时变时滞区间神经网络的全局鲁棒稳定性判据

本文主要研究时变时滞区间神经网络的全局鲁棒稳定性问题, 利用区间神经网络的等价转换和自由矩阵技术, 给出一个新的区间神经网络平衡点的时滞依赖全局鲁棒稳定性的充分条件, 这个条件以线性矩阵不等式的形式给出, 容易验证, 保守性低.最后, 通过数值实例验证了所提算法的正确性和更低的保守性.     

基于LMI的时变时滞Cohen-Grossberg神经网络鲁棒稳定性

 研究了时变时滞Cohen-Grossberg神经网络的全局鲁棒稳定性问题.基于线性矩阵不等式技术,给出了保证时变时滞Cohen-Grossberg神经网络平衡点唯一性和全局鲁棒稳定性的新判据.这些新判据不依赖于时滞的大小和放大函数,且与现有的一些结果相比,具有易于验证、适用范围广、条件更不保守等特点.仿真结果验证了本文方法的有效性.     

中立型BAM神经网络的鲁棒稳定性分析

本文主要研究不确定中立型BAM神经网络的鲁棒渐近稳定性问题, 不确定参数具有较范数有界更一般的线性分式形式, 考虑了中立时滞与状态时滞不相等的情况, 激励函数只要求满足有界和全局李普希兹条件,通过构造一个新的Lyapunov泛函, 利用Lyapunov-Krasovskii稳定性理论和一些不等式技术, 得到了具有较小约束的时滞中立型BAM神经网络的鲁棒渐近稳定性条件, 这个充分条件以线性矩阵不等式的形式给出, 容易验证.最后, 通过数值实例验证了所提算法的正确性和保守性.     

时滞依赖型区间时滞系统非脆弱H_∞控制

针对一类状态和控制输入矩阵均为区间矩阵的不确定时滞系统,其中状态和控制输入同时具有未知但有上界的时间滞后,基于Lyapunov稳定性理论,利用线性矩阵不等式(LMI)方法,讨论了该类时滞系统的时滞依赖型非脆弱H∞状态反馈控制器设计问题.在区间不确定性和控制器执行机构扰动均满足增益有界条件下,得到了该类时滞系统的满足H∞性能的一个充分条件.通过求解一个线性矩阵不等式(LMIs)组,即可获得鲁棒H∞控制器.最后对某型飞机作机动飞行仿真,仿真结果表明该鲁棒控制器设计方法是有效的.     

随机变时滞神经网络的全局渐近稳定性

研究了一类具有变时滞随机神经网络模型平衡点的全局渐近稳定性问题,通过构造李亚普诺夫函数并利用线性矩阵不等式理论,得出了随机变时滞神经网络的全局渐近稳定性的充分条件。     

多时滞Cohen-Grossberg神经网络鲁棒稳定性的新判据

分析了一类具有多时滞及参数摄动的Cohen-Grossberg神经网络的全局鲁棒稳定性.通过构造适当的Lyapunov泛函,以线性矩阵不等式形式给出了平衡点全局鲁棒稳定的判据.此外,所有结论的建立都不需要假定互连矩阵的对称性及激活函数的可微性和单调性.仿真结果进一步证明了结论的有效性.     

具比例时滞杂交双向联想记忆神经网络的全局指数稳定性

对一类具比例时滞杂交双向联想记忆神经网络进行研究,利用Brouwer不动点定理证明该网络的平衡点的存在唯一性.利用变换将具比例时滞杂交双向联想记忆神经网络变换成等价的具不等常时滞与变系数杂交双向联想记忆神经网络.利用不等式技巧建立一拟Halanay型不等式系统,进而得到了确保该系统全局指数稳定的时滞独立的充分条件.并给出两个算例验证所得结论的正确性.     

变时滞随机递归神经网络的全局指数稳定性

利用自由权值矩阵和不等式分析技巧,研究了一类随机变时滞神经网络的全局指数稳定性问题.该模型中考虑了神经网络的外部随机扰动因素,更加接近真实网络.通过构造适当的Lyapunov-Krasovskii泛函,以线性矩阵不等式形式给出了的全局指数稳定性判据,能够利用Matlab的LMI工具箱很容易地进行检验.此外,仿真结果进一步证明了结论的有效性.     

一类非线性不确定时滞系统的记忆与无记忆复合H∞状态反馈控制

针对一类具有状态非线性不确定性的线性时滞系统,基于Lyapunov稳定性理论,利用线性矩阵不等式（LMI）方法,讨论了该类时滞系统的记忆与无记忆复合H∞状态反馈控制器的设计问题。在非线性不确定性满足增益有界条件下,得到了该类时滞系统的满足鲁棒H∞性能的一个充分条件。通过求解一个线性矩阵不等式-LMI,即可获得鲁棒H∞控制器。     

输入饱和约束下一类多智能体编队系统鲁棒一致性分析

针对输入饱和约束奈件下具有不对称时滞的二阶多智能体编队系统的鲁棒一致性问题,本文综合利用Lya-punov-Krasovskii泛函方法和线性矩阵不等式的方法对其进行了研究.首先在n维欧氏空间中建立了二阶多智能体所组成的编队系统的数学模型;然后设计了分布式的基于一致性的具有饱和约束和不对称时滞的编队控制律;进一步,利用非线性扇区法处理了饱和项,将其转化为一种简单的非线性项,从而建立了Lyapunov-Krasovskii泛函,并利用LMI方法对编队系统进行了鲁棒一致性分析,得到了系统达到鲁棒一致时的线性矩阵不等式条件,并通过仿真分析验证了所得条件的正确性.     

Robust Global Exponential Stability for Interval Reaction–Diffusion Hopfield Neural Networks With Distributed Delays

This brief presents a sufficient condition for the existence, uniqueness, and robust global exponential stability of the equilibrium solution for a class of interval reaction diffusion Hopfield neural networks with distributed delays and Dirichlet boundary conditions by constructing suitable Lyapunov functional and utilizing some inequality techniques. The result imposes constraint conditions on the boundary values of the network parameters. The result is also easy to verify and plays an important role in the design and application of globally exponentially stable neural circuits.     

Global asymptotic and robust stability of recurrent neural networks with time delays

In this paper, two related problems, global asymptotic stability (GAS) and global robust stability (GRS) of neural networks with time delays, are studied. First, GAS of delayed neural networks is discussed based on Lyapunov method and linear matrix inequality. New criteria are given to ascertain the GAS of delayed neural networks. In the designs and applications of neural networks, it is necessary to consider the deviation effects of bounded perturbations of network parameters. In this case, a delayed neural network must be formulated as a interval neural network model. Several sufficient conditions are derived for the existence, uniqueness, and GRS of equilibria for interval neural networks with time delays by use of a new Lyapunov function and matrix inequality. These results are less restrictive than those given in the earlier references.     

A Projection Neural Network with Time Delays for Solving Linear Variational Inequality Problems and Its Applications

In this paper, a new projection neural network with discrete and distributed delays is presented for solving linear variational inequality problems. Some novel sufficient conditions ensuring globally exponential stability are derived by employing matrix measure and differential inequality technique, and the easily checkable conditions are less restrictive. Furthermore, based on the Lagrange multiplier, the proposed neural network can solve the quadratic programming problems. Finally, some simulation results with applications to finance and image fusion are given to demonstrate the effective performance of the neural network.     

Robust Exponential Stability of Recurrent Neural Networks With Multiple Time-Varying Delays

New criteria for the uniqueness and global robust exponential stability are established for the equilibrium point of interval recurrent neural networks with multiple time-varying delays via a decomposition method and analysis technique. Results are presented in the form of linear matrix inequality, which can be solved efficiently. Two numerical examples are employed to show the effectiveness of the present results.     

Delay-Dependent Exponential Stability Criterion for BAM Neural Networks with Time-Varying Delays

By employing the Lyapunov stability theory and linear matrix inequality（LMI）technique,delay-dependent stability criterion is derived to ensure the exponential stability of bi-directional associative memory（BAM）neural networks with time-varying delays.The proposed condition can be checked easily by LMI control toolbox in Matlab.A numerical example is given to demonstrate the effectiveness of our results.     

Global exponential stability and periodicity of recurrent neural networks with time delays

In this paper, the global exponential stability and periodicity of a class of recurrent neural networks with time delays are addressed by using Lyapunov functional method and inequality techniques. The delayed neural network includes the well-known Hopfield neural networks, cellular neural networks, and bidirectional associative memory networks as its special cases. New criteria are found to ascertain the global exponential stability and periodicity of the recurrent neural networks with time delays, and are also shown to be different from and improve upon existing ones.     

Global Exponential Stability Analysis of Cohen–Grossberg Neural Networks

In this paper, we investigate the global exponential stability of the Cohen–Grossberg neural networks with time delays, we derive a general sufficient condition ensuring global stability of the neural networks by constructing a novel Lyapunov functional and carefully estimating its derivative. The main advantage of the proposed condition is the drop of the absolute symbol from the absolute values of the self feedback connection weights, thus improves some existing conditions. As a result, some stability conditions for the Cohen–Grossberg neural network without delays are also derived, which generalize and unify some previous results.     

Global Robust Stability Criteria for Interval Delayed Neural Networks Via an LMI Approach

The problem of the global robust stability of delayed interval neural networks is considered. We first illustrate that the results given by Arik recently are unjustified, and then a revised version is proposed in light of Arik's idea. By taking an approach combining the Lyapunov–Krasovskii functional with the linear matrix inequality (LMI), several criteria for determining the robust exponential stability of delayed neural networks are derived, which provide an easily verified guideline. Moreover, the exponential convergence rate is estimated via LMI-Toobox in Matlab. The theoretical analysis and numerical simulations show that the new results are less conservative and less restrictive than the ones reported recently in the literature.     

A Note on “Global Robust Stability Criteria for Interval Delayed Neural Networks Via an LMI Approach”

A recently reported result concerning the global exponential robust stability of delayed neural networks is revisited. It is shown by a counter example that the result is invalid because the proof is incorrect, and then a modified version is given. The paper also presents an improved sufficient condition for global exponential robust stability of the neural networks with unbounded activation functions and time-varying delays. Finally, a numerical simulation is given to show the effectiveness of the obtained result.      

一类具多比例延时的细胞神经网络的指数稳定性

讨论了一类具多比例延时的细胞神经网络的指数稳定性.利用非线性测度得到了一个保证平衡点存在唯一且指数稳定的充分条件,并给出了解的指数收敛速度.最后验证了结论的正确性并进行了模拟仿真.