运用学习规则求解编组站静态配流问题的研究

Study on Resolving Static Wagon-flow Allocation by Using Learning Rules

编组站静态配流问题需要制定配流方案,明确出发列车的编组内容和车流来源。算法的思路是通过构建网络模型,将静态配流问题转化为固定费用的产销平衡运输问题,并将目标函数转化为求最小虚拟到达列车车辆数。首先设定虚拟到达列车并对其赋初值,把出发列车分为可欠轴与不可欠轴两类,在计算过程中调用学习规则保证出发列车满轴,最后求出虚拟到达列车的最小值,得到配流方案。通过简单的算例验证表明,该算法能够在有效的时间内求解大规模的静态配流问题,为静态配流问题提供一种新的方法。

An allocation scheme should be made in marshalling station＇s static wagon-flow allocation as to decide the marshalling formation of departure trains and sources of wagon-flow. The problem of static wagon-flow allocation can be transformed into the problem of balanced transportation with fixed cost by establishing the network model. The objective function can be transformed to work out the minimum number of virtual arriving trains/wagons. The algorithm gives the initial value to virtual arriving trains firstly, divides the departure trains into compulsive full axis and optional full axis, applies the learning rules to guarantee the full axis of departure trains in the process of calculating, and finally work out the minimum virtual arriving trains which could realize the allocation scheme. The example demonstrates that this algorithm can solve the static wagon-flow allocation problem in large scale within a reasonable time limitation which provides a new approach to the static wagon-flow allocation problem.