基于车辆运行数据的纯电动汽车用户驾驶风格识别与驾驶能耗分析

驾驶风格是用来体现驾驶员在车辆运行状态下对车辆操作的行为特征,对用户驾驶风格进行识别与分析,有利于推进智能驾驶的发展。根据基于116 辆纯电动汽车的车辆运行数据,通过主成分分析方法与K-means 聚类算法,对用户驾驶行为进行分类分析,对驾驶风格进行了分类识别。利用XGBoost 算法构建纯电动汽车驾驶行为与能耗输入模型,利用SHAP 对模型进行解释。结果表明,将驾驶风格聚为3 类具有较好的分类效果,可分别对应冷静型、普通型与激进型;当驾驶员的驾驶风格趋向于激进型时时,车辆的驾驶能耗越高,驾驶风格激进一个层级,车辆百公里电耗增加3~4倍。当驾驶员行车时,其车速越高,油门踏板踩得越深,车辆加速度的绝对值越大,车辆的驾驶能耗越高。驾驶员的驾驶风格越激进,车辆的驾驶能耗越高。

Driving Style Recognition and Driving Energy Consumption Analysis of Pure Electric Vehicle Users Based on Vehicle Operating Data

Driving style is used to reflect the behavior characteristics of the driver??s operation of the vehicle in the running state of the vehicle, and to identify and analyze the user??s driving style, which is conducive to the development of intelligent driving. Based on the vehicle operating data of 116 pure electric vehicles in this paper, the principle component analysis method and the K-means clustering algorithm are used to classify and analyze the user??s driving behavior, and the driving style is classified and identified. The XGBoost algorithm is used to construct a pure electric vehicle driving behavior and energy consumption input model, and SHAP is used to explain the model. The results show that grouping the driving styles into three categories has a better classification effect, and they can correspond to the calm, normal and aggressive types respectively.When the driver??s driving style tends to be more aggressive, the higher the vehicle??s driving energy consumption.For each tier of aggressive driving style, the vehicle??s energy consumption per 100km increases by 3-4 times.