基于遗传算法-神经网络的半主动悬架控制仿真  

Simulation of vehicle semi-active suspension control based on genetic algorithm and neural networks

作　　者：郑泉[1] 

机构地区：[1]安徽农业大学农业工程系,安徽合肥230036

出　　处：《合肥工业大学学报（自然科学版）》2002年第2期230-235,共6页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目 (0 0 0 43 2 3 8)

摘　　要：分析了汽车悬架的非线性特性 ,提出了一种采用遗传算法 -神经网络的控制方法实现对车辆半主动悬架系统的控制 ,并用一个 4自由度的车辆模型 ,分别对有该控制规律的半主动悬架和传统的被动悬架进行了计算机仿真 ,结果表明前者比后者具有更好的减振效果。文章将神经网络与遗传算法相结合 ,使控制器对付复杂问题的能力大大增强 。A method of adopting genetic algorithm and neural networks to control the semi active suspension of vehicle is presented. With the help of a four degree of freedom vehicle model,the conventional passive suspension and the semi active suspension with a control strategy by genetic algorithm and neural networks are simulated respectively. The results show that the latter is superior to the former in improving the ride comfort. By combining genetic algorithm with neural networks,the ability of the controllor to deal with complicated problems is improved greatly.This paper provides a new way of studying the semi active suspension control.

关 键 词：半主动悬架 遗传算法 神经网络 仿真 汽车 控制系统 

分 类 号：U463.33[机械工程—车辆工程]