当前位置: X-MOL 学术Neurocomputing › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Master-Slave Synchronization of Neural Networks via Event-Triggered Dynamic Controller
Neurocomputing ( IF 5.5 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.neucom.2020.08.062
Yong Wang , Sanbo Ding , Ruoxia Li

Abstract This paper investigates the event-triggered dynamic feedback control for master–slave synchronization of neural networks with actuator saturation. Firstly, a novel event-triggered mechanism with an exponentially decaying term is proposed. It reduces the value of measure function, which corresponds to decrease the event-triggered frequency. Secondly, a dynamic feedback controller is designed to synchronize the neural networks. In this way, the control input is described as a specific time-varying signal between two consecutive event-triggered instants. Thirdly, by constructing Lyapunov functional and utilizing the generalized sector condition, some sufficient synchronization criteria are established via linear matrix inequalities. Whereafter, the co-designed problem of control gains and triggering parameters is discussed. The rigorous mathematical analysis is provided to show that the presented event-triggered mechanism can eliminate the Zeno behavior. Finally, a numerical example is employed to illustrate the effectiveness of the proposed approach.

中文翻译:

通过事件触发的动态控制器实现神经网络的主从同步

摘要 本文研究了用于执行器饱和的神经网络主从同步的事件触发动态反馈控制。首先,提出了一种具有指数衰减项的新型事件触发机制。它降低了测量函数的值,这对应于降低事件触发频率。其次,设计了一个动态反馈控制器来同步神经网络。这样,控制输入被描述为两个连续事件触发时刻之间的特定时变信号。第三,通过构造Lyapunov泛函并利用广义扇区条件,通过线性矩阵不等式建立了一些充分的同步准则。随后,讨论了控制增益和触发参数的协同设计问题。提供了严格的数学分析以表明所提出的事件触发机制可以消除 Zeno 行为。最后,通过一个数值例子来说明所提出方法的有效性。
更新日期:2021-01-01
down
wechat
bug