Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network

Dongdong Zheng; Wenfang Xie

doi:10.1109/ACC.2015.7170998

Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network

Dongdong Zheng, Wenfang Xie

Concordia University

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

7 Citations (Scopus)

Abstract

A new identification algorithm for nonlinear singularly perturbed system using multi-time scales recurrent highorder neural networks is proposed in this paper. The high-order neural networks have simple structure and strong nonlinear approximation capability, which enables it to model the nonlinear singularly perturbed systems more accurately with less computation complexity, compared to multilayer neural networks. The optimal bounded ellipsoid algorithm, which is originally designed for discrete time systems, is introduced to update the weights of continuous multi-time scales neural networks. Compared to other widely used gradient-like updating methods, the on-line identification algorithm proposed in this paper can realize faster convergence, due to the adaptive 'learning rate' of the weights updating laws. The effectiveness of the proposed scheme is demonstrated by simulation results.

Original language	English
Title of host publication	ACC 2015 - 2015 American Control Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1824-1829
Number of pages	6
ISBN (Electronic)	9781479986842
DOIs	https://doi.org/10.1109/ACC.2015.7170998
Publication status	Published - 28 Jul 2015
Externally published	Yes
Event	2015 American Control Conference, ACC 2015 - Chicago, United States Duration: 1 Jul 2015 → 3 Jul 2015

Publication series

Name	Proceedings of the American Control Conference
Volume	2015-July
ISSN (Print)	0743-1619

Conference

Conference	2015 American Control Conference, ACC 2015
Country/Territory	United States
City	Chicago
Period	1/07/15 → 3/07/15

Access to Document

10.1109/ACC.2015.7170998

Cite this

Zheng, D., & Xie, W. (2015). Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network. In ACC 2015 - 2015 American Control Conference (pp. 1824-1829). Article 7170998 (Proceedings of the American Control Conference; Vol. 2015-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACC.2015.7170998

@inproceedings{2c86fec04c6947b38e0c732361d2a9a8,

title = "Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network",

abstract = "A new identification algorithm for nonlinear singularly perturbed system using multi-time scales recurrent highorder neural networks is proposed in this paper. The high-order neural networks have simple structure and strong nonlinear approximation capability, which enables it to model the nonlinear singularly perturbed systems more accurately with less computation complexity, compared to multilayer neural networks. The optimal bounded ellipsoid algorithm, which is originally designed for discrete time systems, is introduced to update the weights of continuous multi-time scales neural networks. Compared to other widely used gradient-like updating methods, the on-line identification algorithm proposed in this paper can realize faster convergence, due to the adaptive 'learning rate' of the weights updating laws. The effectiveness of the proposed scheme is demonstrated by simulation results.",

author = "Dongdong Zheng and Wenfang Xie",

note = "Publisher Copyright: {\textcopyright} 2015 American Automatic Control Council.; 2015 American Control Conference, ACC 2015 ; Conference date: 01-07-2015 Through 03-07-2015",

year = "2015",

month = jul,

day = "28",

doi = "10.1109/ACC.2015.7170998",

language = "English",

series = "Proceedings of the American Control Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1824--1829",

booktitle = "ACC 2015 - 2015 American Control Conference",

address = "United States",

}

Zheng, D & Xie, W 2015, Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network. in ACC 2015 - 2015 American Control Conference., 7170998, Proceedings of the American Control Conference, vol. 2015-July, Institute of Electrical and Electronics Engineers Inc., pp. 1824-1829, 2015 American Control Conference, ACC 2015, Chicago, United States, 1/07/15. https://doi.org/10.1109/ACC.2015.7170998

Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network. / Zheng, Dongdong; Xie, Wenfang.
ACC 2015 - 2015 American Control Conference. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1824-1829 7170998 (Proceedings of the American Control Conference; Vol. 2015-July).

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

TY - GEN

T1 - Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network

AU - Zheng, Dongdong

AU - Xie, Wenfang

PY - 2015/7/28

Y1 - 2015/7/28

N2 - A new identification algorithm for nonlinear singularly perturbed system using multi-time scales recurrent highorder neural networks is proposed in this paper. The high-order neural networks have simple structure and strong nonlinear approximation capability, which enables it to model the nonlinear singularly perturbed systems more accurately with less computation complexity, compared to multilayer neural networks. The optimal bounded ellipsoid algorithm, which is originally designed for discrete time systems, is introduced to update the weights of continuous multi-time scales neural networks. Compared to other widely used gradient-like updating methods, the on-line identification algorithm proposed in this paper can realize faster convergence, due to the adaptive 'learning rate' of the weights updating laws. The effectiveness of the proposed scheme is demonstrated by simulation results.

AB - A new identification algorithm for nonlinear singularly perturbed system using multi-time scales recurrent highorder neural networks is proposed in this paper. The high-order neural networks have simple structure and strong nonlinear approximation capability, which enables it to model the nonlinear singularly perturbed systems more accurately with less computation complexity, compared to multilayer neural networks. The optimal bounded ellipsoid algorithm, which is originally designed for discrete time systems, is introduced to update the weights of continuous multi-time scales neural networks. Compared to other widely used gradient-like updating methods, the on-line identification algorithm proposed in this paper can realize faster convergence, due to the adaptive 'learning rate' of the weights updating laws. The effectiveness of the proposed scheme is demonstrated by simulation results.

UR - http://www.scopus.com/inward/record.url?scp=84940941307&partnerID=8YFLogxK

U2 - 10.1109/ACC.2015.7170998

DO - 10.1109/ACC.2015.7170998

M3 - Conference contribution

AN - SCOPUS:84940941307

T3 - Proceedings of the American Control Conference

SP - 1824

EP - 1829

BT - ACC 2015 - 2015 American Control Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 American Control Conference, ACC 2015

Y2 - 1 July 2015 through 3 July 2015

ER -

Identification for nonlinear singularly perturbed system using recurrent high-order multi-time scales neural network

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this