带有离散和分布时滞的神经网络系统稳定性分析  

Stability Analysis of Neural Networks with Discrete and Distributed Time Delays

作　　者：甘滨滨 陈昊[1] 徐彪 杨梦情 胡雅芹 GAN Binbin;CHEN Hao;XU Biao;YANG Mengqing;HU Yaqin(School of Mathematical Sciences,Huaibei Normal University,235000,Huaibei,Anhui,China)

机构地区：[1]淮北师范大学数学科学学院,安徽淮北235000

出　　处：《淮北师范大学学报（自然科学版）》2024年第1期10-15,共6页Journal of Huaibei Normal University：Natural Sciences

基　　金：安徽省自然科学基金项目(2008085MA11);安徽省高等学校质量工程项目(2021jxtd257);淮北师范大学研究生创新基金项目(CX2023047)。

摘　　要：为解决带有离散和分布时滞的神经网络系统稳定性问题。文章通过构造合适的李雅普诺夫泛函,结合Wirtinger不等式和Jensen不等式,得到一个新的由线性矩阵不等式表示的时滞相关指数稳定性判别准则,在一定程度上降低现有稳定性判别条件的保守性。使用2个具体的网络模型,验证了稳定性判别准则的优越性与可行性。To solve the stability problem of neural network systems with discrete and distributed time delays,by constructing a suitable Lyapunov functional and combining with Wirtinger-based inequality and Jenson inequality,a new delay-dependent exponential stability criterion represented by linear matrix inequality is obtained.The conservatism of existing stability criteria is reduced to a certain extent.Two specific neuron network models is employed to demonstrate the superiority and feasibility of the stability discrimination criteria.

关 键 词：神经网络 稳定性分析 李雅普诺夫泛函 分布时滞 

分 类 号：O[理学]