基于自定义神经网络的EPS助力特性研究  

Study of Assist Characteristic of EPS Based on Self-defined Neural Network

作　　者：陈国迎[1] 陈翀[1] 

机构地区：[1]西华大学交通与汽车工程学院,成都610039

出　　处：《拖拉机与农用运输车》2009年第5期17-18,20,共3页Tractor & Farm Transporter

摘　　要：对电动助力转向(EPS)系统的助力特性进行了分析,并利用搭建的自定义神经网络模型对助力特性曲线进行预描,在MATLAB中得到的仿真结果是一组非常理想的助力曲线。这表明该自定义网络能有效预测EPS的助力特性,同时也为后期的回正控制策略研究提供了思路。This paper analyses the assist control strategy of electric power steering system. On the basis of the study, a three-layer self-defined neural network is constructed and trained to forecast the curve of assist characteristics. Through the simulation in MATLAB, the paper gets a set of smooth assist characteristic curves which we are trying to get. The ideal result shows that this self-defined neural network can effectively predict the assist characteristics of electric power-assisted steering system. At the same time, this new neural network model provides a good approach for the further study of return control strategy.

关 键 词：电动助力转向系统 助力特性 MATLAB 自定义神经网络 

分 类 号：U463.444[机械工程—车辆工程]