Robust Stability for a Class of Uncertain Hopfield Neural Networks of Neutral-type with Time-varying Delays
-
摘要: 针对一类不确定中立型时变时滞Hopfield神经网络的鲁棒稳定性问题, 构造了一个新Lyapunov-Krasovskii泛函, 并结合自由矩阵方法和牛顿—莱布尼茨公式, 得到了新的时滞相关稳定性判据. 该判据考虑了中立型时变时滞Hopfield神经网络中的参数不确定性, 所得结果以线性矩阵不等式(Linear matrix inequality, LMI)的形式给出, 容易验证. 最后, 通过两个数值算例验证了该结果的有效性及可行性. 该判据对丰富与完善中立型神经网络的稳定性理论体系, 具有积极的意义.
-
关键词:
- 鲁棒稳定性 /
- 中立型Hopfield神经网络 /
- 线性矩阵不等式 /
- 时变时滞 /
- Lyapunov-Krasovskii泛函
Abstract: This paper investigates the problem of robust stability analysis for a class of uncertain Hopfield neutral neural networks with time-varying delays. By constructing a new Lyapunov-Krasovskii functional, together with the Newton-Leibniz formula and some free-weighting matrix, new delay-dependent stability criteria are obtained. The proposed results are given in terms of linear matrix inequalities (LMI), which can be easily verified. Finally, two examples show the practicability and validity of the novel criteria. The proposed criteria have a vital significance for enriching and improving the stability theory of neural networks. -
[1] Wang Zhan-Shan. Stability Problem for Continuous-time Recurrent Neural Networks with Delays. Shenyang: Northeastern University Press, 2007 (王占山. 连续时间时滞递归神经网络的稳定性. 沈阳: 东北大学出版社, 2007) [2] Hou L L, Zong G D, Wu Y Q. Robust exponential stability analysis of discrete-time switched Hopfield neural networks with time delay. Nonlinear Analysis: Hybrid Systems, 2011, 5(3): 525-534 [3] Zhang Q, Wei X P, Xu J. Delay-dependent global stability condition for delayed Hopfield neural networks. Nonlinear Analysis: Real World Applications, 2007, 8(3): 997-1002 [4] Lian J, Zhang K, Feng Z. Stability analysis for switched Hopfield neural networks with time delay. Optimal Control Applications and Methods, 2012, 33(4): 433-444 [5] Lisena B. Exponential stability of Hopfield neural networks with impulses. Nonlinear Analysis: Real World Applications, 2011, 12(4): 1923-1930 [6] Liu W, Fu C J, Hu H C. Global exponential stability of a class of Hopfield neural networks with delays. Neural Computing and Applications, 2011, 20(8): 1205-1209 [7] Shi P L, Dong L Z. Existence and exponential stability of anti-periodic solutions of Hopfield neural networks with impulses. Applied Mathematics and Computation, 2010, 216(2): 623-630 [8] Ahn C K. An H∞ approach to stability analysis of switched Hopfield neural networks with time-delay. Nonlinear Dynamics, 2010, 60(4): 703-711 [9] Gui Z J, Ge W G, Yang X S. Periodic oscillation for a Hopfield neural networks with neutral delays. Physics Letters A, 2007, 364(3-4): 267-273 [10] Xiao B. Existence and uniqueness of almost periodic solutions for a class of Hopfield neural networks with neutral delays. Applied Mathematics Letters, 2009, 22(4): 528-533 [11] Zong G D, Liu J, Zhang Y X, Hou L L. Delay-range-dependent exponential stability criteria and decay estimation for switched Hopfield neural networks of neutral type. Nonlinear Analysis: Hybrid Systems, 2010, 4(3): 583-592 [12] Xu S Y, Lam J, Ho D W C, Zhou Y. Delay-dependent exponential stability for a class of neural networks with time delays. Journal of Computational and Applied Mathematics, 2005, 183(1): 16-28 [13] Park J H, Kwon O M. Design of state estimator for neural networks of neutral-type. Applied Mathematics and Computation, 2008, 202(1): 360-369 [14] Liao C W, Lu C Y. Passivity analysis for uncertain time-varying delayed neural networks with neutral type. In: Proceedings of the 2nd International Conference on Innovative Computing, Information and Control. Kumamoto, Japan: IEEE, 2007. 70 [15] Mao X Z, Li X, Liu J P. New robust stability criterion for neural networks of neutral type with time-varying delays. In: Proceedings of the 4th International Conference on Natural Computation. Ji’nan, China: IEEE, 2008. 491-494 [16] Zhu J, Zhang Q L, Yang C Y. Delay-dependent robust stability for Hopfield neural networks of neutral-type. Neurocomputing, 2009, 72(10-12): 2609-2617 [17] Li Q P, Li W L. Exponential stability on a class of delayed neural networks of neutral type. In: Proceedings of the 29th Chinese Control Conference. Beijing, China: IEEE, 2010. 2402-2406 [18] Mahmoud M S, Ismail A. Improved results on robust exponential stability criteria for neutral-type delayed neural networks. Applied Mathematics and Computation, 2010, 217(7): 3011-3019
点击查看大图
计量
- 文章访问数: 1630
- HTML全文浏览量: 94
- PDF下载量: 1107
- 被引次数: 0