Journal "Software Engineering"
a journal on theoretical and applied science and technology
ISSN 2220-3397

Issue N5 2025 year

DOI: 10.17587/prin.16.231-239
High Voltage Equipment Diagnostics based on Ultraviolet Imaging Processing using Adaptive Computer Vision Method
A. I. Khalyasmaa, PhD, Head of the Scientific laboratory, a.i.khaliasmaa@urfu.ru, Ural Federal University named after the first President of Russia B. N. Yeltsin, Ekaterinburg, 620062, Russian Federation
Corresponding author: Alexandra I. Khalyasmaa, PhD, Head of the Scientific Laboratory, Ural Federal University named after the first President of Russia B. N. Yeltsin, Ekaterinburg, 620062, Russian Federation, E-mail: a.i.khaliasmaa@urfu.ru
Received on December 11, 2024
Accepted on January 15, 2025

Inspection of high voltage equipment is being automated in order to improve efficiency of repair and maintenance procedures. Also, it is necessary to use methods of energized equipment inspection without installation of multiple sensors on each equipment unit. It can be done using analysis of surface partial discharges in ultraviolet spectrum. Processing of ultraviolet images needs expert knowledge and requires a lot of time to carry out. The method for automated detection of surface partial discharges on ultraviolet images is proposed. The algorithm combines deterministic algorithms of computer vision, the proposed algorithm of adaptive threshold filtering and machine learning to optimize heuristic parameters of the algorithm. Combination of different filters together with division of the initial image into multiple blocks results in minimization of false-negative results. Application of morphological transformations enables minimization of false-positive results while retaining shapes of true discharges on the image. The proposed algorithm has demonstrated 80 % accuracy in detection of surface partial discharges on UV images of high voltage disconnectors of a real power station. The algorithm is characterized by low computational complexity, high interpretability, resistance to image noise and invariance to survey angle. Therefore, it can be used in highly automated decision support systems of equipment inspection.

Keywords: high voltage equipment, equipment inspection, surface partial discharge, computer vision, image filtration, ultraviolet control
pp. 231—239
For citation:
Khalyasmaa A. I. High Voltage Equipment Diagnostics based on Ultraviolet Imaging Processing using Adaptive Computer Vision Method, Programmnaya Ingeneria, 2025, vol. 16, no. 5, pp. 231—239. DOI: 10.17587/prin.16.231-239 (in Russian).
References:
  1. Jin L., Ai J., Tian Z., Zhang Y. Detection of polluted insulators using the information fusion of multispectral images, IEEE Transactions on Dielectrics and Electrical Insulation, 2017, vol. 24, no. 6, pp. 3530—3538. DOI: 10.1109/TDEI.2017.006516.
  2. Lei H., Zang C., Jiang Z. et al. Ultraviolet imaging method to detect the damage of pillar insulators, High Voltage Electrical Ap­paratus, 2009, vol. 45, no. 5. pp. 87—91.
  3. Jiahao H., Bo J., Guiquan X. et al. Research on the Factors Influencing the UV Detection of Corona Discharge Under Combined AC-DC Voltage, Proceedings of the 2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES), Beijing, 2022, pp. 43—48. DOI: 10.1109/SPIES55999.2022.10082260.
  4. Li M., Jing Y., Zhang L. et al. Insulator Defect Detec­tion Based on Ultraviolet Imaging and Acoustic Emission Signal, Proceedings of the 2020 IEEE 3rd Student Conference on Electri­cal Machines and Systems (SCEMS), Jinan, 2020, pp. 472—475. DOI: 10.1109/SCEMS48876.2020.9352424.
  5. Arbuzov R. S., Zharich D. S., Ovsyannikov A. G., Sh-vets N. A. Interpretation of the results of UV inspection of high-voltage equipment, Elektroenergiya. Peredacha i raspredeleniye, 2023, vol. 5 (80), pp. 126—131 (in Russian).
  6. Khalyasmaa A. I., Petrunko N. N. An alternative approach to diagnostics of external insulation of high-voltage equipment of power stations and substations, Informatika i sistemy upravleniya, 2024, vol. 4, no. 82, pp. 72—82. DOI: 10.22250/18142400_2024_82_4_72 (in Russian).
  7. Gyrichidi N., Romanov A. M., Trofimov O. V. et al. GNSS-Based Narrow-Angle UV Camera Targeting: Case Study of a Low-Cost MAD Robot, Sensors, 2024, vol. 24, pp. 3494. DOI: 10.3390/s24113494.
  8. Romanov A. M., Gyrichidi N., Trofimov O. V., Eroshenko S. A. MAD Robot: Concept and Prototype Description of the Robot for Multi-Spectral Power Equipment Diagnostics. Part II, Proceedings of the 2023 Belarusian-Ural-Siberian Smart Energy Con­ference (BUSSEC), Yekaterinburg, 2023, pp. 142—149. DOI: 10.1109/BUSSEC59406.2023.10296278.
  9. Zhao W., Cui A., Fang M. et al. State assessment of 110—220 kV intelligent substation based on multisensor fusion algorithm control and image vision, Frontiers in Energy Research, 2023, no. 10, article 1047359. DOI: 10.3389/fenrg.2022.1047359.
  10. Romanov A. M., Gyrichidi N., Volkova M. A. et al. Automated mission planning for aerial large-scale power plant thermal inspection, Journal of Field Robotics, 2024, no. 41, pp. 1313—1348. DOI: 10.1002/rob.22320.
  11. Zeng Y., Qin X., Li B. et al. A Novel Autonomous Landing Method for Flying—Walking Power Line Inspection Robots Based on Prior Structure Data, Applied Science, 2023, no. 13, article 9544. DOI: 10.3390/app13179544.
  12. Zhao W., Liu W., Hu Y. et al. Extraction method of insulator discharge area in ultraviolet image and its application, Proceedings of the 2017 4th International Conference on Systems and Informatics (ICSAI), Hangzhou, 2017, pp. 857—961. DOI: 10.1109/ICSAI.2017.8248405.
  13. Hu B., Ma L.-X., Yuan S.-J., Yang B. New corona ultraviolet detection system and fault location method, Proceedings of the 2012 China International Conference on Electricity Distribution, Shanghai, 2012, pp. 1—4. DOI: 10.1109/CICED.2012.6508475.
  14. Limin Y., Zhangyu. Ultraviolet Image Processing Method in Corona Detection, Proceedings of the 2009 Second International Workshop on Computer Science and Engineering. Qingdao, 2009, pp. 327—331. DOI: 10.1109/WCSE.2009.680.
  15. Zhang D., Chen S. Intelligent Recognition of Insulator Contamination Grade Based on the Deep Learning of Ultraviolet Discharge Image Information, Energies, 2020, no. 13, article 5221. DOI: 10.3390/en13195221.
  16. Jin L., Zhang D. Contamination Grades Recognition of Ceramic Insulators Using Fused Features of Infrared and Ultraviolet Images, Energies, 2015, no. 8, pp. 837—858. DOI: 10.3390/en8020837.
  17. Wang B., Guo R., Li B. et al. SmartGuard: An autonomous robotic system for inspecting substation equipment, Journal of Field Robotics, 2012, no. 29, pp. 123—137.
  18. Luo K., Zhao J., Huang C. et al. Multi-sensor Fusion Based Inspection Robotic Dog Safety Guardian and Navigation Application, Proceedings of the 2023 2nd International Symposium on Sensor Technology and Control (ISSTC), Hangzhou, 2023, pp. 191—195. Doi: 10.1109/ISSTC59603.2023.10280809.
  19. Lindeberg T. Feature Detection with Automatic Scale Selection, International Journal of Computer Vision, 1998, no. 30, pp. 79—116. DOI: 10.1023/A:1008045108935.
  20. Mikolajczyk K., Schmid C. Indexing based on scale invariant interest points, Proceedings of the International Conference on Computer Vision (ICCV'01), Vancouver, 2001, pp. 525—531. DOI: 10.1023/A:1008045108935.
  21. Lowe D. G. Recognition from Local Scale-Invariant Features, Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, 1999, no. 2, pp. 1150—1157. DOI: 10.1109/ICCV.1999.790410.
  22. Bay H., Tuytelaars T., Van Gool L. SURF: Speeded Up Robust Features, Computer Vision — ECCV 2006, 2006, no. 3951, pp. 404—417. DOI: 10.1007/11744023_32.
  23. Kong H., Akakin H. C., Sarma S. E. A Generalized Laplacian of Gaussian Filter for Blob Detection and Its Applications, IEEE Transactions on Cybernetics, 2013, vol. 43, no. 6, pp. 1719—1733. DOI: 10.1109/TSMCB.2012.2228639.
  24. Miao Z., Jiang X. Interest point detection using rank order LoG filter, Pattern Recognition, 2013, vol. 46, no. 11, pp. 2890—2901. DOI: 10.1016/j.patcog.2013.03.024.
  25. Xu Y., Wu T., Gao F. et al. Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis, Scientific Report, 2020, vol. 10, artilcle 326. DOI: 10.1038/s41598-019-57223-y.
  26. Vincent L., Soille P. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, vol. 13, no. 6, pp. 583—598. DOI: 10.1109/34.87344.
  27. Phansalkar N., More S., Sabale A., Joshi M. Adaptive local thresholding for detection of nuclei in diversity stained cytology images, Proceedings of the 2011 International Conference on Communications and Signal Processing, Kerala, 2011, pp. 218—220. DOI: 10.1109/ICCSP.2011.5739305.
  28. Guan S., Liu B., Chen S. et al. Adaptive median filter salt and pepper noise suppression approach for common path coherent dispersion spectrometer, Scientific Reports, 2024, vol. 14, article 17445. DOI: 10.1038/s41598-024-66649-y.
  29. Stark J. A. Adaptive image contrast enhancement using generalizations of histogram equalization, IEEE Transactions on Image Processing, 2000, vol. 9, no. 5, pp. 889—896. DOI: 10.1109/83.841534.
  30. Pizer S. M., Amburn E. P., Austin J. D. et al. Adaptive histogram equalization and its variations, Computer Vision, Graphics, and Image Processing, 1987, vol. 39, no 3, pp. 355—368. DOI: 10.1016/S0734-189X(87)80186-X.
  31. Image Filtering. OpenCV, available at: https://docs.opencv.org/3.4/d4/d86/group__imgproc__filter.html (date of access 05.09.2023).
  32. Szeliski R. Image Alignment and Stitching: A Tutorial, Foundations and Trends in Computer Graphics and Vision, 2007, vol. 2, no. 1, pp. 1—104. DOI: 10.1561/0600000009.
  33. Matrenin P., Myasnichenko V., Sdobnyakov N. et al. R. Generalized swarm intelligence algorithms with domain-specific heuristics, IAES International Journal of Artificial Intelligence, 2021, vol. 10, no. 1, pp. 157—165. DOI: 10.11591/ijai.v10.i1.pp157-165.
  34. Raj B., Ahmedy I., Idris M. Y. I., Noor R. M. A Hybrid Sperm Swarm Optimization and Genetic Algorithm for Unimodal and Multimodal Optimization Problems, IEEE Access, 2022, vol. 10, pp. 109580—109596. DOI: 10.1109/ACCESS.2022.3208169.