The System for Automated Processing of the Results of Thermal Imaging Diagnostics of Electrical Equipment

The development of the electric power industry is accompanied by the improvement of diagnostic tools for the state of equipment in energy systems. Some of the electrical network equipment is significantly worn out and requires increased attention in order to determine the residual resource. The synthesis of intelligent technologies and generally accepted diagnostic methods is the next step towards the future of the electric power industry. The aim of the project is to develop the principles for the functioning of an automated processing system for results of thermal imaging diagnostics of electrical equipment. The paper examines the criteria for evaluating defects in electrical equipment based on the heating temperature. An algorithm for automating the processing of the results of thermal imaging diagnostics of electrical equipment is also being developed on the basis of artificial neural networks. The software implementation of the detection of electrical installation elements in infrared images is performed using the YOLOv5 architecture. Testing and evaluation of the trained neural network are performed using thermal imaging diagnostics data of working electrical equipment. The neural network model trained as part of the study demonstrates confident detection of electrical installation parts based on the results of detecting thermograms from a test sample. Based on the results of the analysis of regulatory documentation, an approach to determining the degree of defect development has been clearly laid out. In addition to using thermal images of electrical grid equipment, the current load and ambient temperature are also recorded to select a suitable formula for calculating temperature excess or excessive temperature of an electrical installation unit or contact connection. The developed algorithm for automating the processing of the results of thermal imaging diagnostics of electrical installations based on the YOLOv5 neural network reflects the main processes necessary for the functioning of the system. A custom dataset was generated and marked up, including thermograms of real-life electrical installations, on the basis of which a neural network model was trained. Using a test sample, we were able to calculate the values of metrics to evaluate the quality of YOLOv5 model learning. The developed system has been tested on thermograms of electrical equipment. Its use makes it possible to identify not only the developed defects, but also the initial stage of the occurrence of defects in an automated mode.

1. The Energy Strategy of the Russian Federation for the Period up to 2035 Approved by the Decree of the Government of the Russian Federation, June 9, 2020, No 1523-R. Ministry of Energy of the Russian Federation. Available at: https://minenergo.gov.ru/ministry/energy-strategy (accessed 26 September 2024) (in Russian).

2. SMART 35 Recloser: An Innovative Solution for Upgrading Power Centers and Improving the Reliability of 35 kV Networks. Elec.ru – Electrotechnical Internet Portal. Available at: https://www.elec.ru/viewer?url=/files/2017/05/03/Reklouzer-SMART35.pdf (accessed 26 September 2024) (in Russian).

3. Khalyasmaa A. I., Dmitriev S. A., Kokin S. E., Glushkov D. A. (2015) Diagnostics of Electrical Equipment of Power Stations and Substations. Ekaterinburg, Ural University Publishing House, 64 (in Russian).

4. Sekretarev Yu. A., Gorshunov A. A. (2025) Models of the Current Technical Condition of Electrical Equipment for Calculating the Reliability of Power Supply Systems for Single-Users within the Framework of a Risk-Based Approach. Energetika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 68 (1), 17–34. https://doi.org/10.21122/1029-7448-2025-68-1-17-34 (in Russian).

5. Khlebtsov А. Р., Zainutdinova L. КН., Shilin A.N. (2020) Development of Methods and Devices for Diagnostics of Power Electrical Equipment of Transformer Substations; Elektrotekhnicheskiye i informatsionnyye kompleksy i sistemy = Electrical and data processing facilities and systems, 16 (3), 14–27. https://doi.org/10.17122/1999-5458-2020-16-3-14-27 (in Russian).

6. Kuvshinov A. A., Tarakanov V. P. (2016) Diagnostics of the Technical Condition of Electrical Equipment in Power Supply Systems. Togliatti, Togliatti State University. 90 (in Russian).

7. Svi P. M. (1992) Methods and Means of Diagnostics of High Voltage Equipment. Moscow, Energoatomizdat Publ. 240 (in Russian).

8. Maksudov D. V., Fedosov E. M. (2009) Methods of Selection of Partial Discharge Signals in Isolation of Power Transformers. Vestnik USATU, 12 (2), 138–143 (in Russian).

9. Vdoviko V. P. (2007) Partial Discharges in the Diagnosis of High-Voltage Equipment. Moscow, Nauka Publ. 156 (in Russian).

10. Kuchinskiy G. S. (1979) Partial Discharges in High Voltage Structures. Leningrad, Energiya Publ., Leningrad Branch. 224 (in Russian).

11. Gavrilenko A. V., Dolin A. P. (2004) Technique of Vibration Inspection of Power Transformers. Available at: https://megaom.ucoz.ru/_ld/0/40_____.pdf (in Russian).

12. Puzina E. Yu., Tuygunova A. G., Khudonogov I. A. (2020) Systems of Monitoring of Power Transformers of Traction Substations. Irkutsk, Irkutsk State Transport University (IrGUPS). 184 (in Russian).

13. Vavilov V. P. (2009) Infrared Thermography and Thermal Control. Moscow, Spektr Publishing House. 544 (in Russian).

14. Vlasenko S. A., Ignatenko I. V. (2022) Monitoring and Diagnostics of Bolted Electrical Connections of the Traction Power Supply System. Khabarovsk, Far Eastern State Transport University (FESTU) Publishing House. 107 (in Russian).

15. Korenciak D., Sebok M., Gutten M. (2019) Thermal Measurement and its Application for Diagnostics of Distribution Oil Transformers. Energetika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 62 (6), 583–594. https://doi.org/10.21122/1029-7448-2019-62-6-583-594 (in Russian).

16. RD [Guidance Document] 153-34.0-20.363-99. Method for Infrared Inspection of Electrical Equipment and Overhead Lines. Moscow, SPO ORGRES, 2001. 136 (in Russian).

17. RD [Guidance Document] 34.45-51.300-97. Scope and Standards for Tests of Electrical Equipment. Moscow, IC ENAS Publishing House, 2004. 256 (in Russian).

18. Velichko V. A., Chernova A. D. (2023) Proposals for Improving the Criteria System for Assessing the Condition of Electrical Equipment Based on the Results of Infrared Control. Problemy i perspektivy razvitiya elektroenergetiki i elektrotekhniki: materialy V Vseros. nauch.-prakt. (s mezhdunar. uchastiem) konf., posvyashch. prazdnovaniyu 55-letiya KGEU. T. 2 [Problems and Prospects of Development of the Electric Power Industry and Electrical Engineering”: Proceedings V All-Russian Scientific and Practical Conference (with International Participation) Dedicated to the Celebration of the 55th Anniversary of the KGEU. Vol. 2]. Kazan, Kazan StatePower Engineering University, 219–228 (in Russian).

19. Lebed’ N. I. (2022) Simulation Modeling of Automated Control Systems for Technological Processes in the Electric Power Industry and the Agro-industrial Complex. Volgograd, Volgograd State Agrarian University Publ. 88 (in Russian).

20. Standard for Infrared Inspection of Electrical Systems & Rotating Equipment. NJ, Infraspection Institute, 2016. Available at: https://www.atlanticleak.com/wp-content/uploads/2019/08/Standard-for-Infrared-Inspection-of-Electrical-systems-and-Rotating-Equipment.pdf (accessed 26 September 2024).

21. Kim J. S., Choi K. N., Kang S. W. (2021) Infrared Thermal Image-Based Sustainable Fault Detection for Electrical Facilities. Sustainability, 13 (2), 557. https://doi.org/10.3390/su13020557.

22. Xu F., Liu S., Zhang W. (2024) Research on Power Equipment Troubleshooting Based on Improved AlexNet Neural Network. Journal of Measurements in Engineering, 12 (1), 162–182, https://doi.org/10.21595/jme.2023.23786.

23. Wu J., Li X., Zhou Y. (2022) An infrared image detection of power equipment based on super-resolution reconstruction and YOLOv4. The Journal of Engineering, 2022, 1006–1016. https://doi.org/10.1049/tje2.12187.

24. Qi C., Chen Z., Chen X., Bao Y., He T., Hu S., Li J, Liang Y, Tian F, Li M. (2023). Efficient Real-time Detection of Electrical Equipment Images Using a Lightweight Detector Model. Frontiers in Energy Research, 11, 1291382. https://doi.org/10.3389/fenrg.2023.1291382.

25. Pérez-Aguilar D. A., Pérez-Aguilar J. M., Pérez-Aguilar A. P., Risco-Ramos R. H., Malpica-Rodríguez M. E. (2024) Electric Substation Inspection: YOLOv5 in Hotspot Detection Through Thermal Imaging. Ingenius. Revista Ciencia y Tecnología, 31, 43–54. https://doi.org/10.17163/ings.n31.2024.04.

26. Wang Y., Wu B. (2024) Infrared Image Recognition of Substation Equipment Based on Adaptive Feature Fusion and Attention Mechanism. Journal of Electronics & Information Techno-logy, 46 (9), 3749–3756 (in Chinese). https://doi.org/10.11999/JEIT231047.

27. Ahmed K. R. (2021). Smart Pothole Detection Using Deep Learning Based on Dilated Convolution. Sensors, 21 (24), 8406. https://doi.org/10.3390/s21248406.

28. Velichko V. A., Kosenko A. D. (2024) Software Implementation of an Algorithm for Automating Thermal Imaging Diagnostics of Substation Equipment Using the YOLOv5 Neural Network. Universitetskii kompleks kak regional'nyi tsentr obrazovaniya, nauki i kul'tury: materialy Vseros. nauch.-metod. konf., Orenburg, 01–03 fevr. 2024 g. [University Complex as a Regional Center of Education, Science and Culture. Proceedings of the All-Russian Scientific and Methodological Conference, Orenburg, 01–03 February 2024.]. Orenburg, Orenburg State University, 1209–1214 (in Russian).

29. Chernova A. D., Velichko V. A. (2023) Markup of Images of Electrical Installation Elements for Training the YOLOv5 Neural Network. Energetika: sostoyanie, problemy, perspektivy: materialy XIV Vserossiiskoi nauch.-tekhn. konf., Orenburg [Power Engineering: State, Problems, Prospects: Proceedings of the XIV All-Russian Scientific and Technical Conference]. Orenburg, Orenburg State University, 217–222 (in Russian).

30. Yaryshev S. N., Ryzhova V. A. (2022) Deep Learning and Neural Network Technologies in Video Analysis Tasks. St. Petersburg, ITMO University. 82 (in Russian).

31. Train YOLOv5 on Custom Data. Ultralytics. Available at: https://docs.ultralytics.com/yolov5/tutorials/train_custom_data/ (accessed 11 January 2024) (in Russian).

32. Gomede E. (28 August 2023) The Significance of Train-Validation-Test Split in Machine Learning. Medium. Available at: https://medium.com/@evertongomede/the-significance-of-train-validation-test-split-in-machine-learning-91ee9f5b98f3.