铁路装载多件阔大货物时的重心位置优化研究  

Optimization Study of the Railway Gravity Center Position When Loading Several Long and Large Goods

作　　者：陈皓[1] 李雪芹[1] 申泰崑 王海明[1] 

机构地区：[1]西南交通大学交通运输与物流学院,成都610031

出　　处：《综合运输》2017年第8期68-73,共6页China Transportation Review

基　　金：中国铁路总公司科技研究开发计划课题(2014S14022)

摘　　要：针对多件阔大货物装载的综合优化问题,考虑货物更安全、更合理的运输,同时兼顾装载后重车的超限等级和重心位置偏移量的技术指标,以装载方案满足运输安全要求、装载方案理论上符合实际情况等为约束,建立了多件阔大货物装载方案的综合优化模型,并根据模型的特点设计了遗传BP算法进行求解。采用神经网络对样本进行划分,用遗传编码方式表示阔大货物装载排序,通过遗传、交叉、变异对结果进行更改、保留和加强,同时进行多目标的综合优化。实例验证表明,提出的模型和算法能很好地获得全局满意解,且迭代次数较少,能较好解决多件阔大货物装载的综合优化问题。In this paper, for the comprehensive optimization problem of loading several long and large goods, to achieve a more reasonable and safer transportation, we take the technical indexes of the overload rating and the position offsets of the gravity center into account. Besides, in order to make the loading scheme meet the transportation safety requirements and the actual situation in theory. A comprehensive optimization scheme model of loading several long and large goods is established. The Mean Shift algorithm is designed to solve the problem according to the characteristics of the model. The method of neural network is used to classify the samples. And we use the genetic coding to indicate the loading order of the long and large goods. The results have been changed, and strengthened by the genetic crossover and mutation operation. At the same time, the multi-objective optimization has been carried out.The experimental results show that, the proposed model and algorithm can obtain a Global Satisfactory Solution, which has less iterated number. It can solve the comprehensive optimization problem of loading several long and large goods.

关 键 词：铁路运输 混合算法 超限货物 方案优化 

分 类 号：U294.1[交通运输工程—交通运输规划与管理]