Vis enkel innførsel

dc.contributor.advisorKristian Hovde Liland
dc.contributor.advisorIngrid Måge
dc.contributor.authorUthayaseelan, Melvin
dc.date.accessioned2024-08-23T16:31:19Z
dc.date.available2024-08-23T16:31:19Z
dc.date.issued2024
dc.identifierno.nmbu:wiseflow:7110333:59110577
dc.identifier.urihttps://hdl.handle.net/11250/3148064
dc.description.abstractAs the world rapidly advances with groundbreaking technology, the food sector is no exception. Artificial intelligence is increasingly utilized in the food industry to enhance production and quality. However, ensuring quality in the food industry can be challenging due to environmental factors such as fluctuations in temperature and humidity levels, as well as changes in raw material sources. To guarantee high quality and safety standards, it is crucial to develop systems that monitor and regulate these variables, ensuring that consumers receive safe and enjoyable food products. This master thesis delves into applying machine learning and optimization techniques to predict the dry matter content and optimize the quality and production of Norvegia cheese at Tine Jæren. Dry matter plays a critical role in determining the quality of Norvegia cheese, affecting its flavor and texture significantly. The optimal dry matter content for Norvegia cheese should be between 57.6\% and 57.7\%, as it ensures the highest quality and customer satisfaction. The study developed machine learning models that can be used to gain insights from data and predict dry matter content. Different feature selection techniques were employed to identify the variables affecting dry matter content and refine the predictive models. The optimal models will be integrated as a predictive component into an optimization model utilizing an evolutionary algorithm to optimize and enhance the production and dry matter content of fresh Norvegia cheese. This approach optimizes essential dry matter parameters affecting dry matter to improve quality and production efficiency while ensuring customers receive safe and enjoyable food products. The best optimization model developed in this study has been integrated into a user-friendly website tailored for industry application. This website serves as both a prototype and a demonstration of how the optimization model can be implemented in daily operations. This approach can help manage resources and minimize waste, a crucial factor in sustainable food production. In summary, the application of machine learning and optimization techniques to predict dry matter content and optimize the quality and production of Norvegia cheese has the potential to improve the food industry and pave the way for more sustainable and efficient food production practices.
dc.description.abstract
dc.languageeng
dc.publisherNorwegian University of Life Sciences
dc.titleData-driven optimization of an industrial cheese production process
dc.typeMaster thesis


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel