基于自然驾驶数据的电动公交踏板误操作辨识方法  

Identification method for electric bus pedal misoperation based on natural driving data

作　　者：袁伟[1] 袁小慧[1,2] 高岩 李坤宸 赵登峰 刘朝辉[4] YUAN Wei;YUAN Xiao-hui;GAO Yan;LI Kun-chen;ZHAO Deng-feng;LIU Zhao-hui(School of Automobile,Chang'an University,Xi'an 710064,China;School of Vehicle Engineering,Xi'an Aeronautical Institute,Xi'an 710077,China;Key Laboratory of Ministry of Public Security for Road Traffic Safety,Wuxi 214000,China;Zhengzhou Yutong Bus Company Ltd.,Zhengzhou 450016,China)

机构地区：[1]长安大学汽车学院,西安710064 [2]西安航空学院车辆工程学院,西安710077 [3]道路交通安全公安部重点实验室,江苏无锡214000 [4]郑州宇通客车股份有限公司,郑州450016

出　　处：《吉林大学学报（工学版）》2023年第12期3342-3350,共9页Journal of Jilin University:Engineering and Technology Edition

基　　金：道路交通安全公安部重点实验室开放基金项目(2020ZDSYSKFKT01)。

摘　　要：针对驾驶人误踩踏板引发电动公交失控问题,开展了自然驾驶试验和误踩踏板的模拟驾驶试验,采用One-Class SVM和iForest方法建立了踏板误操作辨识方法。试验结果表明:车速、电机转矩、加速踏板开度和制动踏板开度可作为反映踏板误操作行为的特征参数;OneClass SVM和iForest辨识方法识别准确率分别为94.9%和99.5%,但iForest辨识方法在踏板误操作行为的识别精确率方面具有突出优势。利用iForest辨识方法对电动公交运行数据进行辨识,可为降低误踩踏板相关事故发生提供理论支持。Aiming at the problem of electric bus out of control caused by driver's wrong stepping on the pedal,natural driving test and simulated driving test of wrong stepping on the pedal were carried out.The pedal misoperation identification methods were established based on One-Class SVM and iForest respectively.The verification results show that the four parameters could be used to reflect pedal misoperation behavior,vehicle speed,motor torque,accelerator pedal opening and brake pedal opening.The recognition accuracy of one class SVM and iForest identification methods are 94.9%and 99.5%respectively,but iForest identification method has outstanding advantages in the recognition accuracy of pedal misoperation.The iForest method can be used to identify the running data of electric bus,which can provide theoretical support for reducing the accidents related to abnormal braking.

关 键 词：公路运输 踏板误操作 自然驾驶 纯电动公交 机器学习 

分 类 号：U471.3[机械工程—车辆工程]