Development of a hybrid neural network structure for the system of monitoring and fault identification of electrical substation
https://doi.org/10.46973/0201-727X_2024_4_70
Abstract
Railway transport consumes more than 7 % of the energy generated by power plants in the Russian Federation, which is spent both on train traction and on power supply for non-traction consumers (depots, stations, workshops, and district consumers). Thus, an electrical substation (ES) must ensure reliable power supply for various devices of railway transport and power supply of all consumers of railway transport. In this regard, there is a need for timely detection of faults in the ES operation to ensure uninterruptible power supply, as well as to prevent emergency situations. This paper presents a generalized scheme for monitoring and identifying faults of the electrical substation using a hybrid neural network (HNN). The scheme is presented in IDEF0 notation with a detailed description of the functions performed. The algorithm of data preprocessing for verification of crisp and fuzzy values of selected parameters affecting the ES operation is considered. The authors propose the HNN structure based on the operation of a convolutional neural network that derives signs and templates of parameter values, as well as a recurrent neural network that processes crisp input data. The developed HNN will reduce the time for processing input data, obtain timely assessment of the technical condition of the electrical substation under conditions of heterogeneous data, as well as to take measures aimed at preventing substation failure.
About the Authors
A. E. Kolodenkova
Samara State Engineering University
Russian Federation
Russian Federation
Kolodenkova Anna Evgenievna, Chair «Computer Science and Engineering», Doctor of Engineering Sciences, Associated Professor, Professor
S. S. Vereshchagina
Samara State Engineering University
Russian Federation
Russian Federation
Vereshchagina Svetlana Sergeevna, Chair «Computer Science and Engineering», Candidate of Engineering Sciences, Associate Professor
N. A. Tarutin
Samara State Engineering University
Russian Federation
Russian Federation
Tarutin Nikita Alekseevich, Chair «Power Supply for Industrial Enterprises», Postgraduate Student
References
1. Keawlumyai, N. Reliability evaluation of electrical substations considering load growth / N. Keawlumyai, W. Witoontorn, S. Chaitusaney // 11th International Conference on Electrical Engineering / Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). – 2014. – Р. 1–6. – URL: https://ieeexplore.ieee.org/document/7207048 (date of access: 12/02/2024).
2. Rodriguez, M. Enhancing Prescriptive Capabilities in Electrical Substations: A Systemic Impact Factor Approach for Failure Impact Analysis / M. Rodriguez, A. Crespo Marquez, V. GonzalezPrida // Energies. – 2024. – Vol. 4. – Р. 1–14. – URL: https://www.mdpi.com/1996-1073/17/4/770 (date of access: 12/02/2024).
3. Shabanov, V. On the issue of determining the electrical loads of transformer substations / V. Shabanov, A. Rakhimberdina, I. Yanikiev // Electrical and data processing facilities and systems. – 2022. – Vol. 1. – P. 114–122. – DOI 10.17122/1999-5458-2022-18-1-114-122.
4. Shcheglovitova, E. Classification of transformer substations / E. Shcheglovitova, A. Zotova // Energy Systems. – 2024. – Vol. 1. – P. 122–127. – DOI 10.34031/ES.2024.1.016.
5. Bustos-Brinez, O. Application of data analysis techniques for characterization and estimation in electrical substations / O. Bustos-Brinez, A. Zambrano, J. Rosero Garcia // Frontiers in Energy Research. – 2024. – Vol. 12. – P. 1–19. – DOI 10.3389/fenrg.2024.1372347.
6. Leiva Vilaplana, J. Virtualized Protection, Automation, and Control in Electrical Substations : An Open-Source Dynamic Cost-Benefit Assessment Model / J. Leiva Vilaplana, N. Kabbara, T. Coste [et al.] // IEEE Access. – 2024. – P. 1–17. – DOI 10.1109/ACCESS.2024.3435972.
7. GOST 22782.0-81. Explosion-proof electrical equipment. General Engineering requirements and test methods (with Amendments No. 1, 2, 3). – Moscow : Publishing House of Standards, 1984. – 28 p.
8. GOST 32144-2013. Electric energy. Electromagnetic compatibility of technical equipment. Standards for the quality of electric energy in general-purpose power supply systems. – Moscow : Standartinform, 2014. – 19 p.
9. Wu, D. The effects of data preprocessing on probability of default model fairness / D. Wu // World Journal of Advanced Engineering Technology and Sciences. – 2024. – Vol. 12. – P. 872–878. – URL: https://arxiv.org/pdf/2408.15452 (date of access: 02.12.2024).
10. Almarshad, M. Polysomnography Raw Data Extraction, Exploration, and Preprocessing / M. Almarshad, S. BaHammam, S. Islam, S. AlAhmadi, A. Bahammam // Springer/Nature. – 2024. – DOI 10.1007/978-3-031-68263-6_2.
11. Kuznetsov, A. D. Effective preprocessing of data before their analysis / A. D. Kuznetsov, M. D. Porokhnya, V. V. Fioktistova // Youth research today : collection of articles of the VII International scientific and practical conference. – Petrozavodsk : International Center for Scientific Partnership "New Science" (IP Ivanovskaya I. I.), 2024. – P. 120–126. – ISBN 978-5-00215-227-8.
12. Tarasov, V. I. The role of data preprocessing in forecasting time series / V. I. Tarasov, M. O. Usmanov, A. D. Ponomarev // Artificial intelligence in automated control and data processing systems : Collection of articles of the II All-Russian scientific conference : in 5 volumes. Vol. 2, Moscow, April 27–28, 2023. – Moscow : KDU, Dobrosvet, 2023. – P. 145–150. – ISBN 978-5-7913-1352-2.
13. Karatkevich, M. S. Study of the influence of data preprocessing methods on the results of training the LightGBM regression model / M. S. Karatkevich // Sustainable development of society : new scientific approaches and research : collection of materials of the II International scientific and practical conference. – Moscow : ALEF, 2024. – P. 109–119. – ISBN 978-5-605-09446-3.
14. Kolodenkova, A. E. Selection of Basic Parameters for the Diagnosis of Industrial Electrical Equipment Using Computer Technology / A. E. Kolodenkova, S. S. Vereshchagina // Proceedings – 2022 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2022. – Sochi, 2022. – P. 982–986. – ISBN 978-1-6654-8370-4.
15. Kolodenkova, A. E. Development of a Unified Diagnostic Complex of Electrical Equipment for Intelligent Systems / A. E. Kolodenkova, S. S. Vereshchagina // International Russian Automation Conference (RusAutoCon). – Sochi, 2023. – P. 209–213. – ISBN 979-8-3503-4556-8.
16. Tomin, N. V. The concept of building an intelligent system “artificial dispatcher” for an automatic control system of electric networks based on deep reinforcement learning / N. V. Tomin // Bulletin of the Russian Academy of Sciences. Theory and Control Systems. – 2020. – No. 6. – P. 132–151. – DOI 10.31857/S0002338820050121.
17. Kokshev, P. A. Advantages of using a neural network with a multilayer perceptron architecture for a network data analyzer of a digital substation. Dynamics of nonlinear discrete electrical and electronic systems: Proceedings of the XIV AllRussian scientific and technical conference / P. A. Kokshev, N. A. Galanina // Chuvash State University named after I. N. Ulyanov. – Cheboksary, 2021. – P. 127–129. – ISBN 978-5-7677-3286-9.
18. Cheng, L. Research on visualization monitoring technology of vulnerable high-voltage electrical equipment in substation based on BP artificial neural network / L. Cheng, X. Hu // Applied Mathematics and Nonlinear Sciences. – 2024. – Т. 9. – P. 1–23. – DOI 10.2478/amns-2024-1634.
19. Kenessov, Y. Construction of a recurrent neural network-based electrical load forecasting model for a 110 kV substation: a case study in the Western Region of The Republic of Kazakhstan / Y. Kenessov, K. Tokhtibakiev, A. Saukhimov [et al.] // Eastern-European Journal of Enterprise Technologies. – 2024. – Vol. 2. – P. 6–15. – DOI 10.15587/1729-4061.2024.299192.
20. Kolodenkova, A. E. An approach to detecting faults in electrical equipment using convolutional neural networks / A. E. Kolodenkova, S. S. Vereshchagina // Hybrid and synergetic intelligent systems : a collection of articles based on the materials of the scientific VII All-Russian Pospelovskaya Conference. – Kaliningrad, Saint Petersburg : Russian Christian Humanitarian Academy named after F. M. Dostoevsky, 2024. – P. 281–286. – ISBN 978-5-907855-25-0.
Review
For citations:
Kolodenkova A.E., Vereshchagina S.S., Tarutin N.A. Development of a hybrid neural network structure for the system of monitoring and fault identification of electrical substation. Vestnik Rostovskogo Gosudarstvennogo Universiteta Putej Soobshcheniya. 2024;(4):70-79. (In Russ.) https://doi.org/10.46973/0201-727X_2024_4_70
Views:
8
JATS XML
Email this article 