基于EMD-GRU的高速公路行程时间组合预测模型

考虑到高速公路行程时间影响因素繁多且行程时间序列非线性、非平稳特征显著,设计了基于经验模态分解和GRU神经网络的高速公路行程时间组合预测模型.首先,利用高速公路收费数据中车辆进出高速公路的时间信息获取路段行程时间序列;然后,利用经验模态分解算法,将复杂的行程时间序列分解为若干时间尺度不同、相对平稳的本征模态函数分量和残...     

统计分析方法在交通数据检测中的应用

为了加强对车辆的监控,准确地采集数据,合理调节疏导流量,更好地规范交通管理,采集交通流量数据的设备必不可少,同时对于厂家生产的有关交通数据的检测仪器也要制定出一套科学,客观,有效的检测标准,以便确保交通管理的科学性和准确性.经常采集的交通数据包括车流量,车型大小,停车是否越线.本文依据仪器所采集到的数据,给出了对仪器的测量精度是否达到规定标准的统计分析方法.     

基于门控递归单元神经网络的高速公路行程时间预测

为了更高效地预测高速公路行程时间,以高速公路行程时间为研究对象,通过采集车辆在高速公路进出口收费站的刷卡数据获取行程时间,利用门控递归单元神经网络对行程时间进行预测.按照所设计的预测流程,利用广州市机场高速南线高速公路收费数据进行验证,结果显示,预测拟合效果较好,并与LSTM神经网路和BP神经网络进行了对比分析.结果表明:门控递归单元神经网络具有更好的预测准确度.     

多收费方式收费系统资源配置优化方法

随着ETC技术的发展,高速公路收费系统从单人工收费方式逐渐向多收费方式格局演变.同时高速公路收费系统的设计涉及到政府、道路管理者、道路使用者及道路非使用者之间利益的协调发展,因此研究在多收费方式情况下,满足不同利益层面需求的系统资源的优化配置问题具有重要意义.通过建立收费系统资源优化配置模型,在收费制式既定的情况下,利用遗传算法对收费站位置与数量进行寻优,并利用非集计方法对多收费方式情况下的车道配置进行均衡求解,可定量计算出最佳系统资源配置方案,包括确定收费制式、收费站位置与数量、收费方式、各收费站不同收费方式车道组合情况.最后我们进行算例研究,并对优化结果进行了分析比较,可为收费制式的选择及收费站的车道布设提供理论依据.     

基于手机信令大数据的城市居民出行OD预测

为得到具有客观性、动态性的居民出行起止点间交通出行量(OD trips),以中国移动手机信令大数据为基础,阐述了手机信令数据的来源与构成,针对城市居民出行目的,通过数据分析,设置10分钟为划分出行活动的阈值,提出基于手机信令数据获得的OD矩阵的原理与方法,应用数据挖掘技术,对贵阳市居民出行OD矩阵进行了预测.为进一步加强大数据与城市智能交通系统的融合,将得到的城市居民出行OD矩阵应用到真实的城市公交线网中.最后通过MicroCity平台,将数据结果实现可视化.分析结果表明:与传统OD调查方式相比,利用手机信令大数据获得的OD矩阵客观性、动态性较强,信息采集分析周期短,更容易与城市智能交通系统融合,应用可视化平台,可实时反映出城市公交运营状态,为城市智能规划和调度提供重要参考.     

基于改进的时空图卷积网络的交通流预测模型研究

智能交通系统(ITS)作为协调城市交通的核心正快速发展,而交通流量预测是智能交通系统的重要组成部分,被视为成功部署ITS的关键因素.由于交通网络的复杂空间拓扑结构,使交通流量表现出高阶非线性及动态时空复杂性.为更好地对交通网格数据进行预测,文章提出了一种新的时空网络模型DCSTGCN,具备以下特点:1)将切比雪夫多项式(Ch)应用于图卷积神经网络,结合自扩散卷积将传统的固定式交通拓扑结构进行转换,使其更具有随机性、动态性;2)加入空间Transformer模型,在考虑数据异质性问题的同时,利用多头自注意力机制考虑节点、本地邻居节点以及非本地节点的多属性问题,从高维的子空间进行考虑节点之间的隐藏特征信息;3)将时间Transformer与1×1的二维卷积神经网络(Conv2d)相结合,对交通流时间序列信息进行多重权重分配获取重要的时间特征,利用Conv2d网络进行预测输出.通过试验验证,表明该方法模型优于多种对比基线模型.     

计重收费车辆过秤不规范行为统计分析与对策

高速公路由车型收费转变为计重收费,客观上消除了货车运输超载逐利的原动力.伴随计重收费工作的进行,跳秤、连轴加装千斤顶偷逃通行费的违法行为成为高速公路货车运输的顽疾.结合山西省货车运输的实际情况,对计重收费过程中车辆的不规范过秤行为进行统计分析研究,提出了矫正方案并进行了应用实践,现场有效地遏止了这些偷逃通行费的现象.     

高速公路交通事件影响范围的模糊预测

高速公路交通事件的影响范围预测主要包括两个方面:排队长度预测和延误预测.在对排队长度和延误进行实时预测时,需精确预测出事件发生期间的交通流量和通行能力、事件持续时间及车辆到达事件点的时间等参数,而事实上,用于确定这些参数的信息是非常复杂的,得到的这些参数值是模糊的,但是其变化范围是可以精确确定的.充分考虑上述参数的模糊特性,及事件发生期间的交通流量和通行能力的模糊关系,运用α截集表示了车辆到达离去曲线,建立了交通事件排队长度模糊预测模型和延误模糊预测模型.利用2001年6月16日发生在美国210-E高速公路的交通事件验证了该模型的可行性,并分析了事件发生期间交通流量和通行能力及事件持续时间的模糊度变化对排队长度和延误预测结果的影响.     

一个综合QFD技术的概念阶段装备成本估算方法

提出了一种基于性能特点和质量功能展开(QFD)技术的装备成本估算方法,可用于概念设计阶段进行准确的费用估算.应用QFD技术分析得出费用估算所需信息,并利用最小二乘法得出装备成本估算所需费用因子后结合预研装备的的性能值可计算出装备成本.最后通过实例对该方法进行了演示,并给出在不同预算下装备研制成功的概率.     

耦合AF-SVR的短时交通流量预测模型

交通流量预测是城市智能交通系统的重要研究内容之一,是缓解城市拥堵、实现智能交通管理和建设智慧城市的前提,基于短时交通流量的复杂性及非线性等特点,提出耦合AF-SVR的短时交通流量预测模型.模型结合了鱼群算法较好的并行搜索性能和支持向量回归机较好的非线性拟合能力,利用该模型对短时交通流量数据进行仿真实验,结果表明:模型较BP神经网络预测模型具有较高的预测精度,是短时交通流预测的一种有效方法.     

高速公路收费广场的结构设计和管理优化

2017年美国大学生数学建模竞赛B题"Merge After Toll"讨论高速公路收费广场的形状和通行管理方式的优化问题。本文在参考了部分获奖论文基本方法的基础上,对这一问题作了进一步分析,讨论了汇车变道对收费区大小、车流量和安全性的影响,导出了优化收费广场的几个量化指标,并在此基础上分析了收费区设计长度的确定和车流的优化管理方案,给出了相应的仿真计算结果。     

主路多车道无信号交叉口混合交通流的通行能力

Highway capacity is defined as maximum volume of traffic flow through the particular highway section under given traffic conditions,road conditions and so on.Highway construction and management is judged by capacity standard.The reasonable scale and time of highway construction,rational network structure and optimal management mode of highway network can be determined by analyzing the fitness between capacity and traffic volume.All over the world,highway capacity is studied to different extent in different country. Based on the gap acceptance theory,the mixed traffic flow composed of two representative vehicle types heavy and light vehicles is analyzed with probability theory.Capacity model of the minor mixed traffic flows crossing m major lanes,on which the traffic flows fix in with M3 distributed headway,on the unsignalized intersection is set up,and it is an extension of minor lane capacity theory for one vehicle-type and one major-lane traffic flow.     

A dynamical systems approach based on averaging to model the macroscopic flow of freeway traffic

The flow of traffic exhibits distinct characteristics under different conditions, reflecting the congestion during peak hours and relatively free motion during off-peak hours. This requires one to use different mathematical equations to describe the diverse traffic characteristics. Thus, the flow of traffic is best described by a hybrid system, namely different governing equations for the different regimes of response, and it is such a hybrid approach that is investigated in this paper. Existing models for the flow of traffic treat traffic as a continuum or employ techniques similar to those used in the kinetic theory of gases, neither of these approaches gainfully exploit the hybrid nature of the problem. Spurious two-way propagation of disturbances that are physically unacceptable are predicted by continuum models for the flow of traffic. The number of vehicles in a typical section of the highway does not justify its being modeled as a continuum. It is also important to recognize that the basic premises of kinetic theory are not appropriate for the flow of traffic (see [S. Darbha, K.R. Rajagopal, Limit of a collection of dynamical systems: an application to modeling the flow of traffic, Mathematical Models and Methods in Applied Sciences 12 (10) (2002) 1381–1399] for a rationale for the same). A model for the flow of traffic that does not treat traffic as a continuum or use notions from kinetic theory is developed here and corroborated with real-time data collected on US 183 in Austin, Texas. Predictions based on the hybrid system model seem to agree reasonably well with the data collected on US 183.     

基于双层规划的高速公路收费费率优化模型

在全国联网收费的背景下,从动态收费的角度考虑,建立了双层规划模型,上层规划中将路网管理者作为领导者,以高速公路收费效益最大化为目标函数,同时考虑道路运营管理方的合理收益和养护成本支出情况,下层规划则以用户出行效用最大化为目标,充分考虑了道路使用者的道路选择差异性及道路拥堵对交通分布的影响,建立随机用户均衡模型.最后结合...     

An analysis of the traffic on highways with changing surface conditions

In this paper we present an application of the theory of traffic flow formulated by Lighthill and Whitham to problems where a section of a road imposes different conditions on the flow of cars. To represent these situations mathematically, we use a different flow-density relationship which contains implicitly the changes in the properties of this special section of road.With this approach we analyze first some simplified problems of this type, the solutions of which are of use in more complicated problems. Also, we obtain the corresponding steady-state solutions and discuss their stability. Finally, to illustrate these ideas on more realistic situations, we obtain the solutions of the flow produced by heavy rain on a section of a highway and by the slowing down of a convoy of trucks moving on one lane of a three-lane highway.     

带时空相关性分析的行车时间估计模型

基于流体动力学方程的行车时间估计模型不能很好地反映真实的行车时间,需要对其进行一定的改进.在对交通流进行流体动力学建模的基础之上,引入对高速公路路网中不同路段之间的行车时间相关性和同一路段不同季节、不同时段的行车时间相关性分析,建立了带时空相关性分析的时间估计模型,使用统计学的方法消除动力学模型的误差.     

Highway toll pricing

For a tolled highway where consecutive segments allow vehicles to enter and exit unrestrictedly, we propose a simple toll pricing method. It is shown that the method is the unique method satisfying the classical axioms of Additivity and Dummy in the cost sharing literature, and the axioms of Toll Upper Bound for Local Traffic and Routing-proofness. We also show that the toll pricing method is the only method satisfying Routing-proofness Axiom and Cost Recovery Axiom. The main axiom in the characterizations is Routing-proofness which says that no vehicle can reduce its toll charges by exiting and re-entering intermediately. In the special case when there is only one unit of traffic (vehicle) for each (feasible) pair of entrance and exit, we show that our toll pricing method is the Shapley value of an associated game to the problem. In the case when there is one unit of traffic entering at each entrance but they all exit at the last exit, our toll pricing method coincides with the well-known airport landing fee solution-the Sequential Equal Contribution rule of Littlechild and Owen (1973).     

Pavement rehabilitation scheduling and toll pricing under different regulatory regimes

This paper addresses the highway pavement rehabilitation scheduling and toll pricing issues over a planning horizon. In the highway system concerned, two types of agents are considered, namely highway operator and road users. Two models, which account for different highway regulatory regimes (i.e. public and private), are proposed. In the public regulatory model, the government aims to maximize total discounted social welfare of the transportation system over the planning horizon by determining the optimal pavement rehabilitation schedule and toll level. In the private regulatory regime, a profit-driven private operator seeks to optimize the pavement rehabilitation schedule and toll level to maximize its own discounted net profit over the planning horizon. The proposed models treat the interactions between the highway operator and the road users in the system as a bi-level hierarchical problem in which the upper level is a multi-period pavement rehabilitation scheduling and toll pricing problem, while the lower level is a multi-period route choice equilibrium problem. A heuristic solution algorithm that combines a greedy approach and a sensitivity analysis based approach is developed to solve the proposed bi-level multi-period optimization models. An illustrative example is used to show the applications of the proposed models. The findings show that the highway regulatory regime, pavement deterioration parameter and the roughness-induced vehicle operating cost can significantly affect the pavement rehabilitation schedules and the toll level as well as the performance of transportation system in terms of total life-cycle travel demand, net profit and social welfare.     

Balanced vehicular traffic at a bottleneck

The balanced vehicular traffic model is a macroscopic model for vehicular traffic flow. We use this model to study the traffic dynamics at highway bottlenecks either caused by the restriction of the number of lanes or by on-ramps or off-ramps. The coupling conditions for the Riemann problem of the system are applied in order to treat the interface between different road sections consistently. Our numerical simulations show the appearance of synchronized flow at highway bottlenecks.     

路段加油站布局模型

加油站选址和布局是加油站运营的关键因素.本文证明了车辆在L路段上的加油量等于L路段上的成品油消耗量,以此为基础构造了路段加油站布局模型,通过实测某国道某路段的实际通过车流量,展示了模型的具体应用.