Abstract
Microreactors could play a crucial role in decarbonizing our energy portfolio. However, their development and implementation come with specific challenges. Due to their compact size and the harsh operational environment, collecting real-time data on reactor operations can be challenging. Many probe designs cannot withstand extreme conditions (i.e. temperature, radiation) in the reactor. In this context, using Convolutional Neural Networks (CNN) can pave the way for developing a non-intrusive approach that relies solely on ex-core sensors. A well-trained physics-informed CNN can reconstruct the distribution of a given physical quantity over a domain using only a few sensors, allowing us to reconstruct the desired field distribution even in a limited space or complex geometries. In this work, we present the initial steps toward developing a real-time tool for monitoring the thermomechanical behavior of nuclear reactor pressure vessels. Based on an experimental setup, a computational model using the Multiphysics Object-Oriented Simulation Environment framework was built to evaluate the temperature and strain distribution over a convex metal surface heated through radiative heat transfer. This surface represents a section of a nuclear reactor vessel wall. In-situ experimental data from a Texas A&M facility were used to validate the computational model. Part of the data generated by the MOOSE model was used to train the Convolutional Neural Network to reconstruct the vessel wall's outer surface temperature. The CNN generalization was then compared against the experimental and computational data.
This work was supported by the U.S. Department of Energy, Office of Nuclear Energy. The submitted manuscript was created by UChicago Argonne, LLC, operator of Argonne National Laboratory. Argonne, a DOE Office of Science laboratory, is operated under contract DE-AC02-06CH11357.
