2024-11-28T16:25:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"239057246646413126033523341085964995881","date":"2024-11-28T13:37:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162025576028820046011012810672585715080","date":"2024-11-24T17:54:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-17T10:02:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-10T07:27:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-11-07T13:21:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-06T09:31:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-10-20T06:30:51+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":"f4d2d6da-0c82-4e76-a51a-5ca9b48096c8","owner":[],"postedDate":"November 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":40361228,"name":"Physical sciences/Engineering/Chemical engineering"},{"id":40361229,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":40361230,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-03-24T16:05:10+00:00","versionOfRecord":{"articleIdentity":"rs-5297061","link":"https://doi.org/10.1038/s41598-025-94210-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-03-17 15:57:17","publishedOnDateReadable":"March 17th, 2025"},"versionCreatedAt":"2024-11-21 11:30:15","video":"","vorDoi":"10.1038/s41598-025-94210-y","vorDoiUrl":"https://doi.org/10.1038/s41598-025-94210-y","workflowStages":[]},"version":"v1","identity":"rs-5297061","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5297061","identity":"rs-5297061","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}