Research on crack detection method of wind turbine blade based on a deep learning method

Zhu Xiaoxun, Hang Xinyu, Gao Xiaoxia, Yang Xing, Xu Zixu, Wang Yu and Liu Huaxin

Applied Energy, 2022, vol. 328, issue C, No S0306261922014982

Abstract: For the propose of improving the economic benefits of wind turbine utilization, an image recognition model based on deep learning called ‘Multivariate Information You Only Look Once’(MI-YOLO) is proposed which can detect the surface cracks of wind turbine blade efficiently, especially for cracks with light colors. In order to improve the extraction ability of light color and low definition, the Multivariate Information fusion and the use of C3TR module are put forward. Alpha-IOU is used to balance the precision rate and recall rate of the new model, and further improve the mAP. Aim at solving the problem of small amount of data and unbalanced positive and negative samples, two new data enhancement methods are employed. The detection performance of the proposed method is tested using wind turbine’s blade images with cracks taken by Unmanned Aerial Vehicle (UAV). Results show that the MI-YOLO is not only lighter, but also has a higher mAP than the YOLOv5s. Meanwhile, the economic efficiency of the proposed method is analyzed and compared with other detection method with the limitations of the proposed method for offshore wind turbines also being discussed.

Keywords: Wind turbine; Blade crack detection; MI-YOLO; Multivariate information; Data enhancement; Alpha-IOU (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261922014982
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:328:y:2022:i:c:s0306261922014982

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2022.120241

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().