改进YOLOv8的焊缝表面缺陷检测算法  

Improved weld surface defect detection algorithm from YOLOv8

作　　者：张润梅 潘晨飞 陈梓华 陈中 袁彬 Zhang Runmei;Pan Chenfei;Chen Zihua;Chen Zhong;Yuan Bin(School of Mechanical and Electrical Engineering,Anhui Jianzhu University,Hefei,Anhui 230601,China;School of Electronic and Information Engineering,Anhui Jianzhu University,Hefei,Anhui 230601,China)

机构地区：[1]安徽建筑大学机械与电气工程学院,安徽合肥230601 [2]安徽建筑大学电子与信息工程学院,安徽合肥230601

出　　处：《光电工程》2025年第3期111-123,共13页Opto-Electronic Engineering

基　　金：安徽省高校省级自然科学研究项目(2024AH050234);安徽省仿真设计与现代制造工程技术研究中心开放研究项目(SGCZXZD2101-202201);长安大学中央高校基本科研业务费专项资金资助(300102254501-202412);安徽省高等学校科学研究项目(2024AH050245)。

摘　　要：针对复杂背景下焊接缺陷特征不明显、背景信息复杂,导致传统缺陷检测算法在实际应用中精度不佳,特征丢失等问题,本文提出一种改进自YOLOv8的焊缝表面缺陷检测算法(GD-YOLO)。模型首先引进特征提取模块与卷积模块融合,增强模型信息的提取能力;然后在颈部网络中嵌入Slim-Neck结构并在特征融合阶段引用上采样算子CAFARE,辅助增强模型性能;其次,改进注意力机制模块,使之在不显著增加计算负担的情况下,优化整体性能;最后,改用损失函数Inner-SIoU,解决边界框不匹配的问题。实验结果表明,本文模型mAP0.5检测指标比基线模型高7.8%,参数量和计算量分别减少了0.12M、0.7G。In response to the problems of traditional defect detection algorithms,such as poor accuracy and feature loss in practical applications due to the inconspicuous characteristics of welding defects and complex background information,this paper proposes a welding surface defect detection algorithm based on the improved YOLOv8(GD-YOLO).The model first introduces the fusion of feature extraction modules and convolutional modules to enhance its information extraction capabilities.Then,a slim-neck structure is embedded in the neck network,and the upsampling operator CAFARE is referenced in the feature fusion stage to assist in enhancing the model's performance.Subsequently,the attention mechanism module is improved to optimize the overall performance without significantly increasing the computational burden.Finally,the loss function is changed to Inner-SIOU to address the problem of mismatched bounding boxes.Experimental results show that the mAP0.5 detection metric of the model in this paper is 7.8%higher than that of the baseline model,and the number of parameters and the amount of computation are reduced by 0.2 M and 0.7 G,respectively.

关 键 词：深度学习 缺陷检测 YOLOv8 Inner-SIoU 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]