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

PENG Yunchao; LI Yaping; QI Feng; RAO Liantao; LIU Jiuhong; XU Jie

doi:10.11973/wsjc240282

Nondestructive Testing > 2025 > 47(3): 62-70. > DOI: 10.11973/wsjc240282

PENG Yunchao, LI Yaping, QI Feng, RAO Liantao, LIU Jiuhong, XU Jie. Analysis of target detection algorithm for pipeline circumferential weld defects based on YOLOv5[J]. Nondestructive Testing, 2025, 47(3): 62-70. DOI: 10.11973/wsjc240282

Citation:

PDF (1536 KB)

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

1.
PipeChina Network Corporation Eastern Oil Storage and Transportation Co. Ltd., Xuzhou 221008, China
2.
PipeChina Network Corporation Institute of Science and Technology, Langfang 065000, China
3.
School of Materials Science and Physics, China University of Mining and Technology, Xuzhou 221116, China

More Information

Received Date: June 20, 2024

Graphical Abstract

Abstract

Abstract

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.
- internal magnetic leakage testing,
- pipeline circumferential weld,
- automatic recognition,
- YOLOv5 algorithm,
- small object detection

FullText(HTML)

References (30)

References

[1]	宋艾玲,梁光川,王文耀. 世界油气管道现状与发展趋势[J]. 油气储运,2006,25（10）：1-6．
[2]	郭绍忠,朱荣军,刘辉,等. 针对油气管道运输泄露检测技术的研究[J]. 化工管理,2017（22）：86．
[3]	高鹏. 2021年中国油气管道建设新进展[J]. 国际石油经济,2022,30（3）：12-19．
[4]	HAN Z Y ,WENG W G ．An integrated quantitative risk analysis method for natural gas pipeline network[J]. Journal of Loss Prevention in the Process Industries,2010,23（3）：428-436．
[5]	穆海辉. 管道施工中的质量问题、管控措施及典型案例分析[J]. 化学工程与装备,2020（6）：123-125．
[6]	王钰滔,吕延鑫,杨万里,等. 国内外输气管道事故研究综述[J]. 化工设备与管道,2022,59（4）：78-84．
[7]	杨志军,刘玉琢,吴忠义,等. 管道外漏磁检测技术研究[J]. 压力容器,2018,35（3）：56-62．
[8]	尹升. 油气管道完整性管理效能评价技术分析[J]. 全面腐蚀控制,2022,36（9）：86-87．
[9]	赵宁,程晨. 油气管道完整性管理技术的发展趋势探讨[J]. 科技风,2019（17）：147．
[10]	晏祥省,黄彪,吕华鹏. 油气管道完整性管理方法与技术要点分析[J]. 石化技术,2022,29（8）：174-176．
[11]	杨理践,耿浩,高松巍. 长输油气管道漏磁内检测技术[J]. 仪器仪表学报,2016,37（8）：1736-1746．
[12]	田贵云,高斌,高运来,等. 铁路钢轨缺陷伤损巡检与监测技术综述[J]. 仪器仪表学报,2016,37（8）：1763-1780．
[13]	孙燕华,康宜华,宋凯,等. 基于单线圈斜向磁化的钢管漏磁检测方法[J]. 无损检测,2008,30（11）：800-803．
[14]	赵翰学,张咪,郭岩宝,等. 基于机器学习的管道金属损失缺陷识别方法[J]. 石油机械,2020,48（12）：138-145．
[15]	王国庆,李璇,杨理践,等. 基于改进YOLOv5算法的管道漏磁信号识别方法[J]. 计算机测量与控制,2022,30（8）：1-13．
[16]	冯子勇基于深度学习的图像特征学习和分类方法的研究及应用广州华南理工大学2016冯子勇. 基于深度学习的图像特征学习和分类方法的研究及应用[D]. 广州：华南理工大学,2016．
[17]	刘金海,赵贺,神祥凯,等. 基于漏磁内检测的自监督缺陷检测方法[J]. 仪器仪表学报,2020,41（9）：180-187．
[18]	许德刚,王露,李凡. 深度学习的典型目标检测算法研究综述[J]. 计算机工程与应用,2021,57（8）：10-25．
[19]	马天航,胡家铖,郑莉,等. 一种基于人工提取缺陷块的边界搜索方法[J]. 无损检测,2020,42（8）：1-7．
[20]	FENG J ,LI F M ,LU S X ,et al ．Injurious or noninjurious defect identification from MFL images in pipeline inspection using convolutional neural network[J]. IEEE Transactions on Instrumentation and Measurement,2017,66（7）：1883-1892．
[21]	YANG L J ,WANG Z J ,GAO S W ,et al ．Magnetic flux leakage image classification method for pipeline weld based on optimized convolution kernel[J]. Neurocomputing,2019,365：229-238．
[22]	CHEN P C ,LI R ,FU K ,et al ．A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data[J]. Mechanical Systems and Signal Processing,2024,206：110919．
[23]	XU L S ,DONG S H ,WEI H T ,et al. Intelligent identification of girth welds defects in pipelines using neural networks with attention modules[J]. Engineering Applications of Artificial Intelligence,2024（127）：107295．
[24]	戴光,崔巍,杨志军,等. 基于三维有限元的换热管缺陷漏磁场数值模拟[J]. 压力容器,2009,26（8）：21-26,6．
[25]	刘刚管道漏磁内检测关键技术问题研究沈阳沈阳工业大学2010刘刚. 管道漏磁内检测关键技术问题研究[D]. 沈阳：沈阳工业大学,2010．
[26]	曹辉,杨理践,刘俊甫,等. 基于数据融合的小波变换漏磁异常边缘检测[J]. 仪器仪表学报,2019,40（12）：71-79．
[27]	刘延雷,戴光,郑津洋. 漏磁检测管道裂纹的有限元分析与试验研究[J]. 压力容器,2006,23（12）：16-19．
[28]	赵崇林,朱江,胡永进,等. 融合注意力和多尺度特征的航空发动机缺陷检测[J]. 北京航空航天大学学报,2023,49（5）：1-14．
[29]	杨晓丽,段敏,虞汉年,等. 基于YOLO算法的车辆实时检测研究[J]. 仪器仪表与分析监测,2021（1）：7-10．
[30]	张秋雁,朱傥,肖书舟,等. 基于改进YOLOv4算法的高压输电线路异物检测[J]. 应用科技,2023,50（4）：1-7．

Cited By

Get Citation

PDF

XML

Article views (25) PDF downloads (8)

Turn off MathJax

Article Contents

Abstract

References

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

Abstract

References

Catalog

Export File

Citation

Format

Content