Observer-based Ho, control of memristor-based neural networks with unbounded time-varying delays

被引：3
作者：
Meng, Xianhe [1 ]
Wang, Yantao [1 ,2 ]
Liu, Chunyan [3 ]
机构：
[1] Heilongjiang Univ, Sch Math Sci, Harbin 150080, Peoples R China
[2] Heilongjiang Univ, Heilongjiang Prov Key Lab Theory & Computat Comple, Harbin 150080, Peoples R China
[3] Heilongjiang Univ, Sch Informat Management, Harbin 150080, Peoples R China
来源：
NEUROCOMPUTING | 2023年 / 549卷
基金：
中国国家自然科学基金;
关键词：
Memristor-based neural networks; Unbounded time-varying delays; Observer-based H o; control; Observer; Controller; EXPONENTIAL STABILITY; INFINITY CONTROL; STATE ESTIMATION; DESIGN; DISCRETE; SYSTEMS; INPUT;
D O I：
10.1016/j.neucom.2023.126357
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This work is devoted to developing observer-based Ho, control of memristor-based neural networks with unbounded time-varying delays. A suitable observer is first designed, and then the controller is implemented based on the estimated states. Taking into account the dynamic equation of the MNN and that of the observer error, an augmented closed-loop system is given. By proposing a system solutionsbased estimation method, sufficient conditions are obtained to guarantee that the augmented system is globally exponentially stable and satisfies a prescribed Ho, performance level. This approach requires neither model transformation nor the construction of Lyapunov-Krasovskii functionals. In addition, the obtained sufficient conditions contain only a few scalar inequalities, which can be easily addressed by MATLAB. Finally, illustrative simulations are given to test the validity of the theoretical results.& COPY; 2023 Elsevier B.V. All rights reserved.
引用
收藏
页数：13
相关论文
共 50 条
  • [41] Passivity and Passification of Memristor-Based Recurrent Neural Networks With Additive Time-Varying Delays
    Rakkiyappan, Rajan
    Chandrasekar, Arunachalam
    Cao, Jinde
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (09) : 2043 - 2057
  • [42] Exponential stability and periodicity of memristor-based recurrent neural networks with time-varying delays
    Zhang, Wei
    Li, Chuandong
    Huang, Tingwen
    INTERNATIONAL JOURNAL OF BIOMATHEMATICS, 2017, 10 (02)
  • [43] Periodic Dynamics for Memristor-based Bidirectional Associative Memory Neural Networks with Leakage Delays and Time-varying Delays
    Xu, Changjin
    Li, Peiluan
    INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2018, 16 (02) : 535 - 549
  • [44] Observer-based control for time-varying delay neural networks with nonlinear observation
    Phat, V. N.
    Fernando, T.
    Trinh, H.
    NEURAL COMPUTING & APPLICATIONS, 2014, 24 (7-8) : 1639 - 1645
  • [45] Passivity Analysis of Memristor-Based Complex-Valued Neural Networks with Time-Varying Delays
    Velmurugan, G.
    Rakkiyappan, R.
    Lakshmanan, S.
    NEURAL PROCESSING LETTERS, 2015, 42 (03) : 517 - 540
  • [46] Complete periodic adaptive antisynchronization of memristor-based neural networks with mixed time-varying delays
    Wu, Huaiqin
    Li, Ruoxia
    Ding, Sanbo
    Zhang, Xiaowei
    Yao, Rong
    CANADIAN JOURNAL OF PHYSICS, 2014, 92 (11) : 1337 - 1349
  • [47] Stability analysis of stochastic memristor-based recurrent neural networks with mixed time-varying delays
    Zhendong Meng
    Zhengrong Xiang
    Neural Computing and Applications, 2017, 28 : 1787 - 1799
  • [48] Dissipativity analysis of memristor-based complex-valued neural networks with time-varying delays
    Li, Xiaodi
    Rakkiyappan, R.
    Velmurugan, G.
    INFORMATION SCIENCES, 2015, 294 : 645 - 665
  • [49] Exponential synchronization of memristor-based neural networks with time-varying delay and stochastic perturbation
    Wang, Xin
    She, Kun
    Zhong, Shouming
    Cheng, Jun
    NEUROCOMPUTING, 2017, 242 : 131 - 139
  • [50] New results on periodic dynamics of memristor-based recurrent neural networks with time-varying delays
    Duan, Lian
    Guo, Zhenyuan
    NEUROCOMPUTING, 2016, 218 : 259 - 263
12345