基于神经网络路面识别的电动汽车ABS控制研究  

Research on ABS control of electric vehicle based on road recognition using neural network

作　　者：王国微 尹安东 WANG Guowei;YIN Andong(School of Automobile and Traffic Engineering, Hefei University of Technology, Hefei 230009, China)

机构地区：[1]合肥工业大学汽车与交通工程学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2020年第7期878-883,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家科技支撑计划资助项目(2013BAG08B01);国家新能源汽车重点研发计划资助项目(2017YFB0103200)。

摘　　要：为了充分利用路面附着能力以提高电动汽车的制动安全性,文章提出了一种基于径向基函数(radial basis function,RBF)神经网络路面识别的电动汽车制动防抱死系统(anti-lock braking system,ABS)控制方法。采用RBF神经网络进行路面识别,将识别出的最优滑移率作为目标参数,以此设计了一种模糊控制与预测控制相结合的ABS控制策略,同时制定了制动力矩分配策略,从而确保制动系统可靠工作并实现制动能量回收,最后基于CarSim与Matlab/Simulink仿真平台进行了实例样车仿真分析。仿真结果表明,该路面识别方法可以准确识别当前路面状态,ABS控制策略下的制动距离相对于模糊控制策略缩短了6.57%,制动能量回收提高了3.9%。In order to make full use of the road adhesion ability and improve braking safety of electric vehicles,this paper presents an anti-lock braking system(ABS)control method for electric vehicles based on road recognition using radial basis function(RBF)neural network.Firstly,RBF neural network is used to identify road,then the optimal slip rate is taken as the target parameter to design an ABS control strategy which combines fuzzy control with predictive control.At the same time,the braking torque distribution strategy is formulated to ensure braking system to work reliably and realize the braking energy recovery.The simulation results on CarSim and Matlab/Simulink simulation platform show that the road recognition method can accurately identify current road surface state.The braking distance of ABS control strategy is shortened by 6.57%and the braking energy recovery is increased by 3.9%compared with fuzzy control strategy.

关 键 词：电动汽车 路面识别 最优滑移率 制动防抱死系统(ABS) 模糊预测控制 

分 类 号：U462.1[机械工程—车辆工程]