Artificial Intelligence to Accelerate the Construction of Nuclear Reactors

Matthew Memmott, professor at Brigham Young University, has figured out a way to cut years of complicated calculations during the design and licensing of modern nuclear reactors using artificial intelligence (AI). According to the professor, the use of AI in the computational design process can halve the licensing term for a new nuclear reactor.

For this research, Matthew Memmott and his team built a dozen machine learning algorithms. 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 proof of a concept. The researchers tested it on a very difficult nuclear design problem: optimal nuclear shield design. From the technical point of view, the research proves the concept of replacing a portion of the required thermal hydraulic and neutronics simulations with a trained machine learning model to predict temperature profiles based on geometric reactor parameters that are variable, and then optimizing those parameters.

The results showed that the AI model can geometrically optimize the design elements much faster. For example, it took only 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.

Therefore, AI can help to focus on the calculation part of the design. Of course, people will make final design decisions and will perform all safety assessments, but this will save a significant amount of time at the front end.