Receding horizon neural H∞ control for a class of nonlinear unknown systems

Choon Ki Ahn; Soo Hee Han; Wook Hyun Kwon

doi:10.3182/20050703-6-cz-1902.00816

Receding horizon neural H_∞ control for a class of nonlinear unknown systems

Choon Ki Ahn, Soo Hee Han, Wook Hyun Kwon

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

Abstract

in this paper, we present new RHNHC (Receding Horizon Neural H _∞ Control) for nonlinear unknown systems. First, we propose LMI (Linear Matrix Inequality) condition on the terminal weighting matrix for stabilizing RHNHC. Under this condition, noninceasing monotonicity of the saddle point value of the finite horizon dynamic game is shown to be guaranteed. Then, we propose RHNHC for nonlinear unknown systems which guarantees the infinite horizon H_∞ norm bound and the internal stability of the closed-loop systems. Since RHNHC can deal with input and state constraints in optimization problem effectively, it does not cause an instability problem or give a poor performance in contrast to the existing neural H_∞ control schemes.

Original language	English
Title of host publication	Proceedings of the 16th IFAC World Congress, IFAC 2005
Publisher	IFAC Secretariat
Pages	960-965
Number of pages	6
ISBN (Print)	008045108X, 9780080451084
DOIs	https://doi.org/10.3182/20050703-6-cz-1902.00816
Publication status	Published - 2005
Externally published	Yes

Publication series

Name	IFAC Proceedings Volumes (IFAC-PapersOnline)
Volume	16
ISSN (Print)	1474-6670

Keywords

Neural networks
Nonlinear systems
Receding horizon control
Unknown systems

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.3182/20050703-6-cz-1902.00816

Cite this

@inproceedings{90cbd81669a341a18c8e7db008c2794b,

title = "Receding horizon neural H∞ control for a class of nonlinear unknown systems",

abstract = "in this paper, we present new RHNHC (Receding Horizon Neural H ∞ Control) for nonlinear unknown systems. First, we propose LMI (Linear Matrix Inequality) condition on the terminal weighting matrix for stabilizing RHNHC. Under this condition, noninceasing monotonicity of the saddle point value of the finite horizon dynamic game is shown to be guaranteed. Then, we propose RHNHC for nonlinear unknown systems which guarantees the infinite horizon H∞ norm bound and the internal stability of the closed-loop systems. Since RHNHC can deal with input and state constraints in optimization problem effectively, it does not cause an instability problem or give a poor performance in contrast to the existing neural H∞ control schemes.",

keywords = "Neural networks, Nonlinear systems, Receding horizon control, Unknown systems",

author = "Ahn, {Choon Ki} and Han, {Soo Hee} and Kwon, {Wook Hyun}",

note = "Funding Information: 1 This work was supported by the SNU BK21-IT Program.",

year = "2005",

doi = "10.3182/20050703-6-cz-1902.00816",

language = "English",

isbn = "008045108X",

series = "IFAC Proceedings Volumes (IFAC-PapersOnline)",

publisher = "IFAC Secretariat",

pages = "960--965",

booktitle = "Proceedings of the 16th IFAC World Congress, IFAC 2005",

}

TY - GEN

T1 - Receding horizon neural H∞ control for a class of nonlinear unknown systems

AU - Ahn, Choon Ki

AU - Han, Soo Hee

AU - Kwon, Wook Hyun

N1 - Funding Information: 1 This work was supported by the SNU BK21-IT Program.

PY - 2005

Y1 - 2005

N2 - in this paper, we present new RHNHC (Receding Horizon Neural H ∞ Control) for nonlinear unknown systems. First, we propose LMI (Linear Matrix Inequality) condition on the terminal weighting matrix for stabilizing RHNHC. Under this condition, noninceasing monotonicity of the saddle point value of the finite horizon dynamic game is shown to be guaranteed. Then, we propose RHNHC for nonlinear unknown systems which guarantees the infinite horizon H∞ norm bound and the internal stability of the closed-loop systems. Since RHNHC can deal with input and state constraints in optimization problem effectively, it does not cause an instability problem or give a poor performance in contrast to the existing neural H∞ control schemes.

AB - in this paper, we present new RHNHC (Receding Horizon Neural H ∞ Control) for nonlinear unknown systems. First, we propose LMI (Linear Matrix Inequality) condition on the terminal weighting matrix for stabilizing RHNHC. Under this condition, noninceasing monotonicity of the saddle point value of the finite horizon dynamic game is shown to be guaranteed. Then, we propose RHNHC for nonlinear unknown systems which guarantees the infinite horizon H∞ norm bound and the internal stability of the closed-loop systems. Since RHNHC can deal with input and state constraints in optimization problem effectively, it does not cause an instability problem or give a poor performance in contrast to the existing neural H∞ control schemes.

KW - Neural networks

KW - Nonlinear systems

KW - Receding horizon control

KW - Unknown systems

UR - http://www.scopus.com/inward/record.url?scp=79960702816&partnerID=8YFLogxK

U2 - 10.3182/20050703-6-cz-1902.00816

DO - 10.3182/20050703-6-cz-1902.00816

M3 - Conference contribution

AN - SCOPUS:79960702816

SN - 008045108X

SN - 9780080451084

T3 - IFAC Proceedings Volumes (IFAC-PapersOnline)

SP - 960

EP - 965

BT - Proceedings of the 16th IFAC World Congress, IFAC 2005

PB - IFAC Secretariat

ER -