RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems

Wei Yen Wang; Chin Ming Hong; Ming Feng Kuo; Yih Guang Leu; Tsu Tian Lee

doi:10.1109/ICSMC.2009.5346245

RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems

Wei Yen Wang, Chin Ming Hong, Ming Feng Kuo, Yih Guang Leu, Tsu Tian Lee

Department of Electrical Engineering

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

5 Citations (Scopus)

Abstract

This paper proposes a radial basis function neural network adaptive backstepping controller (RBFNN-ABC) for multiple-input multiple-output (MIMO) nonlinear systems in block-triangular form. The control scheme incorporates the adaptive neural backstepping design technique with a first-order filter at each step of the backstepping design to avoid the higher-order derivative problem, which is generated by the backstepping design. This problem may create an unpredictable and unfavorable influence on control performance because higher-order derivative term errors are introduced into the neural approximation model. Finally, simulation results demonstrate that the output tracking error between the plant output and the desired reference can be made arbitrarily small.

Original language	English
Title of host publication	Proceedings 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009
Pages	4946-4951
Number of pages	6
DOIs	https://doi.org/10.1109/ICSMC.2009.5346245
Publication status	Published - 2009
Event	2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009 - San Antonio, TX, United States Duration: 2009 Oct 11 → 2009 Oct 14

Other

Other	2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009
Country	United States
City	San Antonio, TX
Period	2009/10/11 → 2009/10/14

Keywords

Adaptive
Backstepping
MIMO nonlinear systems
Radial basis function (RBF) neural networks (NNs)

ASJC Scopus subject areas

Electrical and Electronic Engineering
Control and Systems Engineering
Human-Computer Interaction

Access to Document

10.1109/ICSMC.2009.5346245

Fingerprint Dive into the research topics of 'RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems'. Together they form a unique fingerprint.

Cite this

RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems. / Wang, Wei Yen ; Hong, Chin Ming; Kuo, Ming Feng; Leu, Yih Guang; Lee, Tsu Tian.

Proceedings 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009. 2009. p. 4946-4951 5346245.

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

Wang, WY , Hong, CM, Kuo, MF, Leu, YG & Lee, TT 2009, RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems. in Proceedings 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009., 5346245, pp. 4946-4951, 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009, San Antonio, TX, United States, 2009/10/11. https://doi.org/10.1109/ICSMC.2009.5346245

@inproceedings{1778f54eaf9347af8ede061cbdd7ce65,

title = "RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems",

abstract = "This paper proposes a radial basis function neural network adaptive backstepping controller (RBFNN-ABC) for multiple-input multiple-output (MIMO) nonlinear systems in block-triangular form. The control scheme incorporates the adaptive neural backstepping design technique with a first-order filter at each step of the backstepping design to avoid the higher-order derivative problem, which is generated by the backstepping design. This problem may create an unpredictable and unfavorable influence on control performance because higher-order derivative term errors are introduced into the neural approximation model. Finally, simulation results demonstrate that the output tracking error between the plant output and the desired reference can be made arbitrarily small.",

keywords = "Adaptive, Backstepping, MIMO nonlinear systems, Radial basis function (RBF) neural networks (NNs)",

author = "Wang, {Wei Yen} and Hong, {Chin Ming} and Kuo, {Ming Feng} and Leu, {Yih Guang} and Lee, {Tsu Tian}",

year = "2009",

doi = "10.1109/ICSMC.2009.5346245",

language = "English",

isbn = "9781424427949",

pages = "4946--4951",

booktitle = "Proceedings 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009",

note = "2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009 ; Conference date: 11-10-2009 Through 14-10-2009",

}

TY - GEN

T1 - RBF neural network adaptive backstepping controllers for MIMO nonaffine nonlinear systems

AU - Wang, Wei Yen

AU - Hong, Chin Ming

AU - Kuo, Ming Feng

AU - Leu, Yih Guang

AU - Lee, Tsu Tian

PY - 2009

Y1 - 2009

N2 - This paper proposes a radial basis function neural network adaptive backstepping controller (RBFNN-ABC) for multiple-input multiple-output (MIMO) nonlinear systems in block-triangular form. The control scheme incorporates the adaptive neural backstepping design technique with a first-order filter at each step of the backstepping design to avoid the higher-order derivative problem, which is generated by the backstepping design. This problem may create an unpredictable and unfavorable influence on control performance because higher-order derivative term errors are introduced into the neural approximation model. Finally, simulation results demonstrate that the output tracking error between the plant output and the desired reference can be made arbitrarily small.

AB - This paper proposes a radial basis function neural network adaptive backstepping controller (RBFNN-ABC) for multiple-input multiple-output (MIMO) nonlinear systems in block-triangular form. The control scheme incorporates the adaptive neural backstepping design technique with a first-order filter at each step of the backstepping design to avoid the higher-order derivative problem, which is generated by the backstepping design. This problem may create an unpredictable and unfavorable influence on control performance because higher-order derivative term errors are introduced into the neural approximation model. Finally, simulation results demonstrate that the output tracking error between the plant output and the desired reference can be made arbitrarily small.

KW - Adaptive

KW - Backstepping

KW - MIMO nonlinear systems

KW - Radial basis function (RBF) neural networks (NNs)

UR - http://www.scopus.com/inward/record.url?scp=74849105230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74849105230&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2009.5346245

DO - 10.1109/ICSMC.2009.5346245

M3 - Conference contribution

AN - SCOPUS:74849105230

SN - 9781424427949

SP - 4946

EP - 4951

BT - Proceedings 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009

T2 - 2009 IEEE International Conference on Systems, Man and Cybernetics, SMC 2009

Y2 - 11 October 2009 through 14 October 2009

ER -