Application of artificial neural networks for monitoring stability parameters of electrical engineering systems

THE RELEVANCE of the study lies in solving the important problem of increasing the stability and reliability of electrical engineering systems (EES). The AIM of the work is to reduce the number of forced shutdowns of electrical equipment during voltage drops caused by short circuits inevitable during operation of electrical networks. The issues of selecting the parameters of minimum voltage protection in electrical engineering systems are considered. As a result of the analysis of operational data and simulation modeling of voltage drops, it was found that when using minimum voltage protection (MVP) with independent characteristics, more than 50% of protection trips with load disconnection occur unreasonably. The basis for disconnecting the load is a violation of the stability of the electrical engineering system. METHODS. The use of MVP with a dependent response time characteristic on the residual voltage value close to the stability limit reduces the share of unreasonable MVP trips, but does not eliminate them completely. To minimize the number of unreasonable protection trips, it is necessary to adapt the parameters of the MVP characteristic to the stability limit dependent on the load and power source mode. To monitor the stability boundary parameters of the electrical engineering system during operation, it is proposed to use artificial neural network algorithms. RESULTS. The tested Levenberg-Marquardt (LM) algorithm showed sufficient accuracy of stability monitoring based on the parameters of the electrical engineering system measured during operation. It is shown that the use of the dependent characteristic of the MVP, the parameters of which are adapted to the load and power source mode using neural network algorithms, allows for approximately a twofold reduction in the number of unjustified load shutdowns and an increase in the stability of the electrical engineering system of continuous production.

1. Ershov M.S., Egorov A.V., Trifonov A.A. Stability of industrial electrical systems. – M.: Nedra Publishing House LLC, 2010. – 319 p.

2. Dzyuin D.V., Skopin G.A., Komkov A.N., Dmitrieva V.V. Dynamic voltage restorer application in the multi-motor electric drive system of a belt conveyor. Power engineering: research, equipment, technology. 2025; 27 (2): 49-62. doi: 10.30724/1998-9903 2025-27-2-49-62.

3. Sattarov RR, Garafutdinov RR. research of the operation of a group of asynchronous motors at short-term voltage slopes for the conditions of the oil industry Power engineering: research, equipment, technology. 2020;22(6):92-100. doi:10.30724/1998-9903-2020-22-6-92-100.

4. Ershov M.S., Komkov A.N., Blyuk V.V. Procedures for calculating stability indicators of multi-machine electrical systems of industrial production / Industrial Power Engineering. - 2021, No. 9. - P. 18-26.

5. Blyuk V., Ershov M., Komkov A. Models and algorithms for quick calculation of electromechanical transition process of multi-machine electrotechnical systems/ Proceedings - 2019 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency, SUMMA 2019. P. 686-689.

6. Galeeva RU, Kuksov SV. Algorithm for simulating the self-starting of a group of asynchronous electric motors with a short-circulated rotor. Power engineering: research, equipment, technology. 2021;23(3):181-193. doi:10.30724/1998-9903-2021-23-3-181-193.

7. Liu A., Wang Y., Zhu Y., Park S.-J. Research on power quality improvement system based on dynamic voltage restorer // IET Power Electron. 2024. Vol. 17. Pp. 1399–1410. DOI: 10.1049/pel2.12696.

8. Ivanov IYu., Novokreshchenov VV., Ivanova VR. Current state of the problems of functioning of relay protection and automation complexes used in an active adaptive network. Power engineering: research, equipment, technology. 2022;24(6):102-123. doi:10.30724/1998 9903-2022-24-6-102-123.

9. Sharygin M. V., Vukolov V. Y., Petrov A. A. Algorithm of automatic adaptation of multidimen sional relay protection setpoints to the configurable power distribution network // Bulletin NGIEI. 2020. № 11 (114). P. 65–78. (In Russ.). DOI: 10.24411/2227-9407-2020-10106 .

10. Viktorovich, V.M., Vasilyevich, D.A., Vladimirovich, M.K. and Nikolaevich, S.V. Comprehensive Automation of Microprocessor Protection Relay Terminals Operated on AC Railways// Journal of Applied Mathematics and Physics. 2022. №10. – P/ 491-503. https://doi.org/10.4236/jamp.2022.102037.

11. Ershov M.S., Nozdrya E.G. Adaptation of indicators and identification of violation of stability of industrial electrical systems / Industrial Power Engineering. 2018. - No. 12. - P. 2-5.

12. Menshov B.G., Ershov M.S., Egorov A.V. Determination of equivalent parameters of the power supply network for calculating the short-circuit current of the load node/Electricity. – 1993. - No. 10. – P. 19-22.

13. Ting Yang, Xiyang Qian and Liqing Ren. Application of Artificial Intelligence Algorithm in Relay Protection of Distribution Network// International Transactions on Electrical Energy Systems Volume 2022, Article ID 7138367, 12 p. https://doi.org/10.1155/2022/713836714.

14. Zozan Saadallah Hussain, Ahmed J. Ali, Ahmed A. Allu, Rakan Khalil Antar. Improvement of protection relay with a single-phase auto reclosing mechanism based on artificial neural network// International Journal of Power Electronics and Drive System (IJPEDS). Vol. 11, No. 1, March 2020, pp. 505- 514. ISSN: 2088-8694. DOI: 10.11591/ijpeds.v11.i1.pp505-514 .

15. Huo, C., Rong, X.-T., Huang, Z.-W., Han, Z.-X., Fan, Y.-P., Wang, Z.-J., & Fu, J.-R. (2025). A Novel Static Voltage Stability Region Boundary Generation Method Combining Analytics with Predictive Correction. Journal of Electrical Engineering & Technology, 20(5), 2977–2991. https://doi.org/10.1007/s42835-025-02206-5

16. Ahmad, H., Yousif, M., Shah, M., & Ullah, N. (2023). Monitoring Transient Stability in Electric Power Systems Using a Hybrid Model of Convolutional Neural Network and Random Forest. Electric Power Components and Systems, 52(6), 946–958. https://doi.org/10.1080/15325008.2023.2237034

17. Umair Shahzad. Probabilistic Transient Stability Assessment of Power Systems Using Artificial Neural Network// Journal of Electrical Engineering, Electronics, Control and Computer Science – JEEECCS, 2021, Volume 8, Issue 27, pages 35-42.