Prototyping of a Machine Learning-Based Burnup Measurement Capability for Pebble Bed Reactor Fuel

The pebble bed reactor is a unique reactor design due to its capacity for continuous multipass circulation of the fuel elements, without causing interruption to reactor operation, with the assistance of the burnup measurement system. Such a system necessarily requires an accurate knowledge of the burnup of each fuel pebble upon ejection from the core so as to inform the reloading decision and to ensure that no pebble exceeds the regulated discharge burnup limit at any point following reinsertion into the reactor core. In this work, we conceptualize, develop, and demonstrate a machine learning-based fuel burnup prediction framework leveraging advanced modeling and simulation capabilities. At its core, machine learning regression models are learned from simulated data to establish the correlation among the irradiated fuel composition (hence burnup), the gamma leakage spectrum, and the gamma spectroscopy results. Sensitivity analysis is conducted to quantify the impact of unknown design parameters, such as fuel enrichment, and irradiation environment, including power density, temperature, and neighboring materials, on the prediction accuracy of various supervised regression algorithms. The effects of a short cooldown period on machine learning prediction accuracy are also investigated. A test data set is used to validate that the data generation methodology proposed in this work successfully results in a machine learning model capable of interpolating its prediction of burnup onto a much wider range of irradiation conditions than were explicitly represented in the training database. The inclusion of a cooldown period of just 2 h leads to a prediction root-mean-square error of <5 MWd/kgU when the fuel enrichment is known and <9 MWd/kgU otherwise.