Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network

Wind turbine generators operate in harsh areas for a long time, resulting in frequent problems such as blade breakage, and traditional blade defect detection methods have low detection accuracy. In this paper, an end-toend target detection algorithm FRE-DETR based on wind turbine blade defects is de...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingwei Yang, Xiaocong Chen, Shengxian Cao, Bo Zhao, Zhenhao Tang, Gong Wang, Xingyu Li, Han Gao
Format: Article
Language:English
Published: Tamkang University Press 2025-04-01
Series:Journal of Applied Science and Engineering
Subjects:
Online Access:http://jase.tku.edu.tw/articles/jase-202512-28-12-0002
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713712098705408
author Jingwei Yang
Xiaocong Chen
Shengxian Cao
Bo Zhao
Zhenhao Tang
Gong Wang
Xingyu Li
Han Gao
author_facet Jingwei Yang
Xiaocong Chen
Shengxian Cao
Bo Zhao
Zhenhao Tang
Gong Wang
Xingyu Li
Han Gao
author_sort Jingwei Yang
collection DOAJ
description Wind turbine generators operate in harsh areas for a long time, resulting in frequent problems such as blade breakage, and traditional blade defect detection methods have low detection accuracy. In this paper, an end-toend target detection algorithm FRE-DETR based on wind turbine blade defects is designed, and the detection speed and detection accuracy of the end-to-end detection model are further improved by redesigning the feature extraction location in the backbone network and proposing a feature selection and fusion module. FRE-DETR is tested on a wind turbine blade defect dataset, and the results show that the model improves the detection accuracy by 2% compared with RTDETR-R18. The inference speed is already higher than RTDETR-R18 when the step size is larger than 2. The Gflops of the model is only 66.8% of that of RTDETR-R18, which also greatly reduces the computational requirements of the hardware when deployed. FRE-DETR meets the requirements of real-time detection.
format Article
id doaj-art-a382e56fc0d74a99a8b281fb58a7da23
institution DOAJ
issn 2708-9967
2708-9975
language English
publishDate 2025-04-01
publisher Tamkang University Press
record_format Article
series Journal of Applied Science and Engineering
spelling doaj-art-a382e56fc0d74a99a8b281fb58a7da232025-08-20T03:13:54ZengTamkang University PressJournal of Applied Science and Engineering2708-99672708-99752025-04-0128122329233910.6180/jase.202512_28(12).0002Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR networkJingwei Yang0Xiaocong Chen1Shengxian Cao2Bo Zhao3Zhenhao Tang4Gong Wang5Xingyu Li6Han Gao7Zhongdian Huachuang Electric Power Technology Research Co., Ltd., 215123, Suzhou, China.Hubei Zhongdian Chunyangshan wind power Co., LTD., 430040, Wuhan, China.Northeast Electric Power University, 132012, Jilin, China.Northeast Electric Power University, 132012, Jilin, China.Northeast Electric Power University, 132012, Jilin, China.Northeast Electric Power University, 132012, Jilin, China.Northeast Electric Power University, 132012, Jilin, China.Northeast Electric Power University, 132012, Jilin, China.Wind turbine generators operate in harsh areas for a long time, resulting in frequent problems such as blade breakage, and traditional blade defect detection methods have low detection accuracy. In this paper, an end-toend target detection algorithm FRE-DETR based on wind turbine blade defects is designed, and the detection speed and detection accuracy of the end-to-end detection model are further improved by redesigning the feature extraction location in the backbone network and proposing a feature selection and fusion module. FRE-DETR is tested on a wind turbine blade defect dataset, and the results show that the model improves the detection accuracy by 2% compared with RTDETR-R18. The inference speed is already higher than RTDETR-R18 when the step size is larger than 2. The Gflops of the model is only 66.8% of that of RTDETR-R18, which also greatly reduces the computational requirements of the hardware when deployed. FRE-DETR meets the requirements of real-time detection.http://jase.tku.edu.tw/articles/jase-202512-28-12-0002integrated energy systemend-to-end algorithmwind turbine blade defecttarget detect; computer vision
spellingShingle Jingwei Yang
Xiaocong Chen
Shengxian Cao
Bo Zhao
Zhenhao Tang
Gong Wang
Xingyu Li
Han Gao
Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
Journal of Applied Science and Engineering
integrated energy system
end-to-end algorithm
wind turbine blade defect
target detect; computer vision
title Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
title_full Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
title_fullStr Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
title_full_unstemmed Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
title_short Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
title_sort research on surface loss detection algorithm of wind turbine blade based on fre detr network
topic integrated energy system
end-to-end algorithm
wind turbine blade defect
target detect; computer vision
url http://jase.tku.edu.tw/articles/jase-202512-28-12-0002
work_keys_str_mv AT jingweiyang researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT xiaocongchen researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT shengxiancao researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT bozhao researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT zhenhaotang researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT gongwang researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT xingyuli researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork
AT hangao researchonsurfacelossdetectionalgorithmofwindturbinebladebasedonfredetrnetwork