Time-delay nonlinear system modelling via delayed neural networks

Jose De Jesús Rubio; Wen Yu; Xiaoou Li

doi:10.1109/WCICA.2006.1712374

Time-delay nonlinear system modelling via delayed neural networks

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, nonlinear systems on-line identification via delayed dynamic neural networks is studied. Dynamic series-parallel neural network model with time delay is persented and the stability conditions are derived using Lyapunov-Krasovskii approach. The conditions for passivity, asymptotic stability stability are established in some senses. All the results are described by linear matrix inequality (LMI). We conclude that the gradient algoritm for weight adjusment is stable and robust to any bounded uncertainties.

Original language	English
Title of host publication	Proceedings of the World Congress on Intelligent Control and Automation (WCICA)
Pages	119-123
Number of pages	5
DOIs	https://doi.org/10.1109/WCICA.2006.1712374
State	Published - 2006
Externally published	Yes
Event	6th World Congress on Intelligent Control and Automation, WCICA 2006 - Dalian, China Duration: 21 Jun 2006 → 23 Jun 2006

Publication series

Name	Proceedings of the World Congress on Intelligent Control and Automation (WCICA)
Volume	1

Conference

Conference	6th World Congress on Intelligent Control and Automation, WCICA 2006
Country/Territory	China
City	Dalian
Period	21/06/06 → 23/06/06

Keywords

Identification
Neural networks
Time-delay

Access to Document

10.1109/WCICA.2006.1712374

Cite this

@inproceedings{d61c3382f4974b7bb3741faaf88290f5,

title = "Time-delay nonlinear system modelling via delayed neural networks",

abstract = "In this paper, nonlinear systems on-line identification via delayed dynamic neural networks is studied. Dynamic series-parallel neural network model with time delay is persented and the stability conditions are derived using Lyapunov-Krasovskii approach. The conditions for passivity, asymptotic stability stability are established in some senses. All the results are described by linear matrix inequality (LMI). We conclude that the gradient algoritm for weight adjusment is stable and robust to any bounded uncertainties.",

keywords = "Identification, Neural networks, Time-delay",

author = "{De Jes{\'u}s Rubio}, Jose and Wen Yu and Xiaoou Li",

year = "2006",

doi = "10.1109/WCICA.2006.1712374",

language = "Ingl{\'e}s",

isbn = "1424403324",

series = "Proceedings of the World Congress on Intelligent Control and Automation (WCICA)",

pages = "119--123",

booktitle = "Proceedings of the World Congress on Intelligent Control and Automation (WCICA)",

note = "6th World Congress on Intelligent Control and Automation, WCICA 2006 ; Conference date: 21-06-2006 Through 23-06-2006",

}

De Jesús Rubio, J, Yu, W & Li, X 2006, Time-delay nonlinear system modelling via delayed neural networks. in Proceedings of the World Congress on Intelligent Control and Automation (WCICA)., 1712374, Proceedings of the World Congress on Intelligent Control and Automation (WCICA), vol. 1, pp. 119-123, 6th World Congress on Intelligent Control and Automation, WCICA 2006, Dalian, China, 21/06/06. https://doi.org/10.1109/WCICA.2006.1712374

Time-delay nonlinear system modelling via delayed neural networks. / De Jesús Rubio, Jose; Yu, Wen; Li, Xiaoou.
Proceedings of the World Congress on Intelligent Control and Automation (WCICA). 2006. p. 119-123 1712374 (Proceedings of the World Congress on Intelligent Control and Automation (WCICA); Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Time-delay nonlinear system modelling via delayed neural networks

AU - De Jesús Rubio, Jose

AU - Yu, Wen

AU - Li, Xiaoou

PY - 2006

Y1 - 2006

N2 - In this paper, nonlinear systems on-line identification via delayed dynamic neural networks is studied. Dynamic series-parallel neural network model with time delay is persented and the stability conditions are derived using Lyapunov-Krasovskii approach. The conditions for passivity, asymptotic stability stability are established in some senses. All the results are described by linear matrix inequality (LMI). We conclude that the gradient algoritm for weight adjusment is stable and robust to any bounded uncertainties.

AB - In this paper, nonlinear systems on-line identification via delayed dynamic neural networks is studied. Dynamic series-parallel neural network model with time delay is persented and the stability conditions are derived using Lyapunov-Krasovskii approach. The conditions for passivity, asymptotic stability stability are established in some senses. All the results are described by linear matrix inequality (LMI). We conclude that the gradient algoritm for weight adjusment is stable and robust to any bounded uncertainties.

KW - Identification

KW - Neural networks

KW - Time-delay

UR - http://www.scopus.com/inward/record.url?scp=34047203035&partnerID=8YFLogxK

U2 - 10.1109/WCICA.2006.1712374

DO - 10.1109/WCICA.2006.1712374

M3 - Contribución a la conferencia

AN - SCOPUS:34047203035

SN - 1424403324

SN - 9781424403325

T3 - Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

SP - 119

EP - 123

BT - Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

T2 - 6th World Congress on Intelligent Control and Automation, WCICA 2006

Y2 - 21 June 2006 through 23 June 2006

ER -

Time-delay nonlinear system modelling via delayed neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this