王鹏玲,朱鸾民,陈力与,王青元

• 1:同济大学交通学院
• 2:西南交通大学电气工程学院

摘要(Abstract)：

针对高速列车运行过程中面临的多源不确定性扰动问题，提出一种基于数据驱动模型预测控制(DDMPC)的速度控制方法。该方法首先通过蒙特卡洛仿真构建多扰动场景下的最优轨迹数据集，并利用混合整数线性规划求解各扰动条件下的能耗最优速度曲线；在此基础上，设计一种基于Hankel矩阵的数据驱动预测模型，结合滚动优化策略，实现对列车速度的实时闭环控制。实验以京张高铁线路与CR450型动车组为对象，在不同扰动强度下进行仿真验证。结果表明，与基于传统模型预测控制以及鲁棒模型预测控制的方法相比，基于DDMPC的速度控制方法在能耗节约、速度跟踪精度和计算效率方面均具有显著优势，尤其在强扰动环境下仍能保持良好的控制鲁棒性与实时性。

关键词(KeyWords)： 列车运行控制;数据驱动;模型预测控制;最优速度曲线;能耗优化;鲁棒控制

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(U2368216,52572348);; 上海市科技计划项目(25692108300)

作者(Author): 王鹏玲,朱鸾民,陈力与,王青元

参考文献(References)：

• [1] Howlett P,Pudney P,Vu X.Local energy minimization in optimal train control[J].Automatica,2009,45(11):2692-2698.
• [2] Vu X,Albrecht A R,Pudney P J,et al.Energy-efficient train control:From local convexity to global optimization and uniqueness[J].Automatica,2013,49(10):3072-3078.
• [3] 卢启衡，冯晓云，王青元.基于遗传算法的追踪列车节能优化[J].西南交通大学学报，2012(2):96-101.Lu Qiheng,Feng Xiaoyun,Wang Qingyuan.Energy-saving optimization of tracking trains based on genetic algorithm[J].Journal of Southwest Jiaotong University,2012(2):96-101.
• [4] 王青元，冯晓云.列车准点节能运行的控制工况最优切换研究[J].中国铁道科学，2016,37(2):91-98.Wang Qingyuan,Feng Xiaoyun.Optimal control mode switching for punctual and energy-saving train operation[J].China Railway Science,2016,37(2):91-98.
• [5] 黄友能，宫少丰，曹源，等.基于粒子群算法的城轨列车节能驾驶优化模型[J].交通运输工程学报，2016,16(2):118-124.Huang Youneng,Gong Shaofeng,Cao Yuan,et al.Energy-efficient driving optimization model for urban rail train based on particle swarm optimization algorithm[J].Journal of Traffic and Transportation Engineering,2016,16(2):118-124.
• [6] 荀径，杨欣，宁滨，等.列车节能操纵优化求解方法综述[J].铁道学报，2014,36(4):14-20.Xun Jing,Yang Xin,Ning Bin,et al.Review of energy-efficient train control optimization methods[J].Journal of the China Railway Society,2014,36(4):14-20.
• [7] 刘晓宇.基于模型预测控制的高速列车精确停车方法研究[D].北京：北京交通大学，2020.Liu Xiao Yu.Research on high-speed train precise parking method based on model predictive control[D].Beijing:Beijing Jiaotong University,2020.
• [8] Yan X,Cai B,Ning B,et al.Moving horizon optimization of dynamic trajectory planning for high-speed train operation[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(5):1258-1270.
• [9] 宋宗莹，杨迎泽，王兴中，等.改进模型预测控制的列车自组网运行控制[J].科技创新与应用，2025,15 (5):22-26.Song Zongying,Yang Yingze,Wang Xingzhong,et al.Train ad-hoc network operation control based on improved model predictive control [J].Technology Innovation and Application,2025,15 (5):22-26.
• [10] 金文斌，张佳辉，姚柏伶，等.基于事件触发预测控制的高速列车轨迹跟踪[J].机车电传动，2024 (4):148-154.Jin Wenbin,Zhang Jiahui,Yao Bailing,et al.High-speed train trajectory tracking based on event-triggered predictive control [J].Electric Drive for Locomotives,2024 (4):148-154.
• [11] 孙鹏飞，张传鑫，蒋春宏，等.结合迭代学习和模型预测的重载列车运行控制[J].中国铁道科学，2023,44(2):111-119.Sun Pengfei,Zhang Chuanxin,Jiang Chunhong,et al.Heavy-haul train operation control combining iterative learning and model prediction[J].China Railway Science,2023,44(2):111-119.
• [12] Zhou L,Li Z,Cao Y,et al.Predictive sliding mode control for high-speed trains via adaptive extended state observer under input constraints:A model-free scheme[J].IEEE Transactions on Intelligent Transportation Systems,2025:1-18.
• [13] 罗啸林，唐涛，林炳跃，等.一种缩短虚拟编组列车追踪间距的鲁棒模型预测控制方法[J].铁道学报，2023,45(8):68-76.Luo Xiaolin,Tang Tao,Lin Bingyue,et al.A robust model predictive control method for reducing tracking distance of virtually coupled train set[J].Journal of the China Railway Society,2023,45(8):68-76.
• [14] Li Z,Zhong L,Yang H,et al.Distributed cooperative tracking control strategy for virtual coupling trains:An event-triggered model predictive control approach[J].Processes,2023,11(12):3293.
• [15] 李智，钟磊，杨浩，等.虚拟编组列车分布式协同预测控制[J].交通运输工程学报，2024,24(5):362-378.Li Zhi,Zhong Lei,Yang Hao,et al.Distributed cooperative predictive control of virtual coupled trains[J].Journal of Traffic and Transportation Engineering,2024,24(5):362-378.
• [16] 康庄，贾利民，秦勇.基于改进模糊滑模控制的列车速度跟踪研究[J].铁道学报，2024,46(4):97-107.Kang Zhuang,Jia Limin,Qin Yong.Train Speed Tracking Based on Improved Fuzzy Sliding Mode Control[J].Journal of the China Railway Society,2024,46(4):97-107.
• [17] Wang P,Goverde R M P.Multi-train trajectory optimization for energy efficiency and delay recovery on single-track railway lines[J].Transportation Research Part B:Methodological,2017,105:340-361.
• [18] Novak H,Lesic V,Vasak M.Energy-efficient model predictive train traction control with incorporated traction system efficiency[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(6):5044-5055.
• [19] 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[J].交通运输工程学报，2019,19(1):147-160.Cai Baigen,Sun Jing,Shangguan Wei.Elastic adjustment strategy for dynamic interval optimization of high-speed trains[J].Journal of Traffic and Transportation Engineering,2019,19(1):147-160.
• [20] Luo X,Wang D,Tang T,et al.A data-driven MPC approach for virtually coupled train set with non-analytic safety distance[J].Transportation Research Part C:Emerging Technologies,2025,174:105087.
• [21] Su S,Zhu Q,Liu J,et al.A data-driven iterative learning approach for optimizing the train control strategy[J].IEEE Transactions on Industrial Informatics,2023,19(7):7885-7893.
• [22] 侯涛，唐丽，牛宏侠.基于数据驱动的高速列车速度复合控制研究[J].交通运输系统工程与信息，2023,23 (3):145-152.Hou Tao,Tang Li,Niu Hongxia.Research on data-driven compound speed control of high-speed trains [J].Journal of Transportation Systems Engineering and Information Technology,2023,23 (3):145-152.
• [23] Shang M,Zhou Y,Fujita H.Deep reinforcement learning with reference system to handle constraints for energy-efficient train control[J].Information Sciences,2021,570:708-721.
• [24] Yin J,Ning C,Tang T.Data-driven models for train control dynamics in high-speed railways:LAG-LSTM for train trajectory prediction[J].Information Sciences,2022,600:377-400.
• [25] 吴卫，阴佳腾，陈照森，等.基于深度强化学习DDDQN的高速列车智能调度调整方法[J].铁道科学与工程学报，2024,21(4):1298-1308.Wu Wei,Yin Jiateng,Chen Zhaosen,et al.Intelligent scheduling adjustment method for high-speed trains based on deep reinforcement learning DDDQN[J].Journal of Railway Science and Engineering,2024,21(4):1298-1308.
• [26] 龚飞杰，上官伟，宋鸿宇，等.基于深度强化学习优化LQR的虚拟重联高速列车间隔控制方法[J].铁道学报，2025,47(11):116-126.Gong Feijie,Shangguan Wei,Song Hongyu,et al.Spacing control for virtually coupled high-speed trains using deep reinforcement learning optimized LQR[J].Journal of the China Railway Society,2025,47(11):116-126.
• [27] 刘通，荀径，宁滨，等.历史数据Q学习的列车节能运行控制方法[C]//2018中国自动化大会(CAC2018)论文集.北京：北京交通大学，2018:336-342.Liu Tong,Xun Jing,Ning Bin,et al.Energy-efficient train operation control method using Q-learning with historical data[C]//Proceedings of the 2018 Chinese Automation Congress (CAC).Beijing:Beijing Jiaotong University,2018:336-342.
• [28] 上官伟，敦旖晨，蔡伯根，等.基于群体合作演化的高速列车编队运行多目标优化[J].铁道学报，2023,45(8):99-109.Shangguan Wei,Dun Yichen,Cai Baigen,et al.Multi-objective optimization of high-speed train formation operation based on group cooperation evolution[J].Journal of the China Railway Society,2023,45(8):99-109.
• [29] 王义惠，朱松巍，刘硕，等.基于速度距离网络的列车运行曲线优化[J].北京交通大学学报，2020,44(2):36-43.Wang Yihui,Zhu Songwei,Liu Shuo,et al.Train operation curve optimization based on speed-distance network[J].Journal of Beijing Jiaotong University,2020,44(2):36-43.