基于事件触发的不连续惯性神经网络有限时间同步

doi:10.13438/j.cnki.jdzk.2025.05.004

吉首大学学报（自然科学版） ›› 2025, Vol. 46 ›› Issue (5): 19-28.DOI: 10.13438/j.cnki.jdzk.2025.05.004

基于事件触发的不连续惯性神经网络有限时间同步

曾智源，戴厚平，陈腾

(吉首大学数学与统计学院，湖南吉首 416000)

出版日期:2025-09-25 发布日期:2025-11-07
作者简介:曾智源(2001—),男,湖南娄底人,吉首大学数学与统计学院硕士生,主要从事非线性系统控制研究
基金资助:
国家自然科学基金地区资助项目（12461047）

Finite-Time Synchronization of Discontinuous Inertial Neural Networks Based on Event-Triggered Mechanism

ZENG Zhiyuan,DAI Houping,CHEN Teng

(College of Mathematics and Statistics,Jishou University,Jishou 416000,Hunan China)

Online:2025-09-25 Published:2025-11-07

摘要/Abstract

摘要：研究了一类具有不连续激活函数的时滞惯性神经网络的有限时间事件触发控制问题.通过变量替换方法,将二阶惯性神经网络转化为一阶神经网络形式.基于不连续激活函数的特性,采用Filippov解框架定义了神经网络的解,结合有限时间稳定性理论设计了一款新的事件触发控制器,并限制触发间隔以避免芝诺现象发生.在此基础上,推导出网络实现有限时间同步的判别准则,以确保该类二阶惯性神经网络在有限时间内实现同步.

关键词： 事件触发控制, 惯性神经网络, 有限时间同步, 时滞

Abstract: The finite-time event-triggered control problem of a class of time-delay inertial neural networks with discontinuous activation functions is studied.The second-order inertial neural network is transformed into the form of a first-order neural network through the variable substitution method.Based on the characteristics of discontinuous activation functions,the solution of the neural network is defined using the Filippov solution framework.A new event-triggered controller is designed in combination with the finite-time stability theory,and the trigger interval is restricted to avoid the Zeno phenomenon.On this basis,the discrimination criteria for the network to achieve finite-time synchronization are derived to ensure that this type of second-order inertial neural network achieves synchronization within a finite time.

Key words: event triggering mechanism, inertial neural network, finite time synchronization, time-lag

曾智源, 戴厚平, 陈腾. 基于事件触发的不连续惯性神经网络有限时间同步[J]. 吉首大学学报（自然科学版）, 2025, 46(5): 19-28.

ZENG Zhiyuan, DAI Houping, CHEN Teng. Finite-Time Synchronization of Discontinuous Inertial Neural Networks Based on Event-Triggered Mechanism [J]. Journal of Jishou University(Natural Sciences Edition), 2025, 46(5): 19-28.

参考文献

[1] MCCULLOCH WARREN S,PITTS WALTER.A Logical Calculus of the Ideas Immanent in Nervous Activity[J].The Bulletin of Mathematical Biophysics,1943,5(4):115-133.
[2] ZHANG Jin,PENG Chen.Synchronization of Master-Slave Neural Networks with a Decentralized Event Triggered Communication Scheme[J].Neurocomputing,2016,173(3):1824-1831.
[3] SANGIORGIO MATTEO,DERCOLE FABIO,GUARISO GIORGIO.Forecasting of Noisy Chaotic Systems with Deep Neural Networks[J].Chaos Solitons Fractals,2021,153:111570.DOI:10.1016/j.chaos.2021.111570.
[4] LI Hongyi,WANG Chuan,SHI Peng,et al.New Passivity Results for Uncertain Discrete-Time Stochastic Neural Networks with Mixed Time Delays[J].Neurocomputing,2010,73(16):3291-3299.
[5] GE Chao,PARK JU H,HUA Changchun,et al.Robust Passivity Analysis for Uncertain Neural Net Works with Discrete and Distributed Time-Varying Delays[J].Neurocomputing,2019,364:330-337.
[6] 王宇,张诗茹,张渝佶,等.比例时滞神经网络的全局多项式镇定性[J].吉首大学学报(自然科学版),2022,43(3):15-25.
[7] LI Wenhua,GAO Xingbao,LI Ruoxia.Stability and Synchronization Control of Inertial Neural Networks with Mixed Delays[J].Applied Mathematics and Computation,2020,367:124779.DOI:10.1016/j.amc.2019.124779.
[8] 张国东,龙常青.带有混合时滞的惯性神经网络系统的反同步控制[J].中南民族大学学报(自然科学版),2020,39(3):321-326.
[9] CHEN Yonggang,ZHANG Nannan,YANG Juanjuan.A Survey of Recent Advances on Stability Analysis,State Estimation and Synchronization Control for Neural Networks[J].Neurocomputing,2023,515:26-36.
[10] BHAT SANJAY P,BERNSTEIN DENNIS S.Finite-Time Stability of Continuous Autonomous Systems[J].SIAM Journal on Control and Optimization,2000,38(3):751-766.
[11] BURTON T A.Uniform Asymptotic Stability in Functional Differential Equations[J].Proceedings of the American Mathematical Society,1978,68(2):195-199.
[12] LI Ning,SUN Haiyi,JING Xin,et al.Dynamic Modeling and Aperiodically Intermittent Strategy for Adaptive Finite-Time Synchronization Control of the Multi-Weighted Complex Transportation Networks with Multiple Delays[J].Chinese Physics B,2021,30(9):184-193.
[13] CHENG Jun,PARK JU H,KARIMI HAMID REZA,et al.A Flexible Terminal Approach to Sampled-Data Exponentially Synchronization of Markovian Neural Networks with Time-Varying Delayed Signals[J].IEEE Transactions on Cybernetics,2018,48(8):2232-2244.
[14] WEN Shiping,ZENG Zhigang,CHEN MICHAEL Z Q,et al.Synchronization of Switched Neural Networks with Communication Delays via the Event-Triggered Control[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2334-2343.
[15] 周军,童东兵,陈巧玉.基于事件触发控制带有多时变时滞的主从系统同步[J].应用数学和力学,2019,40(12):1389-1398.
[16] 葛超,常晨蕾,姚征,等.基于事件触发机制的神经网络同步控制[J].计算机应用,2023,43(5):1641-1646.
[17] CUI Wenxia,WANG Zhenjie,JIN Wenbin.Fixed-Time Synchronization of Markovian Jump Fuzzy Cellular Neural Networks with Stochastic Disturbance and Time-Varying Delays[J].Fuzzy Sets and Systems,2021,411:68-84.
[18] ZHANG Wanli,YANG Ting.Finite-Time Synchronization of Discontinuous Network Systems via Two Control Schemes[J].Franklin Open,2024,6:100068.DOI:10.1016/j.fraope.2023.100068.
[19] KHALIL HASSAN K,GRIZZEL JESSY.Nonlinear Systems[M].Berlin,Germany:Prentice Hall Upper Saddle River,2002:162-179.
[20] 王君蓝.基于非降阶法的时滞高阶惯性神经网络的分析与设计[D].哈尔滨：黑龙江大学,2022:5-20.

基于事件触发的不连续惯性神经网络有限时间同步

Finite-Time Synchronization of Discontinuous Inertial Neural Networks Based on Event-Triggered Mechanism

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价