Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms

Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failure due to defects, fatigue, and weather-induced damage. These large-scale composite structures are fundamentally enclosed acoustic cavities and currently have limited, if any...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of vibration and acoustics 2017-12, Vol.139 (6)
Hauptverfasser: Regan, Taylor, Beale, Christopher, Inalpolat, Murat
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 6
container_start_page
container_title Journal of vibration and acoustics
container_volume 139
creator Regan, Taylor
Beale, Christopher
Inalpolat, Murat
description Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failure due to defects, fatigue, and weather-induced damage. These large-scale composite structures are fundamentally enclosed acoustic cavities and currently have limited, if any, structural health monitoring (SHM) in place. A novel acoustics-based structural sensing and health monitoring technique is developed, requiring efficient algorithms for operational damage detection of cavity structures. This paper describes the selection of a set of statistical features for acoustics-based damage detection of enclosed cavities, such as wind turbine blades, as well as a systematic approach used in the identification of competent machine learning algorithms. Logistic regression (LR) and support vector machine (SVM) methods are identified and used with optimal feature selection for decision-making via binary classification algorithms. A laboratory-scale wind turbine with hollow composite blades was built for damage detection studies. This test rig allows for testing of stationary or rotating blades, of which time and frequency domain information can be collected to establish baseline characteristics. The test rig can then be used to observe any deviations from the baseline characteristics. An external microphone attached to the tower will be utilized to monitor blade health while blades are internally ensonified by wireless speakers. An initial test campaign with healthy and damaged blade specimens is carried out to arrive at several conclusions on the detectability and feature extraction capabilities required for damage detection.
doi_str_mv 10.1115/1.4036951
format Article
fullrecord <record><control><sourceid>asme_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1115_1_4036951</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>472828</sourcerecordid><originalsourceid>FETCH-LOGICAL-a398t-781273122bfb9f2bce2dbd08d6a60d9812f9f5d224839feda851c2c7b1255f563</originalsourceid><addsrcrecordid>eNotkE1LAzEYhIMoWKsHz1726mFr3jeb3eRY6ydUFGzxGLKbZJuyHyXZCv57t7SnGZiHYRhCboHOAIA_wCyjLJcczsgEOIpUSCzOR08zkUpK8ZJcxbilFBjjfEK-fnxnktU-lL6zyWOjjU2edKvrUexgq8H3XbKOvquT7_3Ohl8frUk-dLU58EurQ3fI5k3dBz9s2nhNLpxuor056ZSsX55Xi7d0-fn6vpgvU82kGNJCABYMEEtXSodlZdGUhgqT65waOaZOOm4QM8Gks0YLDhVWRQnIueM5m5L7Y28V-hiDdWoXfKvDnwKqDlcoUKcrRvbuyOrYWrXt96Ebp6msQIGC_QNPfFlp</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms</title><source>ASME Transactions Journals (Current)</source><source>Alma/SFX Local Collection</source><creator>Regan, Taylor ; Beale, Christopher ; Inalpolat, Murat</creator><creatorcontrib>Regan, Taylor ; Beale, Christopher ; Inalpolat, Murat</creatorcontrib><description>Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failure due to defects, fatigue, and weather-induced damage. These large-scale composite structures are fundamentally enclosed acoustic cavities and currently have limited, if any, structural health monitoring (SHM) in place. A novel acoustics-based structural sensing and health monitoring technique is developed, requiring efficient algorithms for operational damage detection of cavity structures. This paper describes the selection of a set of statistical features for acoustics-based damage detection of enclosed cavities, such as wind turbine blades, as well as a systematic approach used in the identification of competent machine learning algorithms. Logistic regression (LR) and support vector machine (SVM) methods are identified and used with optimal feature selection for decision-making via binary classification algorithms. A laboratory-scale wind turbine with hollow composite blades was built for damage detection studies. This test rig allows for testing of stationary or rotating blades, of which time and frequency domain information can be collected to establish baseline characteristics. The test rig can then be used to observe any deviations from the baseline characteristics. An external microphone attached to the tower will be utilized to monitor blade health while blades are internally ensonified by wireless speakers. An initial test campaign with healthy and damaged blade specimens is carried out to arrive at several conclusions on the detectability and feature extraction capabilities required for damage detection.</description><identifier>ISSN: 1048-9002</identifier><identifier>EISSN: 1528-8927</identifier><identifier>DOI: 10.1115/1.4036951</identifier><language>eng</language><publisher>ASME</publisher><ispartof>Journal of vibration and acoustics, 2017-12, Vol.139 (6)</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a398t-781273122bfb9f2bce2dbd08d6a60d9812f9f5d224839feda851c2c7b1255f563</citedby><cites>FETCH-LOGICAL-a398t-781273122bfb9f2bce2dbd08d6a60d9812f9f5d224839feda851c2c7b1255f563</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925,38520</link.rule.ids></links><search><creatorcontrib>Regan, Taylor</creatorcontrib><creatorcontrib>Beale, Christopher</creatorcontrib><creatorcontrib>Inalpolat, Murat</creatorcontrib><title>Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms</title><title>Journal of vibration and acoustics</title><addtitle>J. Vib. Acoust</addtitle><description>Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failure due to defects, fatigue, and weather-induced damage. These large-scale composite structures are fundamentally enclosed acoustic cavities and currently have limited, if any, structural health monitoring (SHM) in place. A novel acoustics-based structural sensing and health monitoring technique is developed, requiring efficient algorithms for operational damage detection of cavity structures. This paper describes the selection of a set of statistical features for acoustics-based damage detection of enclosed cavities, such as wind turbine blades, as well as a systematic approach used in the identification of competent machine learning algorithms. Logistic regression (LR) and support vector machine (SVM) methods are identified and used with optimal feature selection for decision-making via binary classification algorithms. A laboratory-scale wind turbine with hollow composite blades was built for damage detection studies. This test rig allows for testing of stationary or rotating blades, of which time and frequency domain information can be collected to establish baseline characteristics. The test rig can then be used to observe any deviations from the baseline characteristics. An external microphone attached to the tower will be utilized to monitor blade health while blades are internally ensonified by wireless speakers. An initial test campaign with healthy and damaged blade specimens is carried out to arrive at several conclusions on the detectability and feature extraction capabilities required for damage detection.</description><issn>1048-9002</issn><issn>1528-8927</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNotkE1LAzEYhIMoWKsHz1726mFr3jeb3eRY6ydUFGzxGLKbZJuyHyXZCv57t7SnGZiHYRhCboHOAIA_wCyjLJcczsgEOIpUSCzOR08zkUpK8ZJcxbilFBjjfEK-fnxnktU-lL6zyWOjjU2edKvrUexgq8H3XbKOvquT7_3Ohl8frUk-dLU58EurQ3fI5k3dBz9s2nhNLpxuor056ZSsX55Xi7d0-fn6vpgvU82kGNJCABYMEEtXSodlZdGUhgqT65waOaZOOm4QM8Gks0YLDhVWRQnIueM5m5L7Y28V-hiDdWoXfKvDnwKqDlcoUKcrRvbuyOrYWrXt96Ebp6msQIGC_QNPfFlp</recordid><startdate>20171201</startdate><enddate>20171201</enddate><creator>Regan, Taylor</creator><creator>Beale, Christopher</creator><creator>Inalpolat, Murat</creator><general>ASME</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20171201</creationdate><title>Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms</title><author>Regan, Taylor ; Beale, Christopher ; Inalpolat, Murat</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a398t-781273122bfb9f2bce2dbd08d6a60d9812f9f5d224839feda851c2c7b1255f563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Regan, Taylor</creatorcontrib><creatorcontrib>Beale, Christopher</creatorcontrib><creatorcontrib>Inalpolat, Murat</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of vibration and acoustics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Regan, Taylor</au><au>Beale, Christopher</au><au>Inalpolat, Murat</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms</atitle><jtitle>Journal of vibration and acoustics</jtitle><stitle>J. Vib. Acoust</stitle><date>2017-12-01</date><risdate>2017</risdate><volume>139</volume><issue>6</issue><issn>1048-9002</issn><eissn>1528-8927</eissn><abstract>Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failure due to defects, fatigue, and weather-induced damage. These large-scale composite structures are fundamentally enclosed acoustic cavities and currently have limited, if any, structural health monitoring (SHM) in place. A novel acoustics-based structural sensing and health monitoring technique is developed, requiring efficient algorithms for operational damage detection of cavity structures. This paper describes the selection of a set of statistical features for acoustics-based damage detection of enclosed cavities, such as wind turbine blades, as well as a systematic approach used in the identification of competent machine learning algorithms. Logistic regression (LR) and support vector machine (SVM) methods are identified and used with optimal feature selection for decision-making via binary classification algorithms. A laboratory-scale wind turbine with hollow composite blades was built for damage detection studies. This test rig allows for testing of stationary or rotating blades, of which time and frequency domain information can be collected to establish baseline characteristics. The test rig can then be used to observe any deviations from the baseline characteristics. An external microphone attached to the tower will be utilized to monitor blade health while blades are internally ensonified by wireless speakers. An initial test campaign with healthy and damaged blade specimens is carried out to arrive at several conclusions on the detectability and feature extraction capabilities required for damage detection.</abstract><pub>ASME</pub><doi>10.1115/1.4036951</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1048-9002
ispartof Journal of vibration and acoustics, 2017-12, Vol.139 (6)
issn 1048-9002
1528-8927
language eng
recordid cdi_crossref_primary_10_1115_1_4036951
source ASME Transactions Journals (Current); Alma/SFX Local Collection
title Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A13%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-asme_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Wind%20Turbine%20Blade%20Damage%20Detection%20Using%20Supervised%20Machine%20Learning%20Algorithms&rft.jtitle=Journal%20of%20vibration%20and%20acoustics&rft.au=Regan,%20Taylor&rft.date=2017-12-01&rft.volume=139&rft.issue=6&rft.issn=1048-9002&rft.eissn=1528-8927&rft_id=info:doi/10.1115/1.4036951&rft_dat=%3Casme_cross%3E472828%3C/asme_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true