| 187 | 1 | 118 |
| 下载次数 | 被引频次 | 阅读次数 |
基于全新的控制协议，研究了同时具有惯性项和忆阻项的神经网络预设时间同步问题。文中所考虑的网络模型可以广泛应用于生物突触模拟，具有较好的生物神经网络特性。通过构造合适的Lyapunov函数，利用不等式技巧，提出了惯性忆阻神经网络预设时间同步准则。所提出的控制协议可以使系统在任意预先给定的时间内稳定，该时间与系统初值和控制参数等都无关。最后，通过数值仿真验证了所得理论结果的有效性。
Abstract：Based on a novel control protocol, the synchronization problem of predefined-time of neural networks with inertia and memristor is studied. The network model considered in this paper can be widely used to simulate biological synapses, and has good biological neural network characteristics. This paper proposes a predefined-time synchronization criterion for inertial memristive neural networks by constructing a suitable Lyapunov function and using inequality technique. Meanwhile, the proposed control protocol can make the system stable in predefined-time, which is independent of the initial value and control parameters. Finally, the numerical simulation verifies the validity of the proposed theoretical results.
[1] CHUA L O. Memristor:the missing circuit element[J]. IEEE Transactions on Circuit Theory, 1971, 18(5):507-519.
[2] PERSHIN Y V, DIVENTRA M. Experimental demonstration of associative memory with memristive neural networks[J].Neural Networks, 2010, 23(7):881-886.
[3] JO S H, CHANG T, EBONG I, et al. Nanoscale memristor device as synapse in neuromorphic systems[J]. Nano Letters,2010, 10(4):1297-1301.
[4] SAINI S J, SAINI J S. Secure communication using memristor based chaotic circuit[C]//Proceedings of the 2014International Conference on Parallel, Distributed and Grid Computing, December 11-13, 2014, Solan, India. New York:IEEE Xplore, 2015:159-163.
[5] WANG B, ZOUF C, CHENG J. A memristor-based chaotic system and its application in image encryption[J]. Optik,2018, 154:538-544.
[6] HU J, WANG J. Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays[C]//Proceedings of the 2010 International Joint Conference on Neural Networks, July 18-23, 2010, Barcelona, Spain.New York:IEEE Xplore, 2010:1-8.
[7] DI MARCO M, FORTI M, PANCIONI L. New conditions for global asymptotic stability of memristor neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(5):1822-1834.
[8] WU A L, ZENG Z G. Exponential stabilization of memristive neural networks with time delays[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(12):1919-1929.
[9] WANG Z S, DING S B, HUANG Z J, et al. Exponential stability and stabilization of delayed memristive neural networks based on quadratic convex combination method[J].IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(11):2337-2350.
[10] LIN S S, SHIH C W. Complete stability for standard cellular neural networks[J]. International Journal of Bifurcation and Chaos, 1999, 9(5):909-918.
[11] GUAN Z H, CHEN G R. On delayed impulsive Hopfield neural networks[J]. Neural Networks, 1999, 12(2):273-280.
[12] COHEN M A, GROSSBERG S. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks[J]. Advances in Psychology, 1987,42:288-308.
[13] BABCOCK K L, WESTERVELT R M. Stability and dynamics of simple electronic neural networks with added inertia[J]. Physica D:Nonlinear Phenomena, 1986, 23(1/2/3):464-469.
[14] WHEELER D W, SCHIEVEW C. Stability and chaos in an inertial two-neuron system[J]. Physi ca D:Nonlinear Phenomena, 1997, 105(4):267-284.
[15] LIN D Y, CHEN X F, YU G P, et al. Global exponential synchronization via nonlinear feedback control for delayed inertial memristor-based quaternion-valued neural networks with impulses[J]. Applied Mathematics and Computation, 2021, 401:126093.
[16] ZHANG W, HUANG T W, HE X, et al. Global exponential stability of inertial memristor-based neural networks with time-varying delays and impulses[J]. Neural Networks, 2017, 95:102-109.
[17] WANG L M, ZENG Z G, ZONG X F, et al. Finite-time stabilization of memristor-based inertial neural networks with discontinuous activations and distributed delays[J].Journal of the Franklin Institute, 2019, 356(6):3628-3643.
[18] WEI F, CHENG C, WANG W B. Finite-time stabilization of memristor-based inertial neural networks with timevarying delays combined with interval matrix method[J].Knowledge-Based Systems, 2021, 230:107395.
[19] POLYAKOV A. Nonlinear feedback design for fixed-time stabilization of linear control systems[J]. IEEE Transactions on Automatic Control, 2012, 57(8):2106-2110.
[20] UDHAYAKUMAR K, SHANMUGASUNDARAM S,JANANI K, et al. Fixed-time synchronization of delayed impulsive inertial neural networks with discontinuous activation functions via indefinite LKF method[J]. Journal of the Franklin Institute, 2022, 359(2):1361-1384.
[21] ZHANG L Z, YANG Y Q. Different control strategies for fixed-time synchronization of inertial memristive neural networks[J]. Neural Processing Let ters, 2022, 54(5):3657-3678.
[22] CHEN C, LI L X, PENG H P, et al. Fixed-time synchronization of inertial memristor-based neural networks with discrete delay[J]. Neural Networks, 2019, 109:81-89.
[23] GAO J, CHEN Y M. Finite-time and fixed-time synchronization for inertial memristive neural networks with timevarying delay and linear coupling[J]. IAENG International Journal of Applied Mathematics, 2022, 52(3):IJAM_52_3_02.
[24] LIN L X. Finite-time synchronization of memristor-based neural networks:energy cost estimation[J]. International Journal of Dynamics and Control, 2023, 11(2):738-747.
[25] LIN L X. Projective synchronization of two coupled Lorenz chaotic systems in predefined time[J]. International Journal of Dynamics and Control, 2022, 10(3):879-889.
[26] XIAO Q, HUANG Z K, ZENG Z G. Passivity analysis for memristor-based inertial neural networks with discrete and distributed delays[J]. IEEE Transactions on Systems, Man,and Cybernetics:Systems, 2019, 49(2):375-385.
[27] WANG L M, GE M F, HU J H, et al. Global stability and stabilization for inertial memristive neural networks with unbounded distributed delays[J]. Nonlinear Dynamics,2019, 95(2):943-955.
[28] LI N, ZHENGW X. Synchronization criteria for inertial memristor-based neural networks with linear coupling[J].Neural Networks, 2018, 106:260-270.
基本信息:
DOI：10.12194/j.ntu.20221207007
中图分类号:TP183;TN60
引用信息:
[1]蒋竺宴,刘小洋.惯性忆阻神经网络预设时间同步控制[J],2023,22(02):36-42+65.DOI:10.12194/j.ntu.20221207007.
基金信息:
国家自然科学基金面上项目（62276119）;; 江苏省研究生科研与实践创新计划项目（KYCX22＿2860）