Confidence interval estimation for path flow estimator

The uncertainty of an origin-destination (O-D) trip table estimate is affected by two factors: (i) the multiplicity of solutions due to the underspecified nature of the problem, and (ii) the errors of traffic counts. In this paper, a confidence interval estimation procedure for path flow estimator (PFE) is developed for assessing the quality of O-D trip tables estimated from traffic counts. The confidence interval estimation consists of two parts: (i) a generalized demand scale (GDS) measure for quantifying the intrinsic underspecified nature of the O-D estimation problem at various spatial levels, and (ii) an error bound to quantify the contribution of input errors (traffic counts) to the estimation results. Numerical results using PFE as the O-D estimator show that the proposed confidence interval estimation procedure is able to separate the two sources of uncertainty in constructing the confidence intervals at various spatial levels. Simulation results also confirm that the proposed quality measure indeed contain the true estimates within the defined confidence intervals.     

A genetic algorithm-based method for improving quality of travel time prediction intervals

The transportation literature is rich in the application of neural networks for travel time prediction. The uncertainty prevailing in operation of transportation systems, however, highly degrades prediction performance of neural networks. Prediction intervals for neural network outcomes can properly represent the uncertainty associated with the predictions. This paper studies an application of the delta technique for the construction of prediction intervals for bus and freeway travel times. The quality of these intervals strongly depends on the neural network structure and a training hyperparameter. A genetic algorithm–based method is developed that automates the neural network model selection and adjustment of the hyperparameter. Model selection and parameter adjustment is carried out through minimization of a prediction interval-based cost function, which depends on the width and coverage probability of constructed prediction intervals. Experiments conducted using the bus and freeway travel time datasets demonstrate the suitability of the proposed method for improving the quality of constructed prediction intervals in terms of their length and coverage probability.     

铁路客运枢纽车道边落客长度指标研究

目前，我国较多铁路车站旅客落客平台均出现常态化拥堵问题，分析发现，造成落客平台拥堵的主要原因是车道边落客长度规模不合理。对车均落客长度这一影响规模计算的关键性指标进行实验研究。通过96组对照实验模拟落客行为，定义驶入长度、停车区长度、驶出长度、驶入角及驶出角5个特征指标并进行轨迹分析，明确了驶入速度、车辆尺寸及驾龄等因素对指标值的影响程度，并给出了指标的建议区间值9.5～12.5 m。在空间紧张的情况下，建议区间值可进一步缩小为8～10 m。     

城市地下道路排水驼峰设置研究

近年来，极端天气频发，城市内涝频繁出现，为防止周边地面雨水等汇入倒灌地下道路造成损失，城市地下道路的排水驼峰设置越来越受瞩目。本文合地下道路建设经验，分析排水驼峰的设计要点，总结设置排水驼峰后与周边衔接细节，同时若因纵断面布置限制，驼峰高程难以达到要求时，提出地下通道排水应考虑的其他措施，以便最大限度的发挥地下道路的功能。     

综合管廊与轨道交通协同设计优化

以北京地铁3号线(一期)综合管廊为例,探讨轨道交通与综合管廊协同设计的优势与问题。首先按照集约适度的设计理念,通过合理调整舱室布局、优化管线安装检修空间和检修通道的方式进行优化标准断面设计;然后通过对综合管廊通风间距及逃生口的创新设计,减少通风井及地面逃生口数量;最后利用施工竖井整合通风口、吊装口、逃生口、出入口等地面构筑物,减少对城市景观的影响。研究表明：通过优化舱室布局、管线安装及检修空间,管廊断面面积得到有效缩减;通过对通风间距、逃生口的设计优化以及对地面构筑物的整合,减少了对城市景观的不利影响,为综合管廊与轨道交通协同设计提供参考。