自动变速车辆起步模糊神经网络控制策略仿真  

Fuzzy Neural Network Control of Automated Mechanical Transmission During Starting

作　　者：陈然[1] 孙冬野[1] 

机构地区：[1]重庆大学机械传动国家重点实验室,重庆400030

出　　处：《系统仿真学报》2010年第4期912-914,共3页Journal of System Simulation

基　　金：国家863计划(2006AA110111)

摘　　要：自动变速器车辆的核心和难点是起步控制。针对传统模糊控制在其参数的模糊化过程中人为因素影响较大,获得较优控制参数困难等缺点,基于优秀驾驶员的起步操作经验,利用神经网络自适应学习功能优化模糊控制参数,设计了模糊神经网络控制策略。应用SIMULINK建立了起步模糊神经网络控制系统仿真模型。仿真实验表明,优化了模糊控制模型隶属函数,该控制策略可较好的解决自动变速车辆起步控制问题,为机械式自动变速车辆的开发设计提供了理论依据。Starting control is the key of automated mechanical transmission for a car. Focused on the problem that ordinary fuzzy controller design has a lot of subjective factors and the fuzzy controller is difficult to optimize,and Neural Network Algorithm was applied to optimize the parameters of the starting fuzzy controller. A simulation model for starting fuzzy neural network controller was established using Simulink. Simulation and test results show that the membership functions of fuzzy model obtain the satisfactory effect. It provides a control method to design car with automatic mechanical transmission.

关 键 词：自动变速器 起步控制 优化 模糊神经网络控制 

分 类 号：TH133[机械工程—机械制造及自动化]