单杏花,郭鹏,韩科,卫铮铮,文曙东

• 1:西南交通大学经济管理学院
• 2:中国铁道科学研究院集团有限公司
• 3:贵阳学院经济管理学院

摘要(Abstract)：

针对铁路调图后新车次需求预测无历史数据的问题，提出一种运行图调整后客流量在目标区段车次间重分布预测算法，通过将调图前后车次合并为一天的车次，在目标区段上，以车次席别为选择目标建立旅客偏好排序列表，基于旅客策略行为建立非参数离散选择模型，采用最大期望算法对旅客到达率和概率质量函数进行联合估计。根据调图前某天的实际预订数据计算面向车次席别集合产品时每种旅客类型的到达概率，从而得到每趟车次席别在非截尾状态下的初始需求。上述估计所得初始需求对应车次席别和旅客首要偏好信息，通过模拟每张售出车票背后的旅客在面临调图后车次席别的选择行为，得到调图后的车次席别中的客流分布。基于伊宁至乌鲁木齐实际高速铁路车次席别预售数据的数值仿真结果表明，为调图后新开车次提供的引流需求主要由调图后取消的车次席别需求和调图前预订标杆车次席别的“再现需求”构成，其中，标杆车次所有在售席别的“再现需求”值总和在调图后的前3个“预售提前期间隔”中分别下降95.33%、91.50%和91.96%,证明所提客流重分布预测算法在考虑旅客策略行为、网络替代效应等因素下的有效性和适用性。

关键词(KeyWords)： 列车运行图;客流分配;非参数离散选择模型;需求非限化估计;旅客策略行为

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(U2368212)

作者(Author): 单杏花,郭鹏,韩科,卫铮铮,文曙东

参考文献(References)：

• [1] Guo P,Xiao B C,Li J.Unconstraining methods in revenue management systems:research overview and prospects [J].Advances in Operations Research,2012,2012:270910.
• [2] Sharif Azadeh S,Marcotte P,Savard G.A taxonomy of demand uncensoring methods in revenue management [J].Journal of Revenue and Pricing Management,2014,13(6):440-456.
• [3] Weatherford L.The history of unconstraining models in revenue management [J].Journal of Revenue and Pricing Management,2016,15(3):222-228.
• [4] 郭鹏.网络环境下收益管理系统需求非限化估计综述[J].计算机工程与应用，2017,53(19):17-25.Guo Peng.Review of demand unconstraining estimation in revenue management systems from perspective of network[J].Computer Engineering and Applications,2017,53(19):17-25.
• [5] 杨婷群，陈坚.考虑铁路旅客偏好差异的离站方式选择行为分析[J].交通运输研究，2024,10(3):1-9.Yang Tingqun,Chen Jian.Departure mode choice behavior considering differences in railway passenger preferences[J].Transport Research,2024,10(3):1-9.
• [6] 单杏花，赵烁.考虑旅客群体出行偏好的高铁客流分配方法[J].铁路计算机应用，2024,33(8):12-18.Shan Xinghua,Zhao Shuo.High-speed railway passenger flow assignment method considering travel preferences of passenger groups [J].Railway Computer Application,2024,33(8):12-18.
• [7] 景荟颖，吕红霞，杨皓男，等.高速铁路动态客流分配方法研究[J].综合运输，2021,43(12):59-66.Jing Huiying,Lv Hongxia,Yang Haonan,et al.Dynamic passenger flow allocation method under high-speed railway network[J].China Transportation Review,2021,43(12):59-66.
• [8] 张宇，李思萌，聂磊.基于购票时序的高速铁路客流分配理论研究[J].中国铁路，2021(11):108-115.Zhang Yu,Li Simeng,Nie Lei.Theoretical research on passenger flow distribution of high speed railway based on ticket purchase sequence[J].China Railway,2021(11):108-115.
• [9] 徐光明，林珊珊，胡心磊，等.高速铁路旅客购票时间选择行为研究[J].铁道学报，2024,46(4):9-19.Xu Guangming,lin Shanshan,Hu Xinlei,et al.Advance booking behavior of high-speed railway passengers[J].Journal of the China Railway Society,2024,46(4):9-19.
• [10] 肖瑶，谭宇燕.基于旅客多维异质性的高速铁路客流分配方法研究[J].铁道运输与经济，2025,47(7):74-85.Xiao Yao,Tan Yuyan.Passenger flow assignment method of high speed railway based on passengers’ multidimensional heterogeneity[J].Railway Transport and Economy,2025,47(7):74-85.
• [11] 李文卿，倪少权，杨渝华，等.基于开行方案的高速铁路客流分配方法研究[J].铁道学报，2021,43(3):1-8.Li Wenqing,Ni Shaoquan,Yang Yuhua,et al.Research on passenger flow assignment method of high-speed railway based on line plan [J].Journal of the China Railway Society,2021,43(3):1-8.
• [12] 颜研，倪少权.基于巢式Logit模型的城市轨道交通客流分配问题研究[J].石家庄铁道大学学报(自然科学版),2015,28(4):99-103.Yan Yan,Ni Shaoquan.Nested logit model for the traffic assignment problem of urban railway transit [J].Journal of Shijiazhuang Tiedao University (Natural Science Edition),2015,28(4):99-103.
• [13] Zhu Y W,Koutsopoulos H N,Wilson N H M.A probabilistic passenger-to-train assignment model based on automated data [J].Transportation Research Part B:Methodological,2017,104:522-542.
• [14] Zhou Y,Yang H,Wang Y,et al.Integrated line configuration and frequency determination with passenger path assignment in urban rail transit networks [J].Transportation Research Part B:Methodological,2021,145:134-151.
• [15] Su H Y,Shi F,Xu G M,et al.Schedule-based passenger assignment for high-speed rail networks considering the ticket-booking process [J].Mathematical Problems in Engineering,2016,2016:1650839.
• [16] Shang P,Li R M,Guo J F,et al.Integrating lagrangian and eulerian observations for passenger flow state estimation in an urban rail transit network:a space-time-state hyper network-based assignment approach [J].Transportation Research Part B:Methodological,2019,121:135-167.
• [17] 郭鹏.航线网络中需求无约束估计的非参数选择模型[J].管理科学学报，2020,23(12):30-51.Guo Peng.A nonparametric discrete choice model for unconstrained demand estimation in airline network[J].Journal of Management Science in China,2020,23(12):30-51.
• [18] 郭鹏，周杰.航线网络中非参数需求非限化估计的MM算法[J].工业工程与管理，2023,28(4):107-120.Guo Peng,Zhou Jie.MM algorithm for nonparametric demand unconstraining estimation in airline network[J].Industrial Engineering And Management,2023,28(4):107-120.
• [19] 郭鹏，周杰.航线网络需求非限化估计中的策略行为发现算法[J].工业工程与管理，2023,28(3):96-110.Guo Peng,Zhou Jie.A strategic behavior discovery algorithm for demand unconstraining estimation in airline network[J].Industrial Engineering And Management,2023,28(3):96-110.
• [20] 郭鹏，萧柏春，李军.收益管理中考虑顾客策略行为的多航班非限化估计方法[J].系统工程理论与实践，2015,35(5):1103-1115.Guo Peng,Xiao Baichun,Li Jun.Multi-flight unconstraining method considering strategic customer behavior in revenue management[J].Systems Engineering Theory & Practice,2015,35(5):1103-1115.