10.14489/td.2023.11.pp.044-050

2023, 11 November

DOI: 10.14489/td.2023.11.pp.044-050

Dolmatov D. O.
APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR SOLVING PROBLEMS OF ACOUSTIC NONDESTRUCTIVE TESTING (REVIEW)
(pp. 44-50)

Abstract. Nowadays, artificial neural networks are finding more and more applications in various fields of human activity. This paper reviews the current state of research and development in the field of application of artificial neural networks for solving problems in acoustic non-destructive testing. The areas of application of neural networks include processing of inspection data, flaw detection, determination of flaw parameters, and determination of material properties. Test data processing includes increasing the signal-to-noise ratio of results, data compression, restoration and processing of flaw images. Within flaw parameter determination, flaw sizing and flaw type identification tasks have been solved using artificial neural networks. One of the most challenging problems related to the introduction of artificial neural networks in acoustic nondestructive testing is the small amount of inspection data that complicates the training of artificial networks. The ways to solve this problem are data exchange between organizations and standardization of inspection results, data augmentation and application of computer modeling.

Keywords: acoustic nondestructive testing, artificial neural networks, acoustic signal processing, flaws detection, flaws sizing.

+ - Информация об авторах (About the Authors) Click to collapse

D. O. Dolmatov (National Research Tomsk Polytechnic University, Tomsk, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Mineo C., Wright B., Nicholson I. et al. (2015). PAUT inspection of complex-shaped composite materials through six DOFs robotic manipulators. Insight-Non-Destructive Testing and Condition Monitoring, 57(3), 31 – 36.
2. Larionov V. V., Lider A. M., Dolmatov D. O., Sednev D. A. (2021). Ultrasonic inspection of defects in metal products of complex shapes. Defektoskopiya, (5), 31 – 36. [in Russian language]
3. Munir N., Park J., Kim H-J. et al. (2020). Performance enhancement of convolutional neural network for ultrasonic flaw classification by adopting autoencoder. NDT & E International, 111. Article number: 102218.
4. Cantero-Chinchilla S., Wilcox P. D., Croxford A. J. (2022). A deep learning based methodology for artefact identification and suppression with application to ultrasonic images. NDT & E International, 126. Article number: 102575.
5. Ha J. M., Seung H. M., Choi W. (2022). Autoencoder-based detection of nearsurface defects in ultrasonic testing. Ultrasonics, 119. Article number: 106637.
6. Pilikos G. Batenburg K. J., Leeuwen T. van et al. (2020). Deep data compression for approximate ultrasonic image formation. 2020 IEEE International Ultrasonics Symposium.
7. Mei Y., Jin H., Yu B. et al. (2021). Visual geometry group-UNet: deep learning ultrasonic image reconstruction for curved parts. The Journal of the Acoustical Society of America, 149(5), 2997 – 3009.
8. Song H., Yang Y. (2020). Super-resolution visualization of subwavelength defects via deep learning-enhanced ultrasonic beamforming: A proof-of-principle study. NDT & E International, 116.
9. Zhang W., Zhu W., Zheng S. et al. (2023). Super-resolution reconstruction of ultrasonic Lamb wave TFM image via deep learning. Measurement Science and Technology, 34(5). Article number: 055406.
10. Zhang F., Li J., Luo L. et al. (2023). Ultrasonic adaptive plane wave high-resolution imaging based on convolutional neural network. NDT & E International. Article number: 102891.
11. Xu Q., Yu G., Zhao Q. et al. (2020). Rail defect detection method based on recurrent neural network. 39th Chinese Control Conference 2020, 6486 – 6490. Shenyang.
12. Huang L., Hong X., Yang Z. et al. (2022). CNN-LSTM network-based damage detection approach for copper pipeline using laser ultrasonic scanning. Ultrasonics, 121. Article number: 106685.
13. Guo Y., Xiao Z., Geng L. (2023). Defect detection of 3D braided composites based on semantic segmentation. The Journal of The Textile Institute, 114(4), 574 – 583.
14. Brekht E. A., Konshina V. N. (2022). Application of the YOLO neural network for defect recognition. Intellektual'nye tekhnologii na transporte, 30(2), 41 – 47. [in Russian language]
15. Kim J. G., Jang C., Kang S. S. (2022). Classification of ultrasonic signals of thermally aged cast austenitic stainless steel (CASS) using machine learning (ML) models. Nuclear Engineering and Technology, 54(1–3), 1167 – 1174.
16. Yan Y., Liu D., Gao B. et al. (2020). A deep learning-based ultrasonic pattern recognition method for inspecting girth weld cracking of gas pipeline. IEEE Sensors Journal, 20(14), 7997 – 8006.
17. Sambath S., Nagaraj P., Selvakumar N. et al. (2010). Automatic detection of defects in ultrasonic testing using artificial neural network. International Journal of Microstructure and Materials Properties, 5(6), 561 – 574.
18. Munir N., Kim H.-J., Kang S. S., Song S.-J. et al. (2018). Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments. Journal of Mechanical Science and Technology, 32(7), 3073 – 3080.
19. Munir N., Kim H.-J., Park J. et al. (2019). Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions. Ultrasonics, 94, 74 – 81.
20. Park J., Lee S.-E., Song S.-J. et al. (2022). System invariant method for ultrasonic flaw classification in weldments using residual neural network. Applied Sciences, 12(3). Article number: 1477.
21. Pyle R. J., Bevan R. L. T., Hughes R. R. et al. (2020). Deep learning for ultrasonic crack characterization in NDE. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 68(5), 1854 – 1865.
22. Latete T., Gauthier B., Belanger P. (2021). Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing. Ultrasonics, 115. Article number: 106436.
23. Cheng X., Ma G., Wu Z. et al. (2023). Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning. NDT & E International, 135(14). Article number: 102804.
24. Solov'ev A. N., Sobol' B. V., Vasil'ev P. V. (2016). Ultrasonic location of internal crack-like defects in a composite elastic cylinder using artificial neural networks. Defektoskopiya, (3), 3 – 9. [in Russian language]
25. Park S. H., Hong J.-Y., Choi S. et al. (2021). Deep learning-based ultrasonic testing to evaluate the porosity of additively manufactured parts with rough surfaces. Metals, 11(2). Article number: 290.
26. Zhang S., Lv G., Guo S. et al. (2021). Porosity characterization of thermal barrier coatings by ultrasound with genetic algorithm backpropagation neural network. Complexity, 2021, 1 – 9.
27. Dapkus P., Mažeika L. (2020). A study of supervised combined neural-network-based ultrasonic method for reconstruction of the spatial distribution of material properties. Information Technology and Control, 49(3), 381 – 394.
28. Singh J., Tant K., Mulholland A. et al. (2022). Deep learning based inversion of locally anisotropic weld properties from ultrasonic array data. Applied Sciences, 12(2). Article number: 532.
29. Rautela M., Gopalakrishnan S., Gopalakrishnan K., Deng Y. (2020). Ultrasonic guided waves based identification of elastic properties using 1d-convolutional neural networks. 2020 IEEE International Conference on Prognostics and Health Management. Detroit.
30. Shukla K., Blackshire J. L., Sparkman D. et al. (2021). A physics-informed neural network for quantifying the microstructural properties of polycrystalline nickel using ultrasound data: A promising approach for solving inverse problems. IEEE Signal Processing Magazine, 39(1), 68 – 77.
31. Jacob G., Dorval A. F. V. (2023). Using DICONDE for NDT Data Exchange. 13th ECNDT. Lisbon.
32. Fan C., Pan M., Luo F. (2014). Ultrasonic broadband time-reversal with multiple signal classification imaging using full matrix capture. Insight-Non-Destructive Testing and Condition Monitoring, 56(9), 487 – 491.
33. Schlachter K., Felsner K., Zambal S. (2022). Training neural networks on domain randomized simulations for ultrasonic inspection. Open Research Europe, 2.

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

The cost of a single article is 500 rubles. (including VAT 20%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/td.2023.11.pp.044-050

and fill out the form