arXiv · 2310.08767
Modeling Fission Gas Release at the Mesoscale using Multiscale DenseNet Regression with Attention Mechanism and Inception Blocks
Abstract
Mesoscale simulations of fission gas release (FGR) in nuclear fuel provide a powerful tool for understanding how microstructure evolution impacts FGR, but they are computationally intensive. In this study, we present an alternate, data-driven approach, using deep learning to predict instantaneous FGR flux from 2D nuclear fuel microstructure images. Four convolutional neural network (CNN) architectures with multiscale regression are trained and evaluated on simulated FGR data generated using a hybrid phase field/cluster dynamics model. All four networks show high predictive power, with $R^{2}$ values above 98%. The best performing network combine a Convolutional Block Attention Module (CBAM) and InceptionNet mechanisms to provide superior accuracy (mean absolute percentage error of 4.4%), training stability, and robustness on very low instantaneous FGR flux values.
Explore related subjects
Keep this discovery
Peter Toma, Md Ali Muntaha, Joel B. Harley, Michael R. Tonks. 2023-10-12. Modeling Fission Gas Release at the Mesoscale using Multiscale DenseNet Regression with Attention Mechanism and Inception Blocks. https://arxiv.org/abs/2310.08767
Cite the original work for its findings. Save a collection to share your selection of sources.