High-Speed Train Braking Control: Applications and CTD4–Digital Twin Perspectives for Operational Safety
DOI:
https://doi.org/10.4108/tsoe.15540Keywords:
high-speed train, braking control, wheel–rail adhesion, wheel-slide protection, CTD4, Digital TwinAbstract
The braking system directly determines the stopping capability, adhesion utilization, and operational safety of high-speed trains. However, braking performance is simultaneously affected by electric–pneumatic braking-force distribution, actuator delay, wheelset dynamics, and wheel-rail adhesion that varies with speed and contact conditions. This paper first systematizes the braking structure at three levels: vehicle, carriage, and wheel, while summarizing the longitudinal dynamics, slip-ratio formulation, and wheel-rail adhesion characteristics to define the feasible braking domain. On this basis, artificial-intelligence approaches are reviewed according to three levels of development: machine learning (ML) for estimation, deep learning (DL) for representation learning, and deep reinforcement learning (DRL) for sequential braking decision-making. The analysis shows that ML and DL improve the estimation of adhesion, stopping response, and wheel-slip conditions, whereas DRL extends toward direct traction/braking command generation; however, the physical feasibility of the resulting actions is not guaranteed when adhesion and actuator states vary outside the training domain. To address this gap, the paper proposes a conceptual CTD4–Digital Twin framework in which the twin updates physical states and parameters, CTD4 learns the return distribution under uncertainty, and a safety projection constrains the action before it is transmitted to the braking system.
Downloads
References
[1] A. Anagnostopoulos, “High-speed railway and safety: Insights from a bibliometric approach,” High-Speed Railway, vol. 2, no. 3, pp. 187–196, 2024, doi: 10.1016/j.hspr.2024.08.004.
[2] C.-F. Lu, “A discussion on technologies for improving the operational speed of high-speed railway networks,” Transp. Saf. Environ., vol. 1, no. 1, pp. 22–36, 2019, doi: 10.1093/tse/tdz003.
[3] J. Wang, Z. Chen, Z. Chen, C. Yang, and W. Gui, “A survey of braking control techniques for railway vehicles,” Sci. China Inf. Sci., vol. 69, Art. no. 131201, 2026, doi: 10.1007/s11432-025-4671-y.
[4] R. Pfaff, Railway Brake Systems: Framework, Requirements, and Solutions. Cham, Switzerland: Springer, 2025, doi: 10.1007/978-3-031-69958-0.
[5] F. Guo and J. He, “Optimal allocation method of electric/air braking force of high-speed train considering axle load transfer,” High-Speed Railway, vol. 2, no. 2, pp. 77–84, 2024, doi: 10.1016/j.hspr.2024.04.004.
[6] J. Wang, Z. Chen, Z. Chen, and W. Gui, “A decentralised braking force distribution strategy for high-speed trains,” IET Intell. Transp. Syst., 2025, doi: 10.1049/itr2.70100.
[7] S. Shrestha, M. Spiryagin, and Q. Wu, “Friction condition characterization for rail vehicle advanced braking system,” Mech. Syst. Signal Process., vol. 134, Art. no. 106324, 2019, doi: 10.1016/j.ymssp.2019.106324.
[8] B. Chen, Z. Huang, R. Zhang, F. Jiang, W. Liu, H. Li, J. Wang, and J. Peng, “Adaptive slip ratio estimation for active braking control of high-speed trains,” ISA Trans., vol. 112, pp. 302–314, 2021, doi: 10.1016/j.isatra.2020.11.027.
[9] Y. Jin, G. Xie, P. Chen, X. Hei, W. Ji, and J. Zhao, “High-speed train emergency brake modeling and online identification of time-varying parameters,” Math. Probl. Eng., vol. 2020, Art. no. 3872852, pp. 1–13, 2020, doi: 10.1155/2020/3872852.
[10] C. Chang, B. Chen, Y. Cai, and J. Wang, “Experimental investigation of high-speed wheel-rail adhesion characteristics under large creepage and water conditions,” Wear, vols. 540–541, Art. no. 205254, 2024, doi: 10.1016/j.wear.2024.205254.
[11] T. D. Tran, C. S. Doan, T. D. Le, V. D. Do, and X. K. Dang, “Suspension control strategies for high-speed trains: A comprehensive review and future perspectives,” J. Current Sci. Technol., vol. 16, no. 3, Art. no. 206, 2026, doi: 10.59796/jcst.V16N3.2026.206.
[12] P. Havaei and M. A. Sandidzadeh, “Intelligent-PID controller design for speed track in automatic train operation system with heuristic algorithms,” J. Rail Transp. Plan. Manag., vol. 22, Art. no. 100321, 2022, doi: 10.1016/j.jrtpm.2022.100321.
[13] X. Wang and T. Tang, “Optimal operation of high-speed train based on fuzzy model predictive control,” Adv. Mech. Eng., vol. 9, no. 3, pp. 1–14, 2017, doi: 10.1177/1687814017693192.
[14] Y. Guo, P. Sun, X. Feng, and K. Yan, “Adaptive fuzzy sliding mode control for high-speed train using multi-body dynamics model,” IET Intell. Transp. Syst., vol. 17, pp. 450–461, 2023, doi: 10.1049/itr2.12270.
[15] Z. Li, D. Huang, and L. Cai, “Adaptive nonsingular terminal sliding mode tracking control for high-speed trains with input constraints and parametric uncertainties,” Int. J. Control Autom. Syst., vol. 22, pp. 753–764, 2024, doi: 10.1007/s12555-022-0659-6.
[16] Z. Li, L. Zhou, H. Yang, and Y. Yan, “Model-free adaptive robust control method for high-speed trains,” Transp. Saf. Environ., vol. 6, no. 1, Art. no. tdad013, 2024, doi: 10.1093/tse/tdad013.
[17] L. Zhou, Z. Li, H. Yang, and C. Tan, “Integral predictive sliding mode control for high-speed trains: A dynamic linearization and input constraint-based data-driven scheme,” Control Eng. Pract., vol. 154, Art. no. 106139, 2025, doi: 10.1016/j.conengprac.2024.106139.
[18] J. Wang, Z. Chen, and Z. Chen, “Model predictive control for high-speed train braking systems with priority-based force distribution,” IEEE Trans. Control Syst. Technol., vol. 34, no. 4, pp. 2162–2169, 2026, doi: 10.1109/TCST.2026.3685687.
[19] V.-D. Do, X.-K. Dang, S. Ly, and N.-T. Nguyen, “Positioning the semi-submersible platform using model predictive control with thruster constraints,” in Proc. 2023 Asia Meeting on Environment and Electrical Engineering (EEE-AM), 2023, doi: 10.1109/EEE-AM58328.2023.10395200.
[20] X.-P. Nguyen, X.-K. Dang, V.-D. Do, J. M. Corchado, and H.-N. Truong, “Robust Adaptive Fuzzy-Free Fault-Tolerant Path Planning Control for a Semi-Submersible Platform Dynamic Positioning System With Actuator Constraints,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 11, pp. 12701–12715, 2023, doi: 10.1109/TITS.2023.3297252.
[21] X.-K. Dang, V.-D. Do, and Z. Koboevic, “Short-term Motion Control for Semi-submersible Platform Based on Constrained Fuzzy Genetic Optimization Controller,” Adv. Electr. Comput. Eng., vol. 25, no. 3, pp. 79–92, 2025, doi: 10.4316/AECE.2025.03009.
[22] X.-K. Dang, V.-D. Do, N.-T. Nguyen, and S. Ly, “Integrating model predictive control with deep learning for sway reduction in ship-to-shore crane operations,” EAI Endorsed Trans. Transp. Syst. Ocean Eng., vol. 1, no. 1, 2025, doi: 10.4108/tsoe.10838.
[23] T.-D. Nguyen, T.-D. Nguyen, T.-T. Pham, and V.-M. Nguyen, “Speed control of marine diesel engine based on Lyapunov neural network combined with adaptive backpropagation algorithm,” EAI Endorsed Trans. Transp. Syst. Ocean Eng., vol. 1, no. 1, 2025, doi: 10.4108/tsoe.11168.
[24] X.-K. Dang, J. M. Corchado, V.-V. Le, and V.-D. Do, “Non-parametric vibration-based structural damage detection for coastal structures: Multi-dimension to single input convolutional neural network approach,” Adv. Electr. Comput. Eng., vol. 24, no. 4, pp. 3–18, 2024, doi: 10.4316/AECE.2024.04001.
[25] X. Chen, J. Yin, and C. Ning, “Intelligent train stopping control for railways: A deep learning approach,” IET Intell. Transp. Syst., vol. 17, no. 10, pp. 1935–1950, 2023, doi: 10.1049/itr2.12385.
[26] B. Namoano, C. Emmanouilidis, and A. Starr, “Detecting wheel slip from railway operational data through a combined wavelet, long short-term memory and neural network classification method,” Eng. Appl. Artif. Intell., vol. 137, Part B, Art. no. 109173, 2024, doi: 10.1016/j.engappai.2024.109173.
[27] A. Zirek and C. Uysal, “A machine learning based voting regression method for adhesion estimation in wheel-rail contact,” Veh. Syst. Dyn., vol. 63, no. 10, pp. 1920–1937, 2025, doi: 10.1080/00423114.2024.2390578.
[28] H. Ni, Q. Fu, J. Easton, N. Zhao, and T. N. Arvanitis, “Reinforcement learning in railway research and applications: A review,” Transp. Res. Interdiscip. Perspect., vol. 39, Art. no. 102165, 2026, doi: 10.1016/j.trip.2026.102165.
[29] L. Ning, M. Zhou, Z. Hou, R. M. P. Goverde, F.-Y. Wang, and H. Dong, “Deep deterministic policy gradient for high-speed train trajectory optimization,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 8, pp. 11562–11574, 2022, doi: 10.1109/TITS.2021.3105380.
[30] M. Zhou, X. Liu, H. Wang, and H. Dong, “Memory-based TD3 for autonomous train speed trajectory optimization under virtual coupling,” IEEE Trans. Intell. Transp. Syst., vol. 27, no. 4, pp. 3973–3985, 2026, doi: 10.1109/TITS.2026.3667481.
[31] J. Lin, X. Qiu, and M. Li, “Tracking interval control for urban rail trains based on safe reinforcement learning,” Eng. Appl. Artif. Intell., vol. 137, Art. no. 109226, 2024, doi: 10.1016/j.engappai.2024.109226.
[32] E. A. Thompson, P. Lu, P. K. Alimo, H. B. Atuobi, E. T. Akoto, and C. K. Abbew, “Revolutionizing railway systems: A systematic review of digital twin technologies,” High-Speed Railway, vol. 3, no. 3, pp. 238–250, 2025, doi: 10.1016/j.hspr.2025.05.005.
[33] Z. Y. Zhang, D. Shang, and S. Su, “Digital twin in railway industry: A bibliometric analysis and systematic review,” Digital Twin, vol. 3, no. 1, Art. no. 2533858, 2026, doi: 10.1080/27525783.2025.2533858.
[34] D. Ershenko, G. Derbysheva, A. Panayi, and C. Fortin, “Quantitative metrics for validation and decision-making in digital twins: A comparative study on a railway braking system,” Proc. Des. Soc., vol. 5, pp. 2671–2680, 2025, doi: 10.1017/pds.2025.10281.
[35] H. Yang, Y. Fu, and D. Wang, “Multi-ANFIS model based synchronous tracking control of high-speed electric multiple unit,” IEEE Trans. Fuzzy Syst., vol. 26, no. 3, pp. 1472–1484, 2018, doi: 10.1109/TFUZZ.2017.2725819.
[36] T. Lu and B. Liu, “Automatic driving operation strategy of urban rail train based on improved DQN algorithm,” J. Artif. Intell., vol. 5, pp. 113–129, 2023, doi: 10.32604/jai.2023.043970.
[37] J. Peng et al., “A Digital Twin-Driven Hybrid Estimate Method for Health Status of Train Braking System,” in Proc. 2022 IEEE 25th Int. Conf. Comput. Supported Cooperative Work in Design (CSCWD), pp. 335–340, 2022, doi: 10.1109/CSCWD54268.2022.9776057.
[38] D. Valencia, H. Williams, Y. Xing, T. Gee, B. A. MacDonald, and M. Liarokapis, “CTD4 – a Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics,” Proc. AAAI Conf. Artif. Intell., vol. 39, no. 20, pp. 20956–20963, 2025, doi: 10.1609/aaai.v39i20.35391.
[39] A. Cunillera, N. Besinovic, R. M. Lentink, N. van Oort, and R. M. P. Goverde, “A literature review on train motion model calibration,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 4, pp. 3660–3677, 2023, doi: 10.1109/TITS.2023.3236062.
[40] Q. Wu et al., “Freight train air brake models,” Int. J. Rail Transp., vol. 11, no. 1, pp. 1–49, 2023, doi: 10.1080/23248378.2021.2006808.
[41] Q. Wang, Z. Wang, J. Mo, R. Wang, and K. Wang, “Effect and mechanism of wheel-rail adhesion on torsional vibration and stability of the braking system,” Tribol. Int., vol. 179, Art. no. 108182, 2023, doi: 10.1016/j.triboint.2022.108182.
[42] C. Lu, D. Chen, J. Shi, and Z. Li, “Research on wheel-rail dynamic interaction of high-speed railway under low adhesion condition,” Eng. Fail. Anal., vol. 157, Art. no. 107935, 2024, doi: 10.1016/j.engfailanal.2023.107935.
[43] D. Kvarda, A. Meierhofer, and K. Six, “Testing and modelling of transient adhesion phenomena in rolling-sliding contacts,” Friction, vol. 12, pp. 1016–1027, 2024, doi: 10.1007/s40544-023-0825-8.
[44] C. Huang, X. Zhou, Y. Chen, L. Jing, and K. Wang, “Multi-objective optimisation of wheel-rail adhesion for high-speed trains with aerodynamic lift wings,” Veh. Syst. Dyn., vol. 63, no. 2, pp. 375–397, 2025, doi: 10.1080/00423114.2024.2342533.
[45] H. Yang, Y.-T. Fu, K.-P. Zhang, and Z.-Q. Li, “Speed tracking control using an ANFIS model for high-speed electric multiple unit,” Control Eng. Pract., vol. 23, pp. 57–65, 2014, doi: 10.1016/j.conengprac.2013.10.006.
[46] D. Chen, R. Chen, Y. Li, and T. Tang, “Online learning algorithms for train automatic stop control using precise location data of balises,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 3, pp. 1526–1535, 2013, doi: 10.1109/TITS.2013.2265171.
[47] D. Chen and C. Gao, “Soft computing methods applied to train station parking in urban rail transit,” Appl. Soft Comput., vol. 12, pp. 759–767, 2012, doi: 10.1016/j.asoc.2011.10.016.
[48] M. Shang, Y. Zhou, and H. Fujita, “Deep reinforcement learning with reference system to handle constraints for energy-efficient train control,” Inf. Sci., vol. 570, pp. 708–721, 2021, doi: 10.1016/j.ins.2021.04.088.
[49] Y. Huang, W. Lai, D. Chen, G. Lin, and J. Yin, “Enhanced intelligent train operation algorithms for metro train based on expert system and deep reinforcement learning,” PLOS ONE, vol. 20, no. 5, Art. no. e0323478, 2025, doi: 10.1371/journal.pone.0323478.
[50] Q. Wu, M. Spiryagin, P. Liu, C. Cole, and E. Bernal, “Co-simulation methods for train braking dynamics,” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit, vol. 237, no. 8, pp. 1072–1081, 2023, doi: 10.1177/09544097231155564.
[51] H. P. Nguyen, V. D. Doan, T. S. Nguyen, V. H. Cao, and V. C. Pham, “Simulation and Analysis of Vehicle Dynamics Using Simcentre Amesim,” EAI Endorsed Transactions on Transportation Systems and Ocean Engineering, vol. 2, no. 1, 2026, doi: 10.4108/tsoe.11473.
[52] X.-K. Dang, V.-D. Do, T.-D. Tran, and S. Ly, “Real-Time Embedded Control for the Propulsion System of Semi-submersible Platform,” in Proc. 10th International Conference on Coastal and Ocean Engineering, pp. 350–362, 2024, doi: 10.1007/978-981-97-5353-6_27.
[53] L. Pugi, G. Paolieri, M. Giorgetti, L. Berzi, R. Viviani, L. Cabrucci, and L. Bocciolini, “HIL testing of wheel slide protection systems: Criteria for continuous updating and validation,” Railway Eng. Sci., vol. 31, pp. 108–121, 2023, doi: 10.1007/s40534-022-00298-7.
[54] J. Zhou and M. Wu, “Design of hardware-in-the-loop test bench for braking and anti-skid of trains,” in Urban Transport XXVI, WIT Trans. Built Environ., vol. 200, pp. 155–167, 2020, doi: 10.2495/UT200131.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Duc-Quy Nguyen, Ngo Manh Dung, Ngoc -Thuan Nguyen
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
