[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121397-en":3,"doc-seo-121397-105":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},121397,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Surveillance system for drainage pumps with the use of machine learning - Master’s Thesis 2023","The master thesis investigates machine-learning based ways to regulate a storm water facility and to predict inflow to a sump tank for a factory site exposed to frequent flooding. An IoT device is built to log and monitor water levels, and the collected data is combined with local weather station measurements for model training. Long Short-Term Memory and Transformer encoder networks are evaluated on the resulting time series to learn multidimensional correlations. Results are promising, but limited sump-tank logging duration prevents usable forecasting or control performance, indicating strong potential for future improvements.","[www.usn.no](www.usn.no)  \nFMH606 Master’s Thesis 2023 Industrial IT and Automation  \nSurveillance system for drainage pumps with the use of machine learning  \nVebjørn Rimstad Wille  \nFaculty of Technology, Natural Sciences and Maritime Sciences  \nCampus Porsgrunn  \n[www.usn.no](www.usn.no)  \nCourse: FMH606 Master’s Thesis 2023  \nTitle: Surveillance system for drainage pumps with the use of machine learning  \nPages: 102  \nKeywords: Flood, IOT, LSTM, Transformers  \nStudent: Vebjørn Rimstad Wille  \nSupervisor: Håkon Viumdal  \nExternal partner: David Bergene Holm, Håvard Omholt  \nSummary:  \nBergene Holm AS, Avd. Kvelde is a planer factory, surrounded by vast fields that are susceptible to flooding. This thesis looks into the possibilities of building upon the Tokyo Amesh system. The objective is to investigate the feasibility of regulating a storm water facility, or predicting the inflow into the storm water facility with the use of machine learning. To achieve this, an IoT device was built to log and monitor the storm water facility. The collected data was combined with local weather station data, processed, and exposed to a machine learning algorithm for training to predict inflow into the sump tank. Both Long Short-Term Memory networks and Transformer encoder networks were used to train on this time series data to be able to learn multidimensional correlations between the local weather station data and the logged water level of the sump tank within the storm water facility. Both Long Short-term memory and Transformers showed promising results in the prediction, but fell short of being used as either a forecast system or a control system, due to the limited data of the level of the sump tank. The lack of a longer logging time severely impacted the performance of the machine learning networks, as they were not able to achieve acceptable performance. However, due to the promising results, improving this system in the future is highly possible.  \nThe University of South-Eastern Norway accepts no responsibility for the results and  \nconclusions presented in this report.  \nPreface  \nThis master thesis was written as a part of the Industry Master program, Industrial IT and Automation. Therefore, this thesis was written for both the company Bergene Holm AS, and USN. The motivation for this thesis was to look into the possibility of improving a storm water facility at Bergene Holm AS, Avd Kvelde, that received a lot of attention after a spring flood caused severe problems for the factory. The idea was to log the process data and see if it was possible to use machine learning to further enhance the performance of the facility. The changing behavior of weather and how it affects local environments has always fascinated me, making this master thesis captivating. It should be noted that the reader should have some basic understanding of deep neural networks, as this thesis does not delve into the basics of this topic. Due to confidentiality issues, no code from the IoT device is shown, as it contains passwords and other sensitive information. Throughout this thesis,’Kvelde factory’ will be shortened to ’Kvelde’. Lastly, I would like to thank my supervisor Håkon Viumdal for all the help and guidance he has provided. I would also like to thank my external partners from Bergene Holm AS, David Bergene Holm, and Håvard Omholt, both for the time they have dedicated from their otherwise engaged schedules, to help me with insightful comments in this thesis. I would also thank Inge Gjerden for his involvement in the design phase of building the HMI for the IoT system. Finally, I would especially like to thank Bergene Holm AS for the opportunity to work for them and write this master thesis, as it has been a good experience and a pleasure.  \nPorsgrunn, 14th May 2023 Vebjørn Rimstad Wille  \nContents  \nPreface 3  \nContents 5  \nList of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6  \nList of Tables . . . . . . . . .","cbCaisQXSDAmqVNm","https://ap.wps.com/l/cbCaisQXSDAmqVNm","pdf",20768605,1,102,"English","en",105,"# Preface\n# Contents\n# List of Figures\n# List of Tables\n# Nomenclature\n# 1 Introduction\n# 2 Situation At Kvelde\n# 3 IoT System Design and Data Acquisition for Machine Learning\n## The Hardware\n## The Software\n## The Human Machine Interface (HMI)\n## Data gathering\n## Time-series predicting using RNN\n## Time-series predicting using Transformers\n## Tuning and validating the machine learning\n# 4 Data Exploration\n## Results of the Data Analysis\n# 5 Predicting using Machine Learning\n## LSTM tuning and results\n## Transformers tuning and result\n## Comparison between LSTM and Transformers","[{\"question\":\"What problem does the thesis address for the factory in Kvelde?\",\"answer\":\"The thesis targets flooding-related challenges at a storm water facility by exploring how to predict inflow and support regulation of the sump tank using machine learning.\"},{\"question\":\"How is data collected and prepared for the machine learning models?\",\"answer\":\"An IoT device logs and monitors the sump tank water level, and the logged data is combined with local weather station data, then pre-processed for time-series model training and validation.\"},{\"question\":\"Which machine learning architectures are evaluated, and what are the main results?\",\"answer\":\"Long Short-Term Memory (LSTM) networks and Transformer encoder networks are both trained to predict inflow. Both show promising predictive results, but performance is insufficient for reliable forecasting or control due to limited logging time.\"}]","Surveillance system for drainage pumps with the use of machine learning - Master’s Thesis 2023 | PDF",1785735490,257,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"surveillance-system-for-drainage-pumps-with-the-use-of-machine-learning-masters-thesis-2023","",{"@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/surveillance-system-for-drainage-pumps-with-the-use-of-machine-learning-masters-thesis-2023/121397/",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","2026-08-03",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 for the factory in Kvelde?","Question",{"text":75,"@type":76},"The thesis targets flooding-related challenges at a storm water facility by exploring how to predict inflow and support regulation of the sump tank using machine learning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is data collected and prepared for the machine learning models?",{"text":80,"@type":76},"An IoT device logs and monitors the sump tank water level, and the logged data is combined with local weather station data, then pre-processed for time-series model training and validation.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning architectures are evaluated, and what are the main results?",{"text":84,"@type":76},"Long Short-Term Memory (LSTM) networks and Transformer encoder networks are both trained to predict inflow. Both show promising predictive results, but performance is insufficient for reliable forecasting or control due to limited logging time.","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"]