交通运输系统工程与信息 ›› 2025, Vol. 25 ›› Issue (5): 320-332.DOI: 10.16097/j.cnki.1009-6744.2025.05.029

• 系统工程理论与方法 • 上一篇    下一篇

基于救援效用的洪灾物资配送与灾民转移路径规划

刘长石a,万城b,王凤*a,陈宝玺b,岳俊羽c   

  1. 湖南工商大学,a.工商管理学院;b.智能工程与智能制造学院;c.人工智能与先进计算学院,长沙410205
  • 收稿日期:2025-05-16 修回日期:2025-07-26 接受日期:2025-08-14 出版日期:2025-10-25 发布日期:2025-10-25
  • 作者简介:刘长石(1975—),男,湖南邵阳人,教授,博士。
  • 基金资助:
    国家社会科学基金(23BGL011);国家自然科学基金(72401095)。

Route Planning Relief Delivery and Victim Evacuation Based on Rescue Utility in Flood Disaster Scenarios

LIU Changshia, WAN Chengb, WANG Feng*a, CHEN Baoxib,YUE Junyuc   

  1. a. School of Management; b. School of Intelligent Engineering and Intelligent Manufacturing; c. School of Artificial Intelligence and Advanced Computing, Hunan University of Technology and Business, Changsha 410205, China
  • Received:2025-05-16 Revised:2025-07-26 Accepted:2025-08-14 Online:2025-10-25 Published:2025-10-25
  • Supported by:
    National Philosophy and Social Sciences Foundation of China (23BGL011);National Nature Sciences Foundation of China(72401095)。

摘要: 应急物资配送与受困灾民转移是洪灾救援工作的核心问题。为科学衡量运载工具在不同时间抵达需求点产生的实际救援效果,将救援效用理念引入洪灾应急物资配送与灾民转移的协同路径规划。综合考虑卡车与冲锋艇的不同适用场景,受灾点预期救援时间及运载工具的行驶速度、数量与容量等因素,以总救援时间最短和总救援效用最大为目标构建应急物资配送与灾民转移的协同路径规划模型,并根据模型特性设计一种改进非支配排序遗传算法求解。采用2024年江西省南昌市洪涝灾害数据开展实验,结果表明,本文方法能有效开展洪灾应急物资配送与灾民转移的协同路径规划,与先转移灾民后配送应急物资的救援策略以及先配送应急物资后转移灾民的救援策略相比较,本文救援策略可使总救援时间分别节省138min和123min,总救援效用分别超过108.2单位和77.5单位。

关键词: 物流工程, 路径规划, 改进非支配排序遗传算法, 应急物资配送, 灾民转移

Abstract: The key components of flood rescue are the relief delivery and the evacuation of stranded residents in disaster-stricken areas. To scientifically assess the actual effectiveness of rescue efforts based on the arrival times of transport vehicles at demand points, this paper introduces the concept of rescue utility into the joint routing of relief delivery and victim evacuation in flood disaster scenarios. A collaborative routing model is developed with the dual objectives of minimizing the total rescue time and maximizing the total rescue utility of all affected locations. The model comprehensively considers factors such as the differing applicability of trucks and assault boats, the expected rescue times of disaster-stricken sites, as well as the speed, quantity, and capacity of the available transport vehicles. An improved Non-dominated Sorting Genetic Algorithm-II is designed to solve the proposed model. Numerical experiments are conducted based on the data from the 2024 flood disaster in Nanchang, Jiangxi Province of China. The results demonstrate that the proposed approach enables effective joint routing of relief delivery and victim evacuation. Compared to strategies that prioritize evacuating residents before delivering emergency supplies or delivering emergency supplies before evacuating residents, the proposed rescue strategy respectively reduces total rescue time by 138 minutes and 123 minutes and increases total rescue utility respectively by 108.2 units and 77.5 units.

Key words: logistics engineering, routes planning, improved non-dominated sorting genetic algorithm-II, relief delivery, victim evacuation

中图分类号: