Master Thesis - Optimizing UO2 pellet production process Introduction
Västerås, SE
At Westinghouse Electric Company, we are pioneers in nuclear technology and our technology is the basis for nearly half of the world's commercial nuclear power plants in operation. Today, we are also building several new reactors that contribute to more fossil-free energy. Globally, we have over 10,000 employees in 19 countries, of which 1,000 are at our Swedish workplaces in Västerås and Täby. Our Swedish operations were founded in 1969 and supply nuclear fuel as well as products and services in automation, maintenance, testing and decommissioning for customers around the world. Read more about us www.westinghousenuclear.com.
Master thesis - Optimizing UO2 pellet production process
Introduction
Westinghouse Electric Sweden AB is offering a master thesis project that addresses real-world challenges in nuclear fuel production. This project focuses on using machine learning to optimize the production process of UO2 pellets by developing a ranking system for various powder parameters that influence the addition of U3O. And developing an Artificial Intelligence (AI) model to predict the amount of U3O8 addition.
In the practical setting of UO2 pellet production, U3O8 serves as a pore-former, impacting the final density of the pellets. Variations in powder characteristics can lead to inconsistencies U3O8 amount that a powder can take, posing significant challenges in maintaining production plan and standards. By applying machine learning to analyze and rank these parameters, this project aims to provide actionable insights that will directly enhance production efficiency and product consistency.
Objectives
- UO2 powder and pellets data collection from production.
- Employ machine learning techniques to analyze production data and identify key powder parameters.
- Develop a ranking system to determine which parameters most significantly affect the addition of U3O8 in UO2 pellets.
- Generate an AI model to give recommendations for U3O8 addition.
Candidate Requirements
We seek a master’s student with a background in nuclear engineering, material science, data science, or related fields. The ideal candidate will have experience with machine learning and a strong interest in solving real-world manufacturing problems.
Familiarity with data analysis, python or similar tools and a proactive approach to applying theoretical knowledge to practical challenges are essential. Very good knowledge in English, both writing and speaking is necessary and knowledge in Swedish are meritorious. You are also expected to be able to commute to Västerås during the master thesis work when needed.
Details
This master thesis project will be conducted in partnership with KTH and Westinghouse. It is positive if you are a student at KTH for this master thesis. The student will have opportunities to visit Westinghouse’s facilities in Västerås as part of the research. The project is set to start in the beginning of 2025 and should be completed by the end of the semester.
Westinghouse reimburses the student for an approved Master Thesis of 30 credits.
Security clearance is carried out as part of the recruitment process.
If you would like to have more information, please contact Zhongwen Chang by email: zhongwen.chang@westinghouse.com.
We offer
At Westinghouse, we offer an inspiring work environment in a high-tech industry. You will be a part of a network of global experts from several different areas and we offer great opportunities for competence development and career growth, both in Sweden and abroad.
As a member of our team, you will work together with engaged colleagues and be a part of an environment that is both challenging and supportive. Many of our positions are based in activity-based environments which enables a flexible workplace.
At Westinghouse, we have a strong safety culture. Our business is covered by the union agreement Teknikavtalet and local agreements.
Job Segment:
Nuclear Engineering, Nuclear, Security Clearance, Industrial, Engineer, Engineering, Energy, Government, Manufacturing