Resources / Publications
Emily H.Kwapis (1), HongchengLiu (2), Kyle C.Hartig (1)
Progress in Nuclear Energy, 140, August 2021. DOI: 10.1016/j.pnucene.2021.103913
Machine learning; TRISO fuel; X-ray imaging; Material control and accountancy
Modern pebble-bed reactor concepts utilizing TRISO-fueled pebbles use on-line continuous refueling, where fuel pebbles are continuously circulated through the reactor core. Presently, no method exists for the tagging, identification, and tracking of individual TRISO-fueled pebbles as they enter and exit the reactor core. This leaves room for improvement in the nuclear material accountability and nuclear safeguards of TRISO-fueled pebbles. This work presents a methodology to identify individual TRISO-fueled pebbles by exploiting the unique distribution of the TRISO-coated particles, which is imprinted during the manufacturing process, within individual TRISO-fueled pebbles. By combining X-ray imaging and deep learning, our method learns a mapping from radiographic images to a compact Euclidean space where distances provide a direct measurement of the similarity of pebble radiographs. A deep convolutional neural network is trained to optimize the image mapping and triplet loss is implemented to enforce a greater distance between mappings that identify different fuel pebbles. A dataset consisting of 1,250 radiographic Monte Carlo N-Particle (MCNP) Transport simulations of unique TRISO-fueled pebbles is generated for training and testing the deep learning algorithm, which achieves an accuracy of 93.49% 9.35% and by first transforming the dataset with Gaussian blur transformations it achieves an accuracy of 98.70% 2.60%.
Dragonfly was used to perform CT data segmentation to enable a detailed quantitative analysis of samples, such as 3D mapping of volume fraction and trabecular anisotropy in bones .
(1) Nuclear Engineering Program, Department of Materials Science and Engineering, University of Florida, Gainesville, FL 32611, United States of America
(2) Department of Industrial and Systems Engineering, University of Florida, Gainesville, FL 32611, United States of America
Return to Publications list.