{"paper_id":"291ff44d-2fe3-446c-9ae9-2230b279268e","body_text":"Dynamic Reliability Prediction Method of Offshore Wind Turbine Based on CNN-LSTM Fusion | 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 Dynamic Reliability Prediction Method of Offshore Wind Turbine Based on CNN-LSTM Fusion Huiwen Bai, Haiming Wang, Yi Deng, Zhiyuan Ma, Mengnan Cao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9436833/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract With the increasing complexity of the operating environment of offshore wind turbines, traditional reliability prediction methods are difficult to accurately describe their dynamic changes. The paper proposes a dynamic reliability prediction method based on the fusion of Convolutional Neural Network (CNN) and Long Short Term Memory Network (LSTM), aiming to accurately model and predict the health status of wind turbines. This method enhances the sensitivity of wind turbines at different operating stages by extracting spatiotemporal features from multi-source sensor data and combining them with deep learning networks. Firstly, through data preprocessing and feature engineering, the scale inconsistency between multi-source signals was eliminated, and local features were extracted using CNN; Then, LSTM is used to capture temporal dependencies and ultimately output the reliability probability of the unit's health status. The experimental results show that the CNN-LSTM model can more effectively identify the degradation trend and potential faults of wind turbines compared to traditional methods, with an overall RMSE about 77.7% lower than the benchmark model BN. In addition, the ablation experiment verified the critical role of CNN and LSTM modules in overall performance, and the model error degradation was most significant after removing CNN, reaching 53.80%. This method provides more scientific data support and decision-making basis for the health management of offshore wind turbines. offshore wind turbines Dynamic reliability CNN-LSTM Data driven Degradation prediction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 24 May, 2026 Reviewers agreed at journal 24 May, 2026 Reviewers agreed at journal 21 May, 2026 Reviewers invited by journal 08 May, 2026 Editor invited by journal 27 Apr, 2026 Editor assigned by journal 19 Apr, 2026 Submission checks completed at journal 19 Apr, 2026 First submitted to journal 16 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-9436833\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":636693276,\"identity\":\"e7c6ed53-30db-4c8a-85f5-2ce6d375b4e6\",\"order_by\":0,\"name\":\"Huiwen Bai\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIie2QsQrCQAyGcwTO5dTVgujmfCK4ia9iKegDCNLRKS6Kq06+hTi2FM6lOFdcFF9AN4UKnrqJrXVzuG9JAvkIfwAMhj9EemyoSwwc0d/rrgzAMykKeI47Us8ig/IsAUBR1ErZlMih0nmlqgUU3D1TLIo56sDFXSYq7cgmax7GdcK82s5JCmusPDYOdylXbNrlSTHCQlc3UsioN0RGX5QbBW1C0exnVxgF9kPBl9L10pXwMLpOSDmE3LFmm8YjS8dPzbLuHeWV4tZiGvin06BS0R+r7y9usvIZ78d9g8FgMLxxB802W7YopbosAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"SPIC China Power (Gansu) Energy Investment Limited\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Huiwen\",\"middleName\":\"\",\"lastName\":\"Bai\",\"suffix\":\"\"},{\"id\":636693279,\"identity\":\"d65825f0-6592-4eba-b5c9-ad148e5a89f5\",\"order_by\":1,\"name\":\"Haiming Wang\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"SPIC China Power (Gansu) Energy Investment Limited\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Haiming\",\"middleName\":\"\",\"lastName\":\"Wang\",\"suffix\":\"\"},{\"id\":636693281,\"identity\":\"7d175178-ed8f-45df-a646-354eabf8d7f0\",\"order_by\":2,\"name\":\"Yi Deng\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shanghai Energy Technology Development CO,.LTD\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Yi\",\"middleName\":\"\",\"lastName\":\"Deng\",\"suffix\":\"\"},{\"id\":636693283,\"identity\":\"6751f509-0c6e-432d-9e22-d4e07d63163b\",\"order_by\":3,\"name\":\"Zhiyuan Ma\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shanghai Energy Technology Development CO,.LTD\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zhiyuan\",\"middleName\":\"\",\"lastName\":\"Ma\",\"suffix\":\"\"},{\"id\":636693284,\"identity\":\"142f965f-d86e-4ce4-adf2-b0bb9e3e4169\",\"order_by\":4,\"name\":\"Mengnan Cao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shanghai Energy Technology Development CO,.LTD\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mengnan\",\"middleName\":\"\",\"lastName\":\"Cao\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-04-16 10:23:55\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-9436833/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-9436833/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":109428168,\"identity\":\"b5f61fd9-965e-4aff-8148-7e9dd8f51301\",\"added_by\":\"auto\",\"created_at\":\"2026-05-18 03:25:54\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1124702,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"paper.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-9436833/v1_covered_d6d2a59b-2436-4c59-8ec0-19834a18e259.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Dynamic Reliability Prediction Method of Offshore Wind Turbine Based on CNN-LSTM Fusion\",\"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\":\"info@researchsquare.com\",\"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\":\"offshore wind turbines, Dynamic reliability, CNN-LSTM, Data driven, Degradation prediction\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-9436833/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-9436833/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eWith the increasing complexity of the operating environment of offshore wind turbines, traditional reliability prediction methods are difficult to accurately describe their dynamic changes. The paper proposes a dynamic reliability prediction method based on the fusion of Convolutional Neural Network (CNN) and Long Short Term Memory Network (LSTM), aiming to accurately model and predict the health status of wind turbines. This method enhances the sensitivity of wind turbines at different operating stages by extracting spatiotemporal features from multi-source sensor data and combining them with deep learning networks. Firstly, through data preprocessing and feature engineering, the scale inconsistency between multi-source signals was eliminated, and local features were extracted using CNN; Then, LSTM is used to capture temporal dependencies and ultimately output the reliability probability of the unit's health status. The experimental results show that the CNN-LSTM model can more effectively identify the degradation trend and potential faults of wind turbines compared to traditional methods, with an overall RMSE about 77.7% lower than the benchmark model BN. In addition, the ablation experiment verified the critical role of CNN and LSTM modules in overall performance, and the model error degradation was most significant after removing CNN, reaching 53.80%. This method provides more scientific data support and decision-making basis for the health management of offshore wind turbines.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Dynamic Reliability Prediction Method of Offshore Wind Turbine Based on CNN-LSTM Fusion\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-05-18 03:25:17\",\"doi\":\"10.21203/rs.3.rs-9436833/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-05-24T11:01:55+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"162351229671846792632444625478911539313\",\"date\":\"2026-05-24T10:19:12+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"298783383224668295771918856228128604964\",\"date\":\"2026-05-21T06:11:20+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2026-05-08T07:55:23+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvited\",\"content\":\"\",\"date\":\"2026-04-27T06:43:42+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2026-04-19T07:40:59+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2026-04-19T07:40:56+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Discover Computing\",\"date\":\"2026-04-16T10:12:07+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"78a5efb0-5a04-41a0-9836-4b054ac2ab9b\",\"owner\":[],\"postedDate\":\"May 18th, 2026\",\"published\":true,\"recentEditorialEvents\":[{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-05-24T11:01:55+00:00\",\"index\":50,\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"162351229671846792632444625478911539313\",\"date\":\"2026-05-24T10:19:12+00:00\",\"index\":49,\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"298783383224668295771918856228128604964\",\"date\":\"2026-05-21T06:11:20+00:00\",\"index\":47,\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"30\",\"date\":\"2026-05-08T07:55:23+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-05-18T03:25:18+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-05-18 03:25:17\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-9436833\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-9436833\",\"identity\":\"rs-9436833\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}