《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (5): 1641-1646.DOI: 10.11772/j.issn.1001-9081.2022040588

• 前沿与综合应用 • 上一篇    

基于事件触发机制的神经网络同步控制

葛超1,2(), 常晨蕾1, 姚征1, 苏皓1,2   

  1. 1.华北理工大学 电气工程学院,河北 唐山 063210
    2.华北理工大学 唐山市半导体集成电路重点实验室,河北 唐山 063210
  • 收稿日期:2022-04-25 修回日期:2022-06-20 接受日期:2022-06-21 发布日期:2022-09-29 出版日期:2023-05-10
  • 通讯作者: 葛超
  • 作者简介:葛超(1980—),男,河北石家庄人,教授,博士,主要研究方向:网络化控制系统、时滞系统、神经网络、模糊系统 gechao365@126.com
    常晨蕾(1998—),女,河北唐山人,硕士研究生,主要研究方向:神经网络
    姚征(1978—),男,河北唐山人,副教授,硕士,主要研究方向:工业机器人系统建模与优化控制
    苏皓(1980—),男,河北唐山人,副教授,博士,主要研究方向:网络化控制系统。
  • 基金资助:
    河北省自然科学基金资助项目(F2021209006)

Synchronous control of neural network based on event-triggered mechanism

Chao GE1,2(), Chenlei CHANG1, Zheng YAO1, Hao SU1,2   

  1. 1.College of Electrical Engineering,North China University of Science and Technology,Tangshan Hebei 063210,China
    2.Tangshan Key Laboratory of Semiconductor Integrated Circuits,North China University of Science and Technology,Tangshan Hebei 063210,China
  • Received:2022-04-25 Revised:2022-06-20 Accepted:2022-06-21 Online:2022-09-29 Published:2023-05-10
  • Contact: Chao GE
  • About author:GE Chao, born in 1980, Ph. D., professor. His research interests include networked control systems, time-delay systems, neural network, fuzzy systems.
    CHANG Chenlei, born in 1998, M. S. candidate. Her research interests include neural network.
    YAO Zheng, born in 1978, M. S., associate professor. His research interests include modeling and optimal control of industrial robot system.
    SU Hao, born in 1980, Ph. D., associate professor. His research interests include networked control systems.
  • Supported by:
    Natural Science Foundation of Hebei Province(F2021209006)

摘要:

对于混合时滞神经网络同步控制中控制器存在随机摄动的问题,提出一种基于事件触发机制的非脆弱控制器。首先,使用一个服从伯努利分布的随机变量描述控制器增益摄动存在的随机性;其次,在神经网络同步控制过程中引入事件触发机制;接着,构造一个新颖的双边李雅普诺夫函数,充分考虑系统状态信息,同时利用改进的积分不等式对泛函导数进行放缩,得到同步误差系统指数稳定性的充分条件;最后,基于解耦技术设计了非脆弱控制器。通过仿真实例验证了所提控制器的有效性。实验结果表明,在四罐系统中,在相同采样周期下,与现有的指数衰减系数相比,所提控制器获得的指数衰减系数提升了0.16。

关键词: 神经网络, 事件触发机制, 指数同步, 非脆弱控制器, 李雅普诺夫函数

Abstract:

Concerning the problem of random perturbation of controller in synchronous control of neural network with mixed delays, a non-fragile controller based on event-triggered mechanism was proposed. Firstly, a random variable obeying Bernoulli distribution was used to describe the randomness of the existence of controller gain disturbance. Secondly, the event-triggered mechanism was introduced in the synchronous control process of the neural network. Next, a novel bilateral Lyapunov function was constructed to fully consider the system status information, while the functional derivatives were scaled by an improved integral inequality to obtain sufficient conditions for the exponential stability of the synchronization error system. Finally, a non-fragile controller was designed based on the decoupling technique. The effectiveness of the proposed controller was verified by simulation examples. Experimental results show that compared with the existing exponential attenuation coefficient under the same sampling period in the four-tank system, the exponential attenuation coefficient obtained by the proposed controller is improved by 0.16.

Key words: neural network, event-triggered mechanism, exponential synchronization, non-fragile controller, Lyapunov function

中图分类号: