电子测量与仪器学报

唐建华,张鑫,刘金海,刘海超,卢进.基于复合骨干网络的漏磁小缺陷信号检测方法[J].电子测量与仪器学报,2024,38(10):69-77

基于复合骨干网络的漏磁小缺陷信号检测方法

Signal detection method for magnetic flux leakage small defectsbased on composite backbone network

DOI：

英文关键词:magnetic flux leakage deep learning defect detection positive and negative sample feature fusion

基金项目:国家自然科学基金（62373085，U21A20481）项目资助

作者	单位
唐建华	中海油（天津）管道工程技术有限公司天津300452
张鑫	东北大学信息科学与工程学院沈阳110819
刘金海	东北大学信息科学与工程学院沈阳110819
刘海超	1.中海油（天津）管道工程技术有限公司天津300452；3.天津市海底管道重点实验室天津300450；4.海油发展海底管道安全服役保障技术重点实验室天津300450
卢进	1.中海油（天津）管道工程技术有限公司天津300452；3.天津市海底管道重点实验室天津300450；4.海油发展海底管道安全服役保障技术重点实验室天津300450

Author	Institution
Tang Jianhua	CNOOC (Tianjin) Pipeline Engineering Technology Co., Ltd., Tianjin 300452, China
Zhang Xin	College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Liu Jinhai	College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Liu Haichao	1.CNOOC (Tianjin) Pipeline Engineering Technology Co., Ltd., Tianjin 300452, China; 3.Tianjin Key Laboratory of Subsea Pipeline，Tianjin 300450, China; 4.CNOOC Energy Technology & Services Limited Key Laboratory of Safety Guarantee Technology for Subsea Pipeline，Tianjin 300450, China
Lu Jin	1.CNOOC (Tianjin) Pipeline Engineering Technology Co., Ltd., Tianjin 300452, China; 3.Tianjin Key Laboratory of Subsea Pipeline，Tianjin 300450, China; 4.CNOOC Energy Technology & Services Limited Key Laboratory of Safety Guarantee Technology for Subsea Pipeline，Tianjin 300450, China

摘要点击次数: 393

全文下载次数: 1320

中文摘要:

漏磁内检测是管道内检测的核心技术,对保障管道的安全运输至关重要。管道长期处于地下或深海,复杂的环境导致管道表面存在许多小缺陷。由于小缺陷可利用信息有限,传统的深度学习缺陷检测方法识别小缺陷难以获得满意的检测结果。提出了一种基于复合骨干网络的漏磁小缺陷信号检测方法。首先,提出了一种名为背景压缩的数据增强方法,以压缩背景信号进而增强小缺陷关键特征。其次,设计一种自适应的正负样本分配策略,以改善小缺陷在区域候选网络中正负样本分配不均匀的问题。最后,提出了一种小缺陷多分支高分辨率特征提取网络,利用多分支复合结构获得高分辨率特征进行特征融合,以提高网络对小缺陷纹理信息的利用率。以试验场管道数据对所提方法进行验证,实验结果表明,设计的方法是有效的,检测精度达90.3%,与最好结果相比,mAP提升8.4%。

英文摘要:

Magnetic flux leakage (MFL) internal detection is the core technology of pipeline internal detection, which is crucial to ensuring the safe transportation of pipelines. Due to the long-term underground or deep sea environment of pipelines, there are many small defects on the surface of pipelines. Due to the limited information available on small defects, traditional deep learning defect detection methods have difficulty achieving satisfactory detection results for small defects. A composite backbone network-based signal detection method for small magnetic leakage defects is proposed. First, a data enhancement method called background compression is proposed to compress background signals and thus enhance key features of small defects. Secondly, an adaptive positive and negative sample allocation strategy is designed to address the issue of uneven positive and negative sample allocation for small defects in the region proposal network. Finally, a multi-branch high-resolution feature extraction network for small defects is proposed, which uses a multi-branch composite structure to obtain high-resolution features for feature fusion, thereby improving the network’s utilization of small defect texture information. The proposed method is validated using pipeline data from a test site, and the experimental results show that the proposed method is effective, achieving a detection accuracy of 90.3%, with an 8.4% mAP improvement compared to the best results.

查看全文查看/发表评论下载PDF阅读器