Continuous and discrete zeroing neural network for a class of multilayer dynamic system

被引：2

作者：

Xue, Yuting ^{[1
]}

Sun, Jitao ^{[1
,2
]}

Qian, Ying ^{[3
]}

机构：

[1] Tongji Univ, Sch Math Sci, Shanghai 200092, Peoples R China

[2] Zhejiang Normal Univ, Sch Math & Comp Sci, Jinhua 321004, Zhejiang, Peoples R China

[3] Vanderbilt Univ, Dept Elect & Comp Engn, 221 Kirkland Hall, Nashville, TN 37235 USA

来源：

NEUROCOMPUTING | 2022年 / 493卷

基金：

中国国家自然科学基金;

关键词：

Multilayer dynamic system; Zeroing neural network; Nonlinear activation function; Noise-tolerant; FINITE-TIME CONVERGENCE; ACTIVATION FUNCTIONS; ZNN; EQUATION; MODEL;

D O I：

10.1016/j.neucom.2022.04.056

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Multilayer dynamic system is widely used in industry and other fields. Different from common systems, multilayer dynamic system has complex structure leading to challenges for research. In this paper, we study zeroing neural network(ZNN) models for a class of multilayer dynamic system(MLDS). In the case of continuous time, continuous ZNN models for continuous MLDS (MLDS-linear-ZNN, MLDS-nonlinear-ZNN and MLDS-noise-tolerant-ZNN) are proposed based on ZNN design method with theoretical analysis. In the discrete case concurrently, discrete ZNN models (MLDS-linear-mDZNN, MLDS-nonlinear-mDZNN and MLDS-noise-tolerant-mDZNN) with m-step ZeaD formula, a new Zhang et al. discretization formula presented in previous paper, are put forward and corresponding discrete algorithms are obtained. Finally, numerical experiments are carried out to verify the superiority and maneuverability of ZNN models for MLDS proposed in this paper.(c) 2022 Elsevier B.V. All rights reserved.

引用

页码：244 / 252

页数：9

共 50 条

[41] Zeroing Neural Network for Solving Hybrid Multilayered Time-Varying Linear System
Li, Jian
Yao, Ruiling
Feng, Yan
Wang, Shasha
Zhu, Xinhui
IEEE ACCESS, 2020, 8 : 199406 - 199414
[42] A Multilayer Neural Network Based Identification and Control Scheme for a Class of Nonlinear Discrete-Time Systems with Asymptotic Stability Guarantees
Thumati, Balaje T.
Jagannathan, S.
MED: 2009 17TH MEDITERRANEAN CONFERENCE ON CONTROL & AUTOMATION, VOLS 1-3, 2009, : 540 - 545
[43] DYNAMIC EQUIVALENCE IN A CLASS OF NONLINEAR NEURAL NETWORK MODELS
BORMANN, D
ZEITSCHRIFT FUR PHYSIK B-CONDENSED MATTER, 1990, 79 (02): : 307 - 315
[44] Control of a class of nonlinear discrete-time systems using multilayer neural networks
Jagannathan, S
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (05): : 1113 - 1120
[45] Noise-tolerate and adaptive coefficient zeroing neural network for solving dynamic matrix square root
Xiao, Xiuchun
Jiang, Chengze
Mei, Qixiang
Zhang, Yudong
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2024, 9 (01) : 167 - 177
[46] Low-Computational-Complexity Zeroing Neural Network Model for Solving Systems of Dynamic Nonlinear Equations
Zheng, Kangze
Li, Shuai
Zhang, Yunong
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (07) : 4368 - 4379
[47] Dynamic Preservation for a Class of Semi-Discrete Recurrent Neural Networks
Jia, Songfang
Chen, Yanheng
IEEE ACCESS, 2021, 9 : 89336 - 89343
[48] A novel extended Li zeroing neural network for matrix inversion
Gerontitis, Dimitrios
Mo, Changxin
Stanimirovic, Predrag S.
Tzekis, Panagiotis
Katsikis, Vasilios N.
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (19): : 14129 - 14152
[49] NEURAL NETWORK SIMULATION OF A DISCRETE MODEL OF CONTINUOUS EFFECTS OF IRRELEVANT STIMULI
MOLENAAR, PCM
ACTA PSYCHOLOGICA, 1990, 74 (2-3) : 237 - 258
[50] Bifurcation Analysis in a Class of Neural Network Models with Discrete and Distributed Delays
Xu Wenying
Cao Jinde
2014 33RD CHINESE CONTROL CONFERENCE (CCC), 2014, : 6019 - 6024

← 1 2 3 4 5 →