WAVE INTERPRETATION AND NEURAL NET MONITORING OF NOISE IN VOLTAGE SIGNALS ON POWER LINES

DOI: 10.47026/1810-1909-2024-4-5-13

УДК 621.316.722.9

ББК 31.27-05

Dmitry Yu. ALYUNOV, Maxim V. NIKANDROV, Aleksandr L. SLAVUTSKIY

Key words: power lines, wave propagation velocity, random distribution, noise, neural network monitoring.

Noise in voltage signals on power lines is determined by many factors. Therefore, at the standard sampling rate of signals in measuring instruments, it is considered, most often, to be Gaussian. At a high sampling rate, the noise is modulated, its distribution differs from the normal one. The analysis and control of its structure is of interest, for example, for damage diagnostics and determining the damage location.

The purpose of the study is to show the possibility of neural network control of heterogeneous noise in voltage signals on power lines.

Methods. Based on the wave analysis of signals in power lines, a noise model in industrial frequency voltage signals is described, which allows interpreting its modulation as a result of random spatial fluctuations in wave velocity. The control of noise heterogeneity over the harmonic signal period is carried out on the basis of a recurrent ANN in a sliding time window, the duration of which does not exceed 2 ms.

Results. The noise model in power line voltage signals is proposed as a result of wave reflection from the wave velocity spatial inhomogeneities in the line. In the Born’s scattering approximation, noise is described by the simplest analytical formulas with random parameters. A neural network algorithm based on LSTM cells was tested on model signals recordings, which is used in a sliding time window and allows one to control the noise variance in units of percent of the industrial frequency signal amplitude. Estimates of the neural network algorithm accuracy are given.

Conclusions. A comparison of the noise structure obtained using the proposed model with experimental signals recordings confirms the adequacy of the model at a qualitative level. The proposed neural network monitoring algorithm has high accuracy. The approach can be used to monitor the present state of power lines.

References

1. Alyunov D.Yu. Rekurrentnaya neyronnaya set’ dlya kontrolya shiriny spektra nestatsionarnogo sluchaynogo signala [Recurrent neural network for controlling the spectral width of a non-stationary random signal]. Vestnik Chuvashskogo universiteta, 2023, no. 2, pp. 5–17. DOI: 10.47026/1810-1909-2023-2-5-17.
2. Andreev O.N., Ksenofontov S.I., Slavutskii A.L. Modelirovanie i neirosetevaya obrabotka signalov pri perekhodnykh protsessakh v elektrotekhnicheskikh kompleksakh [Modeling and neural network signal processing at transient processes in electrical complexes]. Cheboksary, 2023, 212 p.
3. Antonov V.I. Adaptivnyi strukturnyi analiz elektricheskikh signalov: teoriya i ee prilozheniya v intellektual’noi elektroenergetike [Adaptive structural analysis of electric signals: the theory and its applications in intellectual power engineering]. Cheboksary, Chuvash State University Publ., 2018, 334 p.
4. Bulychev A.V., Gribkov M.A., Dmitrenko A.M. et al. Distantsionnyye zashchity na osnove tsifrovykh metodov otsenki rasstoyaniya do mesta povrezhdeniya [Distance protection based on digital methods for estimating the distance to the damage site]. Elektrotekhnika, 2021, no. 8, pp. 25–30.
5. Lachugin V.F. Volnovyye metody opredeleniya mesta povrezhdeniya na vozdushnykh liniyakh elektroperedachi [Wave methods for determining the location of damage on overhead power lines]. Relay protection and automation, 2023, no. 1(50), 58–61.
6. Andreev O.N., Slavutskii L.A., Tutaev G.M. et al. Lokalizatsiya momenta nachala perekhodnogo protsessa neirosetevymi programmno-apparatnymi sredstvami [Transients initial stage localization by neural net software and hardware]. Elektrotekhnika, 2023, no. 8, pp. 20–24. DOI: 10.3103/s1068371223080023.
7. Kulikov A.L., Anan’ev V.V., Lachugin V.F. et al. Modelirovanie volnovykh protsessov na liniyakh elektroperedachi dlya povysheniya tochnosti opredeleniya mesta povrezhdeniya [Power Line Travelling Wave Processes Modeling for Fault Location Accuracy Improving]. Elektricheskie stantsii, 2015, no. 7, pp. 45–53.
8. Kozlov V.N., Ermakov K.I., Kiryushin M.I. et al. Povysheniye tochnosti volno-vykh metodov OMP vysokovol’tnykh LEP [Improving the accuracy of wave methods for fault location of high-voltage power transmission lines]. Energiya yedinoy seti, 2022, no. 5-6 (66-67), 26–35.
9. Podshivalin A.N., Ismukov G.N. Otsenka sostoyaniya linii elektroperedachi sredstvami aktivnogo volnovogo OMP [Assessment of the state of a power transmission line by means of an active wave OMP]. Relay protection and automation, 2024, no. 1(54), 54–58.
10. Podshivalin A.N., Ismukov G.N. Statisticheskiy izmeritel’nyy organ volnovykh ustroystv RZA [Statistical measuring organ of wave relay protection and automation devices]. Izvestiya Akademii elektrotekhnicheskikh nauk RF, 2021, no. 23, pp. 16–27.
11. Suchkov V.O., Yadarova O.N., Slavutskii L.A. Distantsionnyy ul’trazvukovoy kontrol’ vozdushnogo potoka na osnove iskusstvennoy neyronnoy seti [Remote ultrasonic monitoring of air flow based on an artificial neural network]. Vestnik Chuvashskogo universiteta, 2015, no. 1, pp. 207–212.
12. Bhatnagar M., Yadav A., Swetapadma A. et al. LSTM-based low-impedance fault and high-impedance fault detection and classification. Electr Eng. DOI: 10.1007/s00202-024-02381-0.
13. Guo M.F., Yang N.C., Chen W.F. Deep-Learning-Based Fault Classification Using Hilbert–Huang Transform and Convolutional Neural Network in Power Distribution Systems. IEEE Sensors Journal, 2019, vol. 19, no. 16, pp. 6905–6913. DOI: 10.1109/JSEN.2019.2913006.
14. Ishimaru A. Wave Propagation and Scattering in Random Media. New-York, Academic Press, 1978, 272 p.
15. Leonowicz Z, Jasinski M. Machine Learning and Data Mining Applications in Power Systems. Energies, 2022, vol. 15, DOI: 10.3390/en15051676.
16. Minullin R.G., Akhmetova I.G., Kasimov V.A. et al. Location Monitoring with Determining the Location of Damage and the Current Performance of Overhead Power Lines. Power Technology and Engineering, 2023, vol. 57, no. 1, pp. 145–152. DOI: 10.1007/s10749-023-01635-4.
17. Slavutskii L.A., Lazareva N.M., Portnov M.S. et al. Neural net without “deep learning”: signal approximation by multilayer perceptron. In: 2^nd Conf. on Computer Applications for Management and Sustainable Development of Production and Industry (CMSD-II-2022), Dushanbe, Washington: SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS, 2023, 125640. DOI: 10.1117/12.2669233.
18. Slavutskii L.A., Ivanova N.N. Using the simplest neural network as a tool for fault location in power lines. In: AIP Conference Proceedings, Moscow, 2022, 030006. DOI: 10.1063/5.0074926.
19. Skrobek D., Krzywanski J., Sosnowski M. et al. Artificial Intelligence for Energy Processes and Systems: Applications and Perspectives. Energies 2023, vol. 16, 3441. DOI: 3390/en16083441.
20. Zhou H., Chen J., Ye M. et al. Transient Fault Signal Identification of AT Traction Network Based on Improved HHT and LSTM Neural Network Algorithm. Energies, 2023, vol. 16, 1163. DOI: 10.3390/en16031163

Information about the authors

Dmitry Yu. Alyunov – Post-Graduate Student, Department of Automation and Control in Technical System, Chuvash State University, Russia, Cheboksary (aldmitry89@gmail.com; ORCID: https://orcid.org/0000-0001-8673-3683).

Maxim V. Nikandrov – Candidate of Technical Sciences, Director, LLC «iGRIDS» ltd., Russia, Cheboksary (nixmak@mail.ru; ORCID: https://orcid.org/0000-0001-6846-3384).

Aleksandr L. Slavutskiy – Candidate of Technical Sciences, Deputy Head of Software Development, LLC «NEC TECH», Russia, Cheboksary (slavutskii@gmail.com; ORCID: https://orcid.org/0000-0002-6315-2445).

For citations

Alyunov D.Yu., Nikandrov M.V., Slavutskiy A.L. WAVE INTERPRETATION AND NEURAL NET MONITORING OF NOISE IN VOLTAGE SIGNALS ON POWER LINES. Vestnik Chuvashskogo universiteta, 2024, no. 4, pp. 5–13. DOI: 10.47026/1810-1909-2024-4-5-13 (in Russian).

Download the full article