Article

Received 14.01.2025

Revised 22.05.2025

Accepted 20.06.2025

Retrieved from Vol. 28, No. 1, 2025

Pages 81 -93

Gertsiy, O., Karnatov, S., Gladish, V., & Tkachenko, V. (2025). Modeling an image clustering algorithm for detecting overheated railway axle. The National Transport University Bulletin: A Scientific and Technical Journal, 28(1), 81-93. https://doi.org/10.32703/2617-9040-2025-45-6

Modeling an image clustering algorithm for detecting overheated railway axle

Oleksandr Gertsiy Serhii Karnatov Vitaliy Gladish Valentyna Tkachenko

This  paper  presents  an  approach  to  image  identification  based  on  a  clustering  algorithm  for detecting the thermal characteristics of railway axle boxes. The study analyzes the potential of clustering algorithms  in  the  task  of  digital  image  identification.  The  principles  of  the  proposed  algorithm  are described in the context of image segmentation and compression, as well as pattern recognition in the transportation domain. A block diagram of the algorithm is provided along with an explanation of its operational  principles.  A  scheme  for  implementing  a  machine  vision  system  using  the  proposed algorithm  is  suggested  for the  detection  of  overheated  axle  boxes  in  railway  transport.  Experimental modeling  was  conducted  for  image  segmentation  based  on  color  models  in  the  infrared  spectrum  to identify regions with elevated temperatures in the MATLAB environment. For the experiment, thermal images  of  rolling  stock  axle  boxes  were  selectedone  representing  a  normal  condition  and  the  other representing an overheated condition. The simulation results demonstrated that segmentation based on image color models allows for accurate delineation of the thermal characteristics of axle box images. The  study  confirmed  that  the  use  of  the  proposed  algorithm  and  its  software  implementation  for thermographic cameras is effective for recognizing temperature indicators. Additionally, the algorithm enables  image  compression, which  increases  data  processing  speed  and facilitates  the  monitoring  of thermal characteristics of rolling stock at high speeds

thermographic images; clustering; segmentation; monitoring; modeling; temperature indicators; axle box
  1. Ghaziasgar, M., Bagula, A., & Thron, C. (2020). Computer Vision Algorithms for Image Segmentation, Motion Detection, and Classification. Implementations and Applications of Machine Learning. Studies in Computational Intelligence, 782, 119-138. Springer, Cham. https://doi.org/10.1007/978-3-030-37830-1_5.
  2. Hassner, T., & Liu, C. (Eds.). (2016). Dense image correspondences for computer vision (pp. 3-14). Springer International Publishing. https://doi.org/10.1007/978-3-319-23048-1.
  3. Vishwakarma, A., Dasgupta, A., & Racherla, V. (2025). Detecting and classifying multiple track defects using clustering algorithm. Engineering Structures, 334, 120197. https://doi.org/10.1016/j.engstruct.2025.120197.
  4. Pacheco, F., Cerrada, M., Sánchez, R. V., Cabrera, D., Li, C., & de Oliveira, J. V. (2017). Attribute clustering using rough set theory for feature selection in fault severity classification of rotating machinery. Expert Systems with Applications, 71, 69-86. https://doi.org/10.1016/j.eswa.2016.11.024.
  5. Jiang, Y., Wang, H., Tian, G., Yi, Q., Zhao, J., & Zhen, K. (2019). Fast classification for rail defect depths using a hybrid intelligent method. Optik, 180, 455-468. https://doi.org/10.1016/j.ijleo.2018.11.053.
  6. Rapp, S., Martin, U., Strähle, M., & Scheffbuch, M. (2019). Track-vehicle scale model for evaluating local track defects detection methods. Transportation Geotechnics, 19, 9-18. https://doi.org/10.1016/j.trgeo.2019.01.001.
  7. Li, Q., Yao, K., & Zhang, X. (2020). A change-point detection and clustering method in the recurrent-event context. Journal of Statistical Computation and Simulation, 90(6), 1131–1149. https://doi.org/10.1080/00949655.2020.1718149.
  8. Gomez, M. J., Castejon, C., Corral, E., & Cocconcelli, M. (2023). Railway axle early fatigue crack detection through condition monitoring techniques. Sensors, 23(13), 6143. https://doi.org/10.3390/s23136143.
  9. Amini, A., Entezami, M., Huang, Z., Rowshandel, H., & Papaelias, M. (2016). Wayside detection of faults in railway axle bearings using time spectral kurtosis analysis on high-frequency acoustic emission signals. Advances in Mechanical Engineering, 8(11), 1687814016676000. https://doi.org/10.1177/1687814016676.
  10. Lisanti, G., Karaman, S., Pezzatini, D., & Bimbo, A. D. (2018). A multi-camera image processing and visualization system for train safety assessment. Multimedia Tools and Applications, 77, 1583-1604. https://doi.org/10.1007/s11042-017-43514.
  11. Wei, X., Yang, Z., Liu, Y., Wei, D., Jia, L., & Li, Y. (2019). Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study. Engineering Applications of Artificial Intelligence, 80, 6681. https://doi.org/10.1016/j.engappai.2019.01.008.
  12. Jamshidi, A., Roohi, S. F., Núñez, A., Babuska, R., De Schutter, B., Dollevoet, R., & Li, Z. (2016). Probabilistic defectbased risk assessment approach for rail failures in railway infrastructure. IFAC-PapersOnLine, 49(3), 73-77. https://doi.org/10.1016/j.ifacol.2016.07.013.
  13. Yiakopoulos, C. T., Gryllias, K. C., & Antoniadis, I. A. (2011). Rolling element bearing fault detection in industrial environments based on a K-means clustering approach. Expert Systems with Applications, 38(3), 2888-2911. https://doi.org/10.1016/j.eswa.2010.08.083.
  14. Botvin, M., Butryk, N., & Gertsiy, O. (2019). K-means clustering algorithm in image recognition tasks. Collection of scientific works of the State University of Infrastructure and Technologies series "Transport Systems and Technologies" (34), 199–209. https://doi.org/10.32703/2617-9040-2019-34-2-3.
  15. Zhang, C., Zhong, P., Liu, M., Song, Q., Liang, Z., & Wang, X. (2022). Hybrid Metric K‐Nearest Neighbor Algorithm and Applications. Mathematical Problems in Engineering, 2022(1), 8212546. https://doi.org/10.1155/2022/8212546.
  16. Ando, K., Kuniyoshi, Y., Onogi, N., Uchitane, T., Mukai, N., Iwata, K., Ito, N., & Jiang, Y. (2024). Cluster Detection for Traffic Accidents on Spatiotemporal Networks. Procedia Computer Science, 246, 371-380.. https://doi.org/10.1016/j.procs.2024.09.416.
  17. Huang, B., Zhu, Y., Wang, Z., & Fang, Z. (2021). Imbalanced data classification algorithm based on clustering and SVM. Journal of Circuits, Systems and Computers, 30(02), 2150036. https://doi.org/10.1142/S0218126621500365.
  18. Timchenko, L. I., Basov, V. I., Gertsiy, O. A., Kokriatskaia, N. I., & Ivasiyk, I.D., (2010). Rospiznavannya pivtonovych zobrazhen za shemoyu "gruboi" - "tochnoi" obrobki: Monografia. [Recognition of halftone images according to the scheme of "rough" - "accurate" processing: Monograph]. Kyiv: Naukova Dymka, 180 p. ISBN 978-966-00-0904-6.
  19. Timchenko, L. I., Kokriatskaia, N. I., Gertsiy, A. A., Stepaniuk, D. S., Chernyaschuk, N. L., Kotyra, A., & Amirgaliyev, Y. (2019, November). Elaboration of pyramidal methods applying computation technique “rough-fine” image identification. In Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019 (Vol. 11176, pp. 384-391). SPIE. https://doi.org/10.1117/12.2537179.
  20. Orazayeva, A., Wójcik, W., Pavlov, S., Tymchenko, L., Kokriatska, N., Tverdomed, V., ... & Semenova, L. (2022, December). Biomedical image segmentation method based on contour preparation. In Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2022 (Vol. 12476, pp. 21-26). SPIE. https://doi.org/10.1117/12.2657929.
  21. Timchenko, L., Kokriatskaya, N., Tverdomed, V., Stetsenko, O., Kaplun, V., Kolesnytskyj, O. K., ... & Zhunissova, U. (2023). Segmentation of multigradation images based on spatial connectivity features. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, 13(3), 47-50. https://doi.org/10.35784/iapgos.5352.
  22. Fan, Z., Xie, J. K., Wang, Z. Y., Liu, P. C., Qu, S. J., & Huo, L. (2021, May). Image classification method based on improved KNN algorithm. In Journal of physics: Conference series (Vol. 1930, No. 1, p. 012009). IOP Publishing. https://doi.org/10.1088/1742-6596/1930/1/012009.
  23. Gertsiy, O. (2023). Models of criterion evaluation of the image processing systems effectiveness. Collection of scientific works of the State University of Infrastructure and Technologies series "Transport Systems and Technologies", (41), 143154. https://doi.org/10.32703/2617-9059-2023-41-12.
  24. Gertsiy, O. (2024). Research on graphic data formats for compact representation and comparison of images. Collection of scientific works of the State University of Infrastructure and Technologies series “Transport Systems and Technologies”, (43), 173–187. https://doi.org/10.32703/2617-9059-2024-43-14.
  25. Sacerdoti, F. M., Giordano, A., & Cavaliere, C. (Eds.). (2016). Advanced imaging techniques in clinical pathology (No. 9210). Springer New York. https://doi.org/10.1007/978-1-4939-3469-0_2.
  26. Burger, W., & Burge, M. J. (2022). Digital image processing: An algorithmic introduction. Springer Nature. https://doi.org/10.1007/978-3-031-05744-1.
  27. Sinaga, A. S. R. (2019). Color-based Segmentation of Batik Using the L*a*b Color Space. Sinkron: Jurnal Dan Penelitian Teknik Informatika, 3(2), 175-179. https://doi.org/10.33395/sinkron.v3i2.10102.
  28. Abbadi, N. K. E., & Razaq, E. S. (2020). Automatic gray images colorization based on lab color space. Indonesian Journal of Electrical Engineering and Computer Science, 18(3), 1501-1509. https://doi.org/10.11591/ijeecs.v18.i3.pp1501-1509.
  29. Saifullah, S., Prasetyo, D. B., Dreżewski, R., & Dwiyanto, F. A. (2023). Palm oil maturity classification using K-nearest neighbors based on RGB and L* a* b color extraction. Procedia Computer Science, 225, 3011-3020. https://doi.org/10.1016/j.procs.2023.10.294.

https://doi.org/10.32703/2617-9040-2025-45-6