Genetic algorithm with an improved fitness function for (N)ARX modelling

Q. Chen; K. Worden; P. Peng; A. Y T Leung

doi:10.1016/j.ymssp.2006.01.011

Genetic algorithm with an improved fitness function for (N)ARX modelling

Q. Chen
, K. Worden
, P. Peng
, A. Y T Leung

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

54 Citations (Scopus)

Abstract

In this article a new fitness function is introduced in an attempt to improve the quality of the auto-regressive with exogenous inputs (ARX) model using a genetic algorithm (GA). The GA is employed to identify the coefficients and the number of time lags of the models of dynamic systems with the new fitness function which is based on the prediction error and the correlation functions between the prediction error and the input and output signals. The new fitness function provides the GA with a better performance in the evolution process. Two examples of the ARX modelling of a linear and a non-linear (NARX) simulated dynamic system are examined using the proposed fitness function. © 2006 Elsevier Ltd. All rights reserved.

Original language	English
Pages (from-to)	994-1007
Journal	Mechanical Systems and Signal Processing
Volume	21
Issue number	2
DOIs	https://doi.org/10.1016/j.ymssp.2006.01.011
Publication status	Published - Feb 2007

Research Keywords

ARX model
Fitness function
Genetic algorithm
Model structure

Access Output

10.1016/j.ymssp.2006.01.011

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{561baa78615140fa84ad2143d7aba206,

title = "Genetic algorithm with an improved fitness function for (N)ARX modelling",

abstract = "In this article a new fitness function is introduced in an attempt to improve the quality of the auto-regressive with exogenous inputs (ARX) model using a genetic algorithm (GA). The GA is employed to identify the coefficients and the number of time lags of the models of dynamic systems with the new fitness function which is based on the prediction error and the correlation functions between the prediction error and the input and output signals. The new fitness function provides the GA with a better performance in the evolution process. Two examples of the ARX modelling of a linear and a non-linear (NARX) simulated dynamic system are examined using the proposed fitness function. {\textcopyright} 2006 Elsevier Ltd. All rights reserved.",

keywords = "ARX model, Fitness function, Genetic algorithm, Model structure",

author = "Q. Chen and K. Worden and P. Peng and Leung, \{A. Y T\}",

year = "2007",

month = feb,

doi = "10.1016/j.ymssp.2006.01.011",

language = "English",

volume = "21",

pages = "994--1007",

journal = "Mechanical Systems and Signal Processing",

issn = "0888-3270",

publisher = "Academic Press",

number = "2",

}

TY - JOUR

T1 - Genetic algorithm with an improved fitness function for (N)ARX modelling

AU - Chen, Q.

AU - Worden, K.

AU - Peng, P.

AU - Leung, A. Y T

PY - 2007/2

Y1 - 2007/2

N2 - In this article a new fitness function is introduced in an attempt to improve the quality of the auto-regressive with exogenous inputs (ARX) model using a genetic algorithm (GA). The GA is employed to identify the coefficients and the number of time lags of the models of dynamic systems with the new fitness function which is based on the prediction error and the correlation functions between the prediction error and the input and output signals. The new fitness function provides the GA with a better performance in the evolution process. Two examples of the ARX modelling of a linear and a non-linear (NARX) simulated dynamic system are examined using the proposed fitness function. © 2006 Elsevier Ltd. All rights reserved.

AB - In this article a new fitness function is introduced in an attempt to improve the quality of the auto-regressive with exogenous inputs (ARX) model using a genetic algorithm (GA). The GA is employed to identify the coefficients and the number of time lags of the models of dynamic systems with the new fitness function which is based on the prediction error and the correlation functions between the prediction error and the input and output signals. The new fitness function provides the GA with a better performance in the evolution process. Two examples of the ARX modelling of a linear and a non-linear (NARX) simulated dynamic system are examined using the proposed fitness function. © 2006 Elsevier Ltd. All rights reserved.

KW - ARX model

KW - Fitness function

KW - Genetic algorithm

KW - Model structure

UR - https://www.scopus.com/pages/publications/33750497791

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-33750497791&origin=recordpage

U2 - 10.1016/j.ymssp.2006.01.011

DO - 10.1016/j.ymssp.2006.01.011

M3 - RGC 21 - Publication in refereed journal

SN - 0888-3270

VL - 21

SP - 994

EP - 1007

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

IS - 2

ER -

Genetic algorithm with an improved fitness function for (N)ARX modelling

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this