| 引用本文: | 谭 文, 王耀南, 黄 丹, 曾照福, 周少武, 刘祖润.混沌系统的混合遗传神经网络控制[J].控制理论与应用,2004,21(4):495~500.[点击复制] |
| TAN Wen, WANG Yao-nan, HUANG Dan, ZENG Zhao-fu, ZHOU Shao-wu, LIU Zu-run.Hybrid genetic neural networks for chaotic system control[J].Control Theory and Technology,2004,21(4):495~500.[点击复制] |
|
| 混沌系统的混合遗传神经网络控制 |
| Hybrid genetic neural networks for chaotic system control |
| 摘要点击 1267 全文点击 871 投稿时间：2002-11-07 修订日期：2003-09-23 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2004.4.002 |
| 2004,21(4):495-500 |
| 中文关键词 遗传算法 增强学习 暂态误差预测 混沌控制 神经网络 |
| 英文关键词 genetic algorithm reinforcement learning temporal difference prediction chaos control neural networks |
| 基金项目 国家自然科学基金项目(60375001;60075008;60102010); 湖南省自然科学基金项目(02JJY2095;03JJY3107). |
|
| 中文摘要 |
| 在小扰动控制技术基础上,将暂态误差预测方法和遗传算法结合起来,提出了一种混合遗传神经网络控制非线性混沌系统的新方法(简称HyGANN).通过增强学习训练,HyGANN可产生控制混沌状态的小扰动时间序列信号,Henon映射的计算机仿真结果表明,它不仅有效镇定混沌周期1,2等低周期轨道,还可成功将高周期混轨道变成期望周期行为. |
| 英文摘要 |
| By incorporating the temporal difference prediction technique with the genetic algorithm, a novel hybrid genetic neural network (known as HyGANN) for controlling nonlinear chaotic system based on the scheme of small perturbations was presented . The HyGANN trained by reinforcement learning algorithm could generate small perturbation time series signals to suppress the chaotic states. The computer simulations on Henon map chaotic system have shown that the behavior of period 1 and period 2 can be controlled effectively and the high period orbit can be directed towards desired periodic trajectory. |
|
|
|
|
|