高速铁路多列车运行态势推演方法

王荣笙; 袁志明; 闫璐; 吕宜生; 丁舒忻

doi:10.16383/j.aas.c240623

高速铁路多列车运行态势推演方法

doi: 10.16383/j.aas.c240623 cstr: 32138.14.j.aas.c240623

王荣笙^1,,
袁志明^{2, 3,},
闫璐^4,,
吕宜生^5,,
丁舒忻^{2, 3,}

1.
中国铁道科学研究院集团有限公司科学技术信息研究所北京 100081
2.
中国铁道科学研究院集团有限公司通信信号研究所北京 100081
3.
高速铁路与城轨交通系统技术国家工程研究中心高速铁路行车调度实验室北京 100081
4.
中国铁道科学研究院集团有限公司科技和信息化部北京 100081
5.
中国科学院自动化研究所复杂系统管理与控制国家重点实验室北京 100190

基金项目: 中国铁道科学研究院集团有限公司科研课题 (2023YJ208), 中国国家铁路集团有限公司科技研究开发计划课题 (J2023G007), 国家自然科学基金 (62203468) 资助

详细信息

作者简介:
王荣笙：中国铁道科学研究院集团公司科学技术信息研究所助理研究员. 2023年获得中国铁道科学研究院交通信息工程及控制专业博士学位.主要研究方向为多列车运行态势推演, 高速铁路调度指挥, 列车运行控制. E-mail: wrs20138437@126.com

袁志明：中国铁道科学研究院集团有限公司通信信号研究所研究员. 2016 年获得中国铁道科学研究院交通信息工程及控制专业博士学位. 主要研究方向为铁路运营指挥, 铁路信号控制和铁路智能调度. 本文通信作者. E-mail: zhimingyuan@hotmail.com

闫璐：中国铁道科学研究院集团有限公司研究员. 2022 年获得中国铁道科学研究院交通信息工程及控制专业博士学位. 主要研究方向为铁路调度指挥和列车运行态势推演. E-mail: yanlu@rails.cn

吕宜生：中国科学院自动化研究所复杂系统管理与控制国家重点实验室研究员. 主要研究方向为人工智能, 智能网联驾驶和平行交通管理与控制系统. E-mail: yisheng.lv@ia.ac.cn

丁舒忻：中国铁道科学研究院集团有限公司通信信号研究所副研究员. 2019年获得北京理工大学控制科学与工程专业博士学位. 主要研究方向为列车运行调整, 进化计算. E-mail: dingshuxin@rails.cn

计量
- 文章访问数: 32
- HTML全文浏览量: 23
- 被引次数: 0
出版历程
- 收稿日期: 2024-09-10
- 录用日期: 2024-12-23
- 网络出版日期: 2024-12-30

Deductive Approach of Multi-train Operation Situation for High-speed Railway

WANG Rong-Sheng^1
,,
YUAN Zhi-Ming^{2, 3
,},
YAN Lu^4
,,
LV Yi-Shen^5
,,
DING Shu-Xin^{2, 3
,}

1.
Scientific and Technological Information Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081
2.
Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081
3.
Traffic Management Laboratory for High-Speed Railway, National Engineering Research Center of System Technology for High-Speed Railway and Urban Rail Transit, Beijing 100081
4.
Science and Information Technology Department, China Academy of Railway Sciences Corporation Limited, Beijing 100081
5.
State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190

Funds: Supported by Foundation of China Academy of Railway Sciences Corporation Limited (2023YJ208), Foundation of China State Railway Group Company Limited (J2023G007), and National Natural Science Foundation of China (62203468)

More Information

Author Bio:
WANG Rong-Sheng　Assistant researcher at Scientific and Technological Information Research Institute, Chinese Academy of Railway Sciences Corporation Limited. He received his Ph.D. degree in traffic information engineering and control from China Academy of Railway Sciences in 2023. His research interest covers multi-train operation situation deduction, high-speed railway dispatching command, and train operation control

YUAN Zhi-Ming　Researcher at Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited. He received his Ph.D. degree in traffic information engineering and control from China Academy of Railway Sciences in 2016. His research interest covers railway operation command, railway signaling control, and intelligent train operation. Corresponding author of this paper

YAN Lu　Researcher at China Academy of Railway Sciences Corporation Limited. She received her Ph.D. degree in traffic information engineering and control from China Academy of Railway Sciences in 2022. Her research interest covers railway dispatching command and train operation situation deduction

LV Yi-Sheng　Researcher at the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences. His research interest covers artificial intelligence, intelligent network driving, and parallel traffic management and control systems

DING Shu-Xin　Associate researcher at Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited. He received his Ph.D. degree in control science and engineering from Beijing Institute of Technology in 2019. His research interest covers train operation adjustment and evolution computing

摘要

摘要: 多列车运行态势是列车调度员和司机分别调整运行图和列车驾驶策略的关键信息和重要依据, 表征各列车在未来运行各位置处的速度、加速度、通过时刻等信息. 然而, 由于高铁信号系统交互信息利用率较差, 列车调度员和司机只能凭经验推演多列车运行态势, 基于此给出的运行图和列车驾驶策略的自动化程度较低, 影响铁路运营效率. 为此, 针对多列车运行态势推演问题, 构建多列车运行态势推演系统架构及模型. 以单列车运行态势的离线推演和在线推演方法为基础, 提出多列车运行态势微观推演方法, 以及基于虚拟编队模式的多列车运行态势宏观实时推演方法. 仿真结果表明, 微观推演方法能在 420 s 内计算多列车超速防护曲线和运行图调整的安全下界. 宏观推演方法针对任意临时限速场景, 都能在 7 s 内为列车调度员和司机分别实时提供列车运行调整方案和辅助驾驶策略, 有效降低了铁路人员的工作强度, 提升了高铁运营效率和应急处置能力.
- 高速铁路 /
- 多列车运行态势 /
- 列车运行调整 /
- 列车速度曲线优化 /
- 高速铁路调度控制一体化
Abstract: The multi-train operation situation is critical information and significant basis for the dispatcher and drivers to adjust the train timetable and driving strategies, respectively. It describes the speed, acceleration, passing time, and other information of each train at each future position. However, due to the poor utilization of interactive information in the high-speed railway signaling system, the multi-train operating situation can only be deduced by train dispatchers and drivers based on their experience. As a result, there is a low level of automation for the train timetable and driving strategies, affecting railway operation efficiency. Aiming at the problem of the multi-train operation situation deduction, this paper establishes the architecture and model of the deduction system for the multi-train operation. Based on the offline and online deductive approaches of the single-train operation situation, this paper proposes a microcosmic deductive approach of multi-train operation situation and a macroscopic real-time deductive approach of multi-train operation situation based on mode of virtual coupling. The simulation results indicate that the microscopic deductive approach can calculate the multi-train over-speed protection curve and the safe lower bound of timetable rescheduling within 420 s. As for any temporary speed restriction scenarios, the macroscopic deductive approach can provide real-time train rescheduling solutions and driving strategies for dispatchers and drivers within 7 s, respectively. This approach can effectively reduce the work intensity of high-speed railway staff and improve the efficiency of high-speed railway operations and emergency response capabilities.
- High-speed railway /
- multi-train operation situation /
- train rescheduling /
- train speed profile optimization /
- integration of rescheduling and control for high-speed railway

HTML全文

图 1 高铁信号系统信息交互过程

Fig. 1 Information exchange process of high-speed railway signaling system

下载: 全尺寸图片幻灯片

图 2 多列车运行态势推演系统架构

Fig. 2 System architecture of multi-train operation situation deduction

下载: 全尺寸图片幻灯片

图 3 列车运行工况转换关系

Fig. 3 Conversion relation of train operation conditions

下载: 全尺寸图片幻灯片

图 4 微观推演方法流程图

Fig. 4 Flow chart of the microscopic deduction approach

下载: 全尺寸图片幻灯片

图 5 临时限速影响后行追踪列车的示意图

Fig. 5 Diagram of temporary speed restriction influencing the latter tracking train

下载: 全尺寸图片幻灯片

图 6 宏观推演方法流程图

Fig. 6 Flow chart of the macroscopic deduction approach

下载: 全尺寸图片幻灯片

图 7 列车群组划分示意图

Fig. 7 Diagram of train group division

下载: 全尺寸图片幻灯片

图 8 微观推演方法求解小扰动场景的态势推演结果

Fig. 8 Situation deductive results calculated by the microcosmic deductive approach in the small disturbance scenario

下载: 全尺寸图片幻灯片

图 9 宏观推演方法求解小扰动场景的多列车目标速度曲线

Fig. 9 Multi-train target speed profile calculated by the macroscopic deductive approach in the small disturbance scenario

下载: 全尺寸图片幻灯片

图 10 宏观推演方法求解小扰动场景的列车运行调整方案

Fig. 10 Train rescheduling solution calculated by the macroscopic deductive approach in the small disturbance scenario

下载: 全尺寸图片幻灯片

图 11 微观推演方法求解大干扰场景的多列车运行态势推演结果

Fig. 11 Deductive results of multi-train operation situation calculated by the microcosmic deductive approach in the large disruption scenario

下载: 全尺寸图片幻灯片

图 12 宏观推演方法求解大干扰场景的多列车运行态势推演结果

Fig. 12 Deductive results of multi-train operation situation calculated by the macroscopic deductive approach in the large disruption scenario

下载: 全尺寸图片幻灯片

表 1 仿真实验参数

Table 1 Simulation experiment parameters

参数	数值	单位
线路总长度	117 040	m
车站咽喉区限速值	80	km/h
列车质量	501	t
回转系数	0.11	$-$
列车长度	208.95	m
列车最大运行速度	350	km/h
列车最大加速度	1	m/s$^{2}$
列车最大冲击率	0.5	m/s$^{3}$
闭塞分区长度	1 950	m
安全防护距离	110	m
RBC更新MA的时间步长	1	min

下载: 导出CSV

表 2 列车的计划区间运行时间

Table 2 Planned train running time in each block section

车站	公里标	计划区间运行时间(s)
北京南	K1+105	$-$
亦庄	K22+285	374.219
永乐	K46+565	623.956
武清	K84+454	1 013.680
南仓	K107+969	1 256.050
天津	K118+144	1 544.280

下载: 导出CSV

表 3 小扰动场景下三种推演方法的对比结果

Table 3 Comparison results of the three deduction approaches in the small disturbance scenario

方法	列车总晚点时间(s)	列车总牵引能耗(kW·h)	求解时间(s)
人工推演	768.84	7 925.78	153.26
微观推演	376.65	8 490.64	418.11
宏观推演	663.63	7 870.79	1.81

下载: 导出CSV

表 4 大干扰场景下三种推演方法的对比结果

Table 4 Comparison results of the three deduction approaches in the large disruption scenario

方法	列车总晚点时间(s)	列车总牵引能耗(kW·h)	求解时间(s)
人工推演	34 120.17	29 817.10	554.13
微观推演	31 866.09	31 657.69	3 877.41
宏观推演	34 351.06	29 493.70	6.36

下载: 导出CSV

参考文献(28)

[1]	宁滨, 董海荣, 郑伟, 荀径, 高士根, 王洪伟, 等. 高速铁路运行控制与动态调度一体化的现状与展望. 自动化学报, 2019, 45(12): 2208−2217 Ning Bin, Dong Hai-Rong, Zheng Wei, Xun Jing, Gao Shi-Gen, Wang Hong-Wei, et al. Integration of train control and online rescheduling for high-speed railways: Challenges and future. Acta Automatica Sinica, 2019, 45(12): 2208−2217
[2]	林鹏, 田宇, 袁志明, 张琦, 董海荣, 宋海锋, 等. 高速铁路信号系统运维分层架构模型研究. 自动化学报, 2022, 48(1): 152−161 Lin Peng, Tian Yu, Yuan Zhi-Ming, Zhang Qi, Dong Hai-Rong, Song Hai-Feng, et al. Operation and maintenance of high-speed railway signaling system: Hierarchical structure model. Acta Automatica Sinica, 2022, 48(1): 152−161
[3]	闫璐, 张琦, 王荣笙, 丁舒忻. 基于动力学特性的列车运行态势分析. 铁道运输与经济, 2021, 43(8): 64−70 Yan Lu, Zhang Qi, Wang Rong-Sheng, Ding Shu-Xin. Train operation analysis based on dynamics. Railway Transport and Economy, 2021, 43(8): 64−70
[4]	张琦, 陈峰, 张涛, 袁志明. 高速铁路列车连带晚点的智能预测及特征识别. 自动化学报, 2019, 45(12): 2251−2259 Zhang Qi, Chen Feng, Zhang Tao, Yuan Zhi-Ming. Intelligent prediction and characteristic recognition for joint delay of high speed railway trains. Acta Automatica Sinica, 2019, 45(12): 2251−2259
[5]	Zhou H, Wan Y, Ye H, Li B, Liu B. A novel real-time algorithm for optimizing train speed profiles under complex constraints. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(8): 7987−8002 doi: 10.1109/TITS.2023.3264795
[6]	Sun X, Yao Z, Dong C, David C. Optimal control strategies for metro trains to use the regenerative braking energy: A speed profile adjustment approach. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(6): 5883−5894 doi: 10.1109/TITS.2023.3248653
[7]	Peng S, Yang X, Ding S, Wu J, Sun H. A dynamic rescheduling and speed management approach for high-speed trains with uncertain time-delay. Information Sciences, 2023, 632: 201−220 doi: 10.1016/j.ins.2023.03.003
[8]	Xing Z, Zhang Z, Guo J, Qin Y, Jia L. Rail train operation energy-saving optimization based on improved brute-force search. Applied Energy, 2023, 330: Article No. 120345 doi: 10.1016/j.apenergy.2022.120345
[9]	Ye H, Liu R. A multiphase optimal control method for multi-train control and scheduling on railway lines. Transportation Research Part B: Methodological, 2016, 93: 377−393 doi: 10.1016/j.trb.2016.08.002
[10]	王鹏玲. 面向冲突预测与化解的列车群运行优化控制方法研究[博士学位论文], 西南交通大学, 中国, 2016. Wang P. Multi-train Operation Optimization and Control for Railway Traffic Conflict Detection and Resolution[Ph.D. dissertation], Southwest Jiaotong University, China, 2016.
[11]	Wang P, Goverde R M P. Multi-train trajectory optimization for energy efficiency and delay recovery on single-track railway lines. Transportation Research Part B: Methodological, 2017, 105: 340−361 doi: 10.1016/j.trb.2017.09.012
[12]	Wang P, Goverde R M P. Multi-train trajectory optimization for energy-efficient timetabling. European Journal of Operational Research, 2019, 272(2): 621−635 doi: 10.1016/j.ejor.2018.06.034
[13]	Luan X, Wang Y, De Schutter B, Meng L, Lodewijks G, Corman F. Integration of real-time traffic management and train control for rail networks-part 1: Optimization problems and solution approaches. Transportation Research Part B: Methodological, 2018, 115: 41−71 doi: 10.1016/j.trb.2018.06.006
[14]	Luan X, Wang Y, De Schutter B, Meng L, Lodewijks G, Corman F. Integration of real-time traffic management and train control for rail networks-part 2: Extensions towards energy-efficient train operations. Transportation Research Part B: Methodological, 2018, 115: 72−94 doi: 10.1016/j.trb.2018.06.011
[15]	Rao X. Holistic Rail Network Operation by Integration of Train Automation and Traffic Management[Ph.D. dissertation], ETH Zurich, Switzerland, 2015.
[16]	Rao X, Montigel M, Weidmann U. A new rail optimisation model by integration of traffic management and train automation. Transportation Research Part C: Emerging Technologies, 2016, 71: 382−405 doi: 10.1016/j.trc.2016.08.011
[17]	蔡伯根, 孙婧, 上官伟. 高速列车动态间隔优化的弹性调整策略. 交通运输工程学报, 2019, 19(1): 147−160 doi: 10.3969/j.issn.1671-1637.2019.01.015 Cai Bai-Gen, Sun Jing, Shangguan Wei. Elastic adjustment strategy of dynamic interval optimization for high-speed train. Journal of Traffic and Transportation Engineering, 2019, 19(1): 147−160 doi: 10.3969/j.issn.1671-1637.2019.01.015
[18]	上官伟, 敦旖晨, 蔡伯根, 刘俊囡, 宋鸿宇. 基于群体合作演化的高速列车编队运行多目标优化. 铁道学报, 2023, 45(8): 99−109 doi: 10.3969/j.issn.1001-8360.2023.08.011 Shangguan Wei, Dun Yi-Chen, Cai Bai-Gen, Liu Jun-Nan, Song Hong-Yu. Multi-objective optimization for high-speed train operation in platoon based on swarm cooperation evoluation. Journal of the China Railway Society, 2023, 45(8): 99−109 doi: 10.3969/j.issn.1001-8360.2023.08.011
[19]	宋鸿宇, 上官伟, 盛昭, 张瑞芬. 基于弹复力调整的高速列车群动态运行轨迹优化方法. 交通运输工程学报, 2021, 21(4): 235−250 Song Hong-Yu, Shangguan Wei, Sheng Zhao, Zhang Rui-Fen. Optimization method of dynamic trajectory for high-speed train group based on resilience adjustment. Journal of Traffic and Transportation Engineering, 2021, 21(4): 235−250
[20]	Havaei P, Sandidzadeh M A. Multi-objective train speed profile determination for automatic train operation with conscious search: A new optimization algorithm, a comprehensive study. Engineering Applications of Artificial Intelligence, 2023, 119: Article No. 105756 doi: 10.1016/j.engappai.2022.105756
[21]	Wang R, Zhang T, Yuan Z, Ding S, Zhang Q. A train timetable rescheduling approach based on multi-train tracking optimization of high-speed railways. Railway Sciences, 2023, 2(3): 358−370 doi: 10.1108/RS-05-2023-0022
[22]	彭其渊, 王超宇, 鲁工圆. 基于到发线运用方案的列车到达追踪间隔时间压缩方法及仿真研究. 中国铁道科学, 2020, 41(2): 131−138 doi: 10.3969/j.issn.1001-4632.2020.02.16 Peng Qi-Yuan, Wang Chao-Yu, Lu Gong-Yuan. Compression method and simulation of train arrival interval based on utilization of arrival-departure track. China Railway Science, 2020, 41(2): 131−138 doi: 10.3969/j.issn.1001-4632.2020.02.16
[23]	鲁工圆, 沈子力, 彭其渊, 王超宇. 基于区间速度控制的列车到达追踪间隔时间压缩方法研究. 铁道学报, 2021, 43(1): 19−27 doi: 10.3969/j.issn.1001-8360.2021.01.003 Lu Gong-Yuan, Shen Zi-Li, Peng Qi-Yuan, Wang Chao-Yu. Compressing arrival interval of high-speed trains by speed control within railway section. Journal of the China Railway Society, 2021, 43(1): 19−27 doi: 10.3969/j.issn.1001-8360.2021.01.003
[24]	Wang X, Li S, Cao Y, Xin T, Yang L. Dynamic speed trajectory generation and tracking control for autonomous driving of intelligent high-speed trains combining with deep learning and backstepping control methods. Engineering Applications of Artificial Intelligence, 2022, 115: Article No. 105230 doi: 10.1016/j.engappai.2022.105230
[25]	Wang D, Wu J, Wei Y, Chang X, Yin H. Energy-saving operation in urban rail transit: A deep reinforcement learning approach with speed optimization. Travel Behaviour and Society, 2024, 36: Article No. 100796 doi: 10.1016/j.tbs.2024.100796
[26]	Zhang H, Xu K, Huang D, He D, Wu S, Xian G. Hybrid decision-making for intelligent high-speed train operation: A boundary constraint and pre-evaluation reinforcement learning approach. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(11): 17979−17992 doi: 10.1109/TITS.2024.3404504
[27]	彭俊彬, 刘刚. 动车组牵引与制动, 2009144 Peng Jun-Bin, Liu Gang. Traction and Braking of EMU Trains, 2009144
[28]	王荣笙, 张琦, 闫璐, 丁舒忻. 区域临时限速下列车运行态势在线推演研究. 铁道运输与经济, 2023, 44(7): 127−132 Wang Rong-Sheng, Zhang Qi, Yan Lu, Ding Shu-Xin. Online deduction of train operation situation under regional temporary speed restriction. Railway Transport and Economy, 2023, 44(7): 127−132