计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 250100126-6.doi: 10.11896/jsjkx.250100126

• 计算机图形学&多媒体 • 上一篇    下一篇

C2P-YOLO:一种轻量级的风电塔筒裂缝检测算法

段鹏松1, 高杨1, 张大龙1, 曹仰杰1, 赵杰2   

  1. 1 郑州大学网络空间安全学院 郑州 450000
    2 上海红檀智能科技有限公司 上海 200000
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 曹仰杰(caoyj@zzu.edu.cn)
  • 作者简介:duanps@163.com
  • 基金资助:
    郑州市协同创新重大专项(20XTZX06013);中国工程科技发展战略河南研究院战略咨询研究项目(2022HENYB03);河南省科技攻关项目(232102210050,242102210060)

C2P-YOLO:A Lightweight Crack Detection Algorithm for Wind Turbine Towers

DUAN Pengsong1, GAO Yang1, ZHANG Dalong1, CAO Yangjie1, ZHAO Jie2   

  1. 1 School of Cyberspace Security,Zhengzhou University,Zhengzhou 450000,China
    2 Shanghai Red Sandalwood Intelligent Technology Co.,Ltd.,Shanghai 200000,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    Zhengzhou City Collaborative Innovation Major Project(20XTZX06013),Strategic Consulting Research Project of Henan Research Institute of China Engineering Science and Technology Development Strategy(2022HENYB03) and Science and Technology Tackling Project of Henan Province(232102210050,242102210060).

PDF (PC)

14

摘要： 风电塔筒作为整个风电设备的支撑结构,其安全性至关重要。裂缝作为风电塔筒主要的病害之一,对其进行准确检测十分有必要。受限于特征提取能力不足,现有的裂缝检测算法存在精度较低、模型复杂度较高的问题,不能很好满足端侧设备现场检测的需求。为此,文中提出了一种基于YOLO的风电塔筒安全性检测算法C2P-YOLO。在主干网络部分,该算法利用轻量级的特征提取模块C2P来代替冗余的网络结构,以提取特征图中更丰富的特征信息。在颈部网络部分,该算法添加了轻量化上采样CARFE和注意力机制模块,以补充特征融合过程中的信息损失。实验结果表明,该算法在公开数据集NEU-DET上的mAP分数达到84.9%,相较于同类算法提升了3%~8%,且能保持较好的轻量化特性。

关键词: 深度学习, 缺陷检测, 目标检测

Abstract: The safety of wind turbine tower,as the support structure of the whole wind turbine,is crucial.As one of the main diseases of wind turbine tower,it is necessary to detect cracks accurately.Due to the lack of feature extraction capability,the existing crack detection algorithms have low accuracy and high model complexity,which cannot well meet the needs of end-side equipment on-site detection.For this reason,this paper proposes a YOLO-based wind tower safety detection algorithm C2P-YOLO.In the backbone network part,the algorithm utilizes the lightweight feature extraction module C2P instead of the redundant network structure,in order to extract richer feature information in the feature map.In the neck network part,the algorithm adds the lightweight up-sampling CARFE and attention mechanism modules to complement the information loss in the feature fusion process.Experimental results show that the algorithm achieves a mAP score of 84.9% on the publicly available dataset NEU-DET,which is 3%~8% higher than similar algorithms,and it can maintain a better lightweight property.

Key words: Deep learning, Defect detection, Object detection

中图分类号: 

  • TP183
[1]SHAN L.Selection of the wind turbine tower structure and mechanical properties research[D].Harbin:Harbin Institute of Technology,2009:12-15.
[2]HAN Q,ZHANG Z,XU X Y,et al.Steel surface defect detection algorithm based on FF R-CNN[J].Journal of Taiyuan University of Technology,2021,52(5):754-763.
[3]SI S L.Light weight YOLOv4 steel surface defect detectionmethod[D].Fuxin:Liaoning University of Engineering and Technology,2022.
[4]DING S,YANG C,ZHANG S.Acoustic-Signal-Based Damage Detection of Wind Turbine Blades－A Review[J].Sensors,2023,23(11):4987.
[5]ZHANG Y,YANG Y,SUN J,et al.Surface Defect Detection of Wind Turbine Based on Lightweight YOLOv5s Model[J].Measurement,2023:113222.
[6]GENG R S,SHEN G T,LIU S F.Acoustic emission signal processing and analysis technology[J].Nondestructive Testing,2002,24(1):23-28.
[7]XU D,LIU P F,CHEN Z P.Damage mode identification andsingular signal detection of composite wind turbine blade using acoustic emission[J].Composite Structures,2021,255:112954.
[8]ZHAO Z,CHEN N Z.Acoustic emission based damage source localization for structural digital twin of wind turbine blades[J].Ocean Engineering,2022.
[9]BEJGER A,DRZEWIENIECKI J B,BARTOSZKO P,et al.The Use of Coherence Functions of Acoustic Emission Signals as a Method for Diagnosing Wind Turbine Blades[J].Energies,2023,16(22):7474.
[10]LI J,SU Z,GENG J,et al.Real-time detection of steel strip surface defects based on improved YOLO detection network[J].IFAC-Papers On Line,2018,51:76-81.
[11]ZHANG C,CHANG C,JAMSHIDI M.Concrete bridge surface damage detection using a single-stage detector[J].Comput-Aided Civil Infrastruct Eng,2020,35:389-409.
[12]LIU Q,WANG C,LI Y,et al.A Fabric Defect Detection Method Based on Deep Learning [J].IEEE Access,2022,10:4284-96.
[13]OLIVIER R,HANQIANG C.Nearest Neighbor Value Interpolation[J].International Journal of Advanced Computer Science &Application,2012,3(4):25-30.
[14]WANG J,CHEN K,XU R,et al.Carafe:Content-aware reas-sembly of features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:3007-3016.
[15]LIN H,JING C,HUANG Y,et al.A2 Net:Adjacent Aggregation Networks for Image Raindrop Removal[J].IEEE Access,2020,PP(99):1.
[16]SONG K,YAN Y.A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects[J].Applied Surface Science,2013,285:858-864.
[17]LV X,DUAN F,JIANG J,et al.Deep metallic surface defect detection:The new benchmark and detection network[J].Sensors,2020,20(6):1562.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发