*Result*: 重载列车群组运行模式下 股道分配方法研究.
*Further Information*
*This study addressed track scheduling and allocation challenges for heavy-haul train operations by presenting an integer programming model intended to minimize marshalling and demarshalling times. The model incorporated constraints related to spatial-temporal conflicts, train continuity, and vehicle-track compatibility. Given the NP-hard nature of the problem, direct polynomial-time solutions are infeasible. We proposed a parallel adaptive genetic algorithm that focuses on preserving high-fitness chromosomes during selection and mutation. A specialized parallel solution algorithm was also introduced. Simulation experiments utilizing real data from nine stations and eight sections in northern China reveal that unified track allocation reduces excessive marshalling and demarshalling times associated with disparate train positions. Compared with the manual greedy allocation mode, the proposed method can optimize the demarshalling time by about 2 times on average. Additionally, the introduction of parallel computing strategies enhances solution speed relative to leading solvers like GUROBI. Compared with the Tabu Search Algorithm, our method improved the accuracy by nearly 24% and speeds up the solution. Sensitivity analyses confirm the robustness of our approach across various scenarios and anomalies. [ABSTRACT FROM AUTHOR]*
*为解决重载列车群组运行模式下站场内股道调度与分配难度大的问题, 构建以解编组时间最少为优化目标的重载 列车股道分配整数规划模型, 该模型综合考虑股道分配过程中时空冲突、行车连续性以及车辆与股道工程性质匹配性等约 束条件。该问题为 NP 难问题中的典型组合优化问题, 因此无法在多项式时间内直接求解。为提高所提方法在工程应用领域 的实用性及推广速度, 本文创新性地提出了并行自适应遗传算法, 该方法在选择和变异过程中优先保证适应度值较好染色 体的完整性和选择概率。考虑到本文模型以及编码方式的独特性, 设计了并行求解算法。利用我国北方某地区 9 站 8 区间的 实际线路数据设计仿真实验, 研究结果表明: 群组运行模式下股道统一分配能够显著缓解由于单元列车所在股道位置不同 导致的解编组作业时间过长问题, 相较于人工贪心分配模式, 所提方法将解编组时间平均优化 2 倍左右; 引入并行计算策 略以及高效的解空间探索机制, 提高了复杂场景下股道分配模型求解速度, 从而解决 GUROBI 无法直接求解的超大规模测 试用例; 与当前组合优化领域内广泛采用的禁忌搜索算法相比, 并行自适应遗传算法将精度提高了将近 24%并加快了求解 速度; 通过灵敏度分析验证了本文方法在多场景和异常参数下的运行稳定性, 可为重载群组列车运行模式的进一步推广及 运行调度过程中的及时响应提供理论和方法支撑。 [ABSTRACT FROM AUTHOR]
Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)*