Investigation of Monte Carlo trained CNNs for neutronics predictions of typical and atypical PWR assemblies

The use of Machine Learning (ML) has gained significant attention in recent years for use in the development of surrogate models capable of predicting various neutronics parameters in Pressurized Water Reactors (PWRs). These approaches aim to provide fast and accurate approximations of conventional model outputs which are typically both computationally expensive and time-consuming to run. A novel supervised learning framework LatticeNet, employing Artificial Neural Networks (ANNs) and computer vision techniques, has been shown to be particularly useful in the prediction of assembly and pin-level parameters such as multiplication factor or pin powers. This framework was validated using deterministically-generated training data for a standard fuel assembly, representing best-case input conditions. This paper investigates the performance of LatticeNet as well as the tools developed alongside when given Monte Carlo-generated inputs and assemblies of varying pin dimensions, assessing the network's tolerance to training data uncertainty and atypical configurations.