Application of the deep learning method in studying crack resistance characteristics

Monakhov A.D., Yakovlev N.O.
UDC
620.178.3
DOI
10.18577/2307-6046-2024-0-6-80-91
Article PDF (Russian) (912.68 KB)
How to cite
Monakhov A.D., Yakovlev N.O. Application of the deep learning method in studying crack resistance characteristics // Proceedings of VIAM. 2024. No. 6. DOI: 10.18577/2307-6046-2024-0-6-80-91. URL: https://test.viam.ru/en/journal/2024/6/8
Keywords
fatigue crack growth rate, crack resistance, machine vision, convolutional neural network, stress intensity factor, visual inspection
Abstract

The paper presents an algorithm for determining the length and position of a fatigue crack, based on the use of a three-dimensional convolutional neural network when testing for fatigue crack growth rate. An algorithm for calibrating a video recording system using reference marks in the form of matrix bar codes is proposed. The results of using the algorithm were compared with standard tests. Thus, the kinetic diagram of destruction obtained using a neural network model is characterized by a larger volume of observations, as well as a smaller value of the variance of the approximation error of the measurement results.

Reference list
  1. Erasov V.S., Nuzhny G.A., Grinevich A.V. On assessing the damageability of metallic materials using mechanical testing methods. Deformatsiya i razrushenie materialov, 2015, no. 3, pp. 42–47.
  2. Erasov V.S., Oreshko E.I., Lutsenko A.N. Damageability of materials in tension testing. Aviacionnye materialy i tehnologii, 2015, no. 4 (37), pp. 91–94. DOI: 10.18577/2071-9140-2015-0-4-91-94.
  3. Kablov E.N., Grinevich A.V., Slavin A.V., Kabanov I.V., Gromov V.I., Ampilogov A.Yu., Yakovlev N.O., Polyakov A.N., Yakusheva N.A. Calculated strength characteristics of steels VKS-9M and 300M. Zavodskaya laboratoriya. Diagnostika materialov, 2022, vol. 88, no. 3, pp. 51–60. DOI: 10.26896/1028-6861-2022-88-3-51-60.
  4. Kablov E.N., Putyrsky S.V., Yakovlev A.L., Krokhina V.A., Naprienko S.A. Study of resistance to fatigue fracture of forgings made of high-strength titanium alloy VT22M, manufactured with final deformation in the (α + β)- and β-regions. Titan, 2021, no. 1 (70), pp. 26–33.
  5. Erasov V.S., Oreshko E.I. Fatigue tests of metal materials (review). Part 1. Main definitions, loading parameters, representation of results of tests. Aviacionnye materialy i tehnologii, 2020, no. 4 (61), pp. 59–70. DOI: 10.18577/2071-9140-2020-0-4-59-70.
  6. Mitrakov O.V., Yakovlev N.O., Yakusheva N.A., Grinevich A.V. Destruction features of steel 20ХГСН2МФА-ВД during the fracture toughness test. Aviacionnye materialy i tehnologii, 2019, no. 1 (54), pp. 49–56. DOI: 10.18577/2071-9140-2019-0-1-49-56.
  7. Chen C., Seo H., Jun C.H., Zhao Y. A potential crack region method to detect crack using image processing of multiple thresholding. Signal, Image and Video Processing, 2022, vol. 16, no. 6, pp. 1673–1681.
  8. Abdel-Qader I., Abudayyeh O., Kelly M.E. Analysis of edge-detection techniques for crack identification in bridges. Journal of Computing in Civil Engineering. 2003, vol. 17 (4), рр. 255–263.
  9. Gao H.L., Shen S.S., Yun Y. Fatigue crack length real time measurement method based on camera automatically tracking and positioning. Applied Mechanics and Materials, 2012, vol. 130, pp. 3111–3118.
  10. Sun H., Liu Q., Fang L. Research on fatigue crack growth detection of M (T) specimen based on image processing technology. Journal of Failure Analysis and Prevention, 2018, vol. 18, рр. 1010–1016.
  11. Monakhov A.D., Gulyaev M.M., Gladysheva N.E., Kopteltseva O.Yu., Avtaev V.V., Yakovlev N.O., Gulina I.V. Application of the digital image correlation method for constructing deformation diagrams in true coordinates. Izvestiya vysshikh uchebnykh zavedeniy. Tsvetnaya metallurgiya, 2023, vol. 29, no. 3, pp. 79–88. DOI: 10.17073/0021-3438-2023-3-79-88.
  12. Strohmann T., Starostin-Penner D., Breitbarth E., Requena G. Automatic detection of fatigue crack paths using digital image correlation and convolutional neural networks. Fatigue Fracture of Engineering Materials Structures, 2021, vol. 44, pp. 1336–1348.
  13. Orell O., Jokinen J., Kanerva M. Use of DIC in the characterization of mode II crack propagation in adhesive fatigue testing. International Journal of Adhesion and Adhesives. 2023, vol. 122, рр. 1–10.
  14. Rupil J., Roux S., Hild F., Vincent L. Fatigue microcrack detection with digital image correlation. The Journal of Strain Analysis for Engineering Design, 2011, vol. 46 (6), pp. 492–509.
  15. Avtaev V.V., Yakovlev N.O. Study of static crack resistance and fracture resistance of thin-sheet aluminum alloy using digital image correlation. Deformatsiya i razrusheniye materialov, 2020, nо. 2, pp. 29–35.
  16. Lopez-Crespo P., Shterenlikht A., Patterson E.A. et al. The stress intensity of mixed mode cracks determined by digital image correlation. Journal Strain Analysis, 2008, vol. 43, no. 8, pp. 769–780.
  17. Du Y., Diaz F.A., Burguete R.L., Patterson E.A. Evaluation using digital image correlation of stress intensity factors in an aerospace panel. Experimental Mechanics, 2011, vol. 51, pp. 45–57.
  18. Indolia S., Goswami A.K., Mishra S.P., Asopa P. Conceptual understanding of convolutional neural network a deep learning approach. Procedia Computer Science, 2018, vol. 132, pp. 679–688.
  19. Butakov V.V., Lugovoy A.A., Varrik N.M., Babashov V.G. Assessment of thermal conductivity of a layered highly porous thermal insulation material. Aviation materials and technologies, 2022, no. 3 (68), paper no. 11. Available at: http://www.journal.viam.ru (accessed: February 29, 2024). DOI: 10.18577/2713-0193-2022-0-1-129-142.
  20. Oreshko E.I., Erasov V.S., Sibayev I.G., Lutsenko A.N., Shershak P.V. Machine learning algorithms (review). Part 2. Machine learning metrics. Decision trees and ensembles of decision trees. An algorithm for neural network to forecast properties of ferrite-martensite steel. Aviation materials and technologies, 2022, no. 4 (69), paper no. 12. Available at: http://www.journal.viam.ru (accessed: February 29, 2024). DOI: 10.18577/2713-0193-2022-0-4-132-146.
  21. LeCun Y., Boser B., Denker J.S. et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1989, vol. 1 (4), pp. 541–551.
  22. Yingtao Y., Zhendong G., Xin S. et al. Crack Length Measurement Using Convolutional Neural Networks and Image Processing. Sensors, 2021, vol. 21 (17), pp. 1–16.
  23. Ali R., Chuah J.H., Talip M.S.A. et al. Structural crack detection using deep convolutional neural networks. Automation in Construction, 2022, vol. 133, p. 103989.
  24. Kaiming H., Xiangyu Z., Shaoqing R., Jian S. Deep Residual Learning for Image Recognition. Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016, pp. 770–778. DOI: 10.1109/CVPR.2016.90.
  25. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations. San Diego, 2015, pp. 1–9.
  26. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Munich, 2015, pp. 234–241.
  27. Calculated values of characteristics of aviation metal structural materials: aviation reference book in 4 issues. Moscow: UAC; TsAGI, 2012, is. 4, 118 p.