An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
14 Dec 2023
14 Dec 2023
Historique:
received:
04
05
2023
accepted:
20
11
2023
medline:
15
12
2023
pubmed:
15
12
2023
entrez:
14
12
2023
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 38097620
doi: 10.1038/s41598-023-47914-y
pii: 10.1038/s41598-023-47914-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22275Subventions
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Organisme : U.S. Department of Energy
ID : 22A1059-094FP
Informations de copyright
© 2023. The Author(s).
Références
Zinkle, S. J. & Was, G. S. Materials challenges in nuclear energy. Acta Mater. 61(3), 735–758. https://doi.org/10.1016/j.actamat.2012.11.004 (2013).
doi: 10.1016/j.actamat.2012.11.004
Guérin, Y. 2.21–Fuel Performance of Fast Spectrum Oxide Fuel (Elsevier, 2012).
Gorton, J. P., Schappel, D., Nelson, A. T. & Brown, N. R. Impact of uranium oxide (UO2) fuel with molybdenum (Mo) inserts on pressurized water reactor performance and safety. J. Nucl. Mater. 542, 152492. https://doi.org/10.1016/j.jnucmat.2020.152492 (2020).
doi: 10.1016/j.jnucmat.2020.152492
Parrish, R. J., Liu, X., Winston, A.J., Harp, J. M., & Aitkaliyeva, A. Radial microstructural evolution in low burnup fast reactor MOX fuel. J. Nucl. Mater. https://api.semanticscholar.org/CorpusID:197157107 . (2019).
Frazer, D. M., Cappia, F., Harp, J. M., Medvedev, P., Mcclellan, K., Voit, S.L., Giglio, J. J., Jädernäs, D., & Hosemann, P. Post-irradiation characterization of a high burnup mixed oxide fuel rod with minor actinides. J. Nucl. Mater. https://api.semanticscholar.org/CorpusID:246419921 . (2022).
Porter, D. L. & Crawford, D. C. Fuel performance design basis for the versatile test reactor. Nucl. Sci. Eng. 196, 110–122. https://doi.org/10.1080/00295639.2021.2009983 (2022).
doi: 10.1080/00295639.2021.2009983
Crawford, D. C., Porter, D. L. & Hayes, S. L. Fuels for sodium-cooled fast reactors: US perspective. J. Nucl. Mater. 371(1–3), 202–231. https://doi.org/10.1016/j.jnucmat.2007.05.010 (2007).
doi: 10.1016/j.jnucmat.2007.05.010
Crawford, D. C. et al. An approach to fuel development and qualification. J. Nucl. Mater. 371(1–3), 232–242. https://doi.org/10.1016/j.jnucmat.2007.05.029 (2007).
doi: 10.1016/j.jnucmat.2007.05.029
Carmack, W. J. et al. Metallic fuels for advanced reactors. J. Nucl. Mater. 392, 139–150. https://doi.org/10.1016/j.jnucmat.2009.03.007 (2009).
doi: 10.1016/j.jnucmat.2009.03.007
Aitkaliyeva, A. Recent trends in metallic fast reactor fuels research. J. Nucl. Mater. 558, 153377 (2021).
doi: 10.1016/j.jnucmat.2021.153377
Cassagne, T., Marchebois, H., & Mesquita, T. A review of hydrogen embrittlement of nickel-based alloys for oil and gas applications. CORROSION, (2021).
Greenquist, I. & Powers, J. J. 25-Pin metallic fuel performance benchmark case based on the EBR-II X430 experiments series. J. Nucl. Mater. 556, 153211. https://doi.org/10.1016/j.jnucmat.2021.153211 (2021).
doi: 10.1016/j.jnucmat.2021.153211
Hirschhorn, J. A. et al. Metallic fuel performance benchmarks for versatile test reactor applications. Nucl. Sci. Eng. 196(sup1), 123–147 (2022).
doi: 10.1080/00295639.2022.2043539
Janney, D. E. & Hayes, S. L. Experimentally known properties of U-10Zr alloys: a critical review. Nucl. Technol. 203, 109–128. https://doi.org/10.1080/00295450.2018.1435137 (2018).
doi: 10.1080/00295450.2018.1435137
Yao, T. et al. The advanced characterization, post-irradiation examination, and materials informatics for the development of ultra high-burnup annular U-10Zr metallic fuel. Front. Nucl. Eng. 1, 1050262. https://doi.org/10.3389/fnuen.2022.1050262 (2023).
doi: 10.3389/fnuen.2022.1050262
Cai, L. et al. Understanding fission gas bubble distribution, lanthanide transportation, and thermal conductivity degradation in neutron-irradiated α-U using machine learning. Mater. Charact. 184, 111657. https://doi.org/10.1016/j.matchar.2021.111657 (2022).
doi: 10.1016/j.matchar.2021.111657
Ogata, T. Comprehensive Nuclear Materials 2nd edn, 1–42 (Elsevier, 2020).
doi: 10.1016/B978-0-12-803581-8.11678-9
Mariani, R. D., Porter, D. L., O’Holleran, T. P., Hayes, S. L. & Kennedy, J. R. Lanthanides in metallic nuclear fuels: their behavior and methods for their control. J. Nucl. Mater. 419(1–3), 263–271 (2011).
doi: 10.1016/j.jnucmat.2011.08.036
Di Lemma, F. G. et al. Postirradiation characterization of palladium as an additive for fuel cladding chemical interaction mitigation in metallic fuel. J. Nucl. Mater. https://doi.org/10.1016/j.jnucmat.2021.153403 (2022).
doi: 10.1016/j.jnucmat.2021.153403
Keiser, D. D. Fuel cladding chemical interaction in metallic sodium fast reactor fuels: a historical perspective. J. Nucl. Mater. 514, 393–398. https://doi.org/10.1016/j.jnucmat.2018.09.045 (2019).
doi: 10.1016/j.jnucmat.2018.09.045
Benson, M. T. et al. Out-of-pile and post irradiated examination of lanthanide and lanthanide-palladium interactions for metallic fuel. J. Nucl. Mater. 544, 152727 (2021).
doi: 10.1016/j.jnucmat.2020.152727
Yao, T. et al. α-U and ω-UZr2 in neutron irradiated U-10Zr annular metallic fuel. J. Nucl. Mater. 542, 152536 (2020).
doi: 10.1016/j.jnucmat.2020.152536
Morgan, D. et al. Machine learning in nuclear materials research. Curr. Opin. Solid State Mater. Sci. 26(2), 100975 (2022).
doi: 10.1016/j.cossms.2021.100975
Shen, M. et al. A deep learning based automatic defect analysis framework for In-situ TEM ion irradiations. Comput. Mater. Sci. 197, 110560. https://doi.org/10.1016/j.commatsci.2021.110560 (2021).
doi: 10.1016/j.commatsci.2021.110560
Li, W., Field, K. G. & Morgan, D. Automated defect analysis in electron microscopic images. NPJ Comput. Mater. 4, 36. https://doi.org/10.1038/s41524-018-0093-8 (2018).
doi: 10.1038/s41524-018-0093-8
Minaee, S. et al. Image segmentation using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3523–3542. https://doi.org/10.1109/TPAMI.2021.3059968 (2022).
doi: 10.1109/TPAMI.2021.3059968
pubmed: 33596172
He, J., Deng, Z., Zhou, L., Wang, Y., & Qiao, Y., Adaptive pyramid context network for semantic segmentation, Proc. Conference on Computer Vision and Pattern Recognition 7519–7528 (2019).
Tajbakhsh, N. et al. Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Med. Image Anal. 63, 101693 (2020).
doi: 10.1016/j.media.2020.101693
pubmed: 32289663
Song, Y., Huang, Z., Shen, C., Shi, H. & Lange, D. A. Deep learning-based automated image segmentation for concrete petrographic analysis. Cem. Concr. Res. 135, 106118 (2020).
doi: 10.1016/j.cemconres.2020.106118
He, K., Gkioxari, G., Dollár, P., & Girshick, R., Mask r-cnn, Proc. of the IEEE international conference on computer vision, 2961–2969 (2017).
Xu, F. et al. Advanced characterization-informed framework and quantitative insight to irradiated annular U-10Zr metallic fuels. Sci. Rep. 13, 10616. https://doi.org/10.1038/s41598-023-35619-1 (2023).
doi: 10.1038/s41598-023-35619-1
pubmed: 37391449
pmcid: 10313895
He, K., Zhang, X., Ren, S., & Sun, J., Deep Residual Learning for Image Recognition. Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE. 770–778. arXiv:1512.03385 . https://doi.org/10.1109/CVPR.2016.90 . ISBN 978-1-4673-8851-1. (2016).
Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation, medical image computing and computer-assisted intervention–MICCAI. Cham 2015, 234–241. https://doi.org/10.1007/978-3-319-24574-4_28 (2015).
doi: 10.1007/978-3-319-24574-4_28
Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S. & Cardoso, J. M. Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support 240–248 (Springer, 2017).
doi: 10.1007/978-3-319-67558-9_28
Gonzalez, R. C. & Woods, R. E. Digital Image Processing 3rd edn. (Prentice-Hall Inc, 2006).
Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. https://doi.org/10.1109/TPAMI.1986.4767851 (1986).
doi: 10.1109/TPAMI.1986.4767851
pubmed: 21869365
Nosal, E.-M. Flood-fill algorithms used for passive acoustic detection and tracking. New Trends Environ. Monit. Passiv. Syst. Hyeres France 2008, 1–5. https://doi.org/10.1109/PASSIVE.2008.4786975 (2008).
doi: 10.1109/PASSIVE.2008.4786975
Loshchilov, I., & Hutter, F., Decoupled weight decay regularization, arXiv preprint arXiv:1711.05101 , (2017).
Everingham, M., Van Gool, L., Williams, C. K., Winn, J. & Zisserman, A. The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303–338. https://doi.org/10.1007/s11263-009-0275-4 (2010).
doi: 10.1007/s11263-009-0275-4
Lin, T.-Y., Microsoft coco: Common objects in context, Proc. European conference on computer vision, 740–755 (2014).