利用五轮仪实验数据建立车辆跟驰模型  

A Car-following Model Developed on Five-wheel System Experiment

作　　者：赵淑芝[1] 张枭雄[1] 贾洪飞[1] 韩左慈[2] 

机构地区：[1]吉林大学交通学院,吉林长春130025 [2]吉林省运输管理局,吉林长春130017

出　　处：《公路交通科技》2003年第1期132-135,共4页Journal of Highway and Transportation Research and Development

摘　　要：车辆跟驰模型是微观交通流模拟的一个基本模型 ,用来分析和描述在无法超车的同一车道上一辆车 (驾驶员 )跟随另一辆车的方式。由于实际道路上驾驶员信息的获取困难 ,建立的车辆跟驰模型难以标定或验证。本文利用五轮仪试验系统获取的车辆跟驰数据 ,应用BP神经网络 。Car-following model is a basic model in t raffic microscopic simulation, used to analyze and describe the way one vehicle (driver) follows another in a single lane of traffic. Because of the difficult on collection of open road information, car-following models couldn't not be calibrated or validated easily. A car-following decision support model is developed in this paper using an error Back-Propagation neural network based on five-wheel system experiment.

关 键 词：五轮仪 车辆跟驰模型 车辆数据采集 数据处理系统 期望速度 神经网络 

分 类 号：U491.112[交通运输工程—交通运输规划与管理]