城市公交线网优化的线性模型

为了对现有公交线网进行优化,有效利用现有交通资源,解决城市交通问题,运用系统科学的思想,通过对城市公交线网优化的主要内容、优化原则、优化目标以及约束条件的分析,兼顾考虑乘客出行时间、公交线网密度和公交企业的利益以及公交线网的布局对整个城市的交通系统的影响,提出了优化目标的函数表达式及相应约束条件的数学表达式,建立了公交线网优化的线性模型,并给出了运用逐步筛选法对所提出的数学模型进行求解的方法。     

汽车防追尾碰撞数学模型研究

为了提高车辆在高速行驶状态下的主动安全性能,研究了处于追尾行驶状态的本车与前车的运动学特征;针对前车的不同运动状态分别推导出了跟车距离的计算模型并分析了模型中3个关键参数的随机性和动态性,对制动迟滞时间提出了基于模糊推理的确定方法,对本车制动减速度和前车的运动加速度提出了比较实用的动态测算公式;另外,研究了防追尾碰撞的控制与执行,建立了动态调整安全制动停车距离的神经网络模型,提出了基于危险裕度判别的安全控制方法。     

基于模糊神经网络的既有钢筋混凝土桥梁构件可靠性评估

介绍了模糊神经网络的基本理论知识,根据其知识体系和既有桥梁可靠性的研究特点,结合相关文献的规定和研究成果,引入与所检测的截面裂缝宽度、应变值和应变值相关的评估参数Z,利用既有钢筋混凝土桥梁养护等级标准给出了构件技术状况等级与可靠指标的对应关系,然后根据模糊神经网络的理论优势,对输入变量(实测数据:裂缝宽度,应变值和应变值)进行训练,计算出构件在不同荷载作用下的可靠指标,其可用于既有桥梁结构构件可靠性评估中。并结合一实桥拆除构件的试验结果,得到了一些有益的结论,验证了本方法应用于既有钢筋混凝土桥梁构件可靠性评估的可行性。     

基于实测数据评估交通事件检测中神经网络应用性的研究

神经网络为交通事件自动检测技术摆脱传统方法探测率低、误报率高的状况提供了新的解决思路。在以往局限于仿真数据研究的基础上,本文利用I-880数据库实测交通事件数据对神经网络在交通事件自动检测中的实际应用进行了研究,结果表明:神经网络应用于交通事件自动检测技术中,具有较高的探测率和较低的误报率,但该算法可移植性较差,在实际应用中要予以考虑。     

基于GERT网络的应急救援关键路段识别

为了及时识别出突发事件下城市道路的关键路段,以构建最短应急救援路径,本文提出了一套完整流程.首先,针对路网在应急条件下的贫信息环境特征,设计一种基于模糊综合评判的行程时间估算方法.然后,考虑救援人员的应急心理和经验选择行为,构建面向广义阻抗的GERT(Graph Evaluation and Review Technique)网络模型.最后,运用Dijkstra算法获得救援路径完成关键路段识别.以成都市某区域实际交通网络为算例进行验证,结果表明:基于2种模糊算子估算路段行程速度,其绝对误差为2.722 km/h,精度较高;与传统关键路段识别方法相比,GERT网络模型能更好地反映行程时间和路段拥挤度对路径选择行为的影响(拟合度80.95%),并将重要度识别技术从路网降低到路径层面,效果良好.     

浅谈FAS双中心建设及设备维护

重点分析了西安局集团公司由2K数调主系统组网更新改造为FAS双中心网络的建设方法,并根据日常维护经验,列举了调度台通道故障处理、FASB简易故障判断及计表倒换试验、FASA和FASB系统与MSC之间的业务故障处理等.     

基于灰色—小波神经网络的有效泊位预测

针对停车场有效停车泊位的变化特征,提出了基于灰色—小波神经网络的组合模型.先通过灰色单因素预测模型对有效停车泊位时间序列进行修正处理,再基于分步式小波神经网络模型对修正预测值进行运算,并通过马克科夫链预测模型得到更精确的预测区间,并利用实际案例分析,对模型的预测精度、稳定性、拟合度和训练时间进行了评价.研究表明,灰色—小波神经网络预测模型可降低初始数据波动性的干扰,与传统神经网络相比,预测结果误差波动性降低了10%~19%,稳定性提高了27%~33%,拟合度提高了10%~15%,精确度明显提高.     

Large-scale evacuation network optimization: a bi-level control method with uncertain arterial demand

To improve the efficiency of large-scale evacuations, a network aggregation method and a bi-level optimization control method are proposed in this paper. The network aggregation method indicates the uncertain evacuation demand on the arterial sub-network and balances accuracy and efficiency by refining local road sub-networks. The bi-level optimization control method is developed to reconfigure the aggregated network from both supply and demand sides with contraflow and conflict elimination. The main purpose of this control method is to make the arterial sub-network to be served without congestion and interruption. Then, a corresponding bi-objective network flow model is presented in a static manner for an oversaturated network, and a Genetic Algorithm-based solution method is used to solve the evacuation problem. The numerical results from optimizing a city-scale evacuation network for a super typhoon justify the validity and usefulness of the network aggregation and optimization control methods.     

Predicting the adoption of connected autonomous vehicles: A new approach based on the theory of diffusion of innovations

On the grounds that individuals heavily rely on the information that they receive from their peers when evaluating adoption of a radical innovation, this paper proposes a new approach to forecast long-term adoption of connected autonomous vehicles (CAVs). The concept of resistance is employed to explain why individuals typically tend to defer the adoption of an innovation. We assume that there exists a social network among individuals through which they communicate based on certain frequencies. In addition, individuals can be subject to media advertisement based on certain frequencies. An individual’s perceptions are dynamic and change over time as the individual is exposed to advertisement and communicates with satisfied and dissatisfied adopters. We also explicitly allow willingness-to-pay (WTP) to change as a result of peer-to-peer communication. An individual decides to adopt when (i) there is a need for a new vehicles; (ii) his/her WTP is greater than CAV price; and (iii) his/her overall impression about CAVs reaches a cutoff value. Applicability of the proposed approach is shown using a survey of employees of the University of Memphis. Our results show that the automobile fleet will be near homogenous in about 2050 only if CAV prices decrease at an annual rate of 15% or 20%. We find that a 6-month pre-introduction marketing campaign may have no significant impact on adoption trend. Marketing is shown to ignite CAV diffusion but its effect is capped. CAV market share will be close to 100% only if all adopters are satisfied with their purchases; therefore, the probability that an individual becomes a satisfied adopter plays an important role in the trend of adoption. The effect of the latter probability is more pronounced as time goes by and is also more prominent when CAV price reduces at greater rates. Some caveats may be inserted when considering the study results as the findings are subject to sample bias and data limitations.     

Spatiotemporal traffic forecasting: review and proposed directions

This paper systematically reviews studies that forecast short-term traffic conditions using spatial dependence between links. We extract and synthesise 130 research papers, considering two perspectives: (1) methodological framework and (2) methods for capturing spatial information. Spatial information boosts the accuracy of prediction, particularly in congested traffic regimes and for longer horizons. Machine learning methods, which have attracted more attention in recent years, outperform the naïve statistical methods such as historical average and exponential smoothing. However, there is no guarantee of superiority when machine learning methods are compared with advanced statistical methods such as spatiotemporal autoregressive integrated moving average. As for the spatial dependency detection, a large gulf exists between the realistic spatial dependence of traffic links on a real network and the studied networks as follows: (1) studies capture spatial dependency of either adjacent or distant upstream and downstream links with the study link, (2) the spatially relevant links are selected either by prejudgment or by correlation-coefficient analysis, and (3) studies develop forecasting methods in a corridor test sample, where all links are connected sequentially together, assume a similarity between the behaviour of both parallel and adjacent links, and overlook the competitive nature of traffic links.