[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124315-en":3,"doc-seo-124315-105":30,"detail-sidebar-cat-0-en-105":84},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124315,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Anomaly Detection in Wind Turbine Generator Bearing Using SCADA Data and Machine Learning","Wind Turbines are critical to renewable energy, yet component failures and maintenance delays lead to downtime and financial losses. This thesis develops a data-driven anomaly detection approach for generator bearings in offshore wind turbines using SCADA system data. It combines supervised and unsupervised machine learning to model turbine behavior, capture correlations across components, and identify abnormalities from synthetic datasets. Historical datasets train and validate the models, emphasizing ten highly correlated operational parameters. Results indicate successful detection of early mechanical failure signs and strong generalization to unseen data, including early warning signals across months in the studied period.","ACIT5900  \nMASTER THESIS  \nin  \nApplied Computer and Information Technology (ACIT)  \nMay 2025  \nRobotics and Control  \nAnomaly Detection in Wind Turbine Generator Bearing Using SCADA Data and  \nMachine Learning  \nMd Mahmudul Hasan  \nDepartment of Computer Science Faculty of Technology, Art and Design  \nAnomaly Detection in Wind Turbine Generator Bearing Using SCADA Data and  \nMachine Learning  \nMd Mahmudul Hasan  \n©2025 Md Mahmudul Hasan  \nAnomaly Detection Wind Farms Using SCADA Data  \n[http://www.oslomet.no/](http://www.oslomet.no/)  \nPrinted: Oslo Metropolitan University—OsloMet  \nPreface  \nThis thesis, titled “Anomaly Detection Wind Farms Using SCADA Data,” has been carried out as part of my Master’s degree. The work focuses on understanding the operational behavior of wind turbines and developing methods to detect potential anomalies. As my previous study was in electrical energy and renewable energy, my curiosity evolved when I discovered that I can work with energy datasets by using machine learning models, which I learned from my master’s program. I attempted to bring these areas together through this study.  \nMy Supervisor, Arvind Keprate, and my Co-Supervisor, Pedro Lind, helped me visualize the work scenario, guided me in the data handling process, and inspired me about machine learning possibilities for wind farms, which helped me shape my scope of study.  \nLastly, I hope this work will serve as a meaningful step toward enhancing the reliability of wind turbine energy by using the method to detect future anomalies for the turbine components.  \nMd Mahmudul Hasan  \nMay, 2025  \nABSTRACT  \nWind Turbines (WTs) are critical assets in the global transition towards renewable energy. However, failures and maintenance issues can cause significant downtime and financial losses. Anomaly detection methods for these failures caused by abnormal behavior in the components over time are essential for ensuring operational reliability. The study develops a data-driven approach for anomaly detection for generator bearing in offshore WTs using Supervisory Control and Data Acquisition (SCADA) system data, employing both supervised and unsupervised machine learning approaches to predict turbines behavior, correlation between individual components to connect the operational patterns, and identify the abnormalities from synthetic datasets. The machine learning models are trained and validated using historical datasets, with particular focus on the ten key optional parameters that are highly correlated in turbine components.  \nThe research demonstrates that the proposed methods successfully detect early signs of mechanical failures. The models show strong generalization across unseen data, highlighting the potential for detecting future abnormalities in the real world. Moreover, the result indicates some early warning signs during several months in that year.  \nACKNOWLEDGEMENT  \nFirst and foremost, I would like to express my sincere gratitude to my Supervisor, Arvind Keprate, and Co-Supervisor, Pedro Lind, for their invaluable guidance, support, and encouragement throughout this work. Their expertise, feedback, and patience have been instrumental in shaping the quality and direction of my research. I am deeply thankful to them for their systematic suggestions for producing a well-organized scientific report.  \nI am also thankful to my university for providing a supportive academic environment and access to the resources necessary for work.  \nSpecial thanks go to my family, whose prayers, belief in me, and unwavering love have been a constant source of strength. Without their support, completing this journey would not have been possible.  \nFinally, I would like to thank my friends and well-wishers, especially my friend Duy Tran, who supported and guided me through discussions about WT topics to achieve the best outcome.  \nI also utilized AI platforms to support the analysis and deepen my understanding of the report. These tools assisted in s","cbCaihRn7kyZb0BW","https://ap.wps.com/l/cbCaihRn7kyZb0BW","pdf",9266327,1,102,"English","en",105,"# Preface\n# Abstract\n# Acknowledgement\n# Introduction\n## Background\n## State of the art in anomaly detection of WTs\n## Primary objective and secondary objective\n# Theory\n## Structure and working principles of WTs\n## Critical components and failure mode\n## Drivetrain\n## Gearboxes\n## Bearings","[{\"question\":\"How are the models trained and validated in the research?\",\"answer\":\"Models are trained and validated using historical datasets, with an emphasis on ten key optional parameters that are highly correlated in turbine components.\"}]","Anomaly Detection in Wind Turbine Generator Bearing Using SCADA Data and Machine Learning | PDF",1785821566,257,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":79,"head_meta":81,"extra_data":83,"updated_unix":28},"anomaly-detection-in-wind-turbine-generator-bearing-using-scada-data-and-machine-learning","",{"@graph":36,"@context":78},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/anomaly-detection-in-wind-turbine-generator-bearing-using-scada-data-and-machine-learning/124315/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"How are the models trained and validated in the research?","Question",{"text":76,"@type":77},"Models are trained and validated using historical datasets, with an emphasis on ten key optional parameters that are highly correlated in turbine components.","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,116,121,124,128],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":114,"slug":115},30,"research-report",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},9,"Religion & Spirituality",20,"religion-spirituality",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":119,"slug":123},"World Cup","world-cup",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":125,"slug":127},10,"Lifestyle","lifestyle",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":99,"slug":131},19,"General","general"]