基于对数正态和分布的路径行程时间可靠性模型

Route Travel Time Reliability Model Based on Lognormal Sum Distribution

建立合理的路径行程时间可靠性评价模型，对于准确评价路网运行状态具有重要意义．根据对数正态随机变量之和的概率分布特性，建立了路径的行程时间可靠性评价模型．首先，通过曲线拟合，建立了路段行程时间的概率分布模型，结果表明对数正态分布的拟合效果最佳；其次，利用统计学理论，分别考虑路段相关和路段独立两种情况，建立了基于对数正态和分布的路径行程时间可靠性评价模型；在此基础上，对北京市西三环路径进行了实例分析，以检验模型的准确性．研究结果表明：模型能够准确的评价路径的行程时间可靠性；且路段之间存在弱相关关系，最合理的路段相关系数取值为0．2～0．3．

Establishing a feasible and practical route travel time reliability evaluation model is very important for accurately assessing the road network performance and providing the comprehensive traveler information. A route travel time reliability model is developed based on the probability distribution characteristics of a sum on lognormal random variables. First, the link travel time distribution model is developed resulting in that a lognormal distribution shows the best fitting performance. Second, the lognormal sum distribution-based route travel time reliability model is developed by utilizing the statistical theory and considering both scenarios of correlated versus independent links. Finally, the proposed model is validated by using the West Third-Ring road of Beijing in the case study. The results provide that the developed model can accurately evaluate the route travel time reliability, and that there is a faint correlative relationship between links, in which the best feasible correlation coefficient of links is in the range of 0.2 and0. 3.