高速圆舭艇浅水阻力计算方法

本文给出了根据船模系列浅水试验结果回归而得的高速圆舭艇浅水阻力计算公式．对亚临界速度区和超临界速度区分别采用不同的公式修正浅水对阻力的影响．文中给出了区分上述速度区域的临界速度计算公式，适用于Fr＜0．8的高速圆舭艇．为检验本文公式的计算精度，用两艘实艇浅水试验结果进行核核．结果表明，公式的精度足以满足工程使用要求．     

馈能式磁流变减振器自供电特性研究

本文设计了集馈能与减振功能于一体的磁流变减振器,从能量传递的角度出发,分析了馈能式磁流变悬架系统能量流动路径,提出了馈能式磁流变减振器自供电准则。通过建立1/4馈能式悬架系统模型和基于广义回归神经网络的减振器控制器进行仿真分析,以确定所设计的磁流变减振器在不同路面激励下的自供电工作范围。     

Lightweight Occupancy Estimation on Freeways Using Extended Floating Car Data

Advanced traffic management systems rely heavily on technology to perform accurate estimations of the current state of the traffic as well as its short-term evolution. The objectives are improving traffic flow and enhancing road safety. Their success is based on accurate monitoring of two key variables, specifically speed and occupancy. The latter of the two has, to date, received significantly less attention from the scientific community. In this work we present a lightweight method to perform “on-line” occupancy estimation. We first propose three occupancy measurements calculated from data collected by a floating car: vehicle count, percentage of stop time, and headway. We then extend these discrete values to a continuous estimation of occupancy in space and time. The proposed estimators are based on a pairwise linear regression of each of the previously calculated measurements over certain references obtained from other floating cars or magnetic loop detectors. The method has been calibrated and validated under real traffic conditions and data. Despite the ease of implementation, the method is able to reproduce the occupancy values generated by the actual loop detectors, achieving promising results, with estimation errors down to 6.52%, even before multivehicle systems are considered.     

双体船的静水阻力估算

根据Fr＜0．38的9条具有对称片体的双体船的阻力试验资料，探讨了船型对剩余阻力系数CR的影响，应用归纳方法得到CR的峰、谷值及时应的傅汝德数的表达式．所有估算表达式均以参数：相对片体间距k／b、宽度吃水比b／T、棱形系数CP和排水体积长度系数CV的函数形式表示．按本文提出的双体船阻力估算方法所得结果与模型试验的吻合比较满意．     

10CrNi3MoV船用钢屈服强度检验异常结果的界定

应用数理统计方法对10CrNi3MoV船用钢的屈服强度和化学成分的试验数据进行回归分析,获得两者间的回归方程;并结合该钢的检验标准,确定其屈服强度检验结果的异常界限。     

基于乘客满意度的公交车站立乘客面积研究

公交车内站立乘客面积是影响公共交通乘车阶段乘客满意度的关键指标.将使乘客感受由不满意转变为满意的公交车站立乘客面积的临界值定义为临界站立乘客面积.本文旨在提出临界站立乘客面积的建议值.首先,在呼和浩特市开展了客流调查及问卷调查;然后,基于调查所获数据,采用有序 Logistic回归建立了乘客满意度与站立乘客面积的模型;最后,通过对所建模型的图形化分析,提出临界站立乘客面积(即保证乘客满意的最小站立乘客面积)的建议值为 0.25 m2/人.本文研究成果为公共交通乘车阶段的乘客满意度评价、舒适性评价提供量化依据,为公交车额定载客量的核定提供新思路.     

基于支持向量回归机的道路交通事故预测模型研究

针对道路交通事故预测具有随机波动性较大、信息量较少和非线性数据序列预测的特点,引入支持向量回归机（SVR）,建立基于SVR的道路交通事故预测模型。通过实例计算,证明基于SVR的道路交通事故预测模型具备非线性、所需数据资料较少、建模简单和计算快捷等优点,同时与RBF神经网络预测模型相比,该模型的预测精度高、泛化能力强,更适用于道路交通事故预测。     

大城市合理客运交通出行结构研究

通过考察国际大都市公共交通结构的主要特征,总结出大城市合理客运交通结构的发展趋势。基于对10个国际大城市的相关指标回归分析,探讨了大城市合理公交出行结构预测模型;最后,以杭州为例,应用预测模型,在分析杭州客运交通结构与国际知名大都市客运交通结构的差异以及产生差距原因的基础上,确定了杭州市在地铁建成后的合理客运交通结构。     

我国综合交通系统的社会贡献评价研究——以2000-2017年数据为例

本文首先介绍了研究背景,提出研究目的。通过梳理国内外相关文献,提出现有研究尚未涉及综合交通系统社会贡献方面。在解析综合交通社会贡献机理基础上,根据我国2000—2017年社会系统和综合交通数据确定我国社会系统发展指数S和交通系统发展指数T的组成指标,在每种交通方式内采用因子分析法确定各指标权重,结合各指标数值得到S和T数值。应用格兰杰检验法证明T是S的原因,由S关于T的回归函数可得我国综合交通社会贡献评价函数,处理后得到最佳状态数值,发现实际数值与之相比仍有较大提升空间。最后,提出相关政策建议。     

Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural network models to estimate hourly volumes in the Maryland highway network, and proposes a novel approach that combines neural networks with an existing profiling method. On average, the proposed approach yields 24% more accurate estimates than volume profiles, which are currently used by transportation agencies across the US to compute statewide performance measures. The paper also quantifies the value of using vehicle probe data in estimating hourly traffic volumes, which provides important managerial insights to transportation agencies interested in acquiring this type of data. For example, results show that volumes can be estimated with a mean absolute percent error of about 21% at locations where average number of observed probes is between 30 and 47 vehicles/h, which provides a useful guideline for assessing the value of probe vehicle data from different vendors.