| 一种基于遗传算法的神经网络控制方法研究 |
| |
| 引用本文： | 王清,马广富,弥曼. 一种基于遗传算法的神经网络控制方法研究[J]. 系统仿真学报, 2006, 18(4): 1070-1072,1077 |
| |
| 作者姓名： | 王清 马广富 弥曼 |
| |
| 作者单位： | 1. 广州大学信息与控制工程系,广州,510091
2. 哈尔滨工业大学控制科学与工程系,哈尔滨,150001 |
| |
| 摘 要： | 给出一种采用遗传算法同时进行神经网络控制器的权值和结构优化设计的方法，并将该方法分别应用于球杆系统和连续搅拌反应釜系统的控制，仿真结果表明，用该方法得到的神经网络控制器具有结构简单、泛化能力强、控制效果良好的特点。
|
| 关 键 词： | 遗传算法 神经网络控制器 球杆系统 连续搅拌反应釜系统 |
| 文章编号： | 1004-731X（2006）04-1070-03 |
| 收稿时间： | 2004-12-23 |
| 修稿时间： | 2004-12-232005-09-06 |
Research on Neural Network Control based on Genetic Algorithm |
| |
| WANG Qing,MA Guang-fu,MI Man. Research on Neural Network Control based on Genetic Algorithm[J]. Journal of System Simulation, 2006, 18(4): 1070-1072,1077 |
| |
| Authors: | WANG Qing MA Guang-fu MI Man |
| |
| Affiliation: | 1.Dept. of Information and Control Engineering, Guangzhou University, Guangzhou 510091, China; 2.Dept.of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China |
| |
| Abstract: | A method for a kind of neuro-controller design was proposed, in which the weights and the architecture of the neumcontroller were optimized by the genetic algorithm. The method was used to the control of a ball and beam system and a continuous-stirred tank reactor system respectively. The simulation results indicate that the neuro-controller is of simple structure, high generalization ability and good control effect. |
| |
| Keywords: | genetic algorithm neural networks ball and beam system continuous-stirred tank reactor |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
