Constellation moves tens of thousands of nuclear fuel bundles every year, which requires a cross-trained staff of operators performing a series of challenging tasks with varying expertise. Students on the Constellation team will model the process of moving fuel bundles based on data from 50,000 historical fuel moves. The model will be used to optimize future performance, and enhance operator training.
Abstract:
Each year, Constellation moves 10,000 – 20,000 nuclear fuel bundles within reactors to balance reactor performance. Each move is extremely costly, requiring shutdown of the reactor over several days. Fuel moves require a team of operators to perform a series of challenging tasks, some in 20 – 60’ of water. Jobs are rotated among teams of operators who have varying levels of experience/expertise for specific tasks and experience working with each other.
Constellation would like to better understand the parameters that minimize down-time in their fuel moves. Small improvements in efficiency would results in significant savings. They have a historical database of 50,000 fuel moves, with information such as type of move, equipment operator, supervisor, total time to complete the move, downtime, and more.
Students on the Constellation team will evaluate historical performance data to better explain (ideally, quantitatively model) the time to completion in fuel moves. Constellation is particularly interested in understanding the optimal, historical performance conditions, and identifying where strategic operator training or task assignment could improve future performance.
Impact:
Each movement of nuclear fuel bundles requires about 96 hours of reactor outage. Every hour is extremely valuable, so even small improvements in efficiency would impact the financial bottom line.
A tool that could help categorize and/or predict performance, optimize staff assignments, and/or target areas to prioritize training resources would be a very valuable asset to Constellation’s strategic management and planning.
Scope:
Minimum Viable Product Deliverable (Minimum level of success)
- Understand the current fuel move process
- Complete a literature and background review of relevant literature and current best practice
- Complete classification of historical dataset and develop an appropriate database to support evaluation efforts
- Build a simple data interface for the historical dataset, supporting scenario evaluation that allows for future updating and ongoing analysis after project completion
- Identify potential evaluation techniques, and prioritize with mentors
- Identify most important factors driving efficiency, and formulate a predictive model
Expected Final Deliverable (Expected level of success)
- Validate and refine the predictive model
- Identify recommended strategies for improvement
Stretch Goal Opportunities: (High level of success)
- Customized report generation with recommendations for training plans
- GUI front end development for easier use
- Automated data uploading
Below are the skills needed for this project. Students with the following relevant skills and interest, regardless of major, are encouraged to apply! This is a team based multidisciplinary project. Students on the team are not expected to have experience in all areas, but should be willing to learn and will be asked to perform a breadth of tasks throughout the two semester project.
Data Modeling and Tool Development (3-4 Students)
Specific Skills: Data Modeling, Database design, algorithm implementation
Likely Majors: DATA, IOS, CSE, CS-LSA
Manufacturing Quality Control Techniques (1-2 Students)
Specific Skills: Quality control, process evaluation.
Note: These students will also participate in data modeling
Likely Majors: IOE, ISD
Nuclear Reactor Knowledge (1-2 Students)
Specific Skills: Domain knowledge of nuclear reactors and nuclear power industry
Note: These students will also participate in data modeling
Likely Majors: NERS
Additional Desired Skills/Knowledge/Experience
- Note: All students on the project will participate in data analysis, modeling, and evaluation Students should have experience with some type of data analysis platform (e.g., MatLab, Jupyter Notebooks, Python, etc.) Please indicate your experience in your personal statement/resume
- Interest in nuclear power and clean energy generation
- Successful team-based engineering experience. We particularly value engineering competition team and/or large group research experience
- A proactive approach to problem solving
- Leadership skills (any situation is relevant)
- Practical experience analyzing large real-world data sets
Sponsor Mentor
Ryan Pullara
Ryan has a B.S. in Nuclear, Plasma, and Radiological Engineering from the University of Illinois at Champaign-Urbana. Ryan has spent the last 4 years at Constellation, primarily as a Nuclear Fuels Engineer, and has recently transitioned roles to be the Braidwood Site Reactor Services Manager. Ryan has extensive experience in project management and is a strong advocate for innovation of any kind in the nuclear field.
Executive Mentor
James M. DuBay
Senior Director of Reactor Services
Jim has a B.S. in Nuclear Engineering and Radiological Sciences from the University of Michigan, and an MBA from CU Boulder. He has spent 23 years working in the Nuclear Power Industry, and has worked for 3 of the largest companies in the space (GE, Westinghouse, and Constellation), with a focus primarily on the physical aspects of maintaining the safe operation of Nuclear Reactors. Jim has a passion for innovating to increase reliability and reducing risk, and has the responsibility for the safe execution of all maintenance on or in the 21 nuclear reactors that operate in the Constellation fleet.
Faculty Mentor
Professor Yang Zhang (YZ)
Nuclear Engineering & Radiological Sciences
YZ’s research can be summarized into two words: Matter and Machine. On the basic science side, his group synergistically combines and pushes the boundaries of accelerated molecular simulations, statistical and stochastic thermodynamic theories, and neutron scattering experiments, with the goal of significantly extending our understanding of a wide range of long timescale phenomena, rare events, and far-from-equilibrium properties of materials from the atomic and molecular level. Particular emphasis is given to the physics and chemistry of liquids and complex fluids, especially at interfaces, driven away from equilibrium, or under extreme conditions. On the applied research side, leveraging their expertise in materials and modeling, his group advances the development of swarm robots and collective intelligence, robots in extreme environments, soft robots and human-compatible machines, and understandable artificial intelligence, which can lead to immediate societal impact.
Weekly Meetings: During the winter 2025 semester, the Constellation team will meet on Mondays from 3-5pm. Location TBD.
Work Location: Most of the work will take place on campus in Ann Arbor in various locations.
Course Substitutions: CS Capstone/MDE, CE MDE, ChE Elective, Data Science MDE/Capstone, EE MDE, CoE Honors, IOE Senior Design, NERS 499, SI Elective/Cognate
Citizenship Requirements: Due to Constellation facility access requirements, this project is open to US Citizens or Permanent Residents only.
IP/NDA: Students will sign IP/NDA documents that are unique to Constellation.
Summer Project Activities: No summer activity will take place on the project.
Learn more about the expectations for this type of MDP project
If you have any of these characteristics, highlight them on your Experience and Interest Form and talk about them in your (optional) one way video interview.