Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading

This paper reports a convolutional neural network (CNN)-based damage detection approach for radar-based structural health monitoring of wind turbine blades. Subsequent radar measurements are transformed into an image-type representation for use as CNN input. In contrast to conventional approaches th...

Full description

Saved in:
Bibliographic Details
Main Authors: Erik Streser, Sercan Alipek, Manuel Rao, Jonas Simon, Jochen Moll, Peter Kraemer, Viktor Krozer
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3337
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330841994395648
author Erik Streser
Sercan Alipek
Manuel Rao
Jonas Simon
Jochen Moll
Peter Kraemer
Viktor Krozer
author_facet Erik Streser
Sercan Alipek
Manuel Rao
Jonas Simon
Jochen Moll
Peter Kraemer
Viktor Krozer
author_sort Erik Streser
collection DOAJ
description This paper reports a convolutional neural network (CNN)-based damage detection approach for radar-based structural health monitoring of wind turbine blades. Subsequent radar measurements are transformed into an image-type representation for use as CNN input. In contrast to conventional approaches that require compensation for temperature and loading effects, the proposed framework inherently learns all required information during the training phase. Its damage detection performance (i.e., detecting intact vs. damaged condition) is demonstrated using measurements from multiple embedded radar sensors during fatigue testing of a wind turbine blade with a length of 31 m. The achieved F1-score for correct damage classification is between 91% and 100% for both the unloaded and the loaded blade.
format Article
id doaj-art-6f404d4fdede4ac2928242b3785d383e
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-6f404d4fdede4ac2928242b3785d383e2025-08-20T03:46:49ZengMDPI AGSensors1424-82202025-05-012511333710.3390/s25113337Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue LoadingErik Streser0Sercan Alipek1Manuel Rao2Jonas Simon3Jochen Moll4Peter Kraemer5Viktor Krozer6Department of Physics, Goethe-University Frankfurt, Max-von-Laue Str. 1, 60438 Frankfurt am Main, GermanyDepartment of Mechanical Engineering, University of Siegen, Paul-Bonatz-Straße 9-11, 57076 Siegen, GermanyDepartment of Mechanical Engineering, University of Siegen, Paul-Bonatz-Straße 9-11, 57076 Siegen, GermanyDepartment of Physics, Goethe-University Frankfurt, Max-von-Laue Str. 1, 60438 Frankfurt am Main, GermanyDepartment of Physics, Goethe-University Frankfurt, Max-von-Laue Str. 1, 60438 Frankfurt am Main, GermanyDepartment of Mechanical Engineering, University of Siegen, Paul-Bonatz-Straße 9-11, 57076 Siegen, GermanyDepartment of Physics, Goethe-University Frankfurt, Max-von-Laue Str. 1, 60438 Frankfurt am Main, GermanyThis paper reports a convolutional neural network (CNN)-based damage detection approach for radar-based structural health monitoring of wind turbine blades. Subsequent radar measurements are transformed into an image-type representation for use as CNN input. In contrast to conventional approaches that require compensation for temperature and loading effects, the proposed framework inherently learns all required information during the training phase. Its damage detection performance (i.e., detecting intact vs. damaged condition) is demonstrated using measurements from multiple embedded radar sensors during fatigue testing of a wind turbine blade with a length of 31 m. The achieved F1-score for correct damage classification is between 91% and 100% for both the unloaded and the loaded blade.https://www.mdpi.com/1424-8220/25/11/3337structural health monitoringdamage detectionwind turbine bladeFMCW radarmillimeter-waveconvolutional neural network
spellingShingle Erik Streser
Sercan Alipek
Manuel Rao
Jonas Simon
Jochen Moll
Peter Kraemer
Viktor Krozer
Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
Sensors
structural health monitoring
damage detection
wind turbine blade
FMCW radar
millimeter-wave
convolutional neural network
title Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
title_full Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
title_fullStr Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
title_full_unstemmed Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
title_short Radar-Based Damage Detection in a Wind Turbine Blade Using Convolutional Neural Networks: A Proof-of-Concept Under Fatigue Loading
title_sort radar based damage detection in a wind turbine blade using convolutional neural networks a proof of concept under fatigue loading
topic structural health monitoring
damage detection
wind turbine blade
FMCW radar
millimeter-wave
convolutional neural network
url https://www.mdpi.com/1424-8220/25/11/3337
work_keys_str_mv AT erikstreser radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT sercanalipek radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT manuelrao radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT jonassimon radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT jochenmoll radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT peterkraemer radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading
AT viktorkrozer radarbaseddamagedetectioninawindturbinebladeusingconvolutionalneuralnetworksaproofofconceptunderfatigueloading