energyЭнергетика. Известия высших учебных заведений и энергетических объединений СНГENERGETIKA. Proceedings of CIS higher education institutions and power engineering associations1029-74482414-0341BNTU10.21122/1029-7448-2022-65-1-5-21energy-2129Research ArticleЭЛЕКТРОЭНЕРГЕТИКАELECTRICAL POWER ENGINEERINGРазработка в MATLAB-Simulink искусственной нейронной сети для восстановления искаженной формы вторичного тока. Часть 2An Artificial Neural Network Developed in MATLAB-Simulink for Reconstruction a Distorted Secondary Current Waveform. Part 2РумянцевЮ. B.RumiantsevYu. V.

г. Минск

Minsk

РоманюкФ. А.RomaniukF. A.

Адрес для переписки:Романюк Федор Алексеевич – Белорусский национальный технический университет просп. Независимости, 65/2, 220013, г. Минск, Республика БеларусьТел.: +375 17 331-00-51faromanuk@bntu.by

Address for correspondence:Romaniuk Fiodar A. -Belаrusian National Technical University 65/2, Nezavisimosty Ave., 220013, Minsk, Republic of Belarus Tel.: +375 17 331-00-51 faromanuk@bntu.by

faromanuk@bntu.byБелорусский национальный технический университетБеларусьBelarusian National Technical UniversityBelarus202202022022651521Copyright © Румянцев Ю.B., Романюк Ф.А., 20222022Румянцев Ю.B., Романюк Ф.А.Rumiantsev Y.V., Romaniuk F.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://energy.bntu.by/jour/article/view/2129

Искусственные нейронные сети все чаще используются в различных отраслях электроэнергетики, в том числе в релейной защите. Традиционные микропроцессорные устройства релейной защиты функционируют по принципу вычисления действующих значений контролируемых сигналов тока и напряжения и сравнения их с заранее заданными уставками. Однако вычисляемые действующие величины не всегда отражают реальные процессы, происходящие в защищаемом электрооборудовании, ввиду, например, насыщения трансформатора тока. В таком режиме вторичный ток имеет характерную искаженную форму, которая существенно отличается от идеальной (истинной). Это ведет к занижению вычисляемого релейной защитой действующего значения основной гармоники вторичного тока по сравнению с его истинной действующей величиной и приводит к затягиванию времени срабатывания или отказу функционирования устройств релейной защиты. Одно из перспективных приложений искусственной нейронной сети для целей релейной защиты – восстановление истинной формы сигнала вторичного тока трансформатора тока при его насыщении. В статье рассмотрены этапы реализации нейронной сети в среде MATLAB на примере ее обучения восстановлению искаженной формы вторичного тока. Выполнена проверка функционирования разработанных нейронных сетей в MATLAB-Simulink. С использованием пакета расширения SimPowerSystems реализована модель, позволяющая имитировать режим насыщения трансформатора тока, сопровождающийся искажением формы сигнала его вторичного тока, и ее последующее восстановление с помощью искусственных нейронных сетей. Полученные результаты подтвердили способность нейронных сетей практически полностью восстанавливать искаженную форму вторичного тока трансформатора тока. Применение обученных искусственных нейронных сетей в реальных устройствах релейной защиты представляется перспективным, поскольку обеспечивает повышение их быстродействия и надежности функционирования.

Recently, there has been an increased interest in the use of artificial neural networks in various branches of the electric power industry including relay protection. The operation of the traditional microprocessor-based relay protection device is based on calculation the RMS values of the monitored current and voltage signals and its comparison with the predetermined thresholds. However, calculated RMS values often do not reflect the real processes occurring in the electrical equipment under protection due to, for example, current transformer saturation. In this case secondary current has a characteristic distorted waveform, which is significantly differs from its ideal (true) waveform. This causes underestimation of the calculated RMS value of the secondary current compared to its true value; also, it causes a trip time delay or even to a relay protection devices operation failure. In this regard, one of the perspective applications of the artificial neural network for the relay protection purposes is the current transformer distorted secondary current waveform restoration due to its saturation. The article describes in detail the stages of the practical implementation of the artificial neural networks in the MATLAB-Simulink environment by the example of its use to reconstruct the distorted secondary current waveform of the saturated current transformer. The functioning of the developed neural networks was verified in the MATLAB-Simulink environment; with the use of the SimPowerSystems component library a model was implemented which allow simulating the current transformer saturation, accompanied by the secondary current waveform distortion, and its further restoration using developed artificial neural networks. The obtained results confirmed the ability of the neural networks that had been developed to almost completely restore the distorted secondary current waveform. Thus, it seems promising to use pre-trained artificial neural networks in real relay protection devices, since such use will ensure the speed of real relay protection devices; their operation reliability will also increase.

искусственная нейронная сетьрелейная защитанасыщение трансформатора токаMATLAB-Simulinkartificial neural networkrelay protectioncurrent transformer saturationMATLAB-SimulinkReferencesРумянцев, Ю. В. Разработка в MATLAB-Simulink искусственной нейронной сети для восстановления искаженной формы вторичного тока. Ч. 1 / Ю. В. Румянцев, Ф. А. Романюк // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2021. Т. 64, № 6. С. 479–491. https://doi.org/10.21122/1029-7448-2021-64-6-479-491.Rumiantsev Yu. V., Romaniuk F. A. (2021) An Artificial Neural Network Developed in MATLAB-Simulink for Reconstruction a Distorted Secondary Current Waveform. Part 1. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 64 (6), 479–491. https://doi.org/10.21122/1029-7448-2021-64-6-479-491 (in Russian).Haykin, S. Neural Networks and Learning Machines / S. Haykin; 3rd Ed. New Jersey: Pearson Education Inс., 2009. 936 p. https://doi.org/10.1007/BF02551274.Haykin S. (2009) Neural Networks and Learning Machines. 3rd Ed. Pearson Education Inс. 936.Cybenko, G. Approximation by Superpositions of a Sigmoidal Function / G. Cybenko // Mathematics of Control, Signals, and Systems. 1989. Vol. 2. P. 303–314. https://doi.org/10.1007/BF02551274.Cybenko G. (1989) Approximation by Superpositions of a Sigmoidal Function. Mathematics of Control, Signals, and Systems, 2, 303–314. https://doi.org/10.1007/BF02551274.Neural Network Toolbox. User’s Guide. Version 4 [Electronic Resource]. The MathWorks, 2002. Mode of access: http://cda.psych.uiuc.edu/matlab_pdf/nnet.pdf.Neural Network Toolbox. User’s Guide. Version 4 (2002). The MathWorks. Available at: http://cda.psych.uiuc.edu/matlab_pdf/nnet.pdf.Neural Network Design / M. T. Hagan [et al.]. 2nd Ed. Boston: PWS Publishing, 2014. 1012 p.Hagan M. T., Demuth H. B., Bale M. H., De Jesus O. (2014) Neural Network Design. 2nd Ed. Boston: PWS Publishing. 1012.Медведев, В. С. Нейронные сети. MatLab 6 / В. С. Медведев, В. Г. Потемкин. М.: Диалог-МИФИ, 2002. 496 с.Medvedev V. S., Potemkin V. G. (2002). Neural Networks. MatLab 6. Мoscow, Dialog-MIFI Publ. 496. (in Russian).Совершенствование алгоритма формирования ортогональных составляющих входных величин в микропроцессорных защитах / Ф. А. Романюк [и др.] // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2021. Т. 64, № 2. С. 95–108. https://doi.org/10.21122/1029-7448-2021-64-2-95-108.Romaniuk F. A., Rumiantsev Yu. V., Rumiantsev V. Yu., Novash I. V. (2021) Improvement of Algorithm for Formation of Orthogonal Components of Input Quantities in Microprocessor Protection. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 64 (2), 95–108. https://doi.org/10.21122/1029-7448-2021-64-2-95-108 (in Russian).Формирование ортогональных составляющих входных токов в микропроцессорных защитах электроустановок / Ф. А. Романюк [и др.] // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2021. Т. 64, № 3. С. 191–201. https://doi.org/10.21122/1029-7448-2021-64-3-191-201.Romaniuk F. A., Rumiantsev Yu. V., Rumiantsev V. Yu., Novash I. V. (2021) Formation of Orthogonal Components of Input Currents in Microprocessor Protections of Electrical Equipment. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 64 (3), 191–201. https://doi.org/10.21122/1029-7448-2021-64-3-191-201 (in Russian).Pan, J. An Efficient Compensation Algorithm for Current Transformer Saturation Effects / J. Pan, K. Vu, Y. Hu // IEEE Transactions on Power Delivery. 2004. Vol. 19, Iss. 4. P. 1623–1628. https://doi.org/10.1109/TPWRD.2004.835273.Pan J., Vu K., Hu Y. (2004) An Efficient Compensation Algorithm for Current Transformer Saturation Effects. IEEE Transactions on Power Delivery, 19 (4), 1623–1628. https://doi.org/10.1109/TPWRD.2004.835273.Villamagna, N. A CT Saturation Detection Algorithm Using Symmetrical Components for Current Differential Protection / N. Villamagna, P. Crossley // IEEE Transactions on Power Delivery. 2006. Vol. 21, Iss. 1. P. 38–45. https://doi.org/10.1109/TPWRD.2005.848654.Villamagna N., Crossley P. (2006) A CT Saturation Detection Algorithm Using Symmetrical Components for Current Differential Protection. IEEE Transactions on Power Delivery, 21 (1), 38–45. https://doi.org/10.1109/TPWRD.2005.848654.Wiszniewski, A. Correction of Current Transformer Transient Performance / A. Wiszniewski, W. Rebizant, L. Schiel // IEEE Transactions on Power Delivery. 2008. Vol. 23, Iss. 2. P. 624–632. https://doi.org/10.1109/TPWRD.2008.915832.Wiszniewski A., Rebizant W., Schiel L. (2008) Correction of Current Transformer Transient Performance. IEEE Transactions on Power Delivery, 23 (2), 624–632. https://doi.org/10.1109/TPWRD.2008.915832.Rebizant, W. Digital Signal Processing in Power System Protection and Control / W. Rebizant, J. Szafran, A. Wiszniewski. London: Springer, 2011. 316 p. https://doi.org/10.1007/978-0-85729-802-7.Rebizant W., Szafran J., Wiszniewski A. (2011) Digital Signal Processing in Power System Protection and Control. London, Springer Publ. 316. https://doi.org/10.1007/978-0-85729-802-7.Correction of Current Transformer Distorted Secondary Currents Due to Saturation Using Artificial Neural Networks / D. C. Yu [et al.] // IEEE Transactions on Power Delivery. 2001. Vol. 16, Iss. 2. P. 189–194. https://doi.org/10.1109/61.915481.Yu D. C., Cummins J. C., Wang Zh., Yoon H.-J., Kojovic L. A. (2001) Correction of Current Transformer Distorted Secondary Currents Due to Saturation Using Artificial Neural Networks. IEEE Transactions on Power Delivery, 16 (2), 189–194. https://doi.org/10.1109/61.915481.Khorashadi-Zadeh, H. Correction of Saturated Current Transformers Secondary Current Using ANNs / H. Khorashadi-Zadeh, M. Sanaye-Pasand // IEEE Transactions on Power Delivery. 2006. Vol. 21, Iss. 1. P. 73–79. https://doi.org/10.1109/TPWRD.2005.858799.Khorashadi-Zadeh H., Sanaye-Pasand M. (2006) Correction of Saturated Current Transformers Secondary Current Using ANNs. IEEE Transactions on Power Delivery, 21 (1), 73–79. https://doi.org/10.1109/TPWRD.2005.858799.Lukowicz, M. Artificial Neural Network Based Dynamic Compensation of Current Transformer Errors / M. Lukowicz, E. Rosolowski // Proceedings of the 8th International Symposium on Short-Circuit Currents in Power Systems. 2000. P. 19–24.Lukowicz M., Rosolowski E. (2000) Artificial Neural Network Based Dynamic Compensation of Current Transformer Errors. Proceedings of the 8th International Symposium on Short-Circuit Currents in Power Systems, 19–24.Haghjoo, F. Compensation of CT Distorted Secondary Current Waveform in Online Conditions / F. Haghjoo, M. H. Pak // IEEE Transactions on Power Delivery. 2016. Vol. 31, Iss. 2. P. 711–720. https://doi.org/10.1109/TPWRD.2015.2448634.Haghjoo F., Pak M. H. (2016) Compensation of CT Distorted Secondary Current Waveform in Online Conditions. IEEE Transactions on Power Delivery, 31 (2), 711–720. https://doi.org/10.1109/TPWRD.2015.2448634.Application of ANN Methods for Instrument Transformer Correction in Transmission Line Protection / M. M. Saha [et al.] // Developments in Power System Protection, 7th International Conference. 2001. P. 303–306. https://doi.org/10.1049/cp:20010160.Saha M. M., Izykowski J., Lukowicz M., Rosolowskiz E. (2001) Application of ANN Methods for Instrument Transformer Correction in Transmission Line Protection. Developments in Power System Protection, 7th International Conference, 303–306. https://doi.org/10.1049/cp:20010160.Cummins, J. C. Simplified Artificial Neural Network Structure with the Current Transformer Saturation Detector Provides a Good Estimate of Primary Currents / J. C. Cummins, D. C. Yu, L. A. Kojovic // Power Engineering Society Summer Meeting. 2000. Vol. 3. P. 1373–1378. https://doi.org/10.1109/PESS.2000.868725.Cummins J. C., Yu D. C., Kojovic L. A. (2000) Simplified Artificial Neural Network Structure with the Current Transformer Saturation Detector Provides a Good Estimate of Primary Currents. Power Engineering Society Summer Meeting, 3, 1373–1378. https://doi.org/10.1109/pess.2000.868725.Электрические цепи с ферромагнитными сердечниками в релейной защите / А. Д. Дроздов [и др.]. М.: Энергоатомиздат, 1986. 255 с.Drozdov A. D., Zasypkin A. S., Kuzhekov S. L., Platonov V. V., Podgornyi E. V. (1986) Electric Circuits with Ferromagnetic Cores in Relay Protection. Moscow, Energoatomizdat Publ. 255 (in Russian).Kojovic, L. A. Comparison of Different Current Transformer Modeling Techniques for Protection System Studies / L. A. Kojovic // Power Engineering Society Summer Meeting. 2002. Vol. 3. P. 1084–1089. https://doi.org/10.1109/PESS.2002.1043427.Kojovic L. A. (2002) Comparison of Different Current Transformer Modeling Techniques for Protection System Studies. Power Engineering Society Summer Meeting, 3, 1084–1089. https://doi.org/10.1109/PESS.2002.1043427.Annakkage, U. D. A Current Transformer Model Based on the Jiles-Atherton Theory of Ferromagnetic Hysteresis / U. D. Annakkage, P. G. McLaren // IEEE Transactions on Power Delivery. 2000. Vol. 1, Iss. 1. P. 57–61. https://doi.org/10.1109/61.847229.Annakkage U. D., McLaren P. G. (2000) A Current Transformer Model Based on the Jiles-Atherton Theory of Ferromagnetic Hysteresis. IEEE Transactions on Power Delivery, 1 (1), 57–61. https://doi.org/10.1109/61.847229.Lucas, J. R. Simulation of BH Excursions for Transient Studies / J. R. Lucas, P. G. McLaren // Proceedings of the 33rd Midwest Symposium on Circuits and Systems. 1990. P. 370–373. https://doi.org/10.1109/MWSCAS.1990.140730.Lucas J. R., McLaren P. G. (1990) Simulation of BH Excursions for Transient Studies. Proceedings of the 33rd Midwest Symposium on Circuits and Systems, 370–373. https://doi.org/10.1109/MWSCAS.1990.140730.Kezunovic, M. Experimental Evaluation of EMTP-Based Current Transformer Models for Protective Relay Transient Study / M. Kezunovic, L. A. Kojovic // IEEE Transactions on Power Delivery. 1994. Vol. 9, Iss. 1. P. 405–413. https://doi.org/10.1109/61.277712.Kezunovic M., Kojovic L. A. (1994) Experimental Evaluation of EMTP-Based Current Transformer Models for Protective Relay Transient Study. IEEE Transactions on Power Delivery, 9 (1), 405–413. https://doi.org/10.1109/61.277712.Prochazka, M. Modeling of Current Transformers under Saturation Conditions / M. Prochazka // Advances in Electrical and Electronic Engineering. 2011. Vol. 5, Iss. 1. P. 94–97.Prochazka M. (2011) Modeling of Current Transformers under Saturation Conditions. Advances in Electrical and Electronic Engineering, 5 (1), 94–97.Новаш, И. В. Упрощенная модель трехфазной группы трансформаторов тока в системе динамического моделирования / И. В. Новаш, Ю. В. Румянцев // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2015. № 5. С. 23–38.Novash I. V., Rumiantsev Yu. V. (2015) A Simplified Model of Three-Phase Bank of Current Transformers in the Dynamic Simulation System. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, (5), 23–38 (in Russian).Испытания микропроцессорных токовых защит: теория, моделирование, практика / И. В. Новаш [и др.]. Минск: БНТУ, 2021. 168 с.Novash I. V., Romaniuk F. A., Rumiantsev V. Yu., Rumiantsev Yu. V. (2021) Testing of Microprocessor Current Protections: Theory, Modeling, Practice. Minsk, BNTU. 168 (in Russian).

The authors declare that there are no conflicts of interest present.