基于YOLOv5的管道环焊缝缺陷目标检测算法分析  

Analysis of target detection algorithm for pipeline circumferential weld defects based on YOLOv5

作　　者：彭云超 李亚平 齐峰 饶连涛 刘九宏 徐杰[3] PENG Yunchao;LI Yaping;QI Feng;RAO Liantao;LIU Jiuhong;XU Jie(PipeChina Network Corporation Eastern Oil Storage and Transportation Co.Ltd.,Xuzhou 221008,China;PipeChina Network Corporation Institute of Science and Technology,Langfang 065000,China;School of Materials Science and Physics,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]国家管网集团东部原油储运有限公司,徐州221008 [2]国家管网集团科学技术研究总院分公司,廊坊065000 [3]中国矿业大学材料与物理学院,徐州221116

出　　处：《无损检测》2025年第3期62-70,共9页Nondestructive Testing

基　　金：国家管网集团东部原油储运有限公司揭榜挂帅科技项目(GWHT20220042619)。

摘　　要：基于漏磁内检测技术,采用PyTorch框架,应用YOLOv5算法对实际管道环焊缝缺陷漏磁信号图像进行了自动识别,通过对算法的进一步优化与改进,分析了其对自动识别准确率的影响。试验结果表明,模型在图像数据混合增强后,各指标均有了显著提升,IoU阈值大于0.5的平均精度提升了近30%;通过增加小目标检测层,大幅降低了目标检测损失函数均值,改善了缺陷的目标检测效果;显著提升了缺陷的识别率,最高提升11.05%,获得了较好的自动识别结果。该方法为管道环焊缝信号异常数据判读提供了高效的方法和技术手段,对于管道智能化检测实际生产作业具有重要作用。Based on magnetic flux leakage internal detection technology,the PyTorch framework was used and the YOLOv5 algorithm was applied to automatically identify defects in pipeline circumferential weld seam magnetic flux leakage signal images.Through further optimization and improvement of the algorithm,its impact on the accuracy of automatic recognition was analyzed.The experimental results indicated that after image data mixing and enhancement in the model,all indicators were significantly improved and the average accuracy of IoU thresholds greater than 0.5 was improved by nearly 30%.By adding small object detection layers,the average loss function of object detection was significantly reduced and the object detection effect of defects in images was improved.The recognition rate of defects in images was significantly improved,with a maximum increase of 11.05%,achieving good automatic recognition results.This proposed method provided effective ideas and technical means for the interpretation of abnormal signal data of pipeline circumferential welds,and played an important role in the intelligent detection of pipelines in actual production operations.

关 键 词：漏磁内检测 管道环焊缝 自动识别 YOLOv5算法 小目标检测 

分 类 号：TG115.28[金属学及工艺—物理冶金] TE319[金属学及工艺—金属学]