数据驱动跟驰模型综述

车辆跟驰模型是被交通科学与交通工程领域广泛认可的微观交通流模型,是交通流理论 的基础。近年来,信息感知与获取、大数据、人工智能等技术快速发展,推动了数据驱动跟驰模型 的快速发展。数据驱动跟驰模型,是以真实的车辆行驶数据为基础,利用数据科学与机器学习等 理论和方法,通过样本数据的训练、学习、迭代、进化,挖掘车辆跟驰行为的内在规律。本文系统 回顾了数据驱动跟驰模型在过去20余年的发展历程以及由神经网络和深度学习带动的两次研究 热潮,归纳了基于传统机器学习理论的跟驰模型、基于深度学习的跟驰模型、模型与数据混合驱 动的跟驰模型3类数据驱动跟驰模型,并分别介绍了其中的典型代表。分析数据源发现,尽管各 种高精度轨迹数据不断涌现,目前研究仍多使用美国于2006年发布的Next Generation Simulation (NGSIM)高精度车辆轨迹数据,模型的可移植性和泛化能力值得思考与研究。提出关于模型输 入、输出的3个问题：如何考虑更多驾驶行为变量,是否有必要考虑更多行为变量,现有输入、输出 是否可替换。在模型测试与验证方面,发现并讨论了目前测试不充分、对比不完整、缺少统一测 试集与测试标准等问题。最后,探讨了数据驱动跟驰模型原创性与成功的关键因素等问题。期 望通过本文的梳理,帮助研究者更好地了解数据驱动跟驰模型的过去与现状,促进相关研究的快 速发展。     

Efficient missing data imputing for traffic flow by considering temporal and spatial dependence

The missing data problem remains as a difficulty in a diverse variety of transportation applications, e.g. traffic flow prediction and traffic pattern recognition. To solve this problem, numerous algorithms had been proposed in the last decade to impute the missed data. However, few existing studies had fully used the traffic flow information of neighboring detecting points to improve imputing performance. In this paper, probabilistic principle component analysis (PPCA) based imputing method, which had been proven to be one of the most effective imputing methods without using temporal or spatial dependence, is extended to utilize the information of multiple points. We systematically examine the potential benefits of multi-point data fusion and study the possible influence of measurement time lags. Tests indicate that the hidden temporal–spatial dependence is nonlinear and could be better retrieved by kernel probabilistic principle component analysis (KPPCA) based method rather than PPCA method. Comparison proves that imputing errors can be notably reduced, if temporal–spatial dependence has been appropriately considered.     

Measuring community reaction to urban transportation impacts using Von Neumann‐Morgenstern utility theory

This paper attempts to measure the impacts of urban transportation system improvements or changes on the community. The community's perceptions of the impacts are represented by its utilities (or disutilities) over various ranges of values of the multiple attributes representing these impacts. The utility technique used in the evaluation is based upon von Neumann‐Morgenstern (vN‐M, 1947) Utility Theory, and is applied using Raiffa's (1970) Fractile Method.

The paper specifically applies the technique to model the perceptions of five subgroups within a community to the impact of a new light rail transit system that is being incorporated in the transportation system of the City of Calgary.

Results of the modeling indicate explicitly how the community changes its perception over ranges of values of the attributes evaluated. Biases of various subgroups within the community over these attributes are also shown. Statistical tests indicate that aggregated utility perceptions can represent the utility perceptions of the individual subgroups quite reasonably.     

Path flow estimator for planning applications in small communities

This paper presents an alternative planning framework to model and forecast network traffic for planning applications in small communities, where limited resources debilitate the development and applications of the conventional four-step travel demand forecasting model. The core idea is to use the Path Flow Estimator (PFE) to estimate current and forecast future traffic demand while taking into account of various field and planning data as modeling constraints. Specifically, two versions of PFE are developed: a base year PFE for estimating the current network traffic conditions using field data and planning data, if available, and a future year PFE for predicting future network traffic conditions using forecast planning data and the estimated base year origin–destination trip table as constraints. In the absence of travel survey data, the proposed method uses similar data (traffic counts and land use data) as a four-step model for model development and calibration. Since the Institute of Transportation Engineers (ITE) trip generation rates and Highway Capacity Manual (HCM) are both utilized in the modeling process, the analysis scope and results are consistent with those of common traffic impact studies and other short-range, localized transportation improvement programs. Solution algorithms are also developed to solve the two PFE models and integrated into a GIS-based software called Visual PFE. For proof of concept, two case studies in northern California are performed to demonstrate how the tool can be used in practice. The first case study is a small community of St. Helena, where the city’s planning department has neither an existing travel demand model nor the budget for developing a full four-step model. The second case study is in the city of Eureka, where there is a four-step model developed for the Humboldt County that can be used for comparison. The results show that the proposed approach is applicable for small communities with limited resources.     

Evaluating the effects of bus design on passenger flow: Is agent-based simulation a feasible approach?

In this paper, we propose an agent-based simulation approach that is capable of simulating the flow of passengers on board buses and at bus stops. The intention is that it will be applied during vehicle development to analyze how vehicle design affects passenger flow, and thus also how it affects system performance such as dwell time. In turn, this could aid the developers in making design decisions early in the development process. Besides introducing the simulation tool itself, the paper explores the realism of the data generated by the tool. A number of passenger flow experiments featuring a full-scale bus mockup and 50 participants were carried out. The setup of these experiments mirrored a number of ‘bus journeys’ (regarding vehicle design, number of passengers boarding/alighting at each stop and so on) that had previously been simulated using the simulation tool. When the data from the simulations were compared with the data from the passenger flow experiments, it could be concluded that the tool is indeed able to generate realistic passenger flows, although with some errors when a large number of passengers board/alight. The simulated dwell times were rationally affected by the tested bus layout aspects. It was concluded that the tool makes it possible to evaluate how variations in bus layouts affect passenger flow, providing data of sufficiently high quality to be useful in early phases of vehicle design.     

A theoretical foundation for the relationship between generalized origin–destination matrix and flow matrix based on ordinal graph trajectories

This paper shows the relationship between flow, generalized origin–destination (OD), and alternative route flow from a set of ordinal graph trajectories. In contrast to traffic assignment methods that employ OD matrix to produce flow matrix, we use ordinal trajectory on a network graph as input and produce both the generalized OD matrix and the flow matrix, with the alternative and substitute route flow matrices as additional outputs. By using linear algebra‐like operations on matrix sets, the relationship between network utilization (in terms of flow, generalized OD, alternative route flow, and desire line) and network structure (in terms of distance matrix and adjacency matrix) are derived. Copyright © 2012 John Wiley & Sons, Ltd.     

形成零件组和建立成组生产单元的“生产流程—分类编码”聚类分析法

本文提出了一种利用模糊聚类分析法形成零件组和建立机床组的新方法,实现了生产流程分析法与编码分类法的综合.对于成组加工单元,本文把设备负荷与零件相似系数一起作为形成成组加工单元的主要因素,获得了合理的零件组和机床组,并具有良好的柔性和计算性.     

基于约束卡尔曼滤波的短时交通流量组合预测模型

为了克服单一的交通流预测模型性能不稳定的问题, 提出了基于约束卡尔曼滤波的短时交通流量组合预测模型。约束卡尔曼滤波组合预测模型以各单一预测模型的权重为状态变量, 交通流量为观测变量, 预测结果是单一预测模型的加权和, 加权系数由约束卡尔曼滤波方程递推动态确定, 最后通过广深高速公路上采集的交通流量数据对算法进行了验证。结果表明, 在不同预测步长情况下, 约束卡尔曼滤波组合预测模型要优于最佳的单一预测模型或与其持平, 并且不受某一较差的预测模型影响, 具有较高的鲁棒性。     

龙耀路越江隧道通风模拟研究

该文简要介绍了龙耀路隧道通风系统,运用SES软件模拟分析正常及阻滞工况下隧道通风气流以及火灾工况下的纵向烟气风速,可供类似工程参考。     

水力数值模型在合流污水一期系统中的运用与研究

该文根据水文学、水力学和计算机模拟技术的发展,通过计算机水力模型技术,对上海合流一期排水系统运行进行模拟,提出系统内相关泵站的运行优化方案。然后经过现场实际检验,获得了合理的控制方式,使整个系统更高效、更稳定地运行。