Review of research on the application of artificial intelligence and digital twins for accelerating railway transport flows
https://doi.org/10.46973/0201-727X_2026_1_36
Abstract
The paper provides a scientific review of Russian and international research devoted to increasing the speed and reliability of rail transportation through digitalization and artificial Intelligence (AI) technologies. The analysis shows that the “acceleration” effect is typically achieved by an integrated set of solutions: digital twins of infrastructure and the transportation process, intelligent planning and dispatching, capacity management and predictive maintenance, platform mechanisms for interaction between participants, and technological automation of operations at junctions (including the use of digital automatic couplings). A special focus is given to the Russian practice of coordinating shipments based on the Dynamic Infrastructure Load Model (DILM) as a tool for managing access to infrastructure capacity.
About the Authors
A. T. Osminin
Emperor Alexander I Saint Petersburg State Transport University (PSTU)
Russian Federation
Russian Federation
Osminin Aleksandr Trofimovich, Chair “Operational Management”, Doctor of Engineering Sciences, Professor
T. A. Malakhova
Emperor Alexander I Saint Petersburg State Transport University (PSTU)
Russian Federation
Russian Federation
Malakhova Tatyana Aleksandrovna , Chair “Operational Management”, Candidate of Engineering Sciences, Associate Professor
A. S. Ryashchikov
Emperor Alexander I Saint Petersburg State Transport University (PSTU)
Russian Federation
Russian Federation
Ryashchikov Aleksandr Sergeevich, Chair “Operational Management”, Candidate of Physical and Mathematical Sciences, Associate Professor, Research Fellow
I. I. Osminina
Emperor Alexander I Saint Petersburg State Transport University (PSTU)
Russian Federation
Russian Federation
Osminina Irina Ivanovna, Chair “Operational Management”, Candidate of Engineering Sciences, Associate Professor, Senior Researcher
References
1. Revolutionizing railway systems : A systematic review of digital twin technologies / E. A. Thompson, P. Lu, P. K. Alimo [et. al.] // High-speed Railway. – 2025. – Vol. 3, Issue 3. – P. 238–250. – DOI 10.1016/j.hspr.2025.05.005.
2. A literature review of Artificial Intelligence applications in railway systems / R. Tang, L. De Donato, N. Bešinović [et al.] // Transportation Research Part C : Emerging Technologies. – 2022. – Vol. 140. – Art. 103679.
3. Towards AI-assisted digital twins for smart railways : Preliminary guideline and reference architecture / L. De Donato, R. Dirnfeld, A. Somma [et al.] // Journal of Reliable Intelligent Environments. – 2023. – Vol. 9, No. 3. – P. 303–317.
4. Digital twin in industry : State-of-the-art / F. Tao, H. Zhang, A. Liu [et al.] // IEEE Transactions on Industrial Informatics. – 2019. – Vol. 15, No. 4. – P. 2405–2415.
5. Errandonea, I. Digital twin for maintenance : A literature review / I. Errandonea, S. Beltrán, S. Arrizabalaga // Computers in Industry. – 2020. – Vol. 123. – Art. 103316.
6. Enabling technologies and tools for digital twin / O. Qi, F. Tao, T. Hu [et al.] // Journal of Manufacturing Systems. – 2021. – Vol. 58. – P. 3–21.
7. Kaewunruen, S. Digital twin aided sustainabilitybased lifecycle management for railway turnout systems / S. Kaewunruen, Q. Lian // Journal of Cleaner Production. – 2019. – Vol. 228. – P. 1537–1551.
8. Gibert, X. Deep multitask learning for railway track inspection / X. Gibert, V. M. Patel, R. Chellappa // IEEE Transactions on Intelligent Transportation Systems. – 2017. – Vol. 18, No. 1. – P. 153–164.
9. Systematic review railway infrastructure monitoring : From classic techniques to predictive maintenance / G. Bianchi, C. Fanelli, F. Freddi [et al.] // Advances in Mechanical Engineering. – 2025. – Vol. 17, No. 1. – DOI 10.1177/16878132241285631.
10. Rail Transit Digital Twin and Deep Learning for Passenger Flow Prediction / X. Ou, T. Shi, Z. Duan [et al.] // Electronics. – 2025. – Vol. 14, No. 9. – Art. 1758. – DOI 10.3390/electronics14091758.
11. Liu, Y. A reinforcement learning approach to solving very-short term train rescheduling problem for a single-track rail corridor / Y. Liu, L. Lin, T. Liu // Journal of Rail Transport Planning & Management. – 2024. – Art. 100483. – DOI 10.1016/j.jrtpm.2024.100483.
12. Extending UIC 406-based capacity analysis / N. Weik, F. Corman, G. Medeossi, I. Johansson // Journal of Rail Transport Planning & Management. – 2020. – Vol. 15. – Art. 100199.
13. Landex, A. Capacity measurement with the UIC 406 capacity method / A. Landex // Computers in Railways X : Proceedings of the 10th International Conference on Railway Engineering Design and Operation. – 2008.
14. Vlasova, N. V. Key aspects of the functioning of the dynamic model of infrastructure loading of JSC Russian Railways / N. V. Vlasova, V. A. Olentsevich // Modern technologies. Systems analysis. Modeling. – 2023. – No. 4 (80). – P. 148–157. – DOI 10.26731/1813-9108.2023.4(80).148-157.
15. On approval of the Technology for the operation of the Dynamic Model of Infrastructure Loading of JSC Russian Railways when coordinating GU-12 applications and applications for empty trains : order of November 25, 2022 No. 3090/r (as amended on July 11, 2023) : regulatory document. – URL: cargo.rzd.ru api/media/resources/2532460 (date of access: 10.02.2026).
16. Zyabirov, Kh. Sh. Modern technologies in managing the transportation process in railway transport : monograph / H. Sh. Zyabirov, I. N. Shapkin // Finance and statistics. – 2nd ed. – Moscow, 2024. – 484 p. – ISBN 978-5-00184-112-8.
17. Gulyy, I. M. Theory and methodology of economic evaluation of digital platform solutions in the field of freight mixed transportation based on rail transport : specialty 5.2.3 "Regional and sectoral economics" : dissertation for the degree of doctor of economical sciences / I. M. Gulyy. – St. Petersburg, 2024. – 338 p.
18. Dmitriev, A. V. Formation and development of digital ecosystems of transport and logistics services : specialty 08.00.05 "Economics and Management of the National Economy" (logistics) : dissertation for the degree of doctor of economical sciences / A. V. Dmitriev. – St. Petersburg, 2021. – 410 p.
19. Maslov, E. S. Development of methods for managing transport and forwarding activities based on intelligent information technologies : specialty 05.22.01 "Transport and transport-technological системы страны, ее регионов и городов, органи- зация производства на транспорте» : автореферат диссертации кандидата технических наук / Е. С. Маслов. – Москва, 2019. – 24 с. systems of the country, its regions and cities, organization of production in transport" : abstract of the dissertation of candidate of technical sciences / E. S. Maslov. – Moscow, 2019. – 24 p.
20. European Union Agency for Railways. Mandatory specifications (ETCS, GSM-R, FRMCS, ATO). – URL: https://www.era.europa.eu/erafolder/1-ccs-tsi-appendix-mandatory-specifications-etcs-b4-r1-rmr-gsm-r-b1-mr1-frmcs-b0-atob1 (date of access: 24.01.2026).
21. Europe’s Rail Joint Undertaking. Digital Automatic Coupling (DAC) Factsheet. – URL: https://rail-research.europa.eu/wp-content/uploads/2020/11/DAC-Factsheet.pdf (date of access: 24.01.2026).
22. Federal Ministry of Transport and Digital Infrastructure (Germany). Technical Report : “DAC Technology” – URL: https://www.railwaypro.com/wp/germany-presents-dac-study (date of access: 01/24/2026).
23. Federal Ministry for Digital and Transport (Germany). DAC Demonstrator – Interim Report on the Completion of Phase II – URL: https://www.railwaypro.com/wp/operational-tests-begin-for-dacfreight-train/ (date of access: 24.01.2026).
24. International Union of Railways (UIC). European Digital Automatic Coupling (DAC) : key element for the Green Deal modal shift. – URL: https://uic.org/com/enews/article/european-digitalautomatic-coupling-dac-key-element-for-thegreen-deal-modal (date of access: 24.01.2026).
25. Verband der Güterwagenhalter in Deutschland (VPI). Digital automatic coupling. – URL: https://vpihamburg.de/en/topics/dac (дата обращения: 24.01.2026).
26. Deutsche Bahn. Digitale Schiene Deutschland : Digital twin enables efficient rail operations. – URL: https://digitale-schiene-deutschland.de/en (date of access: 24.01.2026).
Review
For citations:
Osminin A.T., Malakhova T.A., Ryashchikov A.S., Osminina I.I. Review of research on the application of artificial intelligence and digital twins for accelerating railway transport flows. Vestnik Rostovskogo Gosudarstvennogo Universiteta Putej Soobshcheniya. 2026;(1):36-42. (In Russ.) https://doi.org/10.46973/0201-727X_2026_1_36
Views:
38
JATS XML
Email this article 