The advanced reactors group in the nuclear engineering department works on the design and analysis of next generation nuclear reactors with the aim to improve resource utilization and minimize waste.
Pebble bed reactors use fuel in the form of sphere (aka pebbles). A reactor core is composed of hundreds of thousands of these pebbles that are continuously circulated in and out of the reactor, and discarded and replaced with new pebbles as needed. Modeling and simulation allow us to know everything about each of the pebbles, but in reality a very limited set of data will be available. In this project, we would like to use ML to predict the behavior of the reactor based on the operational data and using the synthetic data for training. This work will have a direct impact on the operation of pebble bed reactors that are expected to be deployed in the next 3-5 years.
