基于复合分布的混合交通时间间隔模型

Time Gap Modeling Using Mixture Distributions under Mixed Traffic Conditions

非复合分布模型可用于分析交通流量达1 800 vph的车辆时间间隔,但并不适用于更高交通流量的情况.为解决此类问题,提出了一些基于复合分布的模型.但这类模型的参数标定过程复杂,在一定程度上限制了其应用.针对流量介于1 900 vph到4 100 vph的车辆时间间隔,本文分别采用5种复合分布模型进行分析,即指数-极值分布(EEV)、对数正态-极值分布(LEV)、威布尔-极值分布(WEV)、威布尔-对数正态分布(WLN)和指数-对数正态分布(ELN).然后采用两种方法进行拟合优度检验——基于累计函数分布检验(CDF)和双样本(Cramer-von Mises)&K样本(Anderson-Darling)检验.结果表明,在分析车辆时间间隔方面,威布尔-极值分布(WEV)是最佳的复合分布模型,在Cramer-von Mises检验和K样本Anderson-Darling检验中均具有良好的一致性.

The time-gap data have been modeled through non-composite distribution up to a flow level of 1 800 vph.It has been found that these models are not capable of modeling time gap data at higher flow levels.Some composite distributions have been proposed to overcome this problem.But,due to the fact that the calibration of model parameters used in composite distributions is tedious,there use may be relatively limited.In this paper,five mixture models namely Exponential＋Extreme-value（EEV）,Lognormal＋Extreme-value（LEV）,Weibull ＋Extreme-value（WEV）,Weibull＋Lognormal（WLN） and Exponential＋ Lognormal（ELN） have been used to model time gap data for flows ranging from 1 900 vph to 4 100 vph.Two types of goodness-of-fit tests namely cumulative distribution function（CDF） based and two-sample（Cramer-von Mises test） K-sample（Anderson-Darling test） based tests were performed.Among all the five models,Weibull＋ Extreme Value was found to be the best mixture model for modeling time gap data as it performed consistently well in Cramer-von Mises test and K-sample Anderson-Darling test.