DOI: 10.18503/1995-2732-2026-24-3-188-200
Abstract
At the present stage, the digitalization of the transport sector has created prerequisites for the transformation of railway transport, making it necessary to conduct a detailed study of the potential of artificial intelligence (AI) for improving transportation efficiency. The aim of this paper is to systematize the methods, practical experience, and prospects for the use of AI in railway transport operations management. A review of regulatory documents, scientific publications, and implemented projects in this field over the past decade has been conducted, during which AI has become one of the key drivers of transport development. The analysis has identified technological trends in the integration of AI into railway operations, infrastructure design, and logistics, including machine learning, computer vision, and digital twins. The areas of AI application have been identified, ranging from demand forecasting and strategic-level planning to neural-network-based traction calculation modeling. The advantages of AI implementation (more efficient utilization of line capacity, reduced transportation costs, and improved reliability and safety of infrastructure) as well as barriers to its implementation, including data quality and heterogeneity, regulatory requirements, and the specific characteristics of the transportation process, have been systematized. The feasibility of using AI to reduce uncertainty in selecting an effective train traffic interval regulation system for single-track railway sections is substantiated. Further research into the implementation of AI in railway transport operations management should focus on developing adaptive control systems, integrating heterogeneous data, developing an industry-specific standard, and incorporating training environments into the educational process for railway engineering students.
Keywords
artificial intelligence, machine learning, railway transport operations management, digital twin, predictive analytics, intelligent systems
For citation
Bessonenko S.A., Osipov N.I. Analysis of Experience and Prospects for the Application of Artificial Intelligence to Railway Transport Operations Management. Vestnik Magnitogorskogo Gosudarstvennogo Tekhnicheskogo Universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2026, vol. 24, no. 3, pp. 188-200. https://doi.org/10.18503/1995-2732-2026-24-3-188-200
1. PNST 884-2023 Artificial intelligence in the railway industry. Use cases. Federal Agency for Technical Regulation and Metrology. Available at: https://www.rst.gov.ru. (Accessed on March 29, 2026).
2. White Paper. Artificial Intelligence in Transport and Logistics: Industry Document. Ministry of Transport of the Russian Federation. Available at: https://mintrans.gov.ru/press-center/news/12167 (Accessed on March 29, 2026).
3. Register of Artificial Intelligence Technologies in the Transport Industry. Ministry of Transport of the Russian Federation. Available at: https://mintrans.gov.ru (Accessed on March 29, 2026).
4. Kiryakin V.Yu., Lobanov S.V. Prospects for using AI technologies to improve energy efficiency of predictive train schedules. Zheleznodorozhniy transport [Railway Transport]. 2025;(11):4-12. (In Russ.)
5. Borodin A.F., Nikolaev K.Yu., Shinderov R.V., Prozorov V. V. Organization of car flows: conditions, limitations, digital solutions. Zheleznodorozhniy transport [Railway Transport]. 2025;(6):11-19. (In Russ.)
6. Osminin A.T., Baushev A.N., Osminina I.I., Shatokhin A.A. On the possibility of applying artificial intelligence in the management of railway transport systems and the transportation process. Innovatsionnye tekhnologii na zheleznodorozhnom transporte. Sbornik trudov nauchno-prakticheskoy konferentsii s mezhdunarodnym uchastiem [Innovative Technologies in Railway Transport. Proceedings of the Scientific and Practical Conference with International Participation]. Moscow: Russian University of Transport, 2022, pp. 332-343. (In Russ.)
7. Chebotareva E.A. Development of reserve assessment tools the capacity of railway sections based on the creation of a digital twin and the use of an artificial neural network. Mir transporta i tekhnologicheskikh mashin [World of transport and technological machines]. 2024;(3-2(86)):126-131. (In Russ.) DOI: 10.33979/2073-7432-2024-3-2(86)-126–131.
8. Tretyakov G.M., Mazko N.N., Varlamov A.V. The use of machine learning technologies to automate the planning and management of freight transportation on the railway. Sovremennye naukoemkie tekhnologii [Modern high technologies]. 2024;(4):88-100. (In Russ.) DOI: 10.17513/snt.39977.
9. Bushuev S.V., Golochalov N. S. Train movement simulation based on the application of statistical data. Innovatsionniy transport [Innovative transport]. 2024;(1(51)):52-57. (In Russ.) DOI: 10.20291/2311-164X-2024-1-52-57.
10. Kulagin M.A., Sidorenko V.G. Decision support for preventing safety violations. Nadezhnost [Reliability]. 2021;21(4):38-46. (In Russ.) DOI: 10.21683/1729-2646-2021-21-4-38-46.
11. Larin E.S. Forecasting the energy costs of rolling stock using machine learning algorithms. Dinamika sistem, mekhanizmov i mashin [Dynamics of systems, mechanisms and machines]. 2024;12(3):130-134. (In Russ.) DOI: 10.25206/2310-9793-2024-12-3-130-134.
12. Obukhov A.D. Neural network control of marshalling processes. Mir transporta [World of transport]. 2016;14(1(62)):138-147. (In Russ.)
13. Kazakov A.L., Upyr R.Yu., Domozhirova A.D. Neuronal network approach to study the operation of shuttle-service trains. Vestnik Nauchno-issledovatelskogo instituta zheleznodorozhnogo transporta [Bulletin of the Scientific Research Institute of Railway Transport]. 2023;82(2):158-167. (In Russ.) DOI: 10.21780/2223-9731-2023-82-2-158-167.
14. Kovalev K.E., Novichikhin A.V. The procedure for planning the operation of low-intensity railway lines: logistical aspects and neural network models. Izvestiya Peterburgskogo universiteta putey soobshcheniya [Proceedings of Petersburg Transport University]. 2023;20(2):325-335. (In Russ.) DOI: 10.20295/1815-588X-2023-2-325-335.
15. Zhuravleva N.A., Batalova N.V. Calculation algorithm of the expected passenger flow of innovative railway transport based on a neural model. Innovatsionnye transportnye sistemy i tekhnologii [Innovative transport systems and technologies]. 2025;11(3):474-485. (In Russ.) DOI: 10.17816/transsyst688684.
16. Domanov K.I., Istomin S.G., Shatokhin A.P. Approaches to Creating a Driver Decision Support System for Digital Analysis of Railway Infrastructure Based on Machine Learning and Machine Vision Algorithms. E3S Web of Conferences. Proceedings of the 2nd International Conference on High-Speed Transport Development (HSTD 2023). Les Ulis, EDP Sciences - Web of Conferences. 2023; 05001. DOI: 10.1051/e3sconf/202344605001.
17. Lyubchenko A.A., Smolin I.Yu. Features of the algorithm for recognising car number from the image. Avtomatika, svyaz, informatika [Automation, Communication, Informatics]. 2024;(4):7-9. (In Russ.) DOI: 10.34649/AT.2024.4.4.002.
18. Smirnov F.A., Novichikhin A.V. Automation of acceptance of wagons for transportation: control system and neural network model. Izvestiya Peterburgskogo universiteta putey soobshcheniya [Proceedings of Petersburg Transport University]. 2024;21(3):670-685. (In Russ.) DOI: 10.20295/1815-588X-2024-03-670-685.
19. Sidorenko V.G., Kulagin M.A., Rodina D.M. Intelligent system detecting safety requirements violation in railway infrastructure maintenance. Avtomatika na transporte [Automation on transport]. 2025;11(1):55-65. (In Russ.) DOI: 10.20295/2412-9186-2025-11-01-55-65.
20. Khatlamadzhiyan A.E., Olgeizer I.A., Sukhanov A.V., Ierusalimov V.S. Formation of objective indicators of marshalling yard performance based on data «from the wheel». Avtomatika na transporte [Automation on transport]. 2024;10(3):254-268. (In Russ.) DOI: 10.20295/2412-9186-2024-10-03-254-268.
21. Lyashchenko Z. V., Ignatieva O. V., Schott M. K. Assessment of passenger service quality in railway transport based on passenger emotion assessment using artificial intelligence technologies. Nauka i tekhnika transporta [Transport science and technology]. 2024;(1):58-66. (In Russ.)
22. Istomin S.G., Domanov K.I., Shatokhin A.P. et al. The use of machine learning methods to solve the problem of energy-efficient train movement. Izvestiya Peterburgskogo universiteta putey soobshcheniya [Proceedings of Petersburg Transport University]. 2025;22(1):75-84. (In Russ.) DOI: 10.20295/1815-588X-2025-1-75-84.
23. Ivanova N.V., Zobnin V.D., Orlov V.V. Optimizing delivery routes using artificial intelligence in a changing transport environment. Transportnoe delo Rossii [Transport business of Russia]. 2024;(8):139-144. (In Russ.)
24. Kanarsky V.A. Research on the efficiency of machine learning in signal point monitoring. Nadezhnost [Reliability]. 2023;(1):38-44. (In Russ.) DOI: 10.21683/1729-2646-2023-23-1-38-44.
25. Orlov A.V., Alekseev A.S., Istomin A.V., Badirila L. Forecasting railway infrastructure operation risks using artificial neural networks. Mezhdunarodniy nauchno-issledovatelskiy zhurnal [International Scientific Research Journal]. 2025;(3(153)). (In Russ.) DOI: 10.60797/IRJ.2025.153.35.
26. Malakhov S.V., Kapustin M.Yu. Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks. Vestnik Nauchno-issledovatelskogo instituta zheleznodorozhnogo transporta [Bulletin of the Scientific Research Institute of Railway Transport]. 2021;80(1):13-19. (In Russ.) DOI: 10.21780/2223-9731-2021-80-1-13-19.
27. Bulavin Yu.P., Ignatieva O.V. Reinforcement training in the task of managing the passage of trains through the site. Avtomatika, svyaz, informatika [Automation, Communication, Informatics]. 2024;(11):18-21. (In Russ.) DOI: 10.62994/AT.2024.11.11.003.
28. Golochalov N.S. Reinforcement learning methods in the context of simulation of unmanned train movement. Vestnik Uralskogo gosudarstvennogo universiteta putey soobshcheniya [Bulletin of the Ural State University of Railway Transport]. 2025;(3(67)):53-60. (In Russ.) DOI: 10.20291/2079-0392-2025-3-53-60.
29. Senachin N.M. Optimizing the interaction of autonomous railway systems based on multi-agent learning. Vestnik Uralskogo gosudarstvennogo universiteta putey soobshcheniya [Bulletin of the Ural State University of Railway Transport]. 2025;(3(67)):100-105. DOI: 10.20291/2079-0392-2025-3-100-105. (In Russ.)
30. Kornilov S.N., Mishkurov P.N., Rakhmangulov A.N. Neural network model for railway station management. Akademik Vladimir Nikolaevich Obraztsov – osnovopolozhnik transportnoy nauki. Trudy yubileinoy mezhdunarodnoy nauchno-prakticheskoy konferentsii [Academician Vladimir Nikolaevich Obraztsov, founder of transport science. Proceedings of the Anniversary International Scientific and Practical Conference]. Kursk, Universitetskaya kniga, 2024, pp. 295-301. (In Russ.)
31. Zhang J., Zhang J. Artificial Intelligence Applied on Traffic Planning and Management for Rail Transport: A Review and Perspective. Discrete Dynamics in Nature and Society. 2023;2023:1832501. DOI: 10.1155/2023/1832501.
32. X. Li, M. Zhu, B. Zhang et al. A review of artificial intelligence applications in high-speed railway systems. High-speed Railway. 2024;2(1):11-16. DOI: 10.1016/j.hspr.2024.01.002.
33. Ju. Zhao, Xu. Gao, Zh. Wu et al. Artificial intelligence in rail transit wireless communication systems: Status, challenges and solutions. Physical Communication. 2024;67:102484. DOI: 10.1016/j.phycom.2024.102484.
34. Tang R., Liu R., Lin Zh. Predicting primary delay of train services using graph-embedding based machine learning. Journal of Rail Transport Planning and Management. 2025;34:100518. DOI: 10.1016/j.jrtpm.2025.100518.
35. Saki S., Soori M. Artificial intelligence, machine learning and deep learning in advanced transportation systems, a review. Multimodal Transportation. 2026;5(1):100242. DOI: 10.1016/j.multra.2025.100242.
36. Arthaud F., Lecoeur G., Pierre A. Transformers à Grande Vitesse: Massively parallel real-time predictions of train delay propagation. Journal of Rail Transport Planning and Management. 2024;29:100418. DOI: 10.1016/j.jrtpm.2023.100418.
37. Yue M., Ma Sh. LSTM-Based Transformer for Transfer Passenger Flow Forecasting between Transportation Integrated Hubs in Urban Agglomeration. Applied Sciences (Switzerland). 2023;13(1):637. DOI: 10.3390/app13010637.
38. Chatterjee K., Li J.Q., Ansari F. et al. Hybrid LSTM-Transformer Models for Profiling Highway–Railway Grade Crossings. Journal of Transportation Engineering Part A: Systems. 2026;152(2):04025138. DOI: 10.1061/jtepbs.teeng-9135.
39. Popov P.A., Ozerov A.V., Marshova A.S. Prospects of autonomous railway transport development. BRICS Transport. 2024;3(3). DOI: 10.46684/2024.3.4.
40. Nikishchenkov S.A., Garanin A.V. Automated adjustment technology standard train schedules using software robots. Avtomatika na transporte [Automation on Transport]. 2024;10(1):18-31. (In Russ.) DOI: 10.20295/2412-9186-2024-10-01-18-31.
41. Zhang T., Yi H., Tai Z. et al. The genetic algorithm based on generative adversarial network for dynamic multi-objective optimization problem and application. Knowledge-Based Systems. 2026;332:114939. DOI: 10.1016/j.knosys.2025.114939.