广东工业大学学报2017，Vol.34Issue(1)：78-83,89,7.DOI:10.12052/gdutxb.150151
不确定时滞神经网络的无源性分析
Passivity Analysis for Uncertain Neural Networks with Time-Varying Delay
摘要
Abstract
The passivity of neural networks of neural network systems is studied. Based on the passive network theory, it the less conservative conditions of the neural network can be obtained. Additionally, the robust passivity of the parameters uncertainties' neural networks with time-delay is analyzed. According to theories and approaches of Lyapunov stability, Jensen integral inequality, Schur complement lemma and free weighting matrices, the research shows that the less conservative passive condition of the neural network can be obtained from constructing a new Lyapunov-Krasovskii functional and simplifying the quadratic terms of the Lyapunov-Krasovskii functional's inverse. Meanwhile, the passivity condition is obtained not requiring all the symmetric involved in the employed quadratic Lyapunov-Krasovskii functional matrices to be positive definite. The results show that the method is effective.关键词
神经网络/李雅普诺夫泛函/时滞/无源Key words
neural networks/Lyapunov-Krasovskii functional/time delay/passivity分类
信息技术与安全科学引用本文复制引用
彭诗友,彭世国..不确定时滞神经网络的无源性分析[J].广东工业大学学报,2017,34(1):78-83,89,7.基金项目
国家自然科学基金资助项目(61374081)；广东省自然科学基金资助项目(S2013010013034,2015A030313485) （61374081）
