Development of a neural network for fractographic analysis of hydrogenated zirconium alloys

M.I. Petrov; M.G. Isaenkova; N.S. Saburov; V.A. Markelov; A.A. Plyasov

doi:10.48612/letters/2025-1-49-54

Development of a neural network for fractographic analysis of hydrogenated zirconium alloys

M.I. Petrov

, M.G. Isaenkova, N.S. Saburov, V.A. Markelov, A.A. Plyasov show affiliations and emails

Received 28 December 2024; Accepted 17 February 2025;

Citation: M.I. Petrov, M.G. Isaenkova, N.S. Saburov, V.A. Markelov, A.A. Plyasov. Development of a neural network for fractographic analysis of hydrogenated zirconium alloys. Lett. Mater., 2025, 15(1) 49-54

BibTex https://doi.org/10.48612/letters/2025-1-49-54

Abstract

$SEM fractographic image of a hydrogenated zirconium alloy, processed using VGG-16 and U-Net neural networks to determine the brittle fraction and segment brittle/ductile regions, with corresponding outputs showing the dependence of brittle fraction on hydride orientation and segmented fracture surfaces.$ A methodology for the quantitative assessment of fracture characteristics in hydrogenated zirconium alloys using electron microscopy images has been developed. The study utilized a model Zr-Nb-Sn-Fe zirconium alloy with hydrides of varying orientations to analyze fracture surfaces from mechanical tests on ring-shaped specimens. Two convolutional neural networks were employed: a modified VGG-16 for determining the fraction of brittle components and a U-Net for segmenting images into brittle and ductile regions. These networks achieved high accuracy, with the VGG-16 and U-Net performing at 98.2 % and 94.6 %, respectively, relative to manual annotation. The results demonstrated that the brittle fraction extracted from fractographic images provides a more precise and reliable method for determining fracture characteristics compared to conventional macroscopic parameters, such as the relative change in cross-sectional area. Furthermore, it was shown that the brittle fraction can classify the fracture mechanism into one of two categories — brittle fracture (0 – 0.3) or ductile fracture (0.7 –1) — with high reliability. This study highlights the potential of microparameter-based analysis in evaluating structural fracture characteristics and standardizing fractographic methods. The automated fracture image processing methodology developed is not only applicable to hydrogenated zirconium alloy tubes but also extends to other materials and components. These findings emphasize the advantages of machine learning in automating and enhancing the accuracy of quantitative fractography, with significant potential for industrial applications in material property analysis.

References (23)

1. M. P. Puls, The Effect of Hydrogen and Hydrides on the Integrity of Zirconium Alloy Components, Springer-Verlag London, London, 2012, 451 p.

2. A. T. Motta, L. Capolungo, L. Q. Chen, M. N. Cinbiz, M. R. Daymond, D. A. Koss, E. Lacroix, G. Pastore, P. C. A. Simon, M. R. Tonks, B. D. Wirth, M. A. Zikry, Hydrogen in zirconium alloys: A review, J. Nucl. Mater. 518 (2019) 440 - 460

3. A. V. Tenishev, M. I. Petrov, M. G. Isaenkova, V. V. Mikhal’chik, V. A. Fesenko, A. A. Plyasov, N. S. Saburov, Differential Scanning Calorimetry Determination of the Hydrogen Solubility in E110opt and E635 Zirconium Alloys, Russ. Metall. 2022 (2022) 1427 -1433

4. M. G. Isaenkova, M. I. Petrov, I. V. Kozlov, A. V. Bogomolova, Structural features of hydrogenated E110opt and E635 tubes, Non-Ferrous Met. (2023) 41- 48

5. W. Qin, J. A. Szpunar, J. Kozinski, Hydride-induced degradation of hoop ductility in textured zirconium-alloy tubes: A theoretical analysis, Acta Mater. 60 (2012) 4845 - 4855

6. S. A. Nikulin, A. B. Rozhnov, T. A. Nechaykina, S. O. Rogachev, M. Y. Zadorozhnyy, H. Alsheikh, Effect of low hydrogenation on the low-cycle fatigue of zirconium alloy, Int. J. Fatigue 111 (2018) 1- 6

7. G. Singh, R. Jayaganthan, U. K. Arora, K. I. Vishnu Narayanan, D. Srivastava, Texture Analysis and Fracture Behavior of Zircaloy-4 Processed Through Swaging, Metallogr. Microstruct. Anal. 9 (2020) 273 - 284

8. Y. Zhang, L. You, X. Li, J. Zhou, X. Song, In-situ investigation of the fatigue crack initiation and propagation behavior of Zircaloy-4 with different hydrogen contents at RT and 300°C, J. Nucl. Mater. 532 (2020) 152065

9. C. Gillen, A. Garner, C. Anghel, P. Frankel, Investigating iodine-induced stress corrosion cracking of zirconium alloys using quantitative fractography, J. Nucl. Mater. 539 (2020) 152272

10. H. M. Tung, T. C. Chen, C. C. Tseng, Effects of hydrogen contents on the mechanical properties of Zircaloy-4 sheets, Mater. Sci. Eng. A 659 (2016) 172 -178

11. S. Tsopanidis, R. H. Moreno, S. Osovski, Toward quantitative fractography using convolutional neural networks, Eng. Fract. Mech. 231 (2020) 106992

12. S. Tsopanidis, S. Osovski, Unsupervised machine learning in fractography: Evaluation and interpretation, Mater. Charact. 182 (2021) 111551

13. K. Jones, W. D. Musinski, A. L. Pilchak, R. John, P. A. Shade, A. D. Rollett, E. A. Holm, Predicting fatigue crack growth metrics from fractographs: Towards fractography by computer vision, Int. J. Fatigue 177 (2023) 107915

14. Z. Sun, J. Wu, Q. Li, MCNN-TE: a novel method for fractographic images classification based on multi-channel CNN and texture enhancement, UPB Sci. Bull., Ser. C 81 (2019) 121-132.

15. M. X. Bastidas-Rodriguez, L. Polania, A. Gruson, F. Prieto-Ortiz Deep Learning for Fractographic Classification in Metallic Materials, Engineering Failure Analysis 113 (2020) 104532

16. N. S. Saburov, M. G. Isaenkova, M. I. Petrov, P. S. Dzhumaev, A. A. Plyasov, V. A. Markelov, S. A. Bekrenev, Fracture parameters of the Zr-Nb-Sn-Fe tubes samples with different hydrides orientations during the mechanical testing and plasticity of the material, Phys. At. Nucl. (2025). (in press).

17. A. A. Plyasov, N. S. Saburov, S. A. Bekrenev, M. G. Isaenkova, M. I. Petrov, P. S. Dzhumaev, Experiments on Reorientation of Hydrides in Unirradiated E635 Guide Tubes, Phys. At. Nucl. 86 (2023) 2604 - 2617

18. J. L. González-Velázquez, Fractography and failure analysis, Springer International Publishing, Cham, 2018, 165 p

19. S. P. Lynch, S. Moutsos, A brief history of fractography, J. Fail. Anal. Prev. 6 (2006) 54 - 69

20. S. Cong, Y. Zhou, A review of convolutional neural network architectures and their optimizations, Artif. Intell. Rev. 56 (2023) 1905 -1969

21. W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, K. R. Müller, Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications, Proc. IEEE 109 (2021) 247 - 278

22. K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, ArXiv Prepr. ArXiv1409.1556 (2014). http://arxiv.org/abs/1409.1556.

23. O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, in: IEEE Access, 2015, pp. 234 - 241

Funding

1. Ministry of Science and Higher Education of the Russian Federation - 075-15-2021-1352

Development of a neural network for fractographic analysis of hydrogenated zirconium alloys

Abstract

References (23)

Funding

General information

Information for readers

Information for authors

Information for reviewers