基于旅客多维出行需求的列车开行方案与票价联合优化方法  

Joint Optimization Method of Train Line Planning and Ticket Pricing Based on Multi-Dimensional Travel Demand of Passengers

作　　者：孙国锋 景云[1,2] 李和壁 朱卯午 田志强 SUN Guofeng;JING Yun;LI Hebi;ZHU Maowu;TIAN Zhiqiang(School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China;Frontiers Science Center for Smart High-Speed Railway Systems,Beijing Jiaotong University,Beijing 100044,China;School of Traffic and Transportation,Lanzhou Jiaotong University,Lanzhou Gansu 730070,China;Key Laboratory of Railway Industry on Plateau Railway Transportation Intelligent Management and Control,Lanzhou Jiaotong University,Lanzhou Gansu 730070,China)

机构地区：[1]北京交通大学交通运输学院,北京100044 [2]北京交通大学智慧高铁系统前沿科学中心,北京100044 [3]兰州交通大学交通运输学院,甘肃兰州730070 [4]兰州交通大学高原铁路运输智慧管控铁路行业重点实验室,甘肃兰州730070

出　　处：《中国铁道科学》2024年第6期224-235,共12页China Railway Science

基　　金：国家自然科学基金资助项目(52372300,72161023);高原铁路运输智慧管控铁路行业重点实验室开放课题(GYYSHZ2302)。

摘　　要：为在客运服务产品设计时更好地满足旅客多样化的出行需求,定义旅客多维出行需求为“在OD需求基础上,进一步融合旅客对时间与经济性方面的个性化需求”;在高铁企业客票收入不减少的前提下,以旅客的票价成本、旅行时间成本和出发时间偏差成本构成的广义出行成本最小化为目标,构建基于旅客多维出行需求的列车开行方案与票价联合优化模型;基于自适应大邻域搜索(ALNS)算法设计求解算法,并以徐兰高铁兰州西—西安北段为背景进行案例分析。结果表明:优化后旅客的旅行时间成本略有增加,但其票价成本、出发时间偏差成本和广义出行成本分别降低18.58%,48.10%和19.17%;相比变邻域搜索(VNS)算法和模拟退火(SA)算法,设计的ALNS算法虽然收敛速度最慢,但迭代解质量最好,求解质量分别比前2种算法提升16.62%和23.87%。该方法能满足实际生产中不同规模线路的开行方案与票价联合优化工作的需要,并为客运产品优化提供决策参考。In order to better meet diverse travel demands of passengers in designing passenger service products,the multi-dimensional demands of passengers are defined as“further integrating personalized requirements of passengers in terms of time and cost based on OD demands”.With the objective of minimizing the generalized travel cost consisting of ticket price cost,travel time cost and departure time deviation cost,a joint optimization model for train line planning and ticket pricing based on multi-dimensional travel demands of passengers is constructed with the premise of maintaining the ticket revenue for high-speed rail enterprises.A solution algorithm based on the Adaptive Large Neighborhood Search(ALNS)algorithm is designed,followed by a case study carried out on the section from Lanzhouxi Railway Station to Xi’anbei Railway Station of the Xuzhou-Lanzhou High-Speed Railway.The results indicate that,after optimization,the travel time cost increases slightly,while the ticket price cost,departure time deviation cost and generalized travel cost decrease by 18.58%,48.10%and 19.17%,respectively.Compared with the Variable Neighborhood Search(VNS)and Simulated Annealing(SA)algorithms,the designed ALNS algorithm shows the slowest convergence speed,but the highest iterative solution quality,improving by 16.62%and 23.87%,respectively.This approach can satisfy the requirement of joint optimization work of line planning and ticket pricing across various route scales in actual production,and provide decision-making reference for optimizing passenger transport products.

关 键 词：高速铁路 出行需求 列车开行方案 票价 自适应大邻域搜索算法 

分 类 号：U292.31[交通运输工程—交通运输规划与管理]