公交运力资源优化配置的分析与研究

发布时间：2018-06-02 08:29

本文选题：均衡配置 + 基尼系数　；参考：《昆明理工大学》2012年硕士论文

【摘要】：面对城市日益增长的客流需求,最大限度地优化公交运力资源配置势在必行。改善公交运力配置,不权仅是提高公交运营效率的需要,更是提高公交服务水平,实现公交运力资源均衡配置和创建环境友好型社会的内在需要。要解决公交问题,仅仅依靠增加公交车的数量,或者调整公交线路并不能从根本上解决问题,相反,一味地增加公交车的数量,不权会造成公交资源的浪费,更会加大城市交通的压力。因此,只有充分地利用现有的公交资源,在满足公交企业和乘客多方利益的前提下,对相关资源进行优化配置,才是解决问题的关键所在本文首先在综合分析公交运力配置的影响囚素的基础上,将公交运力优化配置问题定性为多目标优化问题,并进一步介绍了基于基尼系数的多目标优化模型,在分析原模型的基础上,引进了基尼系数这一经济学指标,通过量化表示将资源配置均衡度作为新的目标函数加入原模型,得到了改进的新模型。并通过实例化数据验证,通过前后的调整,各站点的客流量分担率(基尼系数)由原来的0.29改进为0.21,从客流量分布均衡性的角度说明了新模型比原模型具有较好的现实拟合度。本文明确了客流量预测在整个公交运力配置流程中的关键作用。客流量的准确预测是公交资源优化配置的依据和前提。本文给出了基于Elman神经网络的公交客流量预测流程。最后,通过数据搜集,利用北京市某条线路近8年的客流量数据进行了实例预测。最后通过与当前较流行的BP静态神经网络比较,发现Elman神经网络整体上比BP神经网络具有较高的预测精度。
[Abstract]:In the face of the increasing demand of passenger flow in cities, it is imperative to optimize the allocation of public transport capacity resources to the maximum extent. To improve the allocation of public transport capacity is not only the need to improve the efficiency of public transport operation, but also to improve the level of public transport service, to achieve the balanced allocation of public transport capacity resources and to create an environment-friendly society. To solve the problem of public transport, merely relying on increasing the number of buses, or adjusting the bus routes, cannot fundamentally solve the problem. On the contrary, blindly increasing the number of buses will result in a waste of public transport resources. Will increase the pressure of urban traffic. Therefore, the key to solve the problem is to make full use of existing public transport resources and to optimize the allocation of related resources on the premise of satisfying the interests of public transport enterprises and passengers. Based on the comprehensive analysis of the influence of public transport capacity allocation, this paper defines the optimal allocation of public transport capacity as a multi-objective optimization problem, and further introduces the multi-objective optimization model based on Gini coefficient. Based on the analysis of the original model, this paper introduces the Gini coefficient as an economic index, and adds the equilibrium degree of resource allocation as a new objective function to the original model through quantitative expression, and obtains the improved new model. Through the validation of the instantiation data, the Gini coefficient of each station is improved from 0.29 to 0.21 through the adjustment before and after, which shows that the new model has better realistic fit than the original model from the point of view of the equilibrium of passenger flow distribution. This paper clarifies the key role of passenger flow prediction in the whole public transportation capacity allocation process. The accurate forecast of passenger flow is the basis and premise of the optimal allocation of public transportation resources. This paper presents the flow of bus passenger flow forecasting based on Elman neural network. Finally, through the data collection, using the passenger flow data of a certain line in Beijing in the past 8 years, a case prediction is carried out. Finally, compared with the popular BP static neural network, it is found that the Elman neural network has a higher prediction accuracy than the BP neural network as a whole.
【学位授予单位】：昆明理工大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：F224;F572.88

【参考文献】