10.14489/td.2024.12.pp.004-013

2024, 12 December

DOI: 10.14489/td.2024.12.pp.004-013

Barat V. A., Marchenkov A. Yu., Karpova M. V., Bardakov V. V., Lepsheev E. A., Ushanov S. V., Elizarov S. V.
APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR DETECTION OF DEFECTS IN DISSIMILAR WELDED JOINTS BY ACOUSTIC EMISSION METHOD
(pp. 4-13)

Abstract. The paper considers the possibility of using artificial neural networks to detect hits in acoustic emission (AE) testing. A distinctive feature of the proposed method is that the training set of the neural network is formed using a complex technique based on the application of modeling technology, on the one hand, and on calibration measurements carried out in the field, on the other. In this paper, process pipelines with dissimilar welded joints were considered as a test structure. AE signals were modeled using a hybrid method: the signal waveform was determined based on a finite element model, and the AE hits amplitudes were determined on the basis of a physical experiment on cyclic stretching of samples of dissimilar welded joints. Acoustic signals measured on the process pipelines bodies in the field condition were used as noise. A multilayer perceptron was used to classify the data, the architecture of which was selected based on the minimization of the classification error.

Keywords: dissimilar welded joints, acoustic emission, diffusion layers, neural networks in acoustic emission, classification of acoustic emission signals, waveguide modeling.

+ - About the Authors Click to collapse

V. A. Barat (National Research University “MPEI”, Moscow, Russia, ”Interunis-IT” LLC, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

A. Yu. Marchenkov, M. V. Karpova, V. V. Bardakov (National Research University “MPEI”, 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. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
E. A. Lepsheev, S. V. Ushanov (National Research University “MPEI”, Moscow, Russia, ”Interunis-IT” LLC, 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, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Goncharov A. L., Marchenkov A. Yu., Terenty ev E. V. et al. (2019). Study of Structural Non-Homogeneity Impact on Mechanical Properties of Dissimilar Weld Joints of Carbon Steel 20 and Corrosion-Resistant Austenitic 12Kh18N10T Steel. IOP Conference Series: Materials Science and Engineering, 681(012016).

2. Barat V. A., Marchenkov A. Yu., Karpova M. V. et al. (2023). Application of acoustic emission method for detecting diffusion interlayers in different welded joints. Kontrol'. Diagnostika, Vol. 26, 304(10), 4 ‒ 10. [in Russian language] DOI: 10.14489/td.2023.10.pp.004-010
3. Rastegaev I. A., Yasnikov I. S., Rastegaeva I. I. et al. (2022). Estimation of the probability of detecting acoustic emission signals using the amplitude discrimination method at a low signal-to-noise ratio. Defektoskopiya, (3), 3 ‒ 12. [in Russian language]
4. Agletdinov E., Pomponi E., Merson D., Vinogradov A. (2016). A Novel Bayesian Approach to Acoustic Emission Data Analysis. Ultrasonics, 72, 89 ‒ 94.
5. Stepanova L. N., Chernova V. V., Ramazanov I. S. (2019). Using clustering methods for processing acousticemission information. Kontrol'. Diagnostika, (8), 12 ‒ 21. [in Russian language] DOI: 10.14489/td.2019.08.pp.012-021
6. Pomponi E., Vinogradov A. (2013). A Real-Time Approach to Acoustic Emission Clustering. Mechanical Systems and Signal Processing, 40(2), 791 ‒ 804.
7. Ren F., Zhu C., Yuan Z. at al. (2023). Recognition of Shear and Tension Signals Based on Acoustic Emission Parameters and Waveform Using Machine Learning Methods. International Journal of Rock Mechanics and Mining Sciences, 171(4).
8. Matvienko Yu. G., Vasil'ev I. E., Chernov D. V. et al. (2022). Increasing the likelihood of identifying sources of acoustic emission using artificial neural networks сетей. Defektoskopiya, (5), 3 ‒ 12. [in Russian language]
9. Kolář P., Petružálek M. (2022). A Two-Step Algorithm for Acoustic Emission Event Discrimination Based on Recurrent Neural Networks. Computers & Geosciences, 163.
10. Hesser D. F., Mostafavi S., Kocur G. K., Markert B. (2021). Identification of Acoustic Emission Sources for Structural Health Monitoring Applications Based on Convolutional Neural Networks and Deep Transfer Learning. Neurocomputing, 453.
11. Sazonov A. A., Shelobkov V. I., Ivanov V. I. (2020). Influence of acoustic-electronic channel on acoustic emission hit parameters. Kontrol'. Diagnostika, (6), 14 ‒ 22. [in Russian language] DOI: 10.14489/td.2020.06.pp.014-022
12. Masayasu Ohtsu (Ed.), Proverbio E., Calabrese L. (2015). Artificial Neural Network Analysis of Acoustic Emission Data During Longtime Corrosion Monitoring of Post-Tensioned Concrete Structures. Acoustic Emission and Related Non-Destructive Evaluation Techniques in the Fracture Mechanics of Concrete, 225 ‒ 256. Woodhead Publishing. (Woodhead Publishing Series in Civil and Structural Engineering).
13. Rules for organizing and conducting acoustic emission testing of vessels, apparatus and process pipelines No. PB 03-593‒03. (2003). Moscow: PIO OBT. [in Russian language]
14. Rastegaeva I. I., Rastegaev I. A., Agletdinov E. A., Merson D. L. (2022). Comparison of the main time-frequency transformations of spectral analysis of acoustic emission signals. Frontier Materials & Technologies, (1), 49 ‒ 60. [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 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.2024.12.pp.004-013

and fill out the form