| 基于线性矩阵不等式的广义神经网络系统的全局渐近稳定性分析 |
| |
| 引用本文： | 蒋国民,陈玉会. 基于线性矩阵不等式的广义神经网络系统的全局渐近稳定性分析[J]. 淮阴工学院学报, 2005, 14(5): 1-6 |
| |
| 作者姓名： | 蒋国民 陈玉会 |
| |
| 作者单位： | [1]淮阴工学院计算科学系,江苏淮安223001 [2]淮安广播电视大学,江苏淮安223001 |
| |
| 摘 要： | 首先讨论了同时具有离散时滞和分布时滞的神经网络系统即广义神经网络系统平衡点的存在性,然后通过构造Lyapunov-Krasovskii泛函并利用线性矩阵不等式的方法将系统的稳定性问题转化为凸优化问题,建立了系统全局渐近稳定的充分条件.该充分条件可利用标准的Matlab LMI工具箱来验证和求解.
|
| 关 键 词： | 神经网络 线性矩阵不等式 稳定性 |
| 文章编号： | 1009-7961(2005)05-0001-05 |
| 修稿时间： | 2005-07-04 |
LMI- Based Approach for Globally Asymptotic Stability Analysis of Generalized Delayed Neural Network |
| |
| JIANG Guo-min,CHEN Yu-hui. LMI- Based Approach for Globally Asymptotic Stability Analysis of Generalized Delayed Neural Network[J]. Journal of Huaiyin Institute of Technology, 2005, 14(5): 1-6 |
| |
| Authors: | JIANG Guo-min CHEN Yu-hui |
| |
| Affiliation: | JIANG Guo-min~1,CHEN Yu-hui~2 |
| |
| Abstract: | This paper is devoted to the stability analysis of generalized delayed neural network with mixed discrete and distributed delays.We first prove the existence and uniqueness of the equilibrium point under mild conditions.Then,by employing the Lyapunov-Krasovskii function,the addressed stability analysis problem is converted into a convex optimization problem,and a linear matrix inequality(LMI) approach is utilized to establish the sufficient condition for the globally asymptotic stability.This condition can be readily checked by utilizing the Matlab LMI Toolbox. |
| |
| Keywords: | neural network linear matrix inequality stability |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
