基于改进YOLOv5的光伏组件EL图像缺陷检测方法

郑宗惠; 马鹏阁

doi:doi:10.19912/j.0254-0096.tynxb.2024-1101

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于改进YOLOv5的光伏组件EL图像缺陷检测方法

更新时间：2025-12-17

- 基于改进YOLOv5的光伏组件EL图像缺陷检测方法
- Issue 10, Pages: 295-301(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1101
  CLC： P183
- Published Online：31 October 2025，
  
  Published：31 October 2025
- 稿件说明：
移动端阅览
郑宗惠, 马鹏阁. 基于改进YOLOv5的光伏组件EL图像缺陷检测方法[J]. 2025, (10): 295-301.
DOI：

郑宗惠, 马鹏阁. 基于改进YOLOv5的光伏组件EL图像缺陷检测方法[J]. 2025, (10): 295-301. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1101.

摘要

针对光伏组件电致发光（EL）图像中缺陷因复杂背景干扰而难以识别的问题

提出一种基于YOLOv5改进的深度学习模型YOLOv5-PMD

有助于提高光伏组件EL图像缺陷检测的准确性。首先使用轻量级卷积GSConv模块替换颈部网络（Neck）的卷积Conv模块

增强模型准确性的同时可减少模型参数量。其次引入卷积块注意力模块（CBAM）

增强模型对特征的感知能力。最后将原模型的CIoU损失函数替换为EIoU损失函数

更加准确地衡量缺陷的位置。在光伏组件EL图像的公开SolarMonocrystal数据集上

改进模型的训练参数量从7.025×106降到6.695×106

平均精度均值mAP50为89.8%

相较于原模型提高2.6％。

Abstract

The complex background interference in electroluminescence（EL） images of photovoltaic modules poses challenges for accurate defect identification. To address this

an improved deep learning model YOLOV5-PMD based on YOLOv5 is proposed. This model utilizes a lightweight convolution GSConv module to replace the Conv part of the Neck

enhancing accuracy while reducing the number of parameters. In addition

the convolutional CBAM attention mechanism is combined to improve the feature perception ability

and the EIoU loss function is replaced by the CIoU loss function to achieve more accurate defect location. On the public SolarMonocrystal dataset

the improved model reduces the training parameters from 7.025×10 to 6.695×10

and the average accuracy of mAP50 reaches 89.8%

which is 2.6% higher than that of the original model.

关键词

Keywords

references

李明东, 李婧雯. “双碳” 目标下中国分布式光伏发电的发展现状和展望[J]. 太阳能, 2023(5): 5-10.

徐惠. 浅析太阳能光伏组件隐裂的影响及控制措施[J]. 安装, 2020(8): 70-72.

蒋尚俊, 易辉, 李红涛, 等. 基于迁移学习与ResNet的太阳电池缺陷检测方法[J]. 太阳能学报, 2023, 44(7): 116-121.

张德钰. 基于YOLOv5的太阳能电池片EL图像缺陷检测算法[J]. 电视技术, 2024, 48(1): 42-47, 55.

谢林森, 朱文忠, 谢康康, 等. 基于改进YOLOv5s的光伏电池EL缺陷图像检测模型[J]. 国外电子测量技术, 2023, 42(6): 93-102.

LIANG L, WANG X B, LI X F, et al.Research on fault object detection method for photovoltaic panel UAV inspection based on YOLOv5[C]//2023 9th International Conference on Computer and Communications(ICCC). Chengdu, China, 2023: 1766-1770.

CONG Z H, SUN H K, WANG S J, et al.YOLOv5-CPP: improved YOLOv5-based defect detection for photovoltaic panels[C]//2023 42nd Chinese Control Conference (CCC), Tianjin, China, 2023: 8294-8299.

范钧玮, 饶全瑞, 赵薇, 等. 改进的YOLOv5双影像光伏故障小目标检测[J]. 太阳能学报, 2024, 45(7): 510-516.

徐威, 李为相, 方志, 等. 基于改进YOLOv7-tiny的光伏电池缺陷检测算法[J]. 计算机工程与应用, 2024, 60(15): 336-343.

GUAN Q J, YU K, WANG H R, et al.Lightweight protective clothing detection algorithm based on ghost convolution and GSConv convolution[C]//2023 International Conference on the Cognitive Computing and Complex Data (ICCD). Huaian, China, 2023: 73-77.

梁礼明, 龙鹏威, 卢宝贺, 等. 改进GBS-YOLOv7t的钢材表面缺陷检测[J]. 光电工程, 2024, 51(5): 240044.

邓志军, 田秋红. 改进Inception-v3网络的手势图像识别[J]. 计算机系统应用, 2022, 31(11): 157-166.

陈辉, 张傲, 孙帅, 等. 基于改进DeepLabv3+的含噪声热红外图像光伏热斑检测方法[J]. 太阳能学报, 2023, 44(11): 23-30.

王向前, 成高立, 胡鹏, 等. 基于改进YOLOv5的路面裂缝检测方法[J]. 电子技术应用, 2024, 50(3): 80-85.

王银, 高瑞泽, 李茂环, 等. 基于YOLOv5 LiteX算法的光伏组件缺陷检测[J]. 太阳能学报, 2023, 44(9): 101-108.

李安达, 吴瑞明, 李旭东. 改进YOLOv7的小目标检测算法研究[J]. 计算机工程与应用, 2024, 60(1): 122-134.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SEMANTIC SEGMENTATION MODEL OF PHOTOVOLTAIC MODULES BASED ON VISUAL FEATURES

IMPROVED YOLOv5 DUAL-IMAGE PHOTOVOLTAIC FAULT SMALL TARGET DETECTION

基于IDBO优化的BiTCN-BiLSTM-SA光伏组件积灰预测

基于HCF-YOLO的光伏组件红外图像热斑故障检测

信息融合的NRP-AlexNet-SENet风电齿轮箱故障诊断

Related Author

Wang Yin

Shen Lingxin

Li Maohuan

Wang Jian'an

Li Xiaosong

Fan Junwei

Rao Quanrui

Zhao Wei

Related Institution

School of Electronic Information Engineering, Taiyuan University of Science and Technology

Nanjing Dirui Technology Co., Ltd.

School of Information and Electrical Engineering, Ludong University

School of Mathematics and Statistical Science, Ludong University

School of New Energy, Shenyang Institute of Engineering

AI问答

⁰