基于YOLOv5的管道环焊缝缺陷TOFD图谱识别  

Defect recognition of circumferential welds of pipelines in TOFD images based on YOLOv5

作　　者：徐成[1,3] 董仕豪 欧正宇 韩赞东 XU Cheng;DONG Shihao;OU Zhengyu;HAN Zandong(State Key Laboratory of Clean and Efficient Turbomachinery Power Equipment,Department of Mechanical Engineering,Tsinghua University,Beijing,100084,China;Key Laboratory for Advanced Materials Processing Technology,Ministry of Education,Department of Mechanical Engineering,Tsinghua University,Beijing,100084,China;Training Base of Army Engineering University,Xuzhou,221004,China)

机构地区：[1]清华大学,机械工程系,清洁高效透平动力装备全国重点实验室,北京100084 [2]清华大学,机械工程系,先进成形制造教育部重点实验室,北京100084 [3]陆军工程大学训练基地,徐州221004

出　　处：《焊接学报》2025年第4期22-31,共10页Transactions of The China Welding Institution

基　　金：国家自然科学基金资助项目(U23B2096)。

摘　　要：为提高管道环焊缝超声衍射时差法(time of flight diffraction,TOFD)扫描图谱在背景信号干扰、样本量不均衡等情况下的缺陷识别效果,提出了一种改进的YOLOv5s网络模型.针对管道环焊缝TOFD图谱中缺陷形态不规则的特点,通过引入可变形卷积,使得网络自适应缺陷自身的形状特点,提高TOFD图谱中不规则缺陷的特征提取能力;针对TOFD扫描图谱中直通波和底面波等干扰波形对缺陷识别的影响,通过在网络不同深度分别添加自注意力机制,引导网络关注缺陷细微特征的同时抑制界面波对缺陷识别的影响;针对实际样本中各类缺陷不均衡的情况,采用SlideLoss损失函数代替原损失函数,提高网络对样本量较少的裂纹类缺陷的识别精度.对比试验结果表明,改进后的网络能够抑制TOFD图谱复杂背景干扰,提高样本不均衡条件下的识别率.相比原网络,整体平均识别率均值(mean Average Precision,mAP)和裂纹类缺陷的平均识别率(Average Precision,AP)分别提高了8.2%和7.3%.In order to enhance defect recognition in time-of-flight diffraction(TOFD)scan images for circumferential welds of pipelines under conditions such as background signal interference and uneven sample distribution,an improved YOLOv5s network model was proposed.In view of the defects with irregular shapes in TOFD images for circumferential welds of pipelines,deformable convolutions were introduced,enabling the network to adapt to the shape characteristics of defects and improving the feature extraction capability for irregular defects in TOFD images.To study the influence of interference waveforms such as direct wave and bottom wave on defect recognition in TOFD images,self-attention mechanisms were incorporated at different depths of the network,guiding the network to focus on subtle defect features while effectively suppressing the impact of interface waves on defect recognition.Furthermore,to tackle the issue of class imbalance in real-world defect samples,the SlideLoss loss function was employed to replace the original loss function,thereby enhancing the recognition accuracy for crack-type defects with limited sample sizes.Comparative experiments demonstrate that the improved network effectively suppresses complex background interference in TOFD images and improves defect recognition efficiency under imbalanced sample conditions.Compared to those of the original network,the overall mean average precision(mAP)and the average precision(AP)for crack-type defects have increased by 8.2%and 7.3%,respectively.

关 键 词：焊缝缺陷 超声衍射 缺陷识别 注意力机制 可变形卷积 

分 类 号：TG409[金属学及工艺—焊接]