Sequential projection pursuit for optimized vibration-based damage detection in an experimental wind turbine blade

Simon Hoell, Piotr Omenzetter

Research output: Contribution to journalArticle

1 Citation (Scopus)
4 Downloads (Pure)

Abstract

To advance the concept of smart structures in large systems, such as wind turbines, it is desirable to be able to detect structural damage early while
using minimal instrumentation. Data-driven vibration-based damage detection
methods can be competitive in that respect because global vibrational responses
encompass the entire structure. Multivariate damage sensitive features (DSFs)
extracted from acceleration responses enable to detect changes in a structure via statistical methods. However, even though such DSFs contain information about the structural state, they may not be optimized for the damage detection task. This paper addresses the shortcoming by exploring a DSF projection technique specialized for statistical structural damage detection. High dimensional initial DSFs are projected onto a low-dimensional space for improved damage detection performance and simultaneous computational burden reduction. The technique is based on sequential projection pursuit where the projection vectors are optimized one by one using an advanced evolutionary strategy. The approach is applied to laboratory experiments with a small-scale wind turbine blade under wind-like excitations. Autocorrelation function coefficients calculated from acceleration signals are employed as DSFs. The optimal numbers of projection vectors are identified with the help of a fast forward selection procedure. To benchmark the proposed method, selections of original DSFs as well as principal component analysis scores from these features are additionally investigated. The optimized DSFs are tested for damage detection on previously unseen data from the healthy state and a wide range of damage scenarios. It is demonstrated that using selected subsets of the initial and transformed DSFs improves damage detectability compared to the full set of features. Furthermore, superior results can be achieved by projecting autocorrelation coefficients onto just a single optimized projection vector.
Original languageEnglish
Article number025007
Pages (from-to)1-9
Number of pages9
JournalSmart Materials & Structures
Volume27
Issue number2
Early online date6 Dec 2017
DOIs
Publication statusPublished - 15 Jan 2018

Fingerprint

turbine blades
wind turbines
Damage detection
Wind turbines
Turbomachine blades
projection
damage
vibration
Autocorrelation
Intelligent structures
Principal component analysis
Statistical methods
autocorrelation
Experiments
smart structures
coefficients
principal components analysis

Keywords

  • autocorrelation function
  • evolutionary algorithm
  • optimal feature projection
  • sequential projection pursuit
  • structural health monitoring
  • vibration-based damage detection
  • wind turbines

Cite this

Sequential projection pursuit for optimized vibration-based damage detection in an experimental wind turbine blade. / Hoell, Simon; Omenzetter, Piotr.

In: Smart Materials & Structures, Vol. 27, No. 2, 025007, 15.01.2018, p. 1-9.

Research output: Contribution to journalArticle

@article{ad1f39684f654352945d4fa23a48ea69,
title = "Sequential projection pursuit for optimized vibration-based damage detection in an experimental wind turbine blade",
abstract = "To advance the concept of smart structures in large systems, such as wind turbines, it is desirable to be able to detect structural damage early whileusing minimal instrumentation. Data-driven vibration-based damage detectionmethods can be competitive in that respect because global vibrational responsesencompass the entire structure. Multivariate damage sensitive features (DSFs)extracted from acceleration responses enable to detect changes in a structure via statistical methods. However, even though such DSFs contain information about the structural state, they may not be optimized for the damage detection task. This paper addresses the shortcoming by exploring a DSF projection technique specialized for statistical structural damage detection. High dimensional initial DSFs are projected onto a low-dimensional space for improved damage detection performance and simultaneous computational burden reduction. The technique is based on sequential projection pursuit where the projection vectors are optimized one by one using an advanced evolutionary strategy. The approach is applied to laboratory experiments with a small-scale wind turbine blade under wind-like excitations. Autocorrelation function coefficients calculated from acceleration signals are employed as DSFs. The optimal numbers of projection vectors are identified with the help of a fast forward selection procedure. To benchmark the proposed method, selections of original DSFs as well as principal component analysis scores from these features are additionally investigated. The optimized DSFs are tested for damage detection on previously unseen data from the healthy state and a wide range of damage scenarios. It is demonstrated that using selected subsets of the initial and transformed DSFs improves damage detectability compared to the full set of features. Furthermore, superior results can be achieved by projecting autocorrelation coefficients onto just a single optimized projection vector.",
keywords = "autocorrelation function, evolutionary algorithm, optimal feature projection, sequential projection pursuit, structural health monitoring, vibration-based damage detection, wind turbines",
author = "Simon Hoell and Piotr Omenzetter",
note = "Acknowledgments S. Hoell’s work at Lloyd’s Register Foundation Centre for Safety and Reliability Engineering at University of Aberdeen was supported by Lloyd’s Register Foundation. The Foundation helps to protect life and property by supporting engineering-related education, public engagement and the application of research.",
year = "2018",
month = "1",
day = "15",
doi = "10.1088/1361-665X/aa9f8e",
language = "English",
volume = "27",
pages = "1--9",
journal = "Smart Materials & Structures",
issn = "0964-1726",
publisher = "IOP Publishing Ltd.",
number = "2",

}

TY - JOUR

T1 - Sequential projection pursuit for optimized vibration-based damage detection in an experimental wind turbine blade

AU - Hoell, Simon

AU - Omenzetter, Piotr

N1 - Acknowledgments S. Hoell’s work at Lloyd’s Register Foundation Centre for Safety and Reliability Engineering at University of Aberdeen was supported by Lloyd’s Register Foundation. The Foundation helps to protect life and property by supporting engineering-related education, public engagement and the application of research.

PY - 2018/1/15

Y1 - 2018/1/15

N2 - To advance the concept of smart structures in large systems, such as wind turbines, it is desirable to be able to detect structural damage early whileusing minimal instrumentation. Data-driven vibration-based damage detectionmethods can be competitive in that respect because global vibrational responsesencompass the entire structure. Multivariate damage sensitive features (DSFs)extracted from acceleration responses enable to detect changes in a structure via statistical methods. However, even though such DSFs contain information about the structural state, they may not be optimized for the damage detection task. This paper addresses the shortcoming by exploring a DSF projection technique specialized for statistical structural damage detection. High dimensional initial DSFs are projected onto a low-dimensional space for improved damage detection performance and simultaneous computational burden reduction. The technique is based on sequential projection pursuit where the projection vectors are optimized one by one using an advanced evolutionary strategy. The approach is applied to laboratory experiments with a small-scale wind turbine blade under wind-like excitations. Autocorrelation function coefficients calculated from acceleration signals are employed as DSFs. The optimal numbers of projection vectors are identified with the help of a fast forward selection procedure. To benchmark the proposed method, selections of original DSFs as well as principal component analysis scores from these features are additionally investigated. The optimized DSFs are tested for damage detection on previously unseen data from the healthy state and a wide range of damage scenarios. It is demonstrated that using selected subsets of the initial and transformed DSFs improves damage detectability compared to the full set of features. Furthermore, superior results can be achieved by projecting autocorrelation coefficients onto just a single optimized projection vector.

AB - To advance the concept of smart structures in large systems, such as wind turbines, it is desirable to be able to detect structural damage early whileusing minimal instrumentation. Data-driven vibration-based damage detectionmethods can be competitive in that respect because global vibrational responsesencompass the entire structure. Multivariate damage sensitive features (DSFs)extracted from acceleration responses enable to detect changes in a structure via statistical methods. However, even though such DSFs contain information about the structural state, they may not be optimized for the damage detection task. This paper addresses the shortcoming by exploring a DSF projection technique specialized for statistical structural damage detection. High dimensional initial DSFs are projected onto a low-dimensional space for improved damage detection performance and simultaneous computational burden reduction. The technique is based on sequential projection pursuit where the projection vectors are optimized one by one using an advanced evolutionary strategy. The approach is applied to laboratory experiments with a small-scale wind turbine blade under wind-like excitations. Autocorrelation function coefficients calculated from acceleration signals are employed as DSFs. The optimal numbers of projection vectors are identified with the help of a fast forward selection procedure. To benchmark the proposed method, selections of original DSFs as well as principal component analysis scores from these features are additionally investigated. The optimized DSFs are tested for damage detection on previously unseen data from the healthy state and a wide range of damage scenarios. It is demonstrated that using selected subsets of the initial and transformed DSFs improves damage detectability compared to the full set of features. Furthermore, superior results can be achieved by projecting autocorrelation coefficients onto just a single optimized projection vector.

KW - autocorrelation function

KW - evolutionary algorithm

KW - optimal feature projection

KW - sequential projection pursuit

KW - structural health monitoring

KW - vibration-based damage detection

KW - wind turbines

U2 - 10.1088/1361-665X/aa9f8e

DO - 10.1088/1361-665X/aa9f8e

M3 - Article

VL - 27

SP - 1

EP - 9

JO - Smart Materials & Structures

JF - Smart Materials & Structures

SN - 0964-1726

IS - 2

M1 - 025007

ER -