基于模糊神经网络的汽车防撞控制研究  

Study of Car-avoiding Controlling System Based on Fuzzy Neural Network

作　　者：张学军[1] 蓝天[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《兰州交通大学学报》2011年第6期71-74,共4页Journal of Lanzhou Jiaotong University

基　　金：甘肃省科技计划资助(0916RJZA052);高校基本业务费项目(620005);甘肃省教育厅研究生导师科研项目(0704-13)

摘　　要：为了实现汽车的安全行驶,提出了一种基于模糊神经网络的汽车防撞控制方法.使用神经网络对汽车纵向运动进行辨识,并将神经网络和模糊控制结合起来,设计了模糊神经网络加速度控制器,利用神经网络的学习功能修正控制器的隶属度函数的参数和控制规则.仿真结果表明和传统方法相比响应快,超调小,具有很好的鲁棒性和自适应能力.For the purpose of driving safety,a method of car-avoiding controlling system based on fuzzy neural network is proposed in this paper,which using neural network to identify the vehicle longitudinal movement.Fuzzy neural controller for accelerator is designed by integrated the neural network into fuzzy control system for car-avoiding.Aiming at the defects of fuzzy control system,the neural network online learning algorithm is adopted to revise the parameters and fuzzy rules of fuzzy control system.The simulation results show that this method using neural network to implement the fuzzy control system for car-avoiding is super to the old methods,such as PID and fuzzy method,in the view of response,overshoot and robust.

关 键 词：模糊神经网络 汽车防撞 学习算法 自适应模糊控制 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]