According to a BYU professor, Artificial Intelligence is the key to cutting years off the intricate design and licensing procedures for modern nuclear reactors. Professor of chemical engineering Matt Memmott says that, despite it sounding like something out of a science fiction film, nobody is actually giving AI the nuclear codes. The goal is to speed up the process of getting more nuclear power online.  

AI to Tackle Nuclear Reactor Design Complexity, Saving Time and Costs  

In the US, it usually takes 20 years and costs $1 billion to license a new design for a nuclear reactor. Then, it would take five more years and between $5 and $30 billion to develop the reactor. Memmott thinks that a decade or more might be cut out of the whole schedule by using AI in the time-consuming computational design process, saving millions of dollars in the process. This should be crucial given the country’s impending energy needs.  

“Our electricity demand is going to skyrocket in years to come, and we need to figure out how to produce additional power quickly,” Memmott said. “Nuclear power is the only baseload power we can make in the Gigawatt quantities needed that is completely emissions-free. Reducing the time and cost to produce and license nuclear reactors will make that power cheaper and a more viable option for environmentally friendly power to meet the future demand.”  

According to Memmott, designing and building a nuclear reactor is complex and time-consuming because it requires multi-scale efforts. Engineers deal with elements from neutrons on the quantum scale up to coolant flow and heat transfer on the macro scale. He also said there are multiple layers of physics that are “tightly coupled” in that process: the movement of neutrons is tightly coupled to the heat transfer, which is tightly coupled to materials, which is tightly coupled to the corrosion, which is coupled to the coolant flow.  

“A lot of these reactor design problems are so massive and involve so much data that it takes months for teams of people working together to resolve the issues,” he said. “When I was at Westinghouse, it took the team of neutron guys six months just to run one of their complete-core multi-physics models. And if they made a mistake two months in, then they just wasted two months of the valuable computational time, and they would have to start over.”  

Memmott found that AI may reduce that significant time burden and increase power generation to satisfy growing demand and keep electricity prices low for average users. In recent years, rising electricity bills have caused difficulty for homeowners and renters nationwide.  

AI Cuts Nuclear Reactor Design Time from Months to Days  

For his research, he and his BYU colleagues built a dozen machine-learning algorithms to examine their ability to process the simulated data needed to design a reactor. They identified the top three algorithms, then refined the parameters until they found one that worked really well and could handle a preliminary data set as a proof of concept. It worked, so they tested the model on a challenging nuclear design problem: optimal nuclear shield design.  

The resulting papers, recently published in the academic journal Nuclear Engineering and Design, showed that their refined model can geometrically optimize the design elements much faster than the traditional method. For example, it took Memmott’s AI algorithm just two days to develop an optimal shield design for a nuclear reactor, while local molten salt reactor company Alpha Tech Research Corp. took six months to do the same.  

“When you look at nuclear reactor design, you have this huge design space of possibilities — it’s as if you have people combing through this mile-wide area looking for the right reactor design,” Memmott said. “Now AI can help those people focus on that little quarter-sized sweet spot of design, drastically reducing the search time. Of course, humans still ultimately make the final design decisions and carry out all the safety assessments, but it saves a significant amount of time at the front end.”  

Fellow BYU researchers include Andrew Larsen, Ross Lee, Braden Clayton, Edwards Mercado, Ethan Wright, Brent Edgerton, Brian Gonda and chemical engineering professor John Hedengren. Collaborators from Alpha Tech, Caden Wilson and John Benson, also contributed their efforts to the research. 

Source: Brigham Young University