Finite-Time Passivity for Coupled Fractional-Order Neural Networks With Multistate or Multiderivative Couplings

被引:12
|
作者
Liu, Chen-Guang [1 ]
Wang, Jin-Liang [2 ,3 ]
Wu, Huai-Ning [4 ,5 ]
机构
[1] Tiangong Univ, Sch Comp Sci & Technol, Tianjin 300387, Peoples R China
[2] Tiangong Univ, Sch Comp Sci & Technol, Tianjin Key Lab Autonomous Intelligence Technol &, Tianjin 300387, Peoples R China
[3] Linyi Univ, Sch Informat Sci & Technol, Linyi 276005, Shandong, Peoples R China
[4] Beihang Univ, Sch Automat Sci & Elect Engn, Sci & Technol Aircraft Control Lab, Beijing 100191, Peoples R China
[5] Peng Cheng Lab, Shenzhen 518000, Peoples R China
基金
中国国家自然科学基金;
关键词
Couplings; Synchronization; Neural networks; Adaptive systems; Symmetric matrices; Stability criteria; Numerical stability; Coupled fractional-order neural networks (CFNNs); finite-time passivity (FTP); multiderivative couplings; multistate couplings; STABILITY ANALYSIS; STABILIZATION;
D O I
10.1109/TNNLS.2021.3132069
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This article mainly delves into the finite-time passivity (FTP) for coupled fractional-order neural networks with multistate couplings (CFNNMSCs) or coupled fractional-order neural networks with multiderivative couplings (CFNNMDCs). Distinguishing from the traditional FTP definitions, several concepts of FTP for fractional-order systems are given. On one hand, we present several sufficient conditions to ensure the FTP for CFNNMSCs by artfully designing a state-feedback controller and an adaptive state-feedback controller. On the other hand, by utilizing some inequality techniques, two sets of FTP criteria for CFNNMDCs are also established on the basis of the state-feedback and adaptive state-feedback controllers. Finally, numerical examples are used to demonstrate the validity of the derived FTP criteria.
引用
收藏
页码:5976 / 5987
页数:12
相关论文
共 50 条
  • [31] Finite-Time Guaranteed Cost Control of Caputo Fractional-Order Neural Networks
    Thuan Mai Viet
    Binh Tran Nguyen
    Huong Dinh Cong
    ASIAN JOURNAL OF CONTROL, 2020, 22 (02) : 696 - 705
  • [32] Finite-time stability criteria for a class of fractional-order neural networks with delay
    Liping Chen
    Cong Liu
    Ranchao Wu
    Yigang He
    Yi Chai
    Neural Computing and Applications, 2016, 27 : 549 - 556
  • [33] Finite-time synchronisation and passivity of coupled memristive neural networks
    Huang, Yan-Li
    Qiu, Shui-Han
    Ren, Shun-Yan
    INTERNATIONAL JOURNAL OF CONTROL, 2020, 93 (12) : 2824 - 2837
  • [34] Finite-Time Passivity of Coupled Neural Networks with Multiple Weights
    Wang, Jin-Liang
    Xu, Meng
    Wu, Huai-Ning
    Huang, Tingwen
    IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2018, 5 (03): : 184 - 197
  • [35] Finite-time synchronization control of fractional-order memristive neural networks with time varying delays
    Liu, Yihong
    Sun, Yeguo
    PROCEEDINGS OF THE 32ND 2020 CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2020), 2020, : 3231 - 3237
  • [36] Finite-Time Stability for Fractional-Order Bidirectional Associative Memory Neural Networks with Time Delays
    Xu, Chang-Jin
    Li, Pei-Luan
    Pang, Yi-Cheng
    COMMUNICATIONS IN THEORETICAL PHYSICS, 2017, 67 (02) : 137 - 142
  • [37] Finite-time stability for fractional-order complex-valued neural networks with time delay
    Hu, Taotao
    He, Zheng
    Zhang, Xiaojun
    Zhong, Shouming
    APPLIED MATHEMATICS AND COMPUTATION, 2020, 365 (365)
  • [38] Passivity and passification of fractional-order memristive neural networks with time delays
    Ding, Zhixia
    Yang, Le
    Ye, Yanyan
    Li, Sai
    Huang, Zixin
    ISA TRANSACTIONS, 2023, 137 : 314 - 322
  • [39] New Criteria on Finite-Time Stability of Fractional-Order Hopfield Neural Networks With Time Delays
    Du, Feifei
    Lu, Jun-Guo
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (09) : 3858 - 3866
  • [40] New criteria on the finite-time stability of fractional-order BAM neural networks with time delay
    Xuemei Li
    Xinge Liu
    Shuailei Zhang
    Neural Computing and Applications, 2022, 34 : 4501 - 4517