Global inverse optimality for a class of recurrent neural networks with multiple proportional delays

被引：1

作者：

Ma, Weijun ^{[1
,2
]}

Guo, Xuhui ^{[3
]}

Wang, Huaizhu ^{[3
]}

Zheng, Yuanshi ^{[4
]}

机构：

[1] Ningxia Univ, Sch Informat Engn, Yinchuan 750021, Ningxia, Peoples R China

[2] Ningxia Univ, Ningxia Key Lab Artificial Intelligence & Informat, Yinchuan 750021, Ningxia, Peoples R China

[3] Ningxia Univ, Sch Adv Interdisciplinary Studies, Zhongwei 755000, Ningxia, Peoples R China

[4] Xidian Univ, Sch Mechanoelect Engn, Xian 710071, Peoples R China

来源：

INFORMATION SCIENCES | 2024年 / 662卷

基金：

中国国家自然科学基金;

关键词：

Input-to-state stability; Recurrent neural networks; Multiple proportional delays; Inverse optimality; NONLINEAR OPTIMAL-CONTROL; FINITE-TIME STABILITY; TO-STATE STABILITY; EXPONENTIAL STABILITY; ASYMPTOTIC STABILITY; STABILIZATION; DISCRETE; DISSIPATIVITY; DESIGN;

D O I：

10.1016/j.ins.2024.120240

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper formulates two novel theoretical designs of input -to -state stabilizing control for a class of recurrent neural networks with multiple proportional delays. The analysis tool developed in this paper is based on Lyapunov function and inverse optimality method, which does not require solving Hamilton-Jacobi-Bellman equations. Two inverse optimal feedback laws are constructed via the dimensions of state and input, which ensure the input -state stability for the considered system. When the dimensions of state and input are different, we establish a scalar function and give one of the control laws by Sontag's formula. Furthermore, the designs of inverse optimal control reach both global inverse optimality and global asymptotic stability of the system for some meaningful cost functional. Four numerical examples are provided to show the effectiveness of the inverse optimal control.

引用

页数：14

共 50 条

[1] Global Polynomial Stability of a Class of Impulsive Recurrent Neural Networks with Proportional Delays
Zhou L.-Q.
Song X.-H.
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2021, 50 (01): : 91 - 100
[2] On Global Dissipativity of Nonautonomous Neural Networks With Multiple Proportional Delays
Le Van Hien
Doan Thai Son
Hieu Trinh
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (01) : 225 - 231
[3] Global exponential stability of a class of impulsive recurrent neural networks with proportional delays via fixed point theory
Zhou, Liqun
Zhang, Yanyan
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2016, 353 (02): : 561 - 575
[4] Global Exponential Dissipativity of Impulsive Recurrent Neural Networks with Multi-proportional Delays
Liqun Zhou
Neural Processing Letters, 2021, 53 : 1435 - 1452
[5] Global Exponential Dissipativity of Impulsive Recurrent Neural Networks with Multi-proportional Delays
Zhou, Liqun
NEURAL PROCESSING LETTERS, 2021, 53 (02) : 1435 - 1452
[6] Global exponential periodicity and stability of recurrent neural networks with multi-proportional delays
Zhou, Liqun
Zhang, Yanyan
ISA TRANSACTIONS, 2016, 60 : 89 - 95
[7] Global exponential periodicity and stability of a class of memristor-based recurrent neural networks with multiple delays
Zhang, Guodong
Shen, Yi
Yin, Quan
Sun, Junwei
INFORMATION SCIENCES, 2013, 232 : 386 - 396
[8] Dissipativity of a class of cellular neural networks with proportional delays
Zhou, Liqun
NONLINEAR DYNAMICS, 2013, 73 (03) : 1895 - 1903
[9] Dissipativity of a class of cellular neural networks with proportional delays
Liqun Zhou
Nonlinear Dynamics, 2013, 73 : 1895 - 1903
[10] Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays
Cao, Jinde
Yuan, Kun
Li, Han-Xiong
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06): : 1646 - 1651

← 1 2 3 4 5 →