Receding Horizon Robust Control for Nonlinear Systems Based on Linear Differential Inclusion of Neural Networks

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this paper, we present a new receding horizon neural robust control scheme for a class of nonlinear systems based on the linear differential inclusion (LDI) representation of neural networks. First, we propose a linear matrix inequality (LMI) condition on the terminal weighting matrix for a receding horizon neural robust control scheme. This condition guarantees the nonincreasing monotonicity of the saddle point value of the finite horizon dynamic game. We then propose a receding horizon neural robust control scheme for nonlinear systems, which ensures the infinite horizon robust performance and the internal stability of closed-loop systems. Since the proposed control scheme can effectively deal with input and state constraints in an optimization problem, it does not cause the instability problem or give the poor performance associated with the existing neural robust control schemes.

Original languageEnglish
Pages (from-to)659-678
Number of pages20
JournalJournal of Optimization Theory and Applications
Volume160
Issue number2
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Receding Horizon Control
Differential Inclusions
Robust control
Neural Control
Robust Control
Nonlinear systems
Nonlinear Systems
Neural Networks
Neural networks
Horizon
Input Constraints
Linear matrix inequalities
Dynamic Games
Closed loop systems
Robust Performance
Finite Horizon
State Constraints
Infinite Horizon
Saddlepoint
Closed-loop System

Keywords

  • Linear differential inclusion (LDI)
  • Neural networks
  • Nonlinear systems
  • Receding horizon control

ASJC Scopus subject areas

  • Applied Mathematics
  • Control and Optimization
  • Management Science and Operations Research

Cite this

@article{fbe4b09fb57747a8a6582c67fd674ed8,
title = "Receding Horizon Robust Control for Nonlinear Systems Based on Linear Differential Inclusion of Neural Networks",
abstract = "In this paper, we present a new receding horizon neural robust control scheme for a class of nonlinear systems based on the linear differential inclusion (LDI) representation of neural networks. First, we propose a linear matrix inequality (LMI) condition on the terminal weighting matrix for a receding horizon neural robust control scheme. This condition guarantees the nonincreasing monotonicity of the saddle point value of the finite horizon dynamic game. We then propose a receding horizon neural robust control scheme for nonlinear systems, which ensures the infinite horizon robust performance and the internal stability of closed-loop systems. Since the proposed control scheme can effectively deal with input and state constraints in an optimization problem, it does not cause the instability problem or give the poor performance associated with the existing neural robust control schemes.",
keywords = "Linear differential inclusion (LDI), Neural networks, Nonlinear systems, Receding horizon control",
author = "Ahn, {Choon Ki}",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s10957-013-0328-2",
language = "English",
volume = "160",
pages = "659--678",
journal = "Journal of Optimization Theory and Applications",
issn = "0022-3239",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Receding Horizon Robust Control for Nonlinear Systems Based on Linear Differential Inclusion of Neural Networks

AU - Ahn, Choon Ki

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we present a new receding horizon neural robust control scheme for a class of nonlinear systems based on the linear differential inclusion (LDI) representation of neural networks. First, we propose a linear matrix inequality (LMI) condition on the terminal weighting matrix for a receding horizon neural robust control scheme. This condition guarantees the nonincreasing monotonicity of the saddle point value of the finite horizon dynamic game. We then propose a receding horizon neural robust control scheme for nonlinear systems, which ensures the infinite horizon robust performance and the internal stability of closed-loop systems. Since the proposed control scheme can effectively deal with input and state constraints in an optimization problem, it does not cause the instability problem or give the poor performance associated with the existing neural robust control schemes.

AB - In this paper, we present a new receding horizon neural robust control scheme for a class of nonlinear systems based on the linear differential inclusion (LDI) representation of neural networks. First, we propose a linear matrix inequality (LMI) condition on the terminal weighting matrix for a receding horizon neural robust control scheme. This condition guarantees the nonincreasing monotonicity of the saddle point value of the finite horizon dynamic game. We then propose a receding horizon neural robust control scheme for nonlinear systems, which ensures the infinite horizon robust performance and the internal stability of closed-loop systems. Since the proposed control scheme can effectively deal with input and state constraints in an optimization problem, it does not cause the instability problem or give the poor performance associated with the existing neural robust control schemes.

KW - Linear differential inclusion (LDI)

KW - Neural networks

KW - Nonlinear systems

KW - Receding horizon control

UR - http://www.scopus.com/inward/record.url?scp=84896492128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896492128&partnerID=8YFLogxK

U2 - 10.1007/s10957-013-0328-2

DO - 10.1007/s10957-013-0328-2

M3 - Article

AN - SCOPUS:84896492128

VL - 160

SP - 659

EP - 678

JO - Journal of Optimization Theory and Applications

JF - Journal of Optimization Theory and Applications

SN - 0022-3239

IS - 2

ER -