Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques

José Figueroa; José M. Saavedra; José F. Delpiano; Rodrigo Astroza

doi:10.1007/978-3-031-39117-0_47

Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques

José Figueroa, José M. Saavedra, José F. Delpiano, Rodrigo Astroza^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper presents a method for damage identification of wind turbine blades based on vibration data and machine learning (ML) techniques and their validation using experimental data collected at different states of artificially-induced damage. The acceleration responses collected from accelerometers placed along the blades are preprocessed according to the type of network used for damage diagnosis. The ML approach is a supervised strategy in which a multilayered perceptron (MLP) takes a vector of damage-sensitive features, calculated from the acceleration time series. The accuracy of the approach is evaluated, and the effects of the operational and environmental variables (EOV) are discussed.

Original language	English
Title of host publication	Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023
Editors	Maria Pina Limongelli, Pier Francesco Giordano, Carmelo Gentile, Said Quqa, Alfredo Cigada
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	458-467
Number of pages	10
Volume	2
ISBN (Print)	9783031391163
DOIs	https://doi.org/10.1007/978-3-031-39117-0_47
State	Published - 2023
Event	Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 - Volume 2 - Milan, Italy Duration: 30 Aug 2023 → 1 Sep 2023

Publication series

Name	Lecture Notes in Civil Engineering
Volume	433 LNCE
ISSN (Print)	2366-2557
ISSN (Electronic)	2366-2565

Conference

Conference	Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 - Volume 2
Country/Territory	Italy
City	Milan
Period	30/08/23 → 1/09/23

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Artificial Neural Network
Damage Diagnosis
Structural Health Monitoring
Wind Turbine

Access to Document

10.1007/978-3-031-39117-0_47

Cite this

Figueroa, J., Saavedra, J. M., Delpiano, J. F., & Astroza, R. (2023). Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques. In M. P. Limongelli, P. F. Giordano, C. Gentile, S. Quqa, & A. Cigada (Eds.), Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 (Vol. 2, pp. 458-467). (Lecture Notes in Civil Engineering; Vol. 433 LNCE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-39117-0_47

Figueroa, José ; Saavedra, José M. ; Delpiano, José F. et al. / Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques. Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023. editor / Maria Pina Limongelli ; Pier Francesco Giordano ; Carmelo Gentile ; Said Quqa ; Alfredo Cigada. Vol. 2 Springer Science and Business Media Deutschland GmbH, 2023. pp. 458-467 (Lecture Notes in Civil Engineering).

@inproceedings{d6997e650df74262926e68d33ffb2248,

title = "Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques",

abstract = "This paper presents a method for damage identification of wind turbine blades based on vibration data and machine learning (ML) techniques and their validation using experimental data collected at different states of artificially-induced damage. The acceleration responses collected from accelerometers placed along the blades are preprocessed according to the type of network used for damage diagnosis. The ML approach is a supervised strategy in which a multilayered perceptron (MLP) takes a vector of damage-sensitive features, calculated from the acceleration time series. The accuracy of the approach is evaluated, and the effects of the operational and environmental variables (EOV) are discussed.",

keywords = "Artificial Neural Network, Damage Diagnosis, Structural Health Monitoring, Wind Turbine",

author = "Jos{\'e} Figueroa and Saavedra, \{Jos{\'e} M.\} and Delpiano, \{Jos{\'e} F.\} and Rodrigo Astroza",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 - Volume 2 ; Conference date: 30-08-2023 Through 01-09-2023",

year = "2023",

doi = "10.1007/978-3-031-39117-0\_47",

language = "English",

isbn = "9783031391163",

volume = "2",

series = "Lecture Notes in Civil Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "458--467",

editor = "Limongelli, \{Maria Pina\} and Giordano, \{Pier Francesco\} and Carmelo Gentile and Said Quqa and Alfredo Cigada",

booktitle = "Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023",

address = "Germany",

}

Figueroa, J, Saavedra, JM , Delpiano, JF & Astroza, R 2023, Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques. in MP Limongelli, PF Giordano, C Gentile, S Quqa & A Cigada (eds), Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023. vol. 2, Lecture Notes in Civil Engineering, vol. 433 LNCE, Springer Science and Business Media Deutschland GmbH, pp. 458-467, Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 - Volume 2, Milan, Italy, 30/08/23. https://doi.org/10.1007/978-3-031-39117-0_47

Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques. / Figueroa, José; Saavedra, José M.; Delpiano, José F. et al.
Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023. ed. / Maria Pina Limongelli; Pier Francesco Giordano; Carmelo Gentile; Said Quqa; Alfredo Cigada. Vol. 2 Springer Science and Business Media Deutschland GmbH, 2023. p. 458-467 (Lecture Notes in Civil Engineering; Vol. 433 LNCE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques

AU - Figueroa, José

AU - Saavedra, José M.

AU - Delpiano, José F.

AU - Astroza, Rodrigo

PY - 2023

Y1 - 2023

N2 - This paper presents a method for damage identification of wind turbine blades based on vibration data and machine learning (ML) techniques and their validation using experimental data collected at different states of artificially-induced damage. The acceleration responses collected from accelerometers placed along the blades are preprocessed according to the type of network used for damage diagnosis. The ML approach is a supervised strategy in which a multilayered perceptron (MLP) takes a vector of damage-sensitive features, calculated from the acceleration time series. The accuracy of the approach is evaluated, and the effects of the operational and environmental variables (EOV) are discussed.

AB - This paper presents a method for damage identification of wind turbine blades based on vibration data and machine learning (ML) techniques and their validation using experimental data collected at different states of artificially-induced damage. The acceleration responses collected from accelerometers placed along the blades are preprocessed according to the type of network used for damage diagnosis. The ML approach is a supervised strategy in which a multilayered perceptron (MLP) takes a vector of damage-sensitive features, calculated from the acceleration time series. The accuracy of the approach is evaluated, and the effects of the operational and environmental variables (EOV) are discussed.

KW - Artificial Neural Network

KW - Damage Diagnosis

KW - Structural Health Monitoring

KW - Wind Turbine

UR - https://www.scopus.com/pages/publications/85174800942

U2 - 10.1007/978-3-031-39117-0_47

DO - 10.1007/978-3-031-39117-0_47

M3 - Conference contribution

AN - SCOPUS:85174800942

SN - 9783031391163

VL - 2

T3 - Lecture Notes in Civil Engineering

SP - 458

EP - 467

BT - Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023

A2 - Limongelli, Maria Pina

A2 - Giordano, Pier Francesco

A2 - Gentile, Carmelo

A2 - Quqa, Said

A2 - Cigada, Alfredo

PB - Springer Science and Business Media Deutschland GmbH

T2 - Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023 - Volume 2

Y2 - 30 August 2023 through 1 September 2023

ER -

Figueroa J, Saavedra JM , Delpiano JF , Astroza R. Structural Damage Diagnosis of Wind Turbine Blades Based on Machine Learning Techniques. In Limongelli MP, Giordano PF, Gentile C, Quqa S, Cigada A, editors, Experimental Vibration Analysis for Civil Engineering Structures - EVACES 2023. Vol. 2. Springer Science and Business Media Deutschland GmbH. 2023. p. 458-467. (Lecture Notes in Civil Engineering). doi: 10.1007/978-3-031-39117-0_47