共查询到20条相似文献，搜索用时 15 毫秒
1.
文章研究了一类推广的具有变时滞的人工神经网络系统模型的全局指数稳定性.通过Lyapunov稳定性理论,给出了该时滞神经网络系统模型平衡点唯一和全局指数稳定的一类判定条件,并通过典型实例来说明本文结果的应用. 相似文献
2.
Liu Mei-qin 《浙江大学学报(A卷英文版)》2006,7(2):237-244
The problems of determining the global asymptotic stability and global exponential stability for a class of norm-bounded nonlinear neutral differential systems with constant or time-varying delays are investigated in this work. Lyapunov method was used to derive some useful criteria of the systems’ global asymptotic stability and global exponential stability. The stability conditions are formulated as linear matrix inequalities (LMIs) which can be easily solved by various convex optimization algorithms. Moreover, for the exponentially stable system, the exponential convergence rates of the system’s states can be estimated by some parameters of the LMIs. Numerical examples are given to illustrate the application of the proposed method. 相似文献
3.
利用Lyapunov函数并结合不等式的技巧,给出了一些充分判据来确保一类脉冲神经网络系统具有全局指数稳定性的周期解.给出的充分判据仅仅要求激励函数是李普希兹连续的,而对它的有界性、单调性及可微性都不再要求.这些充分判据在实际应用中非常容易验证,也可利用这些判据来设计全局指数周期的脉冲神经网络. 相似文献
4.
To facilitate stability analysis of discrete-time bidirectional associative memory (BAM) neural networks, they were converted into novel neural network models, termed standard neural network models (SNNMs), which interconnect linear dynamic systems and bounded static nonlinear operators. By combining a number of different Lyapunov functionals with S-procedure, some useful criteria of global asymptotic stability and global exponential stability of the equilibrium points of SNNMs were derived. These stability conditions were formulated as linear matrix inequalities (LMIs). So global stability of the discrete-time BAM neural networks could be analyzed by using the stability results of the SNNMs. Compared to the existing stability analysis methods, the proposed approach is easy to implement, less conservative, and is applicable to other recurrent neural networks. 相似文献
5.
重新讨论了Hopfield神经网络平衡点的全局指数稳定性，得到了四个新判据，且列举了相应的例子来说明．由这些定理和例题的证明方法，阐述了Lyapunov函数的选择，网络参数电容Ci、电阻Ri及神经元uj(x)的导数ui(x)上下确界Mi，mi，i＝1，2…，n的处理及不等式放缩的精度在构造网络全局指数稳定性判据中的重要性，得到了表明全局指数稳定性收敛速度的Lyapunov指数α的估计式． 相似文献
6.
杨利辉 《洛阳师范学院学报》2010,29(2):11-13
本文利用Lyapunov泛函及不等式(2ab≤ra2+1/rb2,r>0)导出了判定模糊BAM(bi-directional associa-tive memory)神经网络周期解的存在性与稳定性的一些充分条件,得到了其周期解全局指数稳定性的一些新的简单判据. 相似文献
7.
本文讨论了一类具有变时滞模糊FBAM（fuzzybi—directional associate memory）神经网络平衡点的存在性和全局指数稳定性,利用不动点定理及Halanay型不等式获得了平衡点存在唯一性及全局指数稳定性的充分条件,所得结论容易验证．最后举例说明所得结果的可行性。 相似文献
8.
混合时滞区间神经网络鲁棒指数稳定性 总被引：3，自引：3，他引：0
易春 《内江师范学院学报》2009,24(2):23-26
讨论了混合时滞区间神经网络的全局鲁棒指数稳定性．利用拓扑度理论和不等式技巧给出了一个混合时滞区间神经网络平衡点的存在唯一性以及全局鲁棒指数稳定性的条件。 相似文献
9.
主要考察了一类动态系统——带有不同时间尺度竞争神经网络的全局指数稳定性问题。通过对此类神经网络模型的建立及分析,应用M矩阵理论和Lyapunov函数法,确定了带有不同时间尺度的竞争神经网络的平衡点的存在性和唯一性,并给出了此类神经网络全局指数稳定的判据。 相似文献
10.
11.
By using the properties of nonnegative matrices and techniques of differential inequalities, some sufficient conditions for the global exponential stability of cellular neural networks with time delays were obtained. The criteria do not require such conditions as boundedness and differentiability of activation functions. The conditions of the theorem were verified. 相似文献
12.
HUANG Jian GUAN Zhihong WANG Zhongdong Department of Control Science & Engineering Huazhong University of Science & Technology Wuhan Hubei P.R. China 《重庆大学学报(英文版)》2004,3(1):30-33
1.IntroductionAsthecomplexityofmoderncontrolsystems,itsdimensionbecomesmoreandmorevast.Actuators,sensorsandcontrollersinsystemsareusuallydistributed.Theclose-loopfeedbackcontrolsystemscanbeestablishedviaconnectingthesenodeswithcommunicationnetwork.Thesesystemsareoftencallednetworkedcontrolsystems(NCSs).TheNCSsbasedonfieldbusnetwork,suchasCANbus,havebeenwidelyusedinvariousindustrialareasinrecentyears.Therearemanynewissueswhenusingnewsystems.Thefirstissueisthenetwork-induceddelay(sensor-to-… 相似文献
13.
LI Chuandong LIAO Xiaofeng College of Mathematics Physics Chongqing University Chongqing P.R. China Department of Computer Science Engineering Chongqing University Chongqing P.R. China 《重庆大学学报(英文版)》2004,3(1):39-42
1.IntroductionConsideradelayedneural-networkmodeldescribedbythefollowingfunctionaldifferentialequations.()()()()()()11,nniiiijjjijjjijjtautwgutvgutImt===-++-+邋&1,2,,.in=K(1a)or()()()()()()ttttt=-++-+uAuWGuVGuI&,(1b)where()()()()T12,,,ntututut=轾臌uListhestatevectoroftheneuralnetwork;()12diag,,,naaa=AKisadiagonalmatrixwithpositiveentries,i.e.,0ia>;()ijnnw=Wand()ijnnv=Varetheconnectionweightmatrixanddelayedconnectionweightmatrix,re-spectively;()()()()()()()()T1122,,,nntgutgutgut轾=臌GuKde… 相似文献
14.
本文研究一类时变拢动线性控制系统全局指数稳定性,获得了系统全局指数稳定性的充分条件,这些结论对设计全局指数稳定的控制系统具有重要的理论意义和实用价值. 相似文献
15.
高潮 《重庆大学学报(英文版)》2003,2(1)
~~1()((,)(,))((,)(,))entssssssttttte==--Vxxxxfcycy Similar to the discussion of Theorem 1, it is easy to obtain 1(,)(,)entiiittKe-=-?xxcycy for any t0, where K1 is a constant. One can easily follow from formula above that ()()()etttKet---?xxcycy There exists a positive integer m such that ()e1mKqewt--?. A Poincare mapping F: CC by Fc=xw(c) is defined. Then, from Eq.(14), it can be derived that mmq-?FFcycy This implies that Fm is a contraction mapping; hence there exists a unique fixed p… 相似文献
16.
利用同胚映射理论、向量Lyapunov函数思想、M矩阵理论和不等式技术,研究了具有变时滞的细胞神经网络模型的全局指数稳定性,给出了判定平衡点的存在唯一性以及全局指数稳定性的一个判据,并且估计了收敛速度指标.相比一些最近的文献,本文没有采用传统的Lyapunov泛函方法,并且也不需要输出函数在实数集上满足Lipschitz条件,这样就放宽了对网络的要求,使得获得的结果有更广的应用范围.最后的数值例子表明提供的判据不仅保守性小,而且计算简单. 相似文献
17.
讨论了一类具有时滞的脉冲Cohen-Grossberg神经网络的全局指数稳定性．利用Lyapunov函数和不等式技巧得到了该系统全局指数稳定的一个充分条件,同时给出示例说明结果的有效性． 相似文献
18.
Robust exponential stability analysis of a larger class of discrete-time recurrent neural networks 总被引：1，自引：0，他引：1
ZHANG Jian-hai ZHANG Sen-lin LIU Mei-qin 《浙江大学学报(A卷英文版)》2007,8(12):1912-1920
The robust exponential stability of a larger class of discrete-time recurrent neural networks (RNNs) is explored in this paper. A novel neural network model, named standard neural network model (SNNM), is introduced to provide a general framework for stability analysis of RNNs. Most of the existing RNNs can be transformed into SNNMs to be analyzed in a unified way. Applying Lyapunov stability theory method and S-Procedure technique, two useful criteria of robust exponential stability for the discrete-time SNNMs are derived. The conditions presented are formulated as linear matrix inequalities (LMIs) to be easily solved using existing efficient convex optimization techniques. An example is presented to demonstrate the transformation procedure and the effectiveness of the results. 相似文献
19.
考虑一类时滞脉冲随机Cohen—Grossberg神经网络p阶矩指数稳定。通过构造适当的Lyapunov＂,~,利用Halanay~Hardy不等式,建立了一类时滞脉冲随机Cohen．Grossberg神经网络P阶矩指数稳定的判据。该判据改进和推广了先前文献的一些结果。 相似文献
20.
利用Lyapunov泛涵方法并结合一些不等式技巧获得了一类具自连接的双向联想记忆时延系统平衡点的存在性和全局指数稳定的充分条件. 相似文献