| 基于混合神经网络的一般动态系统MT方法建模 |
| |
| 引用本文： | 姜波,陈绵云,汪秉文,周畅.基于混合神经网络的一般动态系统MT方法建模[J].华中科技大学学报(自然科学版),2003,31(5):31-33. |
| |
| 作者姓名： | 姜波 陈绵云 汪秉文 周畅 |
| |
| 作者单位： | 华中科技大学控制科学与工程系 |
| |
| 基金项目： | 国家自然科学基金资助项目 (79970 0 2 5 ) |
| |
| 摘 要： | 利用MT理论对一般动态系统的分解提出了混合神经网络建模的方法，混合神经网络模型采用动态神经网络和静态神经网络级联的方式，结合了二者的优点，克服了各自的不足之处．探讨了采用混合神经网络对一般动态系统建模的方法．研究结果表明，此方法对于一般动态系统，特别是复杂的非线性动态系统的建模有其独特的优点．
|
| 关 键 词： | 一般动态系统 MT理论 混合神经网络 |
| 文章编号： | 1671-4512(2003)05-0031-03 |
| 修稿时间： | 2002年6月27日 |
The model of general dynamical systems by MT based on composite neural networks |
| |
| Jiang Bo Chen Mianyun Wang Bingwen Zhou Chang Jiang Bo Doctoral Candidate, Dept. of Control Sci. & Eng.,Huazhong Univ. of Sci. & Tech.,Wuhan ,China..The model of general dynamical systems by MT based on composite neural networks[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2003,31(5):31-33. |
| |
| Authors: | Jiang Bo Chen Mianyun Wang Bingwen Zhou Chang Jiang Bo Doctoral Candidate Dept of Control Sci & Eng Huazhong Univ of Sci & Tech Wuhan China |
| |
| Institution: | Jiang Bo Chen Mianyun Wang Bingwen Zhou Chang Jiang Bo Doctoral Candidate, Dept. of Control Sci. & Eng.,Huazhong Univ. of Sci. & Tech.,Wuhan 430074,China. |
| |
| Abstract: | Based on mathematical general systems theory, a general dynamical system can be divided into two parts. The composite neural networks was used to model general dynamical systems. The composite neural networks were composed of recurrent neural networks and multiplayer feedforward neural one. It has the advantages of the two networks. The methods on how to use this kind of neural networks to model a general dynamical system were discussed. The simulation results showed that this method had its own advantage in modeling general dynamical system, especially in modeling complex non-linear dynamical system. |
| |
| Keywords: | general dynamical system MT theory composite neural networks |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
