基于分段学习的BP神经网络的交通流量预测

智能交通系统是目前世界上公认的解决城市交通拥堵问题的最佳方案,实时、准确的交通流量预测是智能交通系统实现的关键技术之一。本文采用改进型BP神经网络建立起交通流的时间序列模型,该模型可用于短期内道路交通流量的预测。     

汽车半轴疲劳寿命预测和可靠性设计

本文重点介绍可靠性工程在汽车设计中的应用。具体以汽车半轴为主要研究对象,阐述半轴载荷谱的测定、载荷谱的编制、半轴疲劳寿命的预测与半轴的有限寿命设计等。     

Real-Time Bus Arrival Information System: An Empirical Evaluation

The provision of real-time information concerning bus arrival times could potentially reduce the uncertainty associated with public transport trips and improve the overall level of service. In addition, real-time predictions might enable operators to apply proactive control strategies. Even though considerable research efforts were devoted to the development of bus arrival prediction schemes, there is a lack of knowledge on the performance of real-world operational systems. This article aims to investigate the performance of a commonly deployed real-time information generation scheme. A conventionally used scheme is implemented and evaluated based on an empirical analysis. Performance metrics concerning the prediction error accuracy and reliability and their impact on expected waiting time were formulated from both passengers’ and operators’ perspectives. The real-time information generator was applied on the trunk line network in Stockholm, Sweden. The accuracy and reliability of the prediction scheme was analyzed by comparing the generated predictions against vehicle positioning data. This scheme was found to systematically underestimate the remaining waiting time by 6.2% on average. The provision of real-time information yields a waiting time estimate that is more than twice as close to the actual waiting times than the timetable. This difference in waiting time expectations is equivalent to 30% of the average waiting time.     

轨道客流影响因素及预测要点

影响轨道客流的因素分别是轨道站点周边的土地开发模式、城市客运结构体系、公共交通经营策略：及轨道的网络形态,本文对此进行了论述,并概括了轨道客流预测工作中的几点注意事项。     

Guaranteed prediction and estimation of the state of a road network

The paper presents an algorithm for the prediction and estimation of the state of a road network comprising freeways and arterials, described by a Cell Transmission Model (CTM). CTM divides the network into a collection of links. Each link is characterized by its fundamental diagram, which relates link speed to link density. The state of the network is the vector of link densities. The state is observed through measurements of speed and flow on some links. Demand is specified by the volume of vehicles entering the network at some links, and by split ratios according to which vehicles are routed through the network. There is model uncertainty: the parameters of the fundamental diagram are uncertain. There is uncertainty in the demand around the nominal forecast. Lastly, the measurements are uncertain. The uncertainty in each model parameter, demand, and measurement is specified by an interval. Given measurements over a time interval [0, t] and a horizon τ ? 0, the algorithm computes a set of states with the guarantee that the actual state at time (t + τ) will lie in this set, consistent with the given measurements. In standard terminology the algorithm is a state prediction or an estimate accordingly as τ > 0 or =0. The flow exiting a link may be controlled by an open- or closed-loop controller such as a signal or ramp meter. An open-loop controller does not change the algorithm, indeed it may make the system more predictable by tightening density bounds downstream of the controller. In the feedback case, the value of the control depends on the estimated state bounds, and the algorithm is extended to compute the range of possible closed-loop control values. The algorithm is used in a proposed design of a decision support system for the I-80 integrated corridor.     

城市燃气长期负荷预测模型的灰色方法

提出利用灰色系统理论 ,建立动态等维灰数递补灰色燃气长期负荷预测模型 ,解决了我国城市燃气长期负荷可用历史数据较少 ,序列的完整性及数据资料的可靠性较低 ,规划设计中往往又需要对未来数年后的用气负荷作出预测的问题。实例预测计算表明 :动态等维灰数递补灰色燃气长期负荷预测模型和方法对城市燃气长期用气负荷的预测具有较好的适应性和较高的精度。     

基于神经网络的水下机器人运动预测控制方法

将神经网络和模糊理论应用于水下机器人运动规划和控制中,提出了能实现模拟控制规则的基于强化学习的自学习和自调整的规划算法,设计了水下机器人实时运动规划器结构以及规划器操作过程,提出了基于预测模糊控制进行水下机器人运动控制的方法。在计算机仿真状态下,实现了对水下机器人这一复杂非线性系统的预测控制,仿真实验结果验证了本文所提的方法的有效性。     

UniTire轮胎稳态模型的联合工况预测能力研究

通过少量的标准试验得到轮胎力学特性参数,可以预测联合工况下(纵滑、侧偏、侧倾)的力学特性,这样就能避免做大量的复合试验。通过对轮胎简化理论模型的简单介绍,提出满足高阶理论边界条件的统一轮胎模型Un iTire,并对动摩擦因数和总切力方向修正系数给予说明。通过轮胎试验数据,使用不同辨识方法验证其预测能力,证明Un iTire轮胎稳态模型具有很高的预测精度。     

京张高铁八达岭隧道下穿长城爆破振动影响的预测与分析

京张高铁八达岭隧道两次下穿世界文化遗产八达岭长城,隧道拟采用钻爆法开挖。为避免长城在爆破振动下发生破坏,在八达岭隧道大跨过渡段布置微振检测系统,用以验证爆破控制技术的效果。同时,收集和整理实测数据,按萨道夫斯基公式及Ricker公式进行回归分析,确定爆破振动的相关参数,从而得出适合八达岭长城地区地质条件的质点峰值速度和拐角频率的预测公式。误差分析验证了预测公式具有较好的适用性,可以为隧道下一步穿越长城核心区爆破参数的确定和安全性控制提供理论依据。     

高铁盐渍土地区溶陷特性的预测模型及因素敏感性分析

近年来,高速铁路在西北地区建设中遇到大量的盐渍土路基,而盐渍土路基很容易发生溶陷变形,这对高速铁路的平顺性有着极为不利的影响。结合兰新铁路第二双线的盐渍土溶陷病害实例,使用改进的普通固结仪开展单因素溶陷试验,以其试验结果为基础,通过正交设计方法开展多因素交互作用下的盐渍土溶陷试验;采用SPSS软件对试验结果开展逐步回归分析,并根据分析结果中方差大小,消除不显著因素,建立溶陷系数简化预测模型,并对所得预测模型进行验证,确定影响氯盐渍土溶陷预变形的因素敏感性。研究结果表明:影响盐渍土的溶陷系数的敏感性因素由高到低排序依次为压实度,轴向压力,含盐量以及轴向压力与压实度的相互作用,影响所占比例分别为0.463,0.172,0.140,0.092。