Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine

This study introduces a new method to locate cracks in wind turbine blades using the support vector machine algorithm and the tangential vibration signal measured at the root blade in static conditions. The method was implemented in hardware and experimentally validated on 200 W wind turbine blades....

Full description

Saved in:
Bibliographic Details
Main Authors: Perla Y. Sevilla-Camacho, José B. Robles-Ocampo, Juvenal Rodríguez-Resendíz, Sergio De la Cruz-Arreola, Marco A. Zuñiga-Reyes, Edwin N. Hernández-Estrada
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Vibration
Subjects:
Online Access:https://www.mdpi.com/2571-631X/8/2/20
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164883141689344
author Perla Y. Sevilla-Camacho
José B. Robles-Ocampo
Juvenal Rodríguez-Resendíz
Sergio De la Cruz-Arreola
Marco A. Zuñiga-Reyes
Edwin N. Hernández-Estrada
author_facet Perla Y. Sevilla-Camacho
José B. Robles-Ocampo
Juvenal Rodríguez-Resendíz
Sergio De la Cruz-Arreola
Marco A. Zuñiga-Reyes
Edwin N. Hernández-Estrada
author_sort Perla Y. Sevilla-Camacho
collection DOAJ
description This study introduces a new method to locate cracks in wind turbine blades using the support vector machine algorithm and the tangential vibration signal measured at the root blade in static conditions. The method was implemented in hardware and experimentally validated on 200 W wind turbine blades. The blade conditions were healthy, and transverse cracked at the root, midsection, and tip. The experimental procedure is easy, and only one low-cost piezoelectric accelerometer is needed, which is affordable and straightforward to install. The machine learning technique used requires a small dataset and low computing power. The results show exceptional performance, achieving an accuracy of 99.37% and a precision of 98.77%. This approach enhances the reliability of wind turbine blade monitoring. It provides a robust early detection and maintenance solution, improving operational efficiency and safety in wind energy production. K-nearest neighbors and decision trees are also used for comparison purposes.
format Article
id doaj-art-afa68f18ff7b4a7f9c115b488f29f43a
institution OA Journals
issn 2571-631X
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Vibration
spelling doaj-art-afa68f18ff7b4a7f9c115b488f29f43a2025-08-20T02:21:52ZengMDPI AGVibration2571-631X2025-04-01822010.3390/vibration8020020Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector MachinePerla Y. Sevilla-Camacho0José B. Robles-Ocampo1Juvenal Rodríguez-Resendíz2Sergio De la Cruz-Arreola3Marco A. Zuñiga-Reyes4Edwin N. Hernández-Estrada5Cuerpo Académico de Energía y Sustentabilidad, Universidad Politécnica de Chiapas, Carretera Tuxtla Gutiérrez—Portillo Zaragoza Km 21+500, Col. Las Brisas, Suchiapa C.P. 29150, MexicoCuerpo Académico de Energía y Sustentabilidad, Universidad Politécnica de Chiapas, Carretera Tuxtla Gutiérrez—Portillo Zaragoza Km 21+500, Col. Las Brisas, Suchiapa C.P. 29150, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Cerro de las Campanas, Las Campanas, Querétaro C.P. 76010, MexicoCuerpo Académico de Energía y Sustentabilidad, Universidad Politécnica de Chiapas, Carretera Tuxtla Gutiérrez—Portillo Zaragoza Km 21+500, Col. Las Brisas, Suchiapa C.P. 29150, MexicoDepartamento de Metal Mecánica, Tecnológico Nacional de México/IT de Tuxtla Gutiérrez, Carretera Panamericana Km 1080, Tuxtla Gutiérrez C.P. 29050, MexicoCuerpo Académico de Energía y Sustentabilidad, Universidad Politécnica de Chiapas, Carretera Tuxtla Gutiérrez—Portillo Zaragoza Km 21+500, Col. Las Brisas, Suchiapa C.P. 29150, MexicoThis study introduces a new method to locate cracks in wind turbine blades using the support vector machine algorithm and the tangential vibration signal measured at the root blade in static conditions. The method was implemented in hardware and experimentally validated on 200 W wind turbine blades. The blade conditions were healthy, and transverse cracked at the root, midsection, and tip. The experimental procedure is easy, and only one low-cost piezoelectric accelerometer is needed, which is affordable and straightforward to install. The machine learning technique used requires a small dataset and low computing power. The results show exceptional performance, achieving an accuracy of 99.37% and a precision of 98.77%. This approach enhances the reliability of wind turbine blade monitoring. It provides a robust early detection and maintenance solution, improving operational efficiency and safety in wind energy production. K-nearest neighbors and decision trees are also used for comparison purposes.https://www.mdpi.com/2571-631X/8/2/20crack locationwind turbinebladevibration signalmachine learningsupport vector machine
spellingShingle Perla Y. Sevilla-Camacho
José B. Robles-Ocampo
Juvenal Rodríguez-Resendíz
Sergio De la Cruz-Arreola
Marco A. Zuñiga-Reyes
Edwin N. Hernández-Estrada
Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
Vibration
crack location
wind turbine
blade
vibration signal
machine learning
support vector machine
title Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
title_full Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
title_fullStr Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
title_full_unstemmed Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
title_short Crack Location in Wind Turbine Blades Using Vibration Signal and Support Vector Machine
title_sort crack location in wind turbine blades using vibration signal and support vector machine
topic crack location
wind turbine
blade
vibration signal
machine learning
support vector machine
url https://www.mdpi.com/2571-631X/8/2/20
work_keys_str_mv AT perlaysevillacamacho cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine
AT josebroblesocampo cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine
AT juvenalrodriguezresendiz cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine
AT sergiodelacruzarreola cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine
AT marcoazunigareyes cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine
AT edwinnhernandezestrada cracklocationinwindturbinebladesusingvibrationsignalandsupportvectormachine