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
收藏
页数：14
相关论文
共 49 条
[1]   Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay [J].
Ahn, Choon Ki .
INFORMATION SCIENCES, 2010, 180 (23) :4582-4594
[2]   Stability analysis of recurrent neural networks with piecewise constant argument of generalized type [J].
Akhmet, M. U. ;
Arugaslan, D. ;
Yilmaz, E. .
NEURAL NETWORKS, 2010, 23 (07) :805-811
[3]   On the global dissipativity of dynamical neural networks with time delays [J].
Arik, S .
PHYSICS LETTERS A, 2004, 326 (1-2) :126-132
[4]   Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays [J].
Cao, Jinde ;
Yuan, Kun ;
Li, Han-Xiong .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06) :1646-1651
[5]   A neural network solution for fixed-final time optimal control of nonlinear systems [J].
Cheng, Tao ;
Lewis, Frank L. ;
Abu-Khalaf, Murad .
AUTOMATICA, 2007, 43 (03) :482-490
[6]   State constrained feedback stabilization [J].
Clarke, FH ;
Stern, RJ .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2003, 42 (02) :422-441
[7]   Stochastic nonlinear stabilization .2. Inverse optimality [J].
Deng, H ;
Krstic, M .
SYSTEMS & CONTROL LETTERS, 1997, 32 (03) :151-159
[8]   Inverse optimal control of stochastic systems driven by Levy processes [J].
Do, K. D. .
AUTOMATICA, 2019, 107 :539-550
[9]   Mean square exponential stability of discrete-time Markov switched stochastic neural networks with partially unstable subsystems and mixed delays [J].
Fan, Lina ;
Zhu, Quanxin .
INFORMATION SCIENCES, 2021, 580 :243-259
[10]   Inverse optimality in robust stabilization [J].
Freeman, RA ;
Kokotovic, PV .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1996, 34 (04) :1365-1391
12345