Genetic optimisation of a neural damage locator

K. Worden, G. Manson, G. Hilson, S.G. Pierce

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

A critical problem in structural health monitoring (SHM) based on pattern recognition methods is the correct selection of features, i.e. measured and processed data for the diagnosis. Various selection strategies have been applied in the past and one approach that has proved effective is the use of combinatorial optimisation methods. This paper presents a case study based on a scheme for damage location in an aircraft wing. The feature selection algorithm is a Genetic Algorithm and the locator (classifier) is an artificial neural network. A comparison is made with the results obtained when the features are selected on the basis of engineering judgement. The study is seen to raise some issues relating to model complexity and generalisation and these matters are discussed in some detail.
LanguageEnglish
Pages529-544
Number of pages15
JournalJournal of Sound and Vibration
Volume309
Issue number3-5
DOIs
Publication statusPublished - Jan 2008

Fingerprint

Structural health monitoring
Combinatorial optimization
Pattern recognition
Feature extraction
Classifiers
Genetic algorithms
damage
Neural networks
optimization
structural health monitoring
classifiers
genetic algorithms
pattern recognition
wings
aircraft
engineering

Keywords

  • health monitoring methodology
  • experimental validation
  • novelty detection
  • aircraft

Cite this

Worden, K. ; Manson, G. ; Hilson, G. ; Pierce, S.G. / Genetic optimisation of a neural damage locator. In: Journal of Sound and Vibration. 2008 ; Vol. 309, No. 3-5. pp. 529-544.
@article{3e7efefe5395489f87fe093e8c017504,
title = "Genetic optimisation of a neural damage locator",
abstract = "A critical problem in structural health monitoring (SHM) based on pattern recognition methods is the correct selection of features, i.e. measured and processed data for the diagnosis. Various selection strategies have been applied in the past and one approach that has proved effective is the use of combinatorial optimisation methods. This paper presents a case study based on a scheme for damage location in an aircraft wing. The feature selection algorithm is a Genetic Algorithm and the locator (classifier) is an artificial neural network. A comparison is made with the results obtained when the features are selected on the basis of engineering judgement. The study is seen to raise some issues relating to model complexity and generalisation and these matters are discussed in some detail.",
keywords = "health monitoring methodology, experimental validation, novelty detection, aircraft",
author = "K. Worden and G. Manson and G. Hilson and S.G. Pierce",
year = "2008",
month = "1",
doi = "10.1016/j.jsv.2007.07.035",
language = "English",
volume = "309",
pages = "529--544",
journal = "Journal of Sound and Vibration",
issn = "0022-460X",
number = "3-5",

}

Genetic optimisation of a neural damage locator. / Worden, K.; Manson, G.; Hilson, G.; Pierce, S.G.

In: Journal of Sound and Vibration, Vol. 309, No. 3-5, 01.2008, p. 529-544.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Genetic optimisation of a neural damage locator

AU - Worden, K.

AU - Manson, G.

AU - Hilson, G.

AU - Pierce, S.G.

PY - 2008/1

Y1 - 2008/1

N2 - A critical problem in structural health monitoring (SHM) based on pattern recognition methods is the correct selection of features, i.e. measured and processed data for the diagnosis. Various selection strategies have been applied in the past and one approach that has proved effective is the use of combinatorial optimisation methods. This paper presents a case study based on a scheme for damage location in an aircraft wing. The feature selection algorithm is a Genetic Algorithm and the locator (classifier) is an artificial neural network. A comparison is made with the results obtained when the features are selected on the basis of engineering judgement. The study is seen to raise some issues relating to model complexity and generalisation and these matters are discussed in some detail.

AB - A critical problem in structural health monitoring (SHM) based on pattern recognition methods is the correct selection of features, i.e. measured and processed data for the diagnosis. Various selection strategies have been applied in the past and one approach that has proved effective is the use of combinatorial optimisation methods. This paper presents a case study based on a scheme for damage location in an aircraft wing. The feature selection algorithm is a Genetic Algorithm and the locator (classifier) is an artificial neural network. A comparison is made with the results obtained when the features are selected on the basis of engineering judgement. The study is seen to raise some issues relating to model complexity and generalisation and these matters are discussed in some detail.

KW - health monitoring methodology

KW - experimental validation

KW - novelty detection

KW - aircraft

UR - http://dx.doi.org/10.1016/j.jsv.2007.07.035

U2 - 10.1016/j.jsv.2007.07.035

DO - 10.1016/j.jsv.2007.07.035

M3 - Article

VL - 309

SP - 529

EP - 544

JO - Journal of Sound and Vibration

T2 - Journal of Sound and Vibration

JF - Journal of Sound and Vibration

SN - 0022-460X

IS - 3-5

ER -