10.14489/td.2026.05.pp.004-013

2026, 05 May

DOI: 10.14489/td.2026.05.pp.004-013

Ushanov S. V., Barat V. A., Kacharsky V. D., Elizarov S. V., Lukashev I. A., Aleksandrov A. S.
USING CONVOLUTIONAL NEURAL NETWORKS TO DETECT ACOUSTIC EMISSION SIGNALS IN A NOISE BACKGROUND
(pp. 4-13)

Abstract. Algorithm for automatic detection of acoustic emission (AE) signals against a background of intensive noise, designed for use in monitoring systems for dynamically loaded objects, is being investigated. The monitored object is a walking dragline excavator ESh-24.95, supporting metal structures of which are equipped with an AE system. During operation of the walking dragline excavator high level of acoustic noise is being observed, generated by the movement of the traction and hoisting ropes and the vibration of loosely fixed structural elements. A distinctive feature of the algorithm for detection of AE impulses against a background of continuous noise is that data processing is realised in stages. In the initial stage methods with low computational complexity, such as location-based filtering and parametric filtering with high data processing speed, are used. In the final stage a convolutional neural network is used for AE impulses detection based on an analysis of the time-frequency distribution of signal energy.

Keywords: acoustic emission, convolutional neural networks, structure health moni-toring system, dragline.

+ - About the Authors Click to collapse

S. V. Ushanov (“Interunis-IT” LLC, Moscow) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
V. A. Barat, V. D. Kacharsky (“Interunis-IT” LLC, Moscow, Russia, National Research University “Moscow Power Engineering Institute”, Moscow, 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.
S. V. Elizarov (“Interunis-IT” LLC, Moscow) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
I. A. Lukashev, A. S. Aleksandrov (“Interunis-IT” LLC, Moscow, Russia, National Research University “Moscow Power Engineering Institute”, Moscow, 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. Kotelnikov, V. V., Rykov, A. N., & Kozelskaya, S. O. (2016). Use of deep learning neural networks for predicting and assessing the criticality level of structural defects. Promyshlennye ASU i kontrollery, (12), 39–45. [in Russian language].
2. Akimov, D. A., Kleymenov, A. D., Kozelskaya, S. O., & Budadin, O. N. (2020). A new approach to assessing the operational safety of composite materials and complex-shaped parts based on artificial intelligence methods using deep neural networks and the results of multi-criteria comprehensive non-destructive testing. Kontrol'. Diagnostika, (7), 18–27. [in Russian language]. https://doi.org/10.14489/td.2020.07.pp.018-027
3. Nikolaev, M. Yu. (2024). Integrated optical system for defect inspection of load-lifting ropes. In Voprosy fundamental'nykh i prikladnykh nauchnykh issledovanii: Sbornik statei mezhdunarodnoi nauchnoi konferentsii (pp. 21–23). [in Russian language]. https://doi.org/10.37539/240207.2024.88.39.002
4. Pavlov, P. V., Tyurnev, D. I., & Sukhachev, N. V. (2024). Neural network system for laser diagnostics of aircraft cockpit glazing elements. Crede Experto: transport, obshchestvo, obrazovanie, yazyk, (2), 61–76. [in Russian language]. https://doi.org/10.51955/2312-1327_2024_2_61
5. Strukov, S. A., Pechenkin, A. Yu., & Belosludtsev, V. N. (2023, November 23–25). Implementation of principles for determining distance to objects based on an artificial neural network. In Priborostroenie v XXI veke – 2022. Integratsiya nauki, obrazovaniya i proizvodstva: Sbornik materialov XVIII Vserossiiskoi nauchno-tekhnicheskoi konferentsii (pp. 56–60). Kalashnikov Izhevsk State Technical University. [in Russian language].
6. Krysko, N. V., Skrynnikov, S. V., Shchipakov, N. A., et al. (2025). Determination of parameters of surface defects in the base metal of pipelines based on comprehensive diagnostic results. Komp'yuternaya optika, 49(2), 311–319. [in Russian language]. https://doi.org/10.18287/2412-6179-CO-1437
7. Saleem, F., Ahmad, Z., & Kim, J. M. (2025). Real-time pipeline leak detection: A hybrid deep learning approach using acoustic emission signals. Applied Sciences, 15(1), Article 205.
8. Hesser, D. F., Mostafavi, S., Kocur, G. K., & Market, B. (2021). Identification of acoustic emission sources for structural health monitoring applications based on convolutional neural networks and deep transfer learning. Neurocomputing, 453, 1–12.
9. Vy, V., Lee, Y., Park, S., et al. (2023). Damage localization using acoustic emission sensors via convolutional neural network and continuous wavelet transform. Mechanical Systems and Signal Processing, 204, Article 110831.
10. Barile, C., Casavola, K., Pappalettera, G., et al. (2022). Acoustic emission and deep learning for the classification of the mechanical behavior of AlSi10Mg AM-SLM specimens. Applied Sciences, 13(1), Article 189.
11. Li, D., Wang, Y., Yan, W.-J., & Ren, W.-X. (2021). Acoustic emission wave classification for rail crack monitoring based on synchrosqueezed wavelet transform and multi-branch convolutional neural network. Structural Health Monitoring, 20(4), 1563–1582.
12. Barat, V. A., Marchenkov, A. Yu., Karpova, M. V., et al. (2024). Application of artificial neural networks for detecting defects in dissimilar welded joints using the acoustic emission method. Kontrol'. Diagnostika, 27(12), 4–13. [in Russian language].
13. Sergeev, A. S., Konyashov, V. V., Sergeev, D. S., & Fedorov, A. V. (2025). Investigation of the features of processing and displaying the results of automated ultrasonic testing of additive manufacturing product quality. Pribory, (2), 23–30. [in Russian language]
14. Nazarenko, S. Yu., & Udod, V. A. (2019). Application of artificial neural networks in radiation non-destructive testing. Defektoskopiya, (6), 53–64. [in Russian language]. https://doi.org/10.1134/S013030821906006X
15. Yablokov, A. E., & Zhila, T. M. (2021). Application of CNNs in vibration diagnostics based on spectrograms and wavelet scalograms of signals. Izvestiya Tul'skogo gosudarstvennogo universiteta. Tekhnicheskie nauki, (12), 452–457. [in Russian language]. https://doi.org/10.24412/2071-6168-2021-12-452-457
16. Liu, T., Zhang, C., Wei, H., & Zhang, K. (2017). Time series forecasting based on wavelet decomposition and feature extraction. Neural Computing and Applications, 28 (Suppl. 1), 183–195.
17. Barat, V., Marchenkov, A., Bardakov, V., et al. (2021). Structural health monitoring of walking dragline excavator using acoustic emission. Applied Sciences, 11(8), Article 3575.
18. Stevens, E., Antiga, L., & Viehmann, T. (2022). PyTorch: Illuminating deep learning. Piter. [in Russian language].

+ - 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 700 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.2026.05.pp.004-013

and fill out the form