基于ETC门架数据的高速公路车辆行驶特征画像方法

Method for Portraying Driving Characteristics of Expressway Vehicles Based on ETC Gantry Data

为合理评估高速公路车辆驾驶行为风险和通行费稽查状态异常程度,进而对风险车辆进行提前预警,提出了一种基于ETC门架数据的车辆行驶特征画像方法。首先,通过分析车辆风险驾驶行为和通行费稽查状态,构建了以超速驾驶行为、疲劳驾驶行为、门架状态异常情况、收费状态异常情况、路径状态异常情况为指标的车辆行驶特征画像指标体系;然后,利用熵权-TOPSIS法和熵权-灰色关联分析建立综合熵权法确定各指标权重;最后,选取8辆车作为实验对象生成车辆行驶特征雷达图来验证该方法的有效性。研究结果表明:在4辆1类客车中,有3辆存在超速驾驶行为,其超速驾驶指数趋于0.8,其余的行驶特征指数均趋于0;在4辆6类货车中,有2辆在疲劳驾驶指数上表现异常,其疲劳驾驶指数趋于0.4,还有1辆的收费状态异常指数趋于0.4,可能存在偷逃费风险。可以看出,该方法能有效区分不同车型的风险类型,在高速公路管理中可用于有针对性的风险决策制定。

In order to reasonably evaluate the risk of driving behavior and the degree of abnormal toll inspection status of vehicles on expressway and to warn the risk vehicles in advance,a method for constructing vehicle driving characteristic portraits based on ETC gantry data was proposed.Firstly,by analyzing the risky driving behavior and the toll inspection status of vehicles,a vehicle driving characteristic portrait index system was constructed with indicators including overspeed driving behavior,fatigue driving behavior,abnormal gantry state,abnormal toll state and abnormal path state.Then,a comprehensive entropy weight method was established by using entropy weight-TOPSIS method and entropy weight-grey correlation analysis to determine the weight of each index.Finally,eight vehicles were selected as the experimental objects to generate radar maps of vehicle driving characteristics to verify the effectiveness of the method.The results showed that three out of four Type 1 buses exhibited overspeed driving behavior,with their overspeed driving index tending towards 0.8,while other driving characteristic indices all tended to 0.Among the four Type 6 trucks,two showed abnormal performance on the fatigue driving index,with the fatigue driving index tending towards 0.4,and one had abnormal toll status index tending towards 0.4,indicating a possible risk of fee evasion.It can be seen that this method can effectively distinguish the risk types of different vehicle models and help expressway managers to make targeted risk decisions.