System for assessment and prediction of the technical condition of power oil-filled transformer equipment of distribution networks using machine learning

RELEVANCE the research is to develop a new system for assessing the technical condition of power oil-filled transformer equipment of distribution networks.
OBJECT. To increase the accuracy of assessing the technical condition of power oil-filled transformer equipment (POTE) of distribution networks through the use of machine learning methods. Currently, an increase in the volume of analyzed information about the state of the management system of distribution networks leads to significant changes in the choice of data processing methods. The use of machine learning methods is associated both with the need to apply operational experience (in the form of expert assessments) and to obtain objective assessments of the condition of transformer equipment of distribution networks from instrumentation and sensors.
METHODS. This work uses research methods such as mathematical modeling and the method of paired comparisons. As an example, we consider the oil-filled power transformer TMN-6300, its diagnostic parameters, external and operating parameters. The technical condition of the TMN-6300 transformer is assessed and a predictive model is created based on the existing monitoring system and machine learning methods, which make it possible to formalize expert knowledge and automate the process of data processing and analysis.
RESULTS. A database has been created to assess and predict the technical condition of POTE of distribution network management systems. The algorithm for predicting the technical condition of POTE of the technical equipment in the form of an artificial neural network model was tested in the developed assessment system.
CONCLUSION. The results of assessing and predicting the technical condition of POTE of the metering system of distribution networks obtained in this work prove the unconditional relationship between the parameters of the metering system and external, operating parameters. The data obtained as a result of modeling helps to increase the accuracy of forecasting the technical condition and determine the longterm prospects for the functioning of POTE the equipment management system, timely maintenance and repairs over the course of years and months.

1. Galyautdinova A., Ivshin I., Vladimirov O., et al. Software and algorithmic support for online assessment of transformer substation technical condition 35/6(10) kV. REEPE 2023: Proceedings of the 5th International Youth Conference on Radio Electronics, Electrical and Power Engineering; 16-18 March 2023; Moscow, Russian Federation. Moscow: IEEE; 2023. pp. 28-40.

2. Decree of the President of the Russian Federation 01.12.2016 № 642 About the Strategy for Scientific and Technological Development of the Russian Federation.

3. Galyautdinova AR, Ivshin IV, Analysis of parameters of power oil filled transformers of distribution networks to assess its technical condition. Proceedings of the V All-Russian scientific and practical (with international participation) conference dedicated to the celebration of the 55th anniversary of KSPEU. In 2 volumes, Kazan, October 11–12, 2023; Kazan: Kazan State Power Energy University, 2023. pp. 234-238. (In Russ.).

4. Khalyasmaa A., Matrenin P., Eroshenko S. Averaged errors as a risk factor for intelligent forecasting systems operation in the power industry. Smart Energy. USSEC 2021: Proceedings of the 2021 Ural-Siberian Smart Energy Conference, USSEC 2021. 13–15 November 2021; Novosibirsk, 2021. pp. 192-196. doi 10.1109/USSEC53120.2021.9655742.

5. Khalyasmaa AI, Revenkov IS, Sidorova AV Application of digital twin technology for analysis and prediction state of power transformer equipment. Vestnik Kazanskogo gosudarstvennogo ehnergeticheskogo universiteta. 2022; 55(3):99-113. (In Russ).

6. Byerly J., Schneider C., Schloss R. et al. Real-time circuit breaker health diagnostics. CPRE 2017: Proceedings of the 70th Annual Conference for Protective Relay Engineers, CPRE 2017. pp. 1-6.

7. Ivshin IV, Galyautdinova AR, Vladimirov OV, et al. Methodology of online assessment of technical state of transformer substation 35/6 (10) kV by express analysis coefficient. Proceedings of the higher educational institutions. ENERGY SECTOR PROBLEMS. 2021; 23(4):14-26. (In Russ). doi: 10.30724/1998-9903-2021-23-4-14-26.

8. Vladimirov O., Galyautdinova A., Ivshin I., et al. Equipment and data transmission system for express analysis of the technical condition of the main equipment of the 35/6(10)kV transformer substation. Efficient Production and Processing. 2021: Proceedings of ICEPP 2021, 18-20 February2021; Kazan: ICEPP 2021. pp. 577-583.

9. Order of the Ministry of Energy of the Russian Federation 26.07.2017 № 676 On approval of the methodology for assessing the technical condition of the main technological equipment and power lines of power plants and electrical networks.

10. www.edu.tltsu.ru Method of paired comparisons (Saaty method).

11. Khruslov L., Rostovikov M., Shishov V. Web-based power quality monitoring system of smart transformer substation RTP-34 MPEI for engineering education. INFORNO-2016: Proceedings of the International Scientific and Practical Conference, INFORNO-2016. pp. 639-642.

12. Nikulin SА, Karnavsky EL Optimization of electrochemical protection installation modes. Automation and remote control. 2014; 3(57): 64–68. (In Russ.)

13. Li Z., Yang J., Zhang Z. et al. Real Time Evaluation Algorithm for Measurement Performance of Substation Voltage Transformer Based on Artificial Neural Network. Proceedings of the 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), 2018. pp.1-4.

14. Gao Q., Zhong C., Wang Y., Wang P., Yu Z., Zhang J. Defect analysis of the same batch of substation equipment based on big data analysis algorithm. Proceedings of the 3rd International Conference on Green Energy and Sustainable Development. 2021. V.651. pp. 1-8.

15. Eroshenko S., Khalyasmaa A., Snegirev D., et al. The impact of data filtration on the accuracy of multiple time-domain forecasting for photovoltaic power plants generation. Applied Sciences (Switzerland), 2020. V. 10, № 22. pp. 1-22. doi: 10.3390/app10228265.

16. Farhadi M., Mollayi N. Application of the least square support vector machine for point-to-point forecasting of the PV power. International Journal of Electrical and Computer Engineering, August 2019. V.9(4). pp. 2205 - 2211.

17. Alimi O., Ouahada K., Abu-Mahfouz A. A review of machine learning approaches to power system security and stability. IEEE Access, art. 8, № 9121208, 2020. pp.113512-113531.

18. Gavrilenko AV, Dolin AP Quality control system for pressing windings and steel of transformers based on vibration measurements, monitoring the condition of oil pumps. Dimrus. Perm, 2015. pp. 60. (In Russ.)