[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125217-en":3,"doc-seo-125217-105":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},125217,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Fermentation Prediction through Machine Learning and its Potential Use in Production Planning and Control","Craft breweries face production planning and control (PPC) challenges driven by complex, unpredictable processes, variable customer demand, and product perishability. Fermentation is the most time-consuming and critical step, adding uncertainty through variable duration that complicates PPC decisions. This thesis examines whether machine learning can accurately predict beer fermentation completion time, and how such forecasts could reduce PPC issues tied to time uncertainty.","Master’s thesis  \nNT NU  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of Mechan ica l and Industrial Engineering  \nCornelius Lassen Hjort Hans Erik Bjørkum Heum  \nFermentation Prediction through Machine Learning and its Potential Use in Production Planning and Control  \nMaster’s thesis in Ingeniørvitenskap og IKT Supervisor: Anita Romsdal  \nJune 2023  \nCornelius Lassen Hjort Hans Erik Bjørkum Heum  \nFermentation Prediction through Machine Learning and its Potential Use in Production Planning and Control  \nMaster’s thesis in Ingeniørvitenskap og IKT Supervisor: Anita Romsdal  \nJune 2023  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of Mechanical and Industrial Engineering  \nPreface  \nThis Master’s thesis is the final report in the Engineering and ICT master program with a specialization in production management at the Norwegian University of Science and Technology (NTNU) .  \nWe would like to thank our supervisor Anita Romsdal for the feedback, comments, and support during the semester.  \nWe would also like to thank Plaato for access to data and cooperation during the project. In particular we would like to thank software engineers Erik Olseng and Kristian Pedersen for sharing valuable insights, good suggestions and support.  \nCornelius Hjort & Hans Erik Heum Trondheim, June 2023  \nAbstract  \nCraft breweries face a multitude of challenges when it comes to production planning and control (PPC), largely due to the complex and unpredictable nature of their production processes combined with variable customer demand and the perishability of their products. Fermentation is the most time consuming production process and arguably the most critical. It adds significant uncertainty due to its variable duration, which poses significant challenges for PPC in craft breweries. Despite inconsistent results from previous attempts to enhance fermentation predictability, emerging technologies allow real-time tracking of the process combined with more data, presenting a potential for machine learning applications.  \nThe purpose of this study is to investigate the feasibility of accurately determining the completion of a beer fermentation process and how this knowledge could be employed to mitigate production planning and control issues related to fermentation process time uncertainty. The research delves deeper into whether machine learning methods can be used to predict how long beer fermentation takes. It also explores the challenges craft breweries face due to the uncertainty, and how fermentation forecasts can be used to reduce them.  \nA theoretical background is conducted to identify key elements of production planning and control in general, along with relevant aspects of machine learning. Furthermore, essential aspects of production planning and control in the beer production industry are further identified via an empirical background. This also includes findings from a multiple case study focusing on production planning and control in craft breweries.  \nThis thesis proposes four predictive models, using a number of input parameters to estimate the completion time of a fermentation process. A neural network, two gradient boosted forests and an automatic ML algorithm were applied to datasets of 40, 60 and 80 hours of information in the fermentation. The best models were more accurate than a baseline model that predicted the average. However, the models are struggling to predict accurately on batches that deviate from normal fermentation activity. Additionally, the study revealed that access to a substantial amount of data with high quality is an important factor when using machine learning combined with IoT.  \nA single case study involving one participating craft brewery is conducted to understand the current state of its production planning and control activities. Followed by an analysis of the information collected by the case company. As a result, we identified","cbCaiinl5FP4qkBn","https://ap.wps.com/l/cbCaiinl5FP4qkBn","pdf",11934940,1,140,"English","en",105,"# Preface\n## Abstract\n## Background and Motivation\n## Predictive Modeling Approach\n## Case Study and Findings\n## Conclusions and Further Work","[{\"question\":\"Why is fermentation a critical challenge for production planning and control in craft breweries?\",\"answer\":\"Fermentation consumes a long time and has variable duration, which introduces significant uncertainty. This uncertainty directly complicates PPC decisions.\"},{\"question\":\"What is the main goal of the thesis regarding machine learning?\",\"answer\":\"The thesis investigates whether machine learning can determine fermentation completion accurately and early enough to mitigate PPC problems caused by fermentation time uncertainty.\"},{\"question\":\"What predictive models were developed and what limited their performance?\",\"answer\":\"Four predictive models were proposed, including a neural network, two gradient boosted forests, and an automatic ML algorithm. The best models outperformed a baseline but struggled when batches deviated from normal fermentation behavior.\"}]","Fermentation Prediction through Machine Learning and its Potential Use in Production Planning and Control | PDF",1785897554,353,{"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},"fermentation-prediction-through-machine-learning-and-its-potential-use-in-production-planning-and-control","",{"@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/fermentation-prediction-through-machine-learning-and-its-potential-use-in-production-planning-and-control/125217/",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","2026-08-05",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},"Why is fermentation a critical challenge for production planning and control in craft breweries?","Question",{"text":75,"@type":76},"Fermentation consumes a long time and has variable duration, which introduces significant uncertainty. This uncertainty directly complicates PPC decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main goal of the thesis regarding machine learning?",{"text":80,"@type":76},"The thesis investigates whether machine learning can determine fermentation completion accurately and early enough to mitigate PPC problems caused by fermentation time uncertainty.",{"name":82,"@type":73,"acceptedAnswer":83},"What predictive models were developed and what limited their performance?",{"text":84,"@type":76},"Four predictive models were proposed, including a neural network, two gradient boosted forests, and an automatic ML algorithm. The best models outperformed a baseline but struggled when batches deviated from normal fermentation behavior.","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"]