Іntelligent locomotive diagnostics systems as a tool for reducing accidents in railway transport
DOI:
https://doi.org/10.33216/1998-7927-2025-296-10-84-93Keywords:
transport, railway transport, railway rolling stock, locomotives, technical condition assessment systems, modeling, intelligent diagnosticsAbstract
In the context of increasing competition in the transport services market, minimizing downtime and ensuring the continuity of transportation are becoming critically important. The integration of new technologies, such as intelligent systems, can be a breakthrough in increasing safety and efficiency. The work developed a conceptual model of an intelligent locomotive diagnostics system that takes into account the specifics of the functioning of railway transport. Critical parameters were identified, the monitoring of which is key for early detection of malfunctions. The developed machine learning algorithms demonstrated high accuracy in detecting anomalies and predicting failures, which significantly exceeds the capabilities of traditional diagnostic methods. Thanks to simulation modeling, it was confirmed that the implementation of such systems can reduce the number of emergency situations by up to 25%, as well as reduce the downtime of locomotives for repair. These results indicate the significant potential of intelligent systems in increasing the safety of railway transportation. The developed prototype of the system allows you to visualize data on the state of locomotives in real time, providing operational information for making management decisions. This creates the prerequisites for optimizing maintenance schedules and transition to repairs based on the actual condition, which will reduce operating costs. The proposed methodology can be used to create similar diagnostic systems for other types of rolling stock, which expands the scope of its application. The developed concept and architecture of the intelligent diagnostic system provides a comprehensive approach to monitoring and predicting the technical condition of locomotives. The proposed machine and deep learning algorithms allow for high-precision detection of anomalies and prediction of potential equipment failures at early stages. This translates diagnostics from a reactive to a proactive approach. The obtained scientific results expand the understanding of the possibilities of applying artificial intelligence in the field of railway safety. Thus, the study not only expands scientific knowledge in the field of intelligent systems, but also provides specific tools for improving the safety and efficiency of railway transport.
References
1. Liabakh N. A., Ignatieva O. V., Shapovalov V. V. Intelligent maintenance and repair on railway transport. Proceedings of the Seventh International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’23). Springer, 2023. P. 247–259. DOI: https://doi.org/10.1007/978 3 031 43792 2_24
2. Ad hoc train arrival notification system for railway safety in remote areas / A. Eduard, D. Urazayev, A. Sabyrbek, D. Orel, D. Zorbas. Internet of Things. 2024. Vol. 25. 101062. DOI: https://doi.org/10.1016/j.iot.2024.101062
3. Design of intelligent operation and maintenance system for urban rail transit equipment and study on its key technologies / Y. Cai, F. Gao, Y. Meng, X. Xuan, J. Zhong. Railway Computer Application. 2023. 32(7). Р. 79–83. DOI: https://doi.org/10.3969/j.issn.1005-8451.2023.07.15
4. Improvement of the Model of Power Losses in the Pulsed Current Traction Motor in an Electric Locomotive / S. Goolak, S. Sapronova, V. Tkachenko, Ie. Riabov, Ye. Batrak. Eastern-European Journal of Enterprise Technologies. 2020. 6(5(108)). Р. 38–46. DOI: https://doi.org/10.15587/1729-4061.2020.218542
5. Determining rational parameters of the capacitive energy storage system for the underground railway rolling stock / O. Fomin, А. Sulym, I. Kulbovsky, P. Khozia, V. Ishchenko. Eastern-European journal of enterprise technologies. 2018. 2/1(92). Р. 63-71. DOI: 10.15587/1729-4061.2018.126080
6. Song G., Wang G., Ren G. Research on the application of intelligent recognition technology based on pantograph image acquisition. Railway Vehicles. 2023. 61(5). Р. 143–148. DOI: https://doi.org/10.3969/j.issn.1002-7602.2023.05.027
7. Expert system based fault diagnosis for railway point machines / Susanne, R., Thorsten, N., Gerrit, S., Arnout, V., & Douwe, B. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit. 2024. № 238(2). Р. 214–224. DOI: https://doi.org/10.1177/09544097231195656
8. Tu X., Zhang S., Wang M. Fault diagnosis methodology based on deep confidence network traction motor bearing. Urban Mass Transit. 2020. Vol. 23(1). Р. 174–178. DOI: https://doi.org/10.16037/j.1007-869x.2020.01.042
9. Theoretical and practical determination of parameters of on-board capacitive energy storage of the underground rolling stock / A.O. Sulim, O.V. Fomin, P.O.Khozya, A. Mastepan. Scientific Bulletin of National Mining University. 2018. Issue 5 (1). P.79-87. DOI: 10.29202/nvngu/2018-5/8
10. Determining the dynamic loading on a semi-wagon when fixing it with a viscous coupling to a ferry deck / O. Fomin, A. Lovska, I. Kulbovskyi, H. Holub, I. Kozarchuk, V. Kharuta. Восточно-Европейский журнал передовых технологий. 2019. № 2(7). С. 6-12. URL: http://nbuv.gov.ua/UJRN/Vejpte_2019_2(7)__2
11. Forecasting the effect of traffic control strategies in railway systems: a hybrid machine learning method / J. Luo, Ch. Wen, Q. Peng, Y. Qin, P. Huang. Physica A: Statistical Mechanics and its Applications. 2023. Vol. 621. 128793. DOI: https://doi.org/10.1016/j.physa.2023.128793 mdpi.com
12. Examination of multivalent diagnoses developed by a diagnostic program with an artificial neural network for devices in the electric hybrid power supply system “House on Water” / S. Duer, K. Zajkowski, M. Harničárová, H. Charun, D. Bernatowicz. Energies. 2021. 14. 2153. DOI: https://doi.org/10.3390/en14102153
13. Shcherbovskykh S., Stefanovych T., Denysyuk P. Reliability analysis of the duplicated wired channels with tripled protective reinforcement. Proceedings of the IEEE XVIII International Conference on the Perspective Technologies and Methods in MEMS Design (MEMSTECH). 2022. P. 89–92. DOI: https://doi.org/10.1109/ MEMSTECH55417.2022.100
14. Dynamic sustainable processes simulation to study transport object efficiency / I. Bondarenko, A. Severino, I. O. Olayode, T. T. Campisi, L. Neduzha. Infrastructures. 2022. №7. 124. DOI: https://doi.org/10.3390/infrastructures7120124
15. Liu A. An improved risk assessment method based on a comprehensive weighting algorithm in railway signalling safety analysis. Safety Science. 2020. Vol. 128. 104768. DOI: https://doi.org/10.1016/j.ssci.2020.104768
16. Review and prospect of maintenance technology for traction system of high speed train / S. Xu, C. Chen, Z. Lin, X. Zhang, J. Dai, L. Liu. Transportation Safety & Environment. 2021. Vol. 3. Issue 3. Р. 1–20. DOI: https://doi.org/10.1093/tse/tdab017
17. Bulakh M., Okorokov A., Baranovskyi D. Risk system and railway safety. IOP Conference Series: Earth and Environmental Science. 2021. 666(4). 042074. DOI: https://doi.org/10.1088/1755-1315/666/4/042074
18. Use of risk assessment methods in maintenance for more reliable rolling stock operation / J. Grenčík, R. Poprocký, J. Galliková, P. Volna. MATEC Web of Conferences. 2018. 157. 04002. DOI: https://doi.org/10.1051/matecconf/201815704002
19. Durability Determination of the Bearing Structure of an Open Freight Wagon Body Made of Round Pipes during its Transportation on the Railway Ferry / O. Fomin, J. Gerlici, A. Lovska, K. Kravchenko, P. Prokopenko, A. Fomina, V. Hauser. Communications-Scientific letters of the University of Zilina. 2019. Vol. 21. № 1. Р. 28-34. URL: https://dspace.snu.edu.ua/handle/123456789/636
20. Method of spectral analysis of traction current of AC electric locomotives / S. Goolak, V. Tkachenko, G. Bureika, G. Vaičiūnas. Transport. 2020. Vol. 35. № 6. Р. 658-668. DOI: http://doi.org/10.3846/transport.2020.14242
