AI 中文总结
针对平面调车场铁路车辆分配问题，提出Zone-DDQN启发式方法，在大型实例上求解效率远超MIP模型，平均运行时间214.42秒，最优性差距5.71%。
AI 中文摘要
铁路车辆调车（即编组作业）决策对铁路场站系统的高效运行至关重要，而铁路场站系统又关乎货物的快速有效运输。在平面调车场中，调车作业主要通过机车推拉铁路车辆来完成列车的编组和解编。在这类场景中，具有预设目的地的铁路车辆分布在多条平行轨道上，必须被移动或调度以形成所需的 outbound 列车。本研究针对平面调车场中的铁路车辆分配问题（Railcar Assignment Problem, RAP），目标是最小化总调车次数。我们提出了一种包含铁路场站实际运营约束的新型混合整数规划（mixed-integer programming, MIP）模型，并证明其具有 NP-hard 复杂性。为求解大规模实例，我们提出了一种综合的基于区域的双深度 Q 网络（Zone-based Double Deep Q-Network, Zone-DDQN）启发式方法，该方法整合了铁路场站结构、场站区域分解和双深度 Q 网络（Double Deep Q-Network, DDQN）。场站区域分解策略将调车场划分为多个平行的场站区域，之后应用 DDQN 在每个区域内单独且依次求解问题。我们在一系列 RAP 实例上对小型、中型和大型调车场进行了计算实验。平均结果显示，Zone-DDQN 启发式方法在小型调车场实例上的平均最优性差距为 5.71%。对于包含超过 150 辆铁路车辆和 30 条轨道的大型调车场实例，MIP 模型无法在 24 小时内获得解，而 Zone-DDQN 启发式方法能够以平均 214.42 秒的运行时间求解这些实例。
英文摘要
Railcar switching, or shunting operations decisions play a significant role in the efficient operation of railyard systems, which are in turn critical to the fast and effective movement of goods. In flat yards, switching operations are primarily performed using locomotives to push and pull railcars in order to assemble and disassemble trains. In such settings, railcars with predefined destinations are located across multiple parallel rail tracks, and must be moved, or switched, in order to form desired outbound trains. This study addresses the Railcar Assignment Problem (RAP) in flat yards with an objective of minimizing the total number of switching movements. We present a novel mixed-integer programming (MIP) model for this problem that incorporates practical operational constraints in rail yards, and demonstrate its NP-hardness. To solve large-scale instances, we propose a comprehensive Zone-based Double Deep Q-Network (Zone-DDQN) heuristic method that integrates railway structure, yard-zone decomposition, and a Double Deep Q-Network (DDQN). The yard-zone decomposition strategy partitions the yard into multiple parallel yard zones, after which the DDQN is applied to solve the problem within each zone individually and sequentially. Computational experiments across small-, medium-, and large-scale yards were conducted on a series of RAP instances. Average results show that the Zone-DDQN heuristic achieves an average optimality gap of $5.71\%$ across small-scale yard instances. For large-scale yard instances containing more than 150 railcars and 30 tracks, the MIP model was not able to obtain solutions within 24 hours. In contrast, the Zone-DDQN heuristic was able to solve these instances with an average running time of 214.42 seconds.
