计算机与现代化 ›› 2025, Vol. 0 ›› Issue (09): 43-49.doi: 10.3969/j.issn.1006-2475.2025.09.006

• 人工智能 • 上一篇    下一篇

基于改进YOLOv8-EDD的光伏板缺陷检测

  


  1. (1.国能锦界能源有限责任公司,陕西 榆林 719319; 2.中国电建集团华东勘测设计研究院有限公司,浙江 杭州 311122;
    3.三峡大学电气与新能源学院,湖北 宜昌 443002)
  • 出版日期:2025-09-24 发布日期:2025-09-24
  • 作者简介: 作者简介:贾涛(1984—),男,陕西榆林人,工程师,本科,研究方向:新能源发电系统运维管理,E-mail: jtao1984@126.com; 吴月超(1988—),男,河北承德人,高级工程师,博士,研究方向:信息系统运维管理,E-mail: wu_yc@fdec.com; 吕洋(1995—),男,工程师,硕士,研究方向:信息系统运维管理,E-mail: lv_y2@hdec.com; 通信作者:付文龙(1988—),男,湖北仙桃人,副教授,博士,研究方向:智能控制,机器视觉,人工智能应用,E-mail: ctgu_fuwenlong@126.com。

Defect Detection of Photovoltaic Panel Based on Improved YOLOv8-EDD


  1. (1. Guoneng Jinjie Energy Co., Ltd., Yulin 719319, China; 
    2. Power China Huadong Engineering Co., Ltd., Hangzhou 311122, China;
    3. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China)
  • Online:2025-09-24 Published:2025-09-24
  • Supported by:
        基金项目:湖北省自然科学基金联合基金资助项目(2024AFD409)

摘要:
摘要:针对现有光伏板缺陷检测方法精度低、检测速度慢等问题,提出一种改进的YOLOv8-EDD光伏板缺陷检测模型。首先,引入多尺度注意力机制EMA,使YOLOv8模型能够更好地关注光伏板缺陷区域;其次,在原有C2f模块中引入可变形卷积DCNv2,增强模型对不规则缺陷形状的提取能力,同时为了缓解由于DCNv2参数量大导致模型检测速度降低的问题,使用DySample轻量级上采样算子替换YOLOv8原有上采样算子,以降低模型参数量和计算复杂度,提高模型的检测速度;最后,引入WIoUv3损失函数,降低低质量样本对模型精度影响,提高模型的泛化能力。实验中,改进的YOLOv8-EDD模型与原始模型相比精度提高了15.3百分点,召回率提高了11.3百分点,均值平均精度提高了10.5百分点,检测速度增长了6.5 FPS。结果表明,本文所提出的改进模型在提高检测精度的同时具有更快的检测速度,更适用于光伏板缺陷检测。


关键词: 关键词:YOLOv8, 光伏板缺陷检测, EMA, DySample, WIoUv3

Abstract:
Abstract: To solve the problems of low accuracy and slow detection speed of existing defect detection methods for photovoltaic panels, an novel defect detection model for photovoltaic panels is proposed based on improved YOLOv8-EDD. Firstly, multi-scale attention mechanism EMA is introduced to enable YOLOv8 model to pay more attention to the defect area of photovoltaic panels. Secondly, deformable convolutional DCNv2 is embedded into the original C2f module to enhance the model’s ability to extract irregular defect shape. At the same time, in order to alleviate the problem of reduced model detection speed due to the large number of DCNv2 parameters, the DySample lightweight upsampling operator is used to replace the original upsampling operator of YOLOv8 to reduce the number of model parameters and calculation complexity, thus to enhance the detecting speed. Finally, WIoUv3 loss function is integrated to reduce the influence of low-quality samples on the accuracy and improve the generalization ability of the model. In the experiment, compared with the original model, the accuracy of the improved YOLOv8-EDD model increases by 15.3 percentage points, the recall rate increases by 11.3 percentage points, mean of the average accuracy increases by 10.5 percentage points, and the detection speed has increased by 6.5 FPS. The results show that the proposed model not only improves the detection accuracy but also has faster detection speed, and is more suitable for the defect detection of photovoltaic panels.

Key words: Key words: YOLOv8, photovoltaic panel defect detection, EMA, DySample, WIoUv3

中图分类号: