Neural network processing of electromagnetic acoustic signals to identify the stress-strain state and damage of power equipment

DOI: 10.47026/1810-1909-2023-4-44-56

УДК 620.179.162

ББК 30.820.51

Mussa G. BASHIROV, Damir Sh. AKCHURIN, Kirill N. KUVAYTSEV, Dmitry E. MAKSIMOCHKIN

Key words

stress-strain state, electromagnetic-acoustic diagnostic method, amplitude and phase spectra of harmonics, frequency characteristics, artificial neural networks, machine learning

Abstract

The purpose of the study is to develop and train an artificial neural network to identify the stress-strain state and damage to the metal of power equipment based on the values of the parameters of the harmonic components of the electromagnetic-acoustic transducer signal.

Materials and methods. Experimental study of the relationship between the parameters of the harmonic components of the signal of an electromagnetic-acoustic transducer with the stress-strain state and damage to the structure of standard metal samples, development of an artificial neural network and methods for its training to identify the stress-strain state and damage to the structure of the metal according to the loading diagram.

Results. Analysis of changes in the microstructure and frequency models of standard steel samples used in power engineering confirmed the possibility of identifying the stress-strain state and damage to the structure of metals based on the values of the parameters of the harmonic components of the electromagnetic-acoustic transducer signal. To solve this problem, an artificial neural network has been developed and trained. After training, the effectiveness of the network in identifying the stress-strain state and damage to the structure of metals reached 92.16%, which is acceptable for the tasks of recognizing the technical condition of metal structural elements of electrical installation equipment.

Conclusions. The use of an artificial neural network to identify the stress-strain state and damage to metal structures based on the harmonic parameters of the electromagnetic-acoustic transducer signal enables to identify areas of concentration of mechanical stress and damage to the metal structure at the early stage of development, thereby increasing reliability and safety operation of electrical equipment.

References

1. Akt tekhnicheskogo rassledovaniya prichin avarii na Sayano-Shushenskoi GES 17 avgusta 2009 goda [Report of technical investigation into the causes of the accident at the Sayano-Shushenskaya HPP on August 17, 2009]. Available at: http://www.gosnadzor.ru/news/aktSSG_bak.doc (Accessed Data: 2023, Aug. 7).
2. Aleshin N.P. Issledovanie vyyavlyaemosti poverkhnostnykh ob”emnykh defektov pri ul’trazvukovom kontrole s primeneniem voln Releya, generiruemykh elektromagnitno-akusticheskim preobrazovatelem [Study of the detectability of surface volumetric defects during ultrasonic testing using Rayleigh waves generated by an electromagnetic-acoustic transducer]. Defektoskopiya, 2021, no. 5, pp.22–30.
3. Analiz prichin avarii na energoustanovkakh, podkontrol’nykh organam Rostekhnadzora za 2021 god [Analysis of the causes of accidents at power plants controlled by Rostechnadzor for 2021]. Available at: http://szap.gosnadzor.ru/activity/energonadzor/nesc_sluch/Analiz%20prichin%20avarii%20za%202021.pdf (Accessed Data: 2023, Aug. 7).
4. Ayazyan G.K., Khorobrov V.R., Galiev R.M. Metod identifikatsii dinamicheskikh kharakte-ristik ob”ektov s zapazdyvaniem [Method for identifying the dynamic characteristics of objects with delay]. Avtomatizatsiya i metrologicheskoe obespechenie v neftyanoi promyshlennosti: mezhvuz. nauchy sbornik [Automation and metrological support in the oil industry: Scientific Collection]. Ufa, Publ. UNI, 1980, pp. 29–33.
5. Bashirov M.G., Bashirova E.M., Yusupova I.G., Akchurin D.Sh. Issledovanie sposobov povysheniya effektivnosti elektromagnitno-akusticheskogo preobrazovaniya sredstv diagnostiki energeticheskogo oborudovaniya [Research on ways to increase the efficiency of electromagnetic-acoustic conversion of diagnostic tools for power equipment]. Promyshlennaya energetika, 2022, no. 10, pp. 2–9.
6. Bashirov M.G., Khusnutdinova I.G., Khusnutdinova L.G., Usmanov D.R. Elektromagnitno-akusticheskii metod otsenki tekhnicheskogo sostoyaniya energeticheskogo oborudovaniya [Electromagnetic-acoustic method for assessing the technical condition of power equipment]. Promyshlennaya energetika, 2016, no. 12, pp. 8–13.
7. Ivanov S.O., Nikandrov M.V., Slavutskii L.A. Neirosetevoe modelirovanie releinoi zashchity s vremennoi zaderzhkoi [Neural network modeling of relay protection with time delay]. Vestnik Chuvashskogo universiteta, 2022, no. 3, pp. 53–60. DOI: 10.47026/1810-1909-2022-3-53-60.
8. Koshcheev M.I., Laryukhin A.A., Slavutskii A.L. Ispol’zovanie adaptivnykh neiroalgoritmov dlya raspoznavaniya anomal’nykh rezhimov sistem vtorichnogo oborudovaniya elektroenergetiki [Using adaptive neuroalgorithms to recognize anomalous modes of secondary equipment systems in the electrical power industry]. Vestnik Chuvashskogo universiteta, 2019, no. 1, pp. 47–58.
9. Bashirov M.G., Bashirova E.M., Yusupova I.G. et al. Modelirovanie i eksperimental’noe issledovanie vliyaniya mekhanicheskikh napryazhenii i povrezhdennosti metalla neftegazovogo oborudovaniya na parametry elektromagnitno-akusticheskogo preobrazovaniya [Modeling and experimental study of the influence of mechanical stresses and metal damage of oil and gas equipment on the parameters of electromagnetic-acoustic conversion]. Neftegazovoe delo, 2023, vol. 21, no. 1, pp. 183–194.
10. Ogorodnikov Yu.I. Zadacha parametricheskoi identifikatsii modelei upravlyaemykh dinamicheskikh sistem kak problema momentov [The problem of parametric identification of models of controlled dynamic systems as a problem of moments]. Sovremennye tekhnologii. Sistemnyi analiz. Modelirovanie, 2017, vol. 56, no. 4, pp. 33–40.
11. Skorosueva O.I. Funktsional’nye vozmozhnosti ML.NET [Functionality ML.NET]. Sovremennye nauchnye issledovaniya i innovatsii, 2023, no. 5. Available at: https://web.snauka.ru/issues/2023/05/100324 (Accessed Date: 2023, Aug. 7).
12. Slavutskii L.A., Slavutskaya E.V. Neirosetevaya obrabotka signalov: zadachi bez «glu-bokogo obucheniya» [Neural network signal processing: tasks without “deep learning”]. Vestnik Chuvashskogo universiteta, 2023, no. 2, pp. 151–160. DOI: 10.47026/1810-1909-2023-2-151-160.
13. Uglov A.L., Khlybov A.A., Bychkov A.L., Kuvshinov M.O. O nerazrushayushchem kontrole ostatochnykh napryazhenii v detalyakh osesimmetrichnoi formy iz stali 03N17K10V10MT [On non-destructive testing of residual stresses in axisymmetrically shaped parts made of steel 03N17K10V10MT]. Vestnik IzhGTU imeni M.T. Kalashnikova, 2019, vol. 22, no. 4, pp. 3–10.
14. Khusnutdinova I.G., Bashirov M.G. Otsenka tekhnicheskogo sostoyaniya i resursa bezopas-noi ekspluatatsii tekhnologicheskikh truboprovodov na osnove elektromagnitno-akusticheskogo effekta [Assessment of the technical condition and resource of safe operation of process pipelines based on the electromagnetic-acoustic effect]. Neftegazovoe delo, 2019, no. 1, pp. 144–162.
15. Ducousso М., Reverdy F. Real-time imaging of microcracks on metallic surface using total fo-cusing method and plane wave imaging with Rayleigh waves. NDT E Int., 2020, vol. 116, p. 102311.
16. Jiang C., Li Z., Zhang Z., Wang S. New Design to Rayleigh Wave EMAT Based on Spatial Pulse Compression. Sensors (Basel), 2023, vol. 23(8), 3943.
17. Leroux S., Bohez S., Verbelen T. et al. Resource-constrained classification using a cascade of neural network layers. In: International Joint Conference on Neural Networks (IJCNN), 2015, pp. 1–7, DOI: 10.1109/IJCNN.2015.7280601.
18. Leroux S., Verbelen T., Simoens P. et al. Iterative neural networks for adaptive inference on resource-constrained devices. Neural Comput & Applic, 2022, vol. 34, pp. 10321–10336. DOI: 10.1007/s00521-022-06910-5.
19. Oh J.W., Jeong J. Convolutional neural network and 2-D image based fault diagnosis of bear-ing without retraining. In: 3^rd International Conference (ICDA 2019), 2019, pp.134–138. DOI: 1145/3314545.3314563.
20. Wang S., Huang S., Wang Q. et al. Accelerated optimizations of an electromagnetic acoustic transducer with artificial neural networks as metamodels, J. Sens. Sens. Syst., 6, 2017, pp. 269–284.

Information about the authors

Mussa G. Bashirov – Doctor of Technical Sciences, Professor, Department of Electrical Equipment and Automation of Industrial Enterprises, Institute of Oil Refining and Petrochemistry, Ufa State Petroleum Technical University, Russia, Salavat (eapp@yandex.ru; ORCID: https://orcid.org/0000-0001-7493-6803).

Damir Sh. Akchurin – Post-Graduate Student, Assistant Lecturer, Department of Electrical Equipment and Automation of Industrial Enterprises, Institute of Oil Refining and Petrochemicals, Ufa State Petroleum Technical University, Russia, Salavat (akihiro177@mail.ru; ORCID: https://orcid.org/0000-0002-2174-8216).

Kirill N. Kuvaytsev – Master’s Program Student of the Direction «Automatization of Technological Processes and Productions», Institute of Oil Refining and Petrochemistry, Ufa State Petroleum Technical University, Russia, Salavat (kirill.kuvaitsev@mail.ru).

Dmitry E. Maksimochkin – Master’s Program Student of the Direction «Automatization of Technological Processes and Productions», Institute of Oil Refining and Petrochemistry, Ufa State Petroleum Technical University, Russia, Salavat (03maksimochkin.de@bashgaz.ru).

For citations

Bashirov M.G., Akchurin D.Sh., Kuvaytsev K.N., Maksimochkin D.E. NEURAL NETWORK PROCESSING OF ELECTROMAGNETIC ACOUSTIC SIGNALS TO IDENTIFY THE STRESS-STRAIN STATE AND DAMAGE OF POWER EQUIPMENT. Vestnik Chuvashskogo universiteta, 2023, no. 4, pp. 44–56. DOI: 10.47026/1810-1909-2023-4-44-56 (in Russian).

Download the full article