Direct model reference adaptive controller based-on neural-fuzzy techniques for nonlinear dynamical systems

Hafizah Husain, Marzuki Khalid, Rubiyah Yusof

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents a direct neural-fuzzy-based Model Reference Adaptive Controller (MRAC) for nonlinear dynamical systems with unknown parameters. The two-phase learning is implemented to perform structure identification and parameter estimation for the controller. In the first phase, similarity index-based fuzzy c-means clustering technique extracts the fuzzy rules in the premise part for the neural-fuzzy controller. This technique enables the recruitment of rule parameters in accordance to the number of clusters and kernel centers it automatically generated. In the second phase, the parameters of the controller are directly tuned from the training data via the tracking error. The consequent parts of the rules are thus determined. This iterative process employs Radial Basis Function Neural Network (RBFNN) structure with a reference model to provide a closed-loop performance feedback.

Original languageEnglish
Pages (from-to)769-776
Number of pages8
JournalAmerican Journal of Applied Sciences
Volume5
Issue number7
Publication statusPublished - 2008

Fingerprint

Nonlinear dynamical systems
Controllers
Fuzzy rules
Parameter estimation
Identification (control systems)
Neural networks
Feedback

Keywords

  • Fuzzy c-means
  • Model reference adaptive control system
  • Neural fuzz
  • Radial basis function
  • Similarity index

ASJC Scopus subject areas

  • General

Cite this

Direct model reference adaptive controller based-on neural-fuzzy techniques for nonlinear dynamical systems. / Husain, Hafizah; Khalid, Marzuki; Yusof, Rubiyah.

In: American Journal of Applied Sciences, Vol. 5, No. 7, 2008, p. 769-776.

Research output: Contribution to journalArticle

@article{c65d9323ff2448f6aeae32a9570d56a3,
title = "Direct model reference adaptive controller based-on neural-fuzzy techniques for nonlinear dynamical systems",
abstract = "This paper presents a direct neural-fuzzy-based Model Reference Adaptive Controller (MRAC) for nonlinear dynamical systems with unknown parameters. The two-phase learning is implemented to perform structure identification and parameter estimation for the controller. In the first phase, similarity index-based fuzzy c-means clustering technique extracts the fuzzy rules in the premise part for the neural-fuzzy controller. This technique enables the recruitment of rule parameters in accordance to the number of clusters and kernel centers it automatically generated. In the second phase, the parameters of the controller are directly tuned from the training data via the tracking error. The consequent parts of the rules are thus determined. This iterative process employs Radial Basis Function Neural Network (RBFNN) structure with a reference model to provide a closed-loop performance feedback.",
keywords = "Fuzzy c-means, Model reference adaptive control system, Neural fuzz, Radial basis function, Similarity index",
author = "Hafizah Husain and Marzuki Khalid and Rubiyah Yusof",
year = "2008",
language = "English",
volume = "5",
pages = "769--776",
journal = "American Journal of Applied Sciences",
issn = "1546-9239",
publisher = "Science Publications",
number = "7",

}

TY - JOUR

T1 - Direct model reference adaptive controller based-on neural-fuzzy techniques for nonlinear dynamical systems

AU - Husain, Hafizah

AU - Khalid, Marzuki

AU - Yusof, Rubiyah

PY - 2008

Y1 - 2008

N2 - This paper presents a direct neural-fuzzy-based Model Reference Adaptive Controller (MRAC) for nonlinear dynamical systems with unknown parameters. The two-phase learning is implemented to perform structure identification and parameter estimation for the controller. In the first phase, similarity index-based fuzzy c-means clustering technique extracts the fuzzy rules in the premise part for the neural-fuzzy controller. This technique enables the recruitment of rule parameters in accordance to the number of clusters and kernel centers it automatically generated. In the second phase, the parameters of the controller are directly tuned from the training data via the tracking error. The consequent parts of the rules are thus determined. This iterative process employs Radial Basis Function Neural Network (RBFNN) structure with a reference model to provide a closed-loop performance feedback.

AB - This paper presents a direct neural-fuzzy-based Model Reference Adaptive Controller (MRAC) for nonlinear dynamical systems with unknown parameters. The two-phase learning is implemented to perform structure identification and parameter estimation for the controller. In the first phase, similarity index-based fuzzy c-means clustering technique extracts the fuzzy rules in the premise part for the neural-fuzzy controller. This technique enables the recruitment of rule parameters in accordance to the number of clusters and kernel centers it automatically generated. In the second phase, the parameters of the controller are directly tuned from the training data via the tracking error. The consequent parts of the rules are thus determined. This iterative process employs Radial Basis Function Neural Network (RBFNN) structure with a reference model to provide a closed-loop performance feedback.

KW - Fuzzy c-means

KW - Model reference adaptive control system

KW - Neural fuzz

KW - Radial basis function

KW - Similarity index

UR - http://www.scopus.com/inward/record.url?scp=41149160733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41149160733&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 769

EP - 776

JO - American Journal of Applied Sciences

JF - American Journal of Applied Sciences

SN - 1546-9239

IS - 7

ER -