| 基于递归小波神经网络的非线性动态系统仿真 |
| |
| 引用本文： | 赵凤遥,马震岳.基于递归小波神经网络的非线性动态系统仿真[J].系统仿真学报,2007,19(7):1453-1455,1539. |
| |
| 作者姓名： | 赵凤遥 马震岳 |
| |
| 作者单位： | 1. 大连理工大学土木水利学院,大连,116024;郑州大学环境与水利学院,郑州,450002
2. 大连理工大学土木水利学院,大连,116024 |
| |
| 摘 要： | 为提高动态递归神经网络的动态系统仿真能力，在Elman神经网络的基础上，提出动态递归小波神经网络（RWNN），给出了其动态梯度下降算法，并将其成功应用于非线性动态系统仿真．仿真算例表明，该网络具有收敛快，精度高等优点，仿真效果很好，同时具有较好的泛化性能，具有广阔的应用前景。
|
| 关 键 词： | Elman神经网络 递归小波神经网络(RWNN) 梯度下降算法 非线性动态系统 仿真 |
| 文章编号： | 1004-731X（2007）07-1453-03 |
| 收稿时间： | 2006-03-02 |
| 修稿时间： | 2006-03-022007-01-15 |
Nonlinear Dynamical System Simulation Based on Recurrent Wavelet Neural Network |
| |
| ZHAO Feng-yao,MA Zhen-yue.Nonlinear Dynamical System Simulation Based on Recurrent Wavelet Neural Network[J].Journal of System Simulation,2007,19(7):1453-1455,1539. |
| |
| Authors: | ZHAO Feng-yao MA Zhen-yue |
| |
| Institution: | 1 .School of Civil and Hydral Engineering, Dalian University of Technology, Dalian 116024, China; 2.School of Environment and Water Conservancy engineering, ZhengzhouUniversity, Zhengzhou 450002, China |
| |
| Abstract: | For the aim of improving the dynamical system simulation ability of recurrent neural network, Based on Elman network, the recurrent wavelet neural network (RWNN ) was proposed in the paper, and the dynamic gradient descent algorithm of RWNN was given. The RWNN could be used in the nonlinear dynamical system simulation successfully. Simulation example shows that RWNN has a faster convergence speed and a better precision in calculation, and a good result on the nonlinear dynamical system simulation is obtained. At the same time, the network also has better generalization ability, which means it has a broad prospect on application. |
| |
| Keywords: | Elman network recurrent wavelet neural network (RWNN) gradient descent algorithm nonlinear dynamical system simulation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
