| 高速公路入口匝道无模型控制研究 |
| |
| 引用本文： | 叶永刚,丛国华,李宝家.高速公路入口匝道无模型控制研究[J].哈尔滨商业大学学报(自然科学版),2007,23(3):378-381. |
| |
| 作者姓名： | 叶永刚 丛国华 李宝家 |
| |
| 作者单位： | 1. 哈尔滨商业大学,基础科学院,哈尔滨,150076
2. 哈尔滨工业大学,人文与管理学院,山东,威海,264209 |
| |
| 摘 要： | 高速公路交通系统是具有非线性、随机性、时变性等特性的复杂系统,用传统的数学模型很难准确地描述,因此依赖数学模型的交通流控制存在很大的局限性.建立了一个包含神经网络的无模型高速公路交通流匝道控制系统,这里以入口匝道的放行率(即控制变量)作为神经网络输出,并给出了神经网络的结构和详细的训练算法,其中训练算法采用了SPSA方法.仿真结果表明,该方法能有效地对高速公路入口匝道实施控制,且比一般的神经网络模型具有更强的在线控制能力.
|
| 关 键 词： | 高速公路 交通流 匝道控制 神经网络 |
| 文章编号： | 1672-0946（2007）03-0378-04 |
| 收稿时间： | 2006-09-19 |
| 修稿时间： | 2006-09-19 |
Model -free ramp control research on freeway |
| |
| YE Yong-gang,CONG Guo-hua,LI Bao-jia.Model -free ramp control research on freeway[J].Journal of Harbin University of Commerce :Natural Sciences Edition,2007,23(3):378-381. |
| |
| Authors: | YE Yong-gang CONG Guo-hua LI Bao-jia |
| |
| Institution: | 1. School of Basic Science , Harbin University of Commerce, Harbin 150001 ,China; 2. School of Humanities and Management, Weihai Branch of Harbin Institute of Technology , Weihai 264209, China |
| |
| Abstract: | Due to traffic system is a heavily nonlinear,stochastic,time-variant and uncertain system,it is too difficult to construct an exactly mathematic model,Traffic flow control systems that include mathematic model are very limited.This paper constructs a model-free control system of traffic flow that includes a neutral network.The output of neural network is the transit rate that is control measure,and shows the frame of neural network,the parameter estimation is completed by simultaneous perturbation stochastic approximation(SPSA).Simulation results show that this algorithm can solve the traffic control problem effectively and it is better real time control than other neutral networks. |
| |
| Keywords: | traffic flow ramp-metering neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
