Lander Ibarra

Luiz Aldeia Machado, Victor Coppo Leite, Elia Merzari et al.

Proactive maintenance strategies, such as Predictive Maintenance (PdM), play an important role in the operation of Nuclear Power Plants (NPPs), particularly due to their capacity to reduce offline time by preventing unexpected shutdowns caused by component failures. In this work, we explore the use of a Convolutional Neural Network (CNN) architecture combined with a computational thermomechanical model to calculate the temperature, stress, and strain of a Pressurized Water Reactor (PWR) fuel rod during operation. This estimation relies on a limited number of temperature measurements from the cladding's outer surface. This methodology can potentially aid in developing PdM tools for nuclear reactors by enabling real-time monitoring of such systems. The training, validation, and testing datasets were generated through coupled simulations involving BISON, a finite element-based nuclear fuel performance code, and the MOOSE Thermal-Hydraulics Module (MOOSE-THM). We conducted eleven simulations, varying the peak linear heat generation rates. Of these, eight were used for training, two for validation, and one for testing. The CNN was trained for over 1,000 epochs without signs of overfitting, achieving highly accurate temperature distribution predictions. These were then used in a thermomechanical model to determine the stress and strain distribution within the fuel rod.

Roberto Ponciroli, Andrea Rovinelli, Lander Ibarra

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. In many applications, the spatial distribution of a field needs to be carefully monitored to detect spikes, discontinuities or dangerous heterogeneities, but invasive monitoring approaches cannot be used. Besides, technical specifications about the process might not be available by preventing the adoption of an accurate model of the system. In this work, a physics-informed, data-driven algorithm that allows addressing these requirements is presented. The approach is based on the implementation of a boundary element method (BEM)-scheme within a convolutional neural network. Thanks to the capability of representing any continuous mathematical function with a reduced number of parameters, the network allows predicting the field value in any point of the domain, given the boundary conditions and few measurements within the domain. The proposed approach was applied to reconstruct a field described by the Helmholtz equation over a three-dimensional domain. A sensitivity analysis was also performed by investigating different physical conditions and different network configurations. Since the only assumption is the applicability of BEM, the current approach can be applied to the monitoring of a wide range of processes, from the localization of the source of pollutant within a water reservoir to the monitoring of the neutron flux in a nuclear reactor.