[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123853-en":3,"doc-seo-123853-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},123853,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques - Master’s Thesis","This master’s thesis analyzes and improves anomaly detection for ventilation processes in building automation, aiming to create a more accurate method than the one previously used for the same purpose. The approach was developed at Fidelix using data collected from the Fidelix Flow_how service. The theoretical part explains the structure and building-automation implementation of ventilation processes, reviews anomaly detection techniques and machine learning methods, and evaluates LSTM, K-means, Isolation Forest and PyCaret. The resulting method is more accurate and faster, while the former version is still in use.","Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques  \nRobin Lyttbacka  \nMaster’s Thesis in Automation Technology  \nThe Degree Programme in Automation Technology – Intelligent systems Vaasa, 2023  \nMASTER THESIS  \nAuthor: Robin Lyttbacka  \nDegree Program and place of study: Automation Technology, Vaasa  \nSpecialization: Intelligent systems  \nSupervisor(s): Ray Pörn, Lauri Westerholm  \nTitle: Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques  \n\n| Date: 12.1.2024 Number of pages: 65 | Appendices: 2 |\n| --- | --- |\n| Abstract\u003Cbr>The purpose of this thesis was to analyze and improve anomaly detection for ventilation processes in building automation. The final goal of the thesis was to develop an anomaly detection method that was more accurate than the one previously used for the same purpose.\u003Cbr>The anomaly detection method was developed at Fidelix. Fidelix is a company that provides building automation solutions. Fidelix has a service called Flow_how and data collected from the Fidelix Flow_how service was used to develop the anomaly detection method.\u003Cbr>The theory part describes how the ventilation process is structured and how it is implemented in a building automation system. Furthermore, different types of anomaly detection methods and different machine learning methods are discussed. The anomaly detection methods that have been used and analyzed are LSTM (Long Short Term Memory), Kmeans, Isolation forest and a Python machine learning library called Pycaret.\u003Cbr>The result of the thesis was an anomaly detection method that was more accurate than the one previously used. The new method is faster than the one previously used. At the time of writing, the previous version is still used. The method developed in this thesis is available for future use. |  |\n\nLanguage: English  \nKey Words: Anomaly detection, building automation, machine learning, Python, unsupervised learning  \nEXAMENSARBETE  \nFörfattare: Robin Lyttbacka  \nUtbildning och ort: Automation, Vasa  \nInriktning: Intelligenta system  \nHandledare: Ray Pörn, Lauri Westerholm  \nTitel: Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques  \nDatum: 12.1.2024 Sidantal: 65 Bilagor: 2  \nAbstrakt  \nSyftet med detta examensarbete var att analysera och förbättra avvikelse detektering förventilations processer inom fastighetsautomatik. Avsikten var att få fram en avvikelsedetekteringsmetod som var mera exakt än den tidigare använda för samma ändamål.  \nAvvikelsedetekteringsmetoden utvecklades vid Fidelix. Fidelix är ett företag som tillhandahåller fastighetsautomatiklösningar. Insamlad data från Fidelix Flow_how tjänst användes för att utvecklaavvikelsedetekteringsmetoden.  \nI teoridelen beskrivs det hur ventilations processen är strukturerad och hur denna implementeras iett fastighetsautomationsystem. Vidare behandlas olika typer av avvikelse detekterings metoder och olika maskininlärningsmetoder. Avvikelsedetekteringsmetoderna som har använts och analyserats är LSTM (Long Short Term Memory), Kmeans, Isolation forest och Python maskininlärningsbibiliotek kallat Pycaret.  \nResultatet blev en avvikelsedetekteringsmetod som är mera exakt än den som tidigare användes. Den nya metoden är också snabbare än den som tidigare användes. För tillfället används fortfarande den tidigare versionen. Det nya programmet finns till förfogande för framtida behov.  \nSpråk: Engelska  \nNyckelord: Anomali detektering, fastighetsautomatik, maskininlärning, Python, oövervakadinlärning  \nOPINNÄYTETYÖ  \nTekijä: Robin Lyttbacka  \nKoulutus ja paikkakunta: Automaatiotekniikka, Vaasa  \nSuuntautumisvaihtoehto: Tekoäly  \nOhjaaja(t): Ray Pörn, Lauri Westerholm  \nNimike: Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques  \nPäivämäärä: 12.1.2024 Sivumäärä: 65 Liitteet: 2  \nTiivistelmä  \nTämän opinnäytetyön tarkoituksena oli analysoida ja parantaa ilmanvaihtoprosessien poikkeamienhav","cbCaiv15GGS10hed","https://ap.wps.com/l/cbCaiv15GGS10hed","pdf",5949310,1,67,"English","en",105,"# 1 Introduction\n## 1.1 Background\n## 1.2 The purpose of the study\n# 2 Theoretical part\n## 2.1 Building automation systems\n## 2.1.1 AHU Processes","[{\"question\":\"What problem does the thesis address in building automation?\",\"answer\":\"The thesis targets improving anomaly detection for ventilation processes in building automation, replacing a less accurate previously used method.\"},{\"question\":\"Which data source was used to develop the anomaly detection method?\",\"answer\":\"The method was developed at Fidelix using data collected from the Fidelix Flow_how service.\"},{\"question\":\"Which anomaly detection and machine learning techniques are evaluated?\",\"answer\":\"The thesis analyzes LSTM, K-means, Isolation Forest, and the Python machine learning library PyCaret.\"}]","Exploring Anomaly Detection in Building Automation Through Machine Learning Techniques - Master’s Thesis | PDF",1785818895,169,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"exploring-anomaly-detection-in-building-automation-through-machine-learning-techniques-masters-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@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/exploring-anomaly-detection-in-building-automation-through-machine-learning-techniques-masters-thesis/123853/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in building automation?","Question",{"text":75,"@type":76},"The thesis targets improving anomaly detection for ventilation processes in building automation, replacing a less accurate previously used method.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data source was used to develop the anomaly detection method?",{"text":80,"@type":76},"The method was developed at Fidelix using data collected from the Fidelix Flow_how service.",{"name":82,"@type":73,"acceptedAnswer":83},"Which anomaly detection and machine learning techniques are evaluated?",{"text":84,"@type":76},"The thesis analyzes LSTM, K-means, Isolation Forest, and the Python machine learning library PyCaret.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]