Hybrid algorithms for technological process control in railway transport: a review

The article presents a review of hybrid algorithms applied to the control of technological processes in railway transport. Special attention is given to the integration of artificial intelligence, optimization, machine learning, and physical modeling methods to improve the efficiency, reliability, and safety of railway systems. The paper discusses key types of hybrid solutions, including neuro-fuzzy systems, evolutionary algorithms with learning, digital twins, simulation–optimization approaches, and combined learning strategies. Examples of successful applications of hybrid models are provided for tasks such as dispatching, condition forecasting, schedule optimization, diagnostics, and energy efficiency. A comparative analysis of the accuracy, performance, and robustness of different approaches is presented. The advantages of hybridization over single-method techniques are highlighted, along with current challenges and future development directions.

1. Неупокоева Е. О., Быстров В. В., Шишаев М. Г. Гибридная технология синтеза транспортно-логистических систем на основе машинного обучения и имитационного моделирования // Экономика. Информатика. – 2024. – Т. 51, № 3. – С. 670–681.

2. R. Tang, L. De Donato, Q. He, F. Flammini et al., “A literature review of Artificial Intelligence applications in railway transport,” Transportation Research Part C, vol. 140, p. 103679, 2022.

3. N. Besinović et al., “Artificial Intelligence in Railway Transport: Taxonomy, Regulations and Applications,” IEEE Transactions on Intelligent Transportation Systems, 2023. (Early Access).

4. F. Anifowose, A. Abdulraheem, J. Abdollahi et al., “Hybrid intelligent systems in petroleum reservoir modeling: the journey so far and the challenges ahead,” Journal of Petroleum Exploration and Production Technology, vol. 7, no. 1, pp. 251–263, 2017.

5. L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–353, 1965.

6. Саттаров Х. А. Гибридные методы исследования режимов работы систем управления в условиях неопределенности // Железнодорожный транспорт: актуальные вопросы и инновации. – 2024. – № 1. – С. 6–11.

7. S. Jiao, R. Zhao, D. Yang et al., “Hybrid physics–machine learning models for predicting rate of penetration in the Halahatang oil field, Tarim Basin,” Scientific Reports, vol. 14, p. 5957, 2024.

8. T. Hou, Z. Hou, Y. Deng et al., “Research on speed control of high-speed trains based on hybrid modeling,” Archives of Transport, vol. 66, no. 2, pp. 65–85, 2023.

9. Y. Shiao and T.-L. Huynh, “A new hybrid control strategy for improving ride comfort on lateral suspension system of railway vehicle,” Journal of Low Frequency Noise, Vibration and Active Control, vol. 43, no. 4, pp. 1842–1859, 2024.

10. Hitachi Ltd, “Railway Traffic Management Systems by Machine Learning: Recovery from Traffic Timetable Disruption by Hybrid AI,” Hitachi Review, vol. 70, no. 5, pp. 88–93, 2021.

11. Веревкина О. И. О гибридном методе прогнозирования рисков на железнодорожном транспорте на основании общего логико-вероятностного метода // Изв. Петербургского ун-та путей сообщения. – 2017. – Т. 14, № 4. – С. 615–627.

12. Веревкина О. И. Результаты применения гибридного метода оценки функциональных рисков нарушения безопасности движения на региональном и линейном уровнях в хозяйстве пути // Надежность и качество сложных систем. – 2019. – № 1(17). – С. 420–424.

13. H. Alawad, M. An, and S. Kaewunruen, “Utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) for Overcrowding Level Risk Assessment in Railway Stations,” Applied Sciences, vol. 10, no. 15, p. 5156, 2020.

14. J. Sresakoolchai, C. Ngamkhanong, and S. Kaewunruen, “Hybrid learning strategies: integrating supervised and reinforcement techniques for railway wheel wear management with limited measurement data,” Frontiers in Built Environment, vol. 11, p. 1546957, 2025.

15. S. Alagesan, B. Indraratna, R. S. Malisetty, Y. Qi, and C. Rujikiatkamjorn, “Prediction of rail ballast breakage using a hybrid ML methodology,” Transportation Geotechnics, vol. 52, p. 101555, 2025.

16. W. Phusakulkajorn, A. Núñez, H. Wang et al., “Artificial intelligence in railway infrastructure: current research, challenges, and future opportunities,” Intelligent Transportation Infrastructure, vol. 2, p. liad016, 2023.

17. Y.Cheng,“Hybridsimulationforresolvingresourceconflictsintraintrafficrescheduling,”Computers in Industry, vol. 35, pp. 233–246, 1998.

18. D. Jones, A. Milne, M. Mladenović et al., “Hybrid simulation methodology incorporating heuristics for scheduling in freight rail networks,” Journal of Simulation, vol. 18, pp. 1–14, 2024.

19. W. Zhao, L. Zhou, and C. Han, “A Hybrid Optimization Approach Combining Rolling Horizon with Deep-Learning-Embedded NSGA-II Algorithm for High-Speed Railway Train Rescheduling Under Interruption Conditions,” Sustainability, vol. 17, no. 6, p. 2375, 2025.

20. H. Lau, Y. Zhao, and L. Xiao, “Development of a hybrid fuzzy genetic algorithm model for solving transportation scheduling problem,” Journal of Information Systems and Technology Management, vol. 12, no. 3, pp. 505–524, 2015.

21. M. Koniorczyk, K. Krawiec, L. A. S. Botelho, N. Bešinović, and K. Domino, “Application of a Hybrid Algorithm Based on Quantum Annealing to Solve a Metropolitan Scale Railway Dispatching Problem,” arXiv preprint arXiv:2309.06763, 2023.

22. A. Yousefi and M. S. Pishvaee, “A hybrid machine learning–optimization approach to pricing and train formation problem under demand uncertainty,” RAIRO – Operations Research, vol. 56, no. 3, pp. 1429–1451, 2022.

23. J. Li, Y. Shi, T. Zhang, X. Li, and X. Wang, “Research on Train Energy Optimization Based on Dynamic Adaptive Hybrid Algorithms,” Electronics, vol. 14, no. 8, p. 1588, 2025.

24. I. Villalba and R. Insa, “Applying a hybrid model considering the interaction between train and power system for energy consumption,” Mathematical Problems in Engineering, vol. 2018, p. 3643474, 2018.

25. X. Li and Y. Liu, “A Hybrid Data and Mechanism Model-driven Digital Twin Modeling Approach for Novel Traction Power Systems,” Urban Rail Transit, vol. 11, no. 2, pp. 213–231, 2025.

26. A. Zhukov, A. Rivero, J. Benois-Pineau, A. Zemmari, and M. Mosbah, “A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information,” Sensors, vol. 24, no. 4, p. 1171, 2024.

27. S. F. Stefenon, A. L. M. Marcato, A. J. S. Neto et al., “Automatic Digitalization of Railway Interlocking Engineering Drawings Based on Hybrid Machine Learning Methods,” Preprint (arXiv:2310.16721), 2024.

28. Артемьев И. С. Автоматизация процессов идентификации железнодорожных подвижных единиц на основе гибридных нейроиммунных моделей: дис. … канд. техн. наук. – СПбГУПС, 2017. – 158 с.

29. A. Galvez, Hybrid digital twins: a co-creation of data science and physics (Ph.D. dissertation), Luleå University of Technology (Sweden), 2022, 196 p.

30. I. Sahin, “Railway traffic control and train scheduling based on inter-train conflict management,” Transportation Research Part B, vol. 33, no. 7, pp. 511–534, 1999.

31. Y. Ou, A.-S. Mihăiţă, A. Ellison, T. Mao, S. Lee, and F. Chen, “Rail Digital Twin and Deep Learning for Passenger Flow Prediction Using Mobile Data,” Electronics, vol. 14, p. 2359, 2025.