Methods of artificial intelligence for acoustic emission diagnostics of fracture stages (A review). P. 2: Artificial neural network and deep learning

Keywords

acoustic emission, artificial neural network, deep learning, convolution neural network, recurrent neural network, identification of defects.

Cite as

Stankevych O. M. and Rebot D. P. Methods of artificial intelligence for acoustic emission diagnostics of fracture stages (A review). P. 2: Artificial neural network and deep learning. Physico¬chemical Mechanics of Materials. 2024. 60(4), 005-015.

https://doi.org/10.15407/pcmm2024.04.005

Abstract

Based on the analysis of the latest studies, the possibilities of using artificial neural networks and deep learning algorithms for automating the processing of acoustic emission (AE) signals to identify fracture stages are considered. The accuracy of the results for different approaches is compared and their advantages and disadvantages are highlighted. Deep learning methods have broad prospects for implementation in practice of AE diag­nostics.

References

1. Z. T. Nazarchuk, V. R. Skal’s’kyi, and O. M. Stankevych, “A Method for the identification of the types of macrofracture of structural materials by the parameters of the wavelet transform of acoustic-emission signals,” Mater. Sci., 49, No. 6, 841-848 (2014). https://doi.org/10.1007/s11003-014-9682-y
2. V. R. Skal’s’kii, V. F Makeev, O. M. Stankevich, O. S. Kyrmanov, S. I. Vynnyts’ka, and V. K. Opanasovich, “Strength evaluation of stomatologic polymers by wavelet transform of acoustic emission signals,” Streng. Mater., 47, Is. 4, 566-572 (2015). https://doi.org/10.1007/s11223-015-9691-6
3. V. R. Skalsky, O. M. Stankevych, and I. S. Kuz, “Application of wavelet transforms for the analysis of acoustic-emission signals accompanying fracture processes in materials (A survey),” Mater. Sci., 54, No. 2, 139-153 (2018). https://doi.org/10.1007/s11003-018-0168-1
4. V. Skalskyi, O. Stankevych, and O. Dubytskyi, “Estimation of effect of hydrogen on the parameters of magnetoacoustic emission signals,” J. Magn. Magn. Mater., 454, 375-385 (2018). https://doi.org/10.1016/j.jmmm.2018.01.089
5. V. R. Skalskyi, O. M. Mokryi, O. I. Zvirko, V. I. Kyryliv, I. M. Romanyshyn, and O. V. Maksymiv, “Estimation of characteristics of nanocrystalline layer using the surface acoustic waves,” Mater. Sci., 59, No. 2, 180-185 (2023). https://doi.org/10.1007/s11003-024-00760-3
6. V. R. Skalskyi, and O. Stankevych, “Acoustic-emmision criterion for optimazing the quantity of fiber in the concrete matrix,” Physicochemical Mechanics of Materials [in Ukrainian], 59, No. 6, 56-63 (2023). https://doi.org/10.1007/s11003-024-00831-5
7. V. R. Skalskyi, I. M. Dmytrakh, Ye. P. Pochapskyi, O. M. Mokryi, A. M. Syrotyuk, B. P. Klym, Yu. I. Kaniuk, I. M. Romanyshyn, P. P. Velykyi, and P. M. Dolishniy, “Investigation of the influence of surface treatment and hardening of 60S2A steel on its volumetric damage by the acoustic test method,” Physicochemical Mechanics of Materials [in Ukrainian], 60, No. 1, 18-25 (2024). https://doi.org/10.1007/s11003-024-00844-0
8. C. Muir, B. Swaminathan, A. S. Almansour, K. Sevener, C. Smith, M. Presby, J. D. Kiser, T. M. Pollock, and S. Daly, “Damage mechanism identification in composites via machine learning and acoustic emission,” npj Computational Materials, 7 (2017). Article number 95. https://doi.org/10.1038/s41524-021-00565-x
9. O. M. Stankevych, and D. P. Rebot, “Methods of artificial intelligence for acoustic emission diagnostics of fracture stages (A review),” Physicochemical Mechanics of Materials [in Ukrainian], 60, No. 3, 5-14 (2024). https://doi.org/10.15407/pcmm2024.04.005
10. O. G. Rudenko, and Ye. V. Bodyanskyi, Artificial Neural Networks [in Ukrainian], SMIT Publ. House, Kharkiv (2006).
11. L. Zhou, P. Wang, C. Zhang, X. Qu, C. Gao, and Y. Xie, “Multi-mode fusion BP neural network model with vibration and acoustic emission signals for process pipeline crack,” Ocean Eng., 264 (2022). Article number 112384. https://doi.org/10.1016/j.oceaneng.2022.112384
12. L. KC, A. Ross, L. Ai, A. Henderson, E. Elbatanouny, M. Bayat, and P. Ziehl, “Determination of vehicle loads on bridges by acoustic emission and an improved ensemble artificial neural network,” Const. Buil. Mater., 364 (2023). Article number 129844. https://doi.org/10.1016/j.conbuildmat.2022.129844
13. P. Kolář, and M. A Petružálek, “A two-step algorithm for acoustic emission event discrimination based on recurrent neural networks,” Comput. Geosci., 163 (2022). Article number 105119. https://doi.org/10.1016/j.cageo.2022.105119
14. V. Soltangharaei, R. Anay, L. Assi, M. Bayat, J. R. Rose, and P. Ziehl, “Analyzing acoustic emission data to identify cracking modes in cement paste using an artificial neural network,” Const. Build. Mater., 267 (2021). Article number 121047. https://doi.org/10.1016/j.conbuildmat.2020.121047
15. L. Cheng, H. Xin, R. M. Groves, and M. Veljkovic, “Acoustic emission source location using Lamb wave propagation simulation and artificial neural network for I-shaped steel girder,” Const. Build. Mater., 273 (2021). Article number 121706. https://doi.org/10.1016/j.conbuildmat.2020.121706
16. D. Shi, X. Chen, P. Chen, K. Shang, and T. Ji, “Revealing the failure mechanism of high strength seawater coral aggregate reinforced concrete slabs based on acoustic emission technology: Parameter analysis and DBN-BPNN classification,” Eng. Struct., 303 (2024). Article number 117439. https://doi.org/10.1016/j.engstruct.2024.117439
17. A. Dobrzycki, S. Mikulski, and W. Opydo, “Using ANN and SVM for the detection of acoustic emission signals accompanying epoxy resin electrical treeing,” Appl. Sci., 9 (2019). Article number 1523. https://doi.org/10.3390/app9081523
18. J. Sun, D. Liu, P. He, L. Guo, B. Cao, L. Zhang, and Z. Li, “Experimental investigation on acoustic emission precursor of rockburst based on unsuper¬vised machine learning method,” Rock Mech. Bulletin, 3, Is. 2 (2024). Article number 100099. https://doi.org/10.1016/j.rockmb.2023.100099
19. R. Qin, Z. Zhang, J. Huang, Z. Du, X. Xiang, G. Wen, and W. He, “Acoustic emission for surface quality monitoring in laser shock peening via dual-feature fusion convolution neural network,” Opt. Laser Technol., 164 (2023). Article number 109505. https://doi.org/10.1016/j.optlastec.2023.109505
20. M. S. Nashed, J. Renno, M. S. Mohamed, and R. L. Rauben, “Gas turbine failure classification using acoustic emissions with wavelet analysis and deep learning,” Expert Sys. Appl., 232 (2023). Article number 120684. https://doi.org/10.1016/j.eswa.2023.120684
21. K. Li, T. Li, M. Ma, D. Wang, W. Deng, and H. Lu, “Laser cladding state recognition and crack defect diagnosis by acoustic emission signal and neural network,” Opt. Laser Technol., 142 (2021). Article number 107161. https://doi.org/10.1016/j.optlastec.2021.107161
22. V. Vy, Y. Lee, J. Bak, S. Park, and H. Yoon, “Damage localization using acoustic emission sensors via convolutional neural network and continuous wavelet transform,” Mech. Syst. Sig. Proc., 204 (2023). Article number 110831. https://doi.org/10.1016/j.ymssp.2023.110831
23. L. Ai, M. Bayat, and P. Ziehl, “Localizing damage on stainless steel structures using acoustic emission signals and weighted ensemble regression-based convolutional neural network,” Measurement, 211 (2023). Article number 112659. https://doi.org/10.1016/j.measurement.2023.112659
24. G. Han, Y-M. Kim, H. Kim, T-M. Oh, K-I. Song, A. Kim, Y. Kim, Y. Cho, and T-H. Kwon, “Autodetection of acoustic emission signals from cracking of concrete structures using convolutional neural networks: Upscaling from specimen,” Expert Syst. Appl., 186 (2021). Article number 115863. https://doi.org/10.1016/j.eswa.2021.115863
25. D. K. Smal, and S. Ray, “Wavelet entropy-based damage characterization and material phase differentiation in concrete using acoustic emissions,” Eng. Fail. Anal., 160 (2024). Article number 108144. https://doi.org/10.1016/j.engfailanal.2024.108144
26. P. Deshpande, V. Pandiyan, R. Crockett, and K. Wasmer, “When AE (acoustic emission) meets AI (artificial intelligence) for wear states detection,” in: Proc. Conf. SCHALL 21, Germany, January (2021), p. 8.
27. S. Ferrisi, G. Zangara, D. R. Izquierdo, D. Lofaro, R. Guido, D. Conforti, and G. Ambrogio, “Tool condition monitoring for milling process using convolutional neural networks,” Procedia Comput. Sci., 232, 1607-16116 (2024). https://doi.org/10.1016/j.procs.2024.01.158
28. F. Qui, Z. Shen, Y. Bai, G. Shan, D. Qu, and W. Chen, “Hydrogen defect acoustic emission recognition by deep learning neural network,” Int. J. Hydrogen Energy, 45, 878-893 (2024). https://doi.org/10.1016/j.ijhydene.2023.09.176
29. Z. Zhao, and N-Z. Chen, “Spatial-temporal graph convolutional networks (STGCN) based method for localizing acoustic emission sources in composite panels,” Comp. Struct., 323 (2023). Article number 117496. https://doi.org/10.1016/j.compstruct.2023.117496
30. F. Ren, C. Zhu, Z. Yuan, M. Karakus, S. Tang, and M. He, “Recognition of shear and tension signals based on acoustic emission parameters and wave¬form using machine learning methods,” Int. J. Rock Mech. Min. Sci., 171 (2023). Article number 105578. https://doi.org/10.1016/j.ijrmms.2023.105578
31. D. F. Hesser, S. Mostafavi, G. K. Kocur, and B. Markert, “Identification of acoustic emission sources for structural health monitoring applications based on convolutional neural networks and deep transfer learning,” Neurocomputing, 453, 1-12 (2021). https://doi.org/10.1016/j.neucom.2021.04.108
32. K. Ohno, and M. Ohtsu, “Crack classification in concrete based on acoustic emission,” Constr. Build. Mater., 24, 2339-2346 (2010). https://doi.org/10.1016/j.conbuildmat.2010.05.004
33. S. Ju, D. Li, and J. Jn, “Machine-learning-based methods for crack classification using acoustic emission technique,” Mech. Syst. Sig. Process, 178 (2022). Article number 109253. https://doi.org/10.1016/j.ymssp.2022.109253
34. X. Wang, Q. Yue, and X. Liu, “Crack pattern identification in cementitious materials based on acoustic emission and machine learning,” J. Build. Eng., 87 (2024). Article number 109124. https://doi.org/10.1016/j.jobe.2024.109124
35. M. Xia, X. Zheng, M. Imran, and M. Shoaib, “Data-driven prognosis method using hybrid deep recurrent neural network,” Appl. Soft Comp., 93 (2020). Article number 106351. https://doi.org/10.1016/j.asoc.2020.106351
36. T.-K. Nguyen, Z. Ahmad, and J.-M. Kim, “A scheme with acoustic emission hit removal for the remaining useful life prediction of concrete structures,” Sensors, 21 (2021). Article number 7761. https://doi.org/10.3390/s21227761
37. F. König, J. Marheineke, G. Jacobs, C. Sous, M. J. Zuo, and Z. Tian, “Data-driven wear monitoring for sliding bearings using acoustic emission signals and long short-term memory neural networks,” Wear, 476 (2021). Article number 203616. https://doi.org/10.1016/j.wear.2021.203616
38. J. Melchiorre, A. M. Bertetto, M. M. Rosso, and G. C. Marano, “Acoustic emission and artificial intelligence procedure for crack source localization,” Sensors, 23 (2023). Article number 693. https://doi.org/10.3390/s23020693
39. K. Wasmer, T. Le-Quang, B. Meylan, and S. A. Shevchik, “In situ quality monitoring in AM using acoustic emission: a reinforcement learning approach,” J. Mater. Eng. Perform., 28, Is. 2, 666-672 (2019). https://doi.org/10.1007/s11665-018-3690-2
40. A. Lange, M. Käding, R. Xu, S. Marx, and J. Östermann, “Semi-supervised learning for acoustic vision monitoring of tendons in pre-stressed concrete bridges,” in: Proc. 14th Int. Workshop on Structural Health Monitoring (2023). https://doi.org/10.12783/shm2023/36855