Driving manipulation analysis and control reconfiguration of heavy-haul trains

Abstract

The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains. In particular, heavy-haul trains are characterized by the difficulty in driving and operation. Considering the uncertainties in train driving and operation, this paper analyzes the relationship between the safety of heavy-haul electric locomotive-hauled trains and driving and operation. It studies the auxiliary intelligent driving safety operation control methods. Through K-means to identify the characteristics of drivers’ driving manipulation, the hidden Markov model adaptively adjusts the train driving and operation sequence, and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation. Based on the train running curve and the locomotive traction/braking characteristics, it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives, thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system. Finally, the train operation simulation and optimized driving verification are carried out by simulating some track sections. The results show that the proposed method can correct and pre-optimize driving operations, improving the smoothness of heavy-haul trains by approximately 10%. It verifies the effectiveness of the proposed train assisted driving control reconstruction method, facilitating the smooth and safe operation of heavy-haul trains.

Keywords

heavy-haul trains / driving manipulation / K-means clustering algorithm / hidden Markov model / control reconfiguration

References

[1] Li Z-y, Zhou Y-l, Yang Het al. . Study on model predictive control of energy saving assisted driving for heavy-haul trains [J]. Journal of Railway Science and Engineering. 2024, 21(8): 3107-3118(in Chinese)

[2] Xu M-l, Li G, Li Wet al. . Analysis of longitudinal force degradation and running safety of heavy-haul combined trains [J]. Journal of Railway Science and Engineering. 2023, 20(1): 321-332(in Chinese)

[3] Li W, Yao M-q, Zhang M-yet al. . Analysis and research of blend braking for longitudinal force optimization of heavy haul combined train [J]. Journal of Railway Science and Engineering. 2023, 20(2): 694-705(in Chinese)

[4] Liu P-f, Wang K-yun. Dynamic performance of heavy-haul combined train applying emergency braking on straight line [J]. Journal of Central South University. 2017, 24(8): 1898-1908.

[5] Gao G-j, Chen W, Zhang Jet al. . Analysis of longitudinal forces of coupler devices in emergency braking process for heavy haul trains [J]. Journal of Central South University. 2017, 24(10): 2449-2457.

[6] Liang X-m, Chen H-l, Zhang B. Design of a wireless transmission communication system for train braking signal [J]. Journal of Railway Science and Engineering. 2024, 21(4): 1579-1590(in Chinese)

[7] Wang W-s, Shangguan W, Liu Jet al. . A local outlier factor based fault detection method for train satellite-based positioning [J]. Journal of Railway Science and Engineering. 2023, 20(10): 4021-4030(in Chinese)

[8] Pan Y-l, Yi C, Yan Let al. . Method for extracting repeated transient vibration characteristics of axle box bearings under variable speed conditions based on multinode network structure [J]. Journal of the China Railway Society. 2025, 47(9): 84-94(in Chinese)

[9] LI Zhi, LIN Sen, ZHANG Qiang. Cloud-edge collaborative training method for federated learning model of intelligent fault detection for rail transit [J/OL]. Computer Science, 1–12 [2024-10-23]. http://kns.cnki.net/kcms/detail/50.1075.tp.20240625.1100.026.html. (in Chinese)

[10] Qin Y-f, Li G, Qi J-pet al. . Fault diagnosis of high-speed train lateral shock absorber based on RIMEVMD [J]. Journal of Railway Science and Engineering. 2025, 22(3): 942-953(in Chinese)

[11] Sun G-d, Pan X-y, Liang Q-het al. . Dynamic balanced teacher: A semi-supervised object detection algorithm for train faults [J]. Engineering Applications of Artificial Intelligence. 2024, 138: 109407.

[12] Liu J, Hu Y, Yang S-kun. A SVM-based framework for fault detection in high-speed trains [J]. Measurement. 2021, 172108779.

[13] Zhang Y, Liu M-y, Chen Y-net al. . Real-time vision-based system of fault detection for freight trains [J]. IEEE Transactions on Instrumentation and Measurement. 2020, 69(7): 5274-5284.

[14] General interim technical specification for China locomotive remote monitoring and diagnosis system (CMD system): TJ/JW 023–2014 [S]. (in Chinese)

[15] Liu C-ji. Research on the improvement of the dynamic image detection system for freight car operation faults (TFDS) [D]. 2023, Beijing, China, Beijing Jiaotong University(in Chinese)

[16] Yang L-l, Luo S-h, Fu M-het al. . Effects of mixed marshalling modes on longitudinal freight train dynamics [J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit. 2023, 23781060-1071.

[17] Liu W-t, Su S, Tang Tet al. . A DQN-based intelligent control method for heavy haul trains on long steep downhill section [J]. Transportation Research Part C: Emerging Technologies. 2021, 129: 103249.

[18] LI Zi-yi, ZHOU Yan-li, YANG Luo-jun, et al. An auxiliary intelligent driving control method, system and product for heavy-haul trains: China, ZL202310425756.X [P]. 2024-05-17. (in Chinese)

[19] Hu R-han. Research on abnormal driving behavior detection technology of train drivers based on unsupervised learning [D]. 2023, Lanzhou, China, Lanzhou Jiaotong University(in Chinese)

[20] Wei X-k, Suo D, Wei D-het al. . Review on the application of machine vision in state detection of rail transit systems [J]. Control and Decision. 2021, 36(2): 257-282(in Chinese)

[21] Wan P, Wu C-z, Ma X-feng. Discrimination threshold of driving anger intensity based on ROC curve and driving behavior characteristics [J]. Journal of Jilin University (Engineering and Technology Edition). 2020, 501121-131(in Chinese)

[22] Li X, Li G-z, Deng M-jet al. . A human fatigue detection method based on speech spectrogram features [J]. Chinese Journal of Scientific Instrument. 2021, 42(2): 123-132(in Chinese)

[23] Shou B. Driver abnormal behavior detection based on unsupervised learning [D]. 2021, Beijing, China, University of Science and Technology of China(in Chinese)

[24] Wang J. Research on self-learning mechanism and behavior safety assessment method of train driver agent [D]. 2012, Beijing, China, Beijing Jiaotong University(in Chinese)

[25] Traficante S, Tinella L, Lopez Aet al. . “Regulating my anxiety worsens the safety of my driving”: The synergistic influence of spatial anxiety and Self-regulation on driving behavior [J]. Accident Analysis & Prevention. 2024, 208: 107768.

[26] Maji A, Ghosh I. A systematic review on round about safety incorporating the safety assessment methodologies, data collection techniques, and driver behavior [J]. Safety Science. 2025, 181106661.

[27] Huang P, Ding H-t, Chen Het al. . A Bayesian Inference-based approach for extracting driving data with implicit intention [J]. Data Technologies and Applications. 2024, 58(4): 608-631.

[28] Herrero-Fernández D, Bogdan-Ganea S R, Setién-Suero Eet al. . The role of subjective risk perception and self-esteem in the relationship between sensation seeking and aberrant behaviors on the road: A moderated-moderation model [J]. Journal of Safety Research. 2024, 90: 31-42.

[29] El Hafidy A, Rachad T, Idri A. Understanding aberrant driving intentions based on the theory of planned behavior: Literature review and meta-analysis [J]. Journal of Safety Research. 2024, 90: 225-243.

[30] Zhou H-x, Sheng W-p, Liu H-en. A modeling method for the driving process of heavy-haul train based on multi-mass model [J]. IEEE Access. 2020, 8: 185548-185556.

[31] Wang Q, Song X-n, Ling F. Fault diagnosis system for rail transit vehicle [J]. Railway Computer Application. 2018, 27568-72(in Chinese)

[32] Yang Y-n, Tang L-x, Wang H. Dynamic multi-organizational PBFT algorithm based on k-means [J]. Journal of Chongqing University (Natural Science Edition). 2024, 47(7): 125-139(in Chinese)

[33] Ntalampiras S, Soupionis Y, Giannopoulos G. A fault diagnosis system for interdependent critical infrastructures based on HMMs [J]. Reliability Engineering & System Safety. 2015, 138: 73-81.

[34] Wang S-y, Mei W-j, Ma R. Parameter estimation of mixed exponential-Rayleigh distribution based on EM algorithm under complex fault data [J]. Journal of Systems Science and Mathematical Sciences. 2025, 45(10): 3267-3278(in Chinese)

[35] Chen Y, Wu J, Liu H-let al. . Visible light and inertial navigation fusion indoor positioning system based on hidden Markov model [J]. Chinese Journal of Lasers. 2020, 47(12): 1206001. in Chinese)

[36] Gao D-z, Fan Y-x, Wang K-yet al. . Research on longitudinal impulse suppression and safety assurance design for heavy-haul trains [J]. Electric Locomotives & Mass Transit Vehicles. 2024, 4711-725

[37] Wu M-q, Shi H, Zhu X-het al. . Research and prospect of fault diagnosis expert system [J]. Computer Automated Measurement & Control. 2005, 13(12): 1301-1304(in Chinese)

[38] ZHU Da-qi, YU Sheng-lin. Review of knowledge-based fault diagnosis methods [J]. Journal of Anhui University of Technology (Natural Science Edition), 2002(3): 197–204. DOI: https://doi.org/10.3969/j.issn.1671-7872.2002.03.007. (in Chinese)

[39] YANG Xing, ZHU Da-qi, SANG Qing-bing. Current status and prospects of expert system research [J]. Application Research of Computers, 2007(5): 4–9. DOI: https://doi.org/10.3969/j.issn.1001-3695.2007.05.002. (in Chinese)

[40] Yi D-hui. Statistical forecasting—Methods and applications [M]. 2001, Beijing, China Statistics Press(in Chinese)

[41] Yin J-t, Chen D-w, Li L-xi. Intelligent train operation algorithms for subway by expert system and reinforcement learning [J]. IEEE Transactions on Intelligent Transportation Systems. 2014, 15(6): 2561-2571.

RIGHTS & PERMISSIONS

Central South University