Stable adaptive control for nonlinear systems using neural networks

Yang Shi; Chundi Mu; Weisheng Yan; Jun Li; Demin Xu

Stable adaptive control for nonlinear systems using neural networks

Yang Shi, Chundi Mu, Weisheng Yan, Jun Li, Demin Xu

School of Marine Science and Technology

Research output: Contribution to conference › Paper › peer-review

Abstract

Stability analysis of neural-network-based nonlinear control has presented great difficulties. For a class of affine nonlinear systems with uncertainties, we employed nonlinear-parameter-neural-networks(NPNN) to approximate on-line the unknown nonlinearities, estimate on-line the NPNN approximation error's bound, and then succeeded in designing the control law and the adaptive laws of NPNN's weights and the NPNN approximation error's bound. The stability of the closed-loop is proved by using Lyapunov theory. Simulation results show that the controller we proposed exhibits excellent tracking performance.

Original language	English
Pages	979-983
Number of pages	5
State	Published - 2000
Event	Proceedings of the 3th World Congress on Intelligent Control and Automation - Hefei, China Duration: 28 Jun 2000 → 2 Jul 2000

Conference

Conference	Proceedings of the 3th World Congress on Intelligent Control and Automation
Country/Territory	China
City	Hefei
Period	28/06/00 → 2/07/00

Keywords

Adaptive control
Affine nonlinear system with uncertainties
Nonlinear-parameter-neural-network
Stability

Cite this

@conference{aca9ed0cb90c43e19b25d3f89f49f743,

title = "Stable adaptive control for nonlinear systems using neural networks",

abstract = "Stability analysis of neural-network-based nonlinear control has presented great difficulties. For a class of affine nonlinear systems with uncertainties, we employed nonlinear-parameter-neural-networks(NPNN) to approximate on-line the unknown nonlinearities, estimate on-line the NPNN approximation error's bound, and then succeeded in designing the control law and the adaptive laws of NPNN's weights and the NPNN approximation error's bound. The stability of the closed-loop is proved by using Lyapunov theory. Simulation results show that the controller we proposed exhibits excellent tracking performance.",

keywords = "Adaptive control, Affine nonlinear system with uncertainties, Nonlinear-parameter-neural-network, Stability",

author = "Yang Shi and Chundi Mu and Weisheng Yan and Jun Li and Demin Xu",

year = "2000",

language = "英语",

pages = "979--983",

note = "Proceedings of the 3th World Congress on Intelligent Control and Automation ; Conference date: 28-06-2000 Through 02-07-2000",

}

TY - CONF

T1 - Stable adaptive control for nonlinear systems using neural networks

AU - Shi, Yang

AU - Mu, Chundi

AU - Yan, Weisheng

AU - Li, Jun

AU - Xu, Demin

PY - 2000

Y1 - 2000

N2 - Stability analysis of neural-network-based nonlinear control has presented great difficulties. For a class of affine nonlinear systems with uncertainties, we employed nonlinear-parameter-neural-networks(NPNN) to approximate on-line the unknown nonlinearities, estimate on-line the NPNN approximation error's bound, and then succeeded in designing the control law and the adaptive laws of NPNN's weights and the NPNN approximation error's bound. The stability of the closed-loop is proved by using Lyapunov theory. Simulation results show that the controller we proposed exhibits excellent tracking performance.

AB - Stability analysis of neural-network-based nonlinear control has presented great difficulties. For a class of affine nonlinear systems with uncertainties, we employed nonlinear-parameter-neural-networks(NPNN) to approximate on-line the unknown nonlinearities, estimate on-line the NPNN approximation error's bound, and then succeeded in designing the control law and the adaptive laws of NPNN's weights and the NPNN approximation error's bound. The stability of the closed-loop is proved by using Lyapunov theory. Simulation results show that the controller we proposed exhibits excellent tracking performance.

KW - Adaptive control

KW - Affine nonlinear system with uncertainties

KW - Nonlinear-parameter-neural-network

KW - Stability

UR - http://www.scopus.com/inward/record.url?scp=0034591853&partnerID=8YFLogxK

M3 - 论文

AN - SCOPUS:0034591853

SP - 979

EP - 983

T2 - Proceedings of the 3th World Congress on Intelligent Control and Automation

Y2 - 28 June 2000 through 2 July 2000

ER -

Stable adaptive control for nonlinear systems using neural networks

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this