1.Engineering Research Center of Railway Industry on Digital and Intelligent Survey and Design System, China Railway Siyuan Survey and Design Group Co. , Ltd. , Wuhan 430063, Hubei, China
2.Digital Intelligence Business Unit, China Railway Siyuan Survey and Design Group Co. , Ltd. , Wuhan 430063, Hubei, China
This research investigated the high-precision and intelligent operation simulation of railways by exploring data-driven modeling of railway engineering and multi-agent autonomous perception simulation theories and methods for train groups. First, vector data models of railway lines were generated through engineering survey and design data, building intelligent agent models including tracks, signals, switches, and trains. Subsequently, the autonomous perception-control model for single-train operation was developed. Finally, by implementing a CTC intelligent agent for data perception, processing analysis, and dynamic monitoring and dispatch of train group operations, achieving autonomous simulation of train groups. Experimental results demonstrate that under the intelligent monitoring and decision-making of the CTC agent, both single-train and train-group models can operate safely and efficiently in simulations. In conclusion, the proposed data-driven modeling resolves precision deficiencies and low modeling efficiency in traditional simulation systems. By leveraging centralized control via the CTC agent, collaborative simulation and autonomous decision-making for train groups are realized, providing theoretical foundations and technical pathways for building autonomous and intelligent railway transportation simulation systems, offering high-credibility simulation tools for railway line design, station planning, and capacity evaluation.
列车计划时刻与仿真运行时刻比较表(单列车)如表4所示,由结果可以看出,赣州西站—定南南站间下行GXXX1次列车计划运行时分为46 min 30 s,仿真运行时分为46 min 16 s;上行GXXX2次列车计划运行时分为46 min 30 s,仿真运行时分为45 min 22 s,研究设计的智能体仿真系统中单列车能够按照计划运行图时刻运行,仿真运行数据与计划运行数据拟合度在97%以上。
MENGJianjun, CHENXiaoqiang, XURuxun,et al. Traction Calculation Analysis and Simulation of Urban Rail Train on Multi-Particle Model[J]. Journal of System Simulation,2015,27(3):603-608,619.
[3]
DONGH R, ZHUH N, GAOS G. An Approach for Energy-Efficient and Punctual Train Operation via Driver Advisory System[J]. IEEE Intelligent Transportation Systems Magazine,2018,10(3):57-67.
[4]
ZHANGH X, GUOM, HUL Y,et al. A Multi-Agent Simulation Based Train Platforming Research for Facilitating Passenger Transfer in a High Speed Railway Station[J]. Simulation Modelling Practice and Theory,2024,130:102856.
[5]
NASHA, HUERLIMANND. Railroad Railroad Simulation using OpenTrack[J]. WIT Transactions on the Built Environment,2004,74:45-54.
SHUAIBin, QINMengyao, XUMinhao. Simulation Study of High Speed Railroad Train Operation Based on Cellular Automata[J]. Computer Simulation,2022,39(8):153-159.
LIJing, WANGTao, LIBo,et al. Refined Search Algorithm for Train Routing in High Speed Railway Network[J]. Railway Transport and Economy,2024,46(2):1-9.
TIANRui, ZHAOFei. Discussion on Functional Architecture and Key Technologies of Intelligent High Speed Railway Traffic Control System[J]. Railway Transport and Economy,2022,44(5):52-56,78.
[15]
王建英. 智能调度集中系统研究[J]. 铁道通信信号,2022,58(7):7-12.
[16]
WANGJianying. Study on Intelligent Centralized Traffic Control System[J]. Railway Signalling & Communication,2022,58(7):7-12.
[17]
费宇晗. 高速铁路自动驾驶智能控制算法研究[D]. 兰州:兰州交通大学,2023.
[18]
SHIP, YANB. A Survey on Intelligent Control for Multiagent Systems[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2021,51(1):161-175.
PENGYunlong, KANGYuanlei, YUYichen,et al. Train Speed Following Control Based on Precise Parking and Energy Saving Optimization[J]. Urban Mass Transit,2024,27(6):215-220.
[22]
LIS K, YANGL X, GAOZ Y. Coordinated Cruise Control for High Speed Train Movements Based on a Multi-Agent Model[J]. Transportation Research Part C:Emerging Technologies,2015,56:281-292.
[23]
WANGX, LIS K, CAOY,et al. Dynamic Speed Trajectory Generation and Tracking Control for Autonomous Driving of Intelligent High Speed Trains Combining with Deep Learning and Back Stepping Control Methods[J]. Engineering Applications of Artificial Intelligence,2022,115:105230.
[24]
CHAIS M, YINJ T, D’ARIANOA,et al. Train Schedule Optimization for Commuter-Metro Networks[J]. Transportation Research Part C:Emerging Technologies,2023,155:104278.