自适应粒子群算法求解编组站车流推算问题的研究

Study on Solution of Train Flow Calculation of Marshalling Station by Using ADPSO

编组站日班计划和阶段计划编制核心之一是出发列车车流来源的推算,由于车流推算的复杂性,其求解算法也是研究重点之一。基于解编顺序建立编组站动态车流推算的数学模型,约束中考虑了单调机资源、车流接续去向和时间等约束,目标函数在优化正点出发列车数的同时考虑总停留车小时的优化。通过设计自适应离散粒子群算法(ADPSO)对数学模型进行求解,以解编顺序为主要优化对象,静态配流采用Lingo编程实现,最后通过算例验证了算法的有效性。

One of the core of drawing day-shift scheme and in-phase scheme is the calculation of train flow resource of departure trains. For the complex of train flow calculation, it's solution calculation is also the core of the research. The mathematic model of dynamic train flow calculation was established based on uncoupling order, the restrictions such as single shunting car resource, train flow direction and time were taken consideration, and target function was taken consideration of optimizing general stopping hours at the same time of optimizing the number of punctual departure trains. Taking uncoupling order as the main optimization object, the mathematic model was taken solution by ADPSO, and static distribution was realized by using Lingo programme. In the end, according to the calculation examples, the validity of the algorithm was proved.