New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay Using Delay-Decomposition Approach
New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay Using Delay-Decomposition Approach
复制标题
使用延迟分解方法的时变延迟神经网络的新延迟相关稳定性准则
DOI：
10.1109/tnnls.2013.2285564
复制
发表时间：
2014-07-01
影响因子：
10.4
通讯作者：
Guan, Xinping
中科院分区：
文献类型：
--
作者：
Ge, Chao;Hua, Changchun;Guan, Xinping
本文主要研究具有时变时滞的神经网络的渐近稳定性问题。激活函数是单调非递减的已知的下限和上限。利用新的Lyapunov-Krasovskii泛函和积分不等式，得到了新的稳定性判据.发展的稳定性准则具有时滞依赖性和结果的特点是线性矩阵不等式。新的和不太保守的解决方案的全球稳定性问题的可行性测试。最后通过数值算例验证了该方法的有效性。
This brief is concerned with the problem of asymptotic stability of neural networks with time-varying delays. The activation functions are monotone nondecreasing with known lower and upper bounds. Novel stability criteria are derived by employing new Lyapunov-Krasovskii functional and the integral inequality. The developed stability criteria have delay dependencies and the results are characterized by linear matrix inequalities. New and less conservative solutions to the global stability problem are provided in terms of feasibility testing. Numerical examples are finally given to demonstrate the effectiveness of the proposed method.