高速铁路列车径路的分类及特征

在高铁网络上对列车径路进行系统分类,并分析各类列车径路的特征。在本线列车径路和跨线列车径路两大类中,将本线列车径路划分为线状径路和环状径路,将跨线列车径路划分为中长途列车径路、区域列车径路和特殊客运产品的列车径路。在重点分析的跨线列车径路中,中长途列车的迂回度较低,其径路应满足非直线系数阈值的约束;区域列车服务于区域客流,可由若干短距离本线列车径路拼接而成,区域客流较大时可以拼接形成环状列车径路;特殊客运产品有特定的服务对象及明确的产品特征,其径路起讫点及运行时间等要素应满足产品特征及市场定位。掌握高铁列车径路的合理分类及其特征有利于科学编制列车开行方案,提高列车运行效率。

基于选择性集成学习的高速列车故障识别研究

在SVM分类识别中,分类器模型一经训练得到,对所有测试样本进行无差别的识别。针对高速列车故障中样本的分类识别是存在区域分类精度的情况,提出了一种基于选择性集成学习的SVM多分类器融合算法。该方法选取测试样本最邻近的k个训练样本;然后选择对其分类效果好的SVM分类器进行融合,以提高分类准确率;最后使用高速列车故障数据进行了实验,并与Ada Boost、KNN、Bayes、SVM分类方法进行了比较。实验结果表明,该算法提高了分类识别准确率。

高铁车票销售投放策略改进研究

分析归纳现行高铁车票销售投放策略存在问题,针对票额自动预分的理论和方法展开研究,通过对列车分级并采取不同的预分模型,以及采用精确投放和模糊投放相结合的车票销售投放改进策略等,实现预售期外一日一车一方案,预售期内票额动态自动调整的目标。列车试点表明,各项效益指标均有提升。

Particle swarm optimization for train schedule of Y-type train routing in urban rail transit

The train schedule usually includes train stop schedule,routing scheme and formation scheme.It is the basis of subway transportation.Combining the practical experience of transport organizations and the principle of the best match between transport capacity and passenger flow demand,taking the minimum value of passenger travel costs and corporation operating costs as the goal,considering the constraints of the maximum rail capacity,the minimum departure frequency and the maximum available electric multiple unit,an optimization model for city subway Y-type operation mode is constructed to determine the operation section of mainline as well as branch line and the train frequency of the Y-type operation mode.The particle swarm optimization(PSO)algorithm based on classification learning is used to solve the model,and the effectiveness of the model and algorithm is verified by a practical case.The results show that the length of branch line in Y-type operation affects the cost of waiting time of passengers significantly.