An improved method of AUD-YOLO for surface damage detection of wind turbine blades
Abstract The detection of wind turbine blades (WTBs) damage is crucial for improving power generation efficiency and extending the lifespan of turbines. However, traditional detection methods often suffer from false positives and missed detections, and they do not adequately account for complex weat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89864-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850191186076106752 |
|---|---|
| author | Li Zou Anqi Chen Xinhua Yang Yibo Sun |
| author_facet | Li Zou Anqi Chen Xinhua Yang Yibo Sun |
| author_sort | Li Zou |
| collection | DOAJ |
| description | Abstract The detection of wind turbine blades (WTBs) damage is crucial for improving power generation efficiency and extending the lifespan of turbines. However, traditional detection methods often suffer from false positives and missed detections, and they do not adequately account for complex weather conditions such as fog and snow. Therefore, this study proposes a WTBs damage detection model based on an improved YOLOv8, named AUD-YOLO. Firstly, the ADown module is integrated into the YOLOv8 backbone to replace some conventional convolutional down-sampling operations, decreasing the parameter count while boosting the model’s capability to extract image features. Secondly, the model incorporates the UniRepLKNet large convolution kernel with the C2f module, enabling it to learn complex image features more comprehensively. Thirdly, a lightweight DySample dynamic up-sampler substitutes the nearest-neighbor interpolation up-sampling method in the original model, thereby obtaining richer semantic information. Experimental results show that the AUD-YOLO model demonstrates outstanding performance in detecting WTBs damage under complex and adverse weather conditions, achieving a 3% improvement in the mAP@0.5 metric and a 6.2% improvement in the mAP@0.5–0.95 metric compared to YOLOv8. Moreover, the model has only 2.5M parameters and 7.2 GFLOPs of computational complexity, this adaptation renders it appropriate for implementation in environments with constrained computational capacity, where precise detection is critical. Lastly, a mobile application named WTBs Damage Detection system is designed and developed, enabling mobile-based detection of WTBs damage. |
| format | Article |
| id | doaj-art-9fc09127a2564e97928fa6754446cdb7 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-9fc09127a2564e97928fa6754446cdb72025-08-20T02:14:59ZengNature PortfolioScientific Reports2045-23222025-02-0115111610.1038/s41598-025-89864-7An improved method of AUD-YOLO for surface damage detection of wind turbine bladesLi Zou0Anqi Chen1Xinhua Yang2Yibo Sun3School of Intelligent Rail Engineering, Dalian Jiaotong UniversitySchool of Intelligent Rail Engineering, Dalian Jiaotong UniversityLiaoning Key Laboratory of Welding and Reliability of Rail Transportation Equipment, Dalian Jiaotong UniversityLiaoning Key Laboratory of Welding and Reliability of Rail Transportation Equipment, Dalian Jiaotong UniversityAbstract The detection of wind turbine blades (WTBs) damage is crucial for improving power generation efficiency and extending the lifespan of turbines. However, traditional detection methods often suffer from false positives and missed detections, and they do not adequately account for complex weather conditions such as fog and snow. Therefore, this study proposes a WTBs damage detection model based on an improved YOLOv8, named AUD-YOLO. Firstly, the ADown module is integrated into the YOLOv8 backbone to replace some conventional convolutional down-sampling operations, decreasing the parameter count while boosting the model’s capability to extract image features. Secondly, the model incorporates the UniRepLKNet large convolution kernel with the C2f module, enabling it to learn complex image features more comprehensively. Thirdly, a lightweight DySample dynamic up-sampler substitutes the nearest-neighbor interpolation up-sampling method in the original model, thereby obtaining richer semantic information. Experimental results show that the AUD-YOLO model demonstrates outstanding performance in detecting WTBs damage under complex and adverse weather conditions, achieving a 3% improvement in the mAP@0.5 metric and a 6.2% improvement in the mAP@0.5–0.95 metric compared to YOLOv8. Moreover, the model has only 2.5M parameters and 7.2 GFLOPs of computational complexity, this adaptation renders it appropriate for implementation in environments with constrained computational capacity, where precise detection is critical. Lastly, a mobile application named WTBs Damage Detection system is designed and developed, enabling mobile-based detection of WTBs damage.https://doi.org/10.1038/s41598-025-89864-7WTBsDamage detectionYOLOv8Mobile application |
| spellingShingle | Li Zou Anqi Chen Xinhua Yang Yibo Sun An improved method of AUD-YOLO for surface damage detection of wind turbine blades Scientific Reports WTBs Damage detection YOLOv8 Mobile application |
| title | An improved method of AUD-YOLO for surface damage detection of wind turbine blades |
| title_full | An improved method of AUD-YOLO for surface damage detection of wind turbine blades |
| title_fullStr | An improved method of AUD-YOLO for surface damage detection of wind turbine blades |
| title_full_unstemmed | An improved method of AUD-YOLO for surface damage detection of wind turbine blades |
| title_short | An improved method of AUD-YOLO for surface damage detection of wind turbine blades |
| title_sort | improved method of aud yolo for surface damage detection of wind turbine blades |
| topic | WTBs Damage detection YOLOv8 Mobile application |
| url | https://doi.org/10.1038/s41598-025-89864-7 |
| work_keys_str_mv | AT lizou animprovedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT anqichen animprovedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT xinhuayang animprovedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT yibosun animprovedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT lizou improvedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT anqichen improvedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT xinhuayang improvedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades AT yibosun improvedmethodofaudyoloforsurfacedamagedetectionofwindturbineblades |