Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7

The blade is one of the key components of the wind turbine, which is vulnerable to the impact of natural environmental factors, resulting in gel coat falling off, cracks, corrosion, and other damage and thus affecting the efficiency of wind power generation and the safety of wind turbine operation....

Full description

Saved in:
Bibliographic Details
Main Authors: Bing LI, Yunshan BAI, Kuan ZHAO, Congbin GUO, Yongjie ZHAI
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2023-08-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202304059
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037362165284864
author Bing LI
Yunshan BAI
Kuan ZHAO
Congbin GUO
Yongjie ZHAI
author_facet Bing LI
Yunshan BAI
Kuan ZHAO
Congbin GUO
Yongjie ZHAI
author_sort Bing LI
collection DOAJ
description The blade is one of the key components of the wind turbine, which is vulnerable to the impact of natural environmental factors, resulting in gel coat falling off, cracks, corrosion, and other damage and thus affecting the efficiency of wind power generation and the safety of wind turbine operation. A defect detection algorithm for wind turbine blades based on HSCA-YOLOv7 is proposed to address the issues of inconsistent defect scale, inaccurate positioning, and low detection accuracy in wind turbine blade images by aerial photography. Firstly, based on the images of wind turbine blades collected by drones, a dataset of blades is created, and Mosaic and MixUp methods are used for data amplification. Then, deep separable convolutions with different expansion rates are introduced into the improved spatial pyramid pooling (ISPP) module to reduce the loss of details caused by pooling operations. Hybrid spatial channel attention (HSCA) is proposed to capture the global visual scene context, increase the semantic difference between target features and the environment, and solve the problem of inconsistent defect scales in blade images. The focal EIoU loss function is used to solve the problem that the length and width of the prediction box are wrongly amplified and improve the positioning ability of the model for blade defects. The experimental results show that the mAP and mAR of the proposed algorithm reach 83.64% and 71.96%, respectively, which are 3.37% and 5% higher than the YOLOv7 baseline algorithm.
format Article
id doaj-art-be7b7d768dee42ef878f66e4ea3aaf12
institution DOAJ
issn 1004-9649
language zho
publishDate 2023-08-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-be7b7d768dee42ef878f66e4ea3aaf122025-08-20T02:56:52ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492023-08-015610435210.11930/j.issn.1004-9649.202304059zgdl-56-10-libingSurface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7Bing LI0Yunshan BAI1Kuan ZHAO2Congbin GUO3Yongjie ZHAI4Department of Automation, North China Electric Power University, Baoding 071003, ChinaDepartment of Automation, North China Electric Power University, Baoding 071003, ChinaDepartment of Automation, North China Electric Power University, Baoding 071003, ChinaDepartment of Automation, North China Electric Power University, Baoding 071003, ChinaDepartment of Automation, North China Electric Power University, Baoding 071003, ChinaThe blade is one of the key components of the wind turbine, which is vulnerable to the impact of natural environmental factors, resulting in gel coat falling off, cracks, corrosion, and other damage and thus affecting the efficiency of wind power generation and the safety of wind turbine operation. A defect detection algorithm for wind turbine blades based on HSCA-YOLOv7 is proposed to address the issues of inconsistent defect scale, inaccurate positioning, and low detection accuracy in wind turbine blade images by aerial photography. Firstly, based on the images of wind turbine blades collected by drones, a dataset of blades is created, and Mosaic and MixUp methods are used for data amplification. Then, deep separable convolutions with different expansion rates are introduced into the improved spatial pyramid pooling (ISPP) module to reduce the loss of details caused by pooling operations. Hybrid spatial channel attention (HSCA) is proposed to capture the global visual scene context, increase the semantic difference between target features and the environment, and solve the problem of inconsistent defect scales in blade images. The focal EIoU loss function is used to solve the problem that the length and width of the prediction box are wrongly amplified and improve the positioning ability of the model for blade defects. The experimental results show that the mAP and mAR of the proposed algorithm reach 83.64% and 71.96%, respectively, which are 3.37% and 5% higher than the YOLOv7 baseline algorithm.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202304059wind turbine bladesdefect detectionyolov7attention mechanismfocal eiou
spellingShingle Bing LI
Yunshan BAI
Kuan ZHAO
Congbin GUO
Yongjie ZHAI
Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
Zhongguo dianli
wind turbine blades
defect detection
yolov7
attention mechanism
focal eiou
title Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
title_full Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
title_fullStr Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
title_full_unstemmed Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
title_short Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7
title_sort surface defect detection algorithm for wind turbine blades based on hsca yolov7
topic wind turbine blades
defect detection
yolov7
attention mechanism
focal eiou
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202304059
work_keys_str_mv AT bingli surfacedefectdetectionalgorithmforwindturbinebladesbasedonhscayolov7
AT yunshanbai surfacedefectdetectionalgorithmforwindturbinebladesbasedonhscayolov7
AT kuanzhao surfacedefectdetectionalgorithmforwindturbinebladesbasedonhscayolov7
AT congbinguo surfacedefectdetectionalgorithmforwindturbinebladesbasedonhscayolov7
AT yongjiezhai surfacedefectdetectionalgorithmforwindturbinebladesbasedonhscayolov7