Anti-Skid System for Ice-Snow Curve Road Surface Based on Visual Recognition and Vehicle Dynamics

Author:

Pang Chenghui,Zhu Haotian,Lin Zhenmao

Abstract

<div class="section abstract"><div class="htmlview paragraph">Preventing skidding is essential for studying the safety of driving in curves. However, the adhesion of the vehicle during the driving process on the wet and slippery road will be significantly reduced, resulting in lateral slippage due to the low adhesion coefficient of the road surface, the speed exceeding the turning critical, and the turning radius being too small when passing through the corner. Therefore, to reduce the incidence of traffic accidents of passenger cars driving in curves on rainy and snowy days and achieve the purpose of planning safe driving speed, this paper proposes a curve active safety system based on a deep learning algorithm and vehicle dynamics model. First,we a convolutional neural network (CNN) model is constructed to extract and judge the characteristics of snow and ice adhesion on roads. By training the residual network, the road surface can be identified and classified under 7 different weather conditions, and the adhesion coefficient of the road surface at this time can be obtained. In addition, the magic formula is used to establish a tire curve driving dynamics model and combined with the curve radius and other parameters to solve the safety speed threshold in the curve driving process. Finally, MATLAB and CarSim software are used to build a simulation platform for verification, and real vehicle experiments verify that the system has strong reliability and robustness. The research shows that the prediction accuracy of the training set and verification set of the system reaches 93.7% and 85.93% respectively. Compared with the traditional back propagation (BP) neural network method, the recognition accuracy of the road adhesion coefficient is improved by 4.53%. Therefore, the recognition algorithm combined with road surface parameter information in this paper has higher prediction accuracy and robustness, which can significantly improve the safety of vehicle driving on curves on rainy and snowy days.</div></div>

Publisher

SAE International

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3