A grey-box neural network based identification model for nonlinear dynamic systems

Zhaohui Cen, Jiaolong Wei, Rui Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents a Model Identification scheme for a class of nonlinear dynamic systems. A novel Grey-Box Neural Network Model (GBNNM), including Multi-Layer Perception (MLP) Neural Network (NN) and integrators, is proposed to approximate both the nonlinearity and dynamics of the object system. A self-defined exciting strategy is introduced into NN training to improve its generalization ability. Unlike previous NN based model identification methods, GBNNM directly inherits system dynamics and models nonlinearities separately. This accords well with the expected model and is easy to implement. Then, the proposed scheme is applied in a high-fidelity Reaction Wheel (RW) in Satellite Attitude Control System (SACS). The proposed scheme using GBNNM is compared with those using static NN or dynamic NN in the same scenario. Results demonstrate the effectiveness and superiority of the scheme.

Original languageEnglish
Title of host publicationProceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011
Pages300-307
Number of pages8
DOIs
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event4th International Workshop on Advanced Computational Intelligence, IWACI 2011 - Wuhan, Hubei, China
Duration: 19 Oct 201121 Oct 2011

Other

Other4th International Workshop on Advanced Computational Intelligence, IWACI 2011
CountryChina
CityWuhan, Hubei
Period19/10/1121/10/11

Fingerprint

Identification (control systems)
Dynamical systems
Neural networks
Attitude control
Wheels
Satellites
Control systems

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Cen, Z., Wei, J., & Jiang, R. (2011). A grey-box neural network based identification model for nonlinear dynamic systems. In Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011 (pp. 300-307). [6160021] https://doi.org/10.1109/IWACI.2011.6160021

A grey-box neural network based identification model for nonlinear dynamic systems. / Cen, Zhaohui; Wei, Jiaolong; Jiang, Rui.

Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011. 2011. p. 300-307 6160021.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cen, Z, Wei, J & Jiang, R 2011, A grey-box neural network based identification model for nonlinear dynamic systems. in Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011., 6160021, pp. 300-307, 4th International Workshop on Advanced Computational Intelligence, IWACI 2011, Wuhan, Hubei, China, 19/10/11. https://doi.org/10.1109/IWACI.2011.6160021
Cen Z, Wei J, Jiang R. A grey-box neural network based identification model for nonlinear dynamic systems. In Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011. 2011. p. 300-307. 6160021 https://doi.org/10.1109/IWACI.2011.6160021
Cen, Zhaohui ; Wei, Jiaolong ; Jiang, Rui. / A grey-box neural network based identification model for nonlinear dynamic systems. Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011. 2011. pp. 300-307
@inproceedings{6bfeea3bdf7d421d9e3de5182f396325,
title = "A grey-box neural network based identification model for nonlinear dynamic systems",
abstract = "This paper presents a Model Identification scheme for a class of nonlinear dynamic systems. A novel Grey-Box Neural Network Model (GBNNM), including Multi-Layer Perception (MLP) Neural Network (NN) and integrators, is proposed to approximate both the nonlinearity and dynamics of the object system. A self-defined exciting strategy is introduced into NN training to improve its generalization ability. Unlike previous NN based model identification methods, GBNNM directly inherits system dynamics and models nonlinearities separately. This accords well with the expected model and is easy to implement. Then, the proposed scheme is applied in a high-fidelity Reaction Wheel (RW) in Satellite Attitude Control System (SACS). The proposed scheme using GBNNM is compared with those using static NN or dynamic NN in the same scenario. Results demonstrate the effectiveness and superiority of the scheme.",
author = "Zhaohui Cen and Jiaolong Wei and Rui Jiang",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/IWACI.2011.6160021",
language = "English",
isbn = "9781612843735",
pages = "300--307",
booktitle = "Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011",

}

TY - GEN

T1 - A grey-box neural network based identification model for nonlinear dynamic systems

AU - Cen, Zhaohui

AU - Wei, Jiaolong

AU - Jiang, Rui

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper presents a Model Identification scheme for a class of nonlinear dynamic systems. A novel Grey-Box Neural Network Model (GBNNM), including Multi-Layer Perception (MLP) Neural Network (NN) and integrators, is proposed to approximate both the nonlinearity and dynamics of the object system. A self-defined exciting strategy is introduced into NN training to improve its generalization ability. Unlike previous NN based model identification methods, GBNNM directly inherits system dynamics and models nonlinearities separately. This accords well with the expected model and is easy to implement. Then, the proposed scheme is applied in a high-fidelity Reaction Wheel (RW) in Satellite Attitude Control System (SACS). The proposed scheme using GBNNM is compared with those using static NN or dynamic NN in the same scenario. Results demonstrate the effectiveness and superiority of the scheme.

AB - This paper presents a Model Identification scheme for a class of nonlinear dynamic systems. A novel Grey-Box Neural Network Model (GBNNM), including Multi-Layer Perception (MLP) Neural Network (NN) and integrators, is proposed to approximate both the nonlinearity and dynamics of the object system. A self-defined exciting strategy is introduced into NN training to improve its generalization ability. Unlike previous NN based model identification methods, GBNNM directly inherits system dynamics and models nonlinearities separately. This accords well with the expected model and is easy to implement. Then, the proposed scheme is applied in a high-fidelity Reaction Wheel (RW) in Satellite Attitude Control System (SACS). The proposed scheme using GBNNM is compared with those using static NN or dynamic NN in the same scenario. Results demonstrate the effectiveness and superiority of the scheme.

UR - http://www.scopus.com/inward/record.url?scp=84858776395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858776395&partnerID=8YFLogxK

U2 - 10.1109/IWACI.2011.6160021

DO - 10.1109/IWACI.2011.6160021

M3 - Conference contribution

SN - 9781612843735

SP - 300

EP - 307

BT - Proceedings of 4th International Workshop on Advanced Computational Intelligence, IWACI 2011

ER -