An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel

Sun, Shoukun; Xu, Fei; Cai, Lu; Salvato, Daniele; Dilemma, Fidelma; Capriotti, Luca; Xian, Min; Yao, Tiankai

doi:10.1038/s41598-023-47914-y

Title: An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel

Journal Article · 14 December 2023 · Scientific Reports

DOI: https://doi.org/10.1038/s41598-023-47914-y · OSTI ID:2229966

Sun, Shoukun ^[1]; Xu, Fei ^[2]; Cai, Lu ^[2]; Salvato, Daniele ^[2]; Dilemma, Fidelma ^[2]; Capriotti, Luca ^[2]; Xian, Min ^[1]; Yao, Tiankai ^[2]

Univ. of Idaho, Idaho Falls, ID (United States)
Idaho National Laboratory (INL), Idaho Falls, ID (United States)

Gaseous fission products from nuclear fission reactions tend to form fission gas bubbles of various shapes and sizes inside nuclear fuel. The behavior of fission gas bubbles dictates nuclear fuel performances, such as fission gas release, grain growth, swelling, and fuel cladding mechanical interaction. Although mechanical understanding of the overall evolution behavior of fission gas bubbles is well known, lacking the quantitative data and high-level correlation between burnup/temperature and microstructure evolution blocks the development of predictive models and reduces the possibility of accelerating the qualification for new fuel forms. Historical characterization of fission gas bubbles in irradiated nuclear fuel relied on a simple threshold method working on low-resolution optical microscopy images. Advanced characterization of fission gas bubbles using scanning electron microscopic images reveals unprecedented details and extensive morphological data, which strains the effectiveness of conventional methods. This paper proposes a hybrid framework, based on digital image processing and deep learning models, to efficiently detect and classify fission gas bubbles from scanning electron microscopic images. The developed bubble annotation tool used a multitask deep learning network that integrates U-Net and ResNet to accomplish instance-level bubble segmentation. With limited annotated data, the model achieves a recall ratio of more than 90%, a leap forward compared to the threshold method. The model has the capability to identify fission gas bubbles with and without lanthanides to better understand the movement of lanthanide fission products and fuel cladding chemical interaction. Lastly, the deep learning model is versatile and applicable to the micro-structure segmentation of similar materials.

View Journal Article

Cite

Export

Save

Research Organization:: Idaho National Laboratory (INL), Idaho Falls, ID (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy (NE), Nuclear Fuel Cycle and Supply Chain. Advanced Fuel Campaign; USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: AC07-05ID14517; 22A1059-094FP; 2899

OSTI ID:: 2229966

Alternate ID(s):: OSTI ID: 2337837

Report Number(s):: INL/JOU-23-71121-Rev001; TRN: US2410384

Journal Information:: Scientific Reports, Vol. 13, Issue 1; ISSN 2045-2322

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

References (35)

Metallic fuels for advanced reactors Carmack, W. J.; Porter, D. L.; Chang, Y. I. Journal of Nuclear Materials, Vol. 392, Issue 2 https://doi.org/10.1016/j.jnucmat.2009.03.007	journal	July 2009
Fuels for sodium-cooled fast reactors: US perspective Crawford, Douglas C.; Porter, Douglas L.; Hayes, Steven L. Journal of Nuclear Materials, Vol. 371, Issue 1-3 https://doi.org/10.1016/j.jnucmat.2007.05.010	journal	September 2007
U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28	book	November 2015
Flood-fill algorithms used for passive acoustic detection and tracking Nosal, Eva-Marie 2008 New Trends for Environmental Monitoring Using Passive Systems https://doi.org/10.1109/PASSIVE.2008.4786975	conference	October 2008
Materials challenges in nuclear energy Zinkle, S. J.; Was, G. S. Acta Materialia, Vol. 61, Issue 3 https://doi.org/10.1016/j.actamat.2012.11.004	journal	February 2013
The advanced characterization, post-irradiation examination, and materials informatics for the development of ultra high-burnup annular U-10Zr metallic fuel Yao, Tiankai; Bachhav, Mukesh; Di Lemma, Fidelma G. Frontiers in Nuclear Engineering, Vol. 1 https://doi.org/10.3389/fnuen.2022.1050262	journal	June 2023
Metallic Fuel Performance Benchmarks for Versatile Test Reactor Applications Hirschhorn, Jacob A.; Powers, Jeffrey J.; Greenquist, Ian Nuclear Science and Engineering https://doi.org/10.1080/00295639.2022.2043539	journal	March 2022
Post-irradiation characterization of a high burnup mixed oxide fuel rod with minor actinides Frazer, D.; Cappia, F.; Harp, J. M. Journal of Nuclear Materials, Vol. 562 https://doi.org/10.1016/j.jnucmat.2022.153545	journal	April 2022
Experimentally Known Properties of U-10Zr Alloys: A Critical Review Janney, Dawn E.; Hayes, Steven L. Nuclear Technology, Vol. 203, Issue 2 https://doi.org/10.1080/00295450.2018.1435137	journal	April 2018
Postirradiation characterization of palladium as an additive for fuel cladding chemical interaction mitigation in metallic fuel Di Lemma, Fidelma G.; Trowbridge, Tammy M.; Capriotti, Luca Journal of Nuclear Materials, Vol. 558 https://doi.org/10.1016/j.jnucmat.2021.153403	journal	January 2022
Microsoft COCO: Common Objects in Context Lin, Tsung-Yi; Maire, Michael; Belongie, Serge ECCV 2014: Computer Vision – ECCV 2014 https://doi.org/10.1007/978-3-319-10602-1_48	book	January 2014
Fuel cladding chemical interaction in metallic sodium fast reactor fuels: A historical perspective Keiser, Dennis D. Journal of Nuclear Materials, Vol. 514 https://doi.org/10.1016/j.jnucmat.2018.09.045	journal	February 2019
α-U and ω-UZr2 in neutron irradiated U-10Zr annular metallic fuel Yao, Tiankai; Capriotti, Luca; Harp, Jason M. Journal of Nuclear Materials, Vol. 542 https://doi.org/10.1016/j.jnucmat.2020.152536	journal	December 2020
Impact of uranium oxide (UO2) fuel with molybdenum (Mo) inserts on pressurized water reactor performance and safety Gorton, Jacob P.; Schappel, Daniel; Nelson, Andrew T. Journal of Nuclear Materials, Vol. 542 https://doi.org/10.1016/j.jnucmat.2020.152492	journal	December 2020
Machine learning in nuclear materials research Morgan, Dane; Pilania, Ghanshyam; Couet, Adrien Current Opinion in Solid State and Materials Science, Vol. 26, Issue 2 https://doi.org/10.1016/j.cossms.2021.100975	journal	April 2022
Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation Tajbakhsh, Nima; Jeyaseelan, Laura; Li, Qian Medical Image Analysis, Vol. 63 https://doi.org/10.1016/j.media.2020.101693	journal	July 2020
A Computational Approach to Edge Detection Canny, John IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, Issue 6 https://doi.org/10.1109/TPAMI.1986.4767851	journal	November 1986
Adaptive Pyramid Context Network for Semantic Segmentation He, Junjun; Deng, Zhongying; Zhou, Lei 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2019.00770	conference	June 2019
Automated defect analysis in electron microscopic images Li, Wei; Field, Kevin G.; Morgan, Dane npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0093-8	journal	July 2018
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
Deep learning-based automated image segmentation for concrete petrographic analysis Song, Yu; Huang, Zilong; Shen, Chuanyue Cement and Concrete Research, Vol. 135 https://doi.org/10.1016/j.cemconres.2020.106118	journal	September 2020
An approach to fuel development and qualification Crawford, Douglas C.; Porter, Douglas L.; Hayes, Steven L. Journal of Nuclear Materials, Vol. 371, Issue 1-3 https://doi.org/10.1016/j.jnucmat.2007.05.029	journal	September 2007
Out-of-pile and postirradiated examination of lanthanide and lanthanide-palladium interactions for metallic fuel Benson, Michael T.; Harp, Jason M.; Xie, Yi Journal of Nuclear Materials, Vol. 544 https://doi.org/10.1016/j.jnucmat.2020.152727	journal	February 2021
Understanding fission gas bubble distribution, lanthanide transportation, and thermal conductivity degradation in neutron-irradiated α-U using machine learning Cai, Lu; Xu, Fei; Di Lemma, Fidelma Giulia Materials Characterization, Vol. 184 https://doi.org/10.1016/j.matchar.2021.111657	journal	February 2022
Image Segmentation Using Deep Learning: A Survey Minaee, Shervin; Boykov, Yuri Y.; Porikli, Fatih IEEE Transactions on Pattern Analysis and Machine Intelligence https://doi.org/10.1109/TPAMI.2021.3059968	journal	January 2021
Recent trends in metallic fast reactor fuels research Aitkaliyeva, Assel Journal of Nuclear Materials, Vol. 558 https://doi.org/10.1016/j.jnucmat.2021.153377	journal	January 2022
A deep learning based automatic defect analysis framework for In-situ TEM ion irradiations Shen, Mingren; Li, Guanzhao; Wu, Dongxia Computational Materials Science, Vol. 197 https://doi.org/10.1016/j.commatsci.2021.110560	journal	September 2021
The Pascal Visual Object Classes (VOC) Challenge Everingham, Mark; Van Gool, Luc; Williams, Christopher K. I. International Journal of Computer Vision, Vol. 88, Issue 2 https://doi.org/10.1007/s11263-009-0275-4	journal	September 2009
Advanced characterization-informed machine learning framework and quantitative insight to irradiated annular U-10Zr metallic fuels Xu, Fei; Cai, Lu; Salvato, Daniele Scientific Reports, Vol. 13, Issue 1 https://doi.org/10.1038/s41598-023-35619-1	journal	June 2023
Lanthanides in metallic nuclear fuels: Their behavior and methods for their control Mariani, R. D.; Porter, D. L.; O’Holleran, T. P. Journal of Nuclear Materials, Vol. 419, Issue 1-3 https://doi.org/10.1016/j.jnucmat.2011.08.036	journal	December 2011
Radial microstructural evolution in low burnup fast reactor MOX fuel Parrish, Riley J.; Liu, Xiang; Winston, Alexander Journal of Nuclear Materials, Vol. 523 https://doi.org/10.1016/j.jnucmat.2019.06.009	journal	September 2019
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations Sudre, Carole H.; Li, Wenqi; Vercauteren, Tom Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support https://doi.org/10.1007/978-3-319-67558-9_28	book	January 2017
25-Pin metallic fuel performance benchmark case based on the EBR-II X430 experiments series Greenquist, Ian; Powers, Jeffrey J. Journal of Nuclear Materials, Vol. 556 https://doi.org/10.1016/j.jnucmat.2021.153211	journal	December 2021
Fuel Performance Design Basis for the Versatile Test Reactor Porter, D. L.; Crawford, D. C. Nuclear Science and Engineering, Vol. 196, Issue sup1 https://doi.org/10.1080/00295639.2021.2009983	journal	January 2022
A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations Morgan, Dane; Shen, Mingren Materials Data Facility https://doi.org/10.18126/n9dj-5mk0	dataset	January 2020

Similar Records

A fine pore-preserved deep neural network for porosity analytics of a high burnup U-10Zr metallic fuel

Journal Article · 2023 · Scientific Reports · OSTI ID:2229931

Wang, Haotian; Xu, Fei; Cai, Lu; +5 more

Quantitative Insight to Fission Gas Bubble Distribution in Irradiated Annular U-10Zr Metallic Fuel Using Deep Learning

Conference · 2023 · OSTI ID:2462697

Tang, Yalei; Yao, Tiankai; Xu, Fei

Quantitative Insight to Fission Gas Pores Distribution in Irradiated Annular U-10Zr Metallic Fuel Using Machine Learning

Conference · 2024 · OSTI ID:2458201

Yao, Tiankai; Tang, Yalei; Xu, Fei

Related Subjects

36 MATERIALS SCIENCE
U-10Zr
Nuclear fuel
Fission gas bubble
Lanthanide migration
Deep learning

Title: An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel

Citation Formats

References (35)

Similar Records

Related Subjects