A Single-Stage Enhancement-Identification Framework for Pipeline MFL Inspection

漏磁 管道(软件) 信号(编程语言) 噪音(视频) 干扰(通信) 工程类 无损检测 信号处理 鉴定(生物学) 声学 电子工程 计算机科学 人工智能 机械工程 电气工程 磁铁 物理 数字信号处理 生物 量子力学 图像(数学) 植物 频道(广播) 程序设计语言
作者
Jian Yong Feng,Xinbo Zhang,Senxiang Lu,Feiran Yang
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:71: 1-13 被引量:27
标识
DOI:10.1109/tim.2022.3176285
摘要

Magnetic flux leakage (MFL) inspection, one of the nondestructive testing methods, has been widely applied in pipeline maintenance. In pipeline MFL data processing, defect identification is a crucial step, which aims at measuring the locations of defect MFL signals in MFL heat maps. MFL signals collected from the pipeline are not ideal, containing noise and interference. In this case, measuring the locations of defect MFL signals, especially the locations of weak defect MFL signals, is a challenge. To address this challenge, an enhancement process is required to coordinate with the identification process. In this manuscript, two separated processes, enhancement and identification, are integrated into a single-stage framework, aiming at improving the defect identification performance through strengthening the differences between defect signal areas and pipe wall signal areas. The proposed framework can enhance the defect areas purposefully, and ignore the noise and interference in non-defect areas, which promotes the measuring effect for locations of defect MFL signals. In the proposed method, an enhancement module is constructed to upsample the MFL heat maps, and the resolution of feature maps in the framework is increased to 288×600. A novel loss function is designed, and the gray value contrast between defect signal areas and pipe wall signal areas in MFL heat maps is enhanced from 10 to 48 approximately through task-oriented joint training. The proposed method achieves 0.967 AP, and the identification accuracy is improved to 97.3%. In addition, the average deviations of identified defect signals are reduced by around 2mm - 9mm, and the uncertainties are reduced to 0.27mm - 0.35mm. The experiment results validate the superiority of the proposed framework in industrial applications.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
1秒前
落后百褶裙完成签到,获得积分10
1秒前
笨笨芝麻发布了新的文献求助10
1秒前
小马甲的应助被星星采纳,获得10
1秒前
1秒前
nc完成签到 ,获得积分10
2秒前
YAN完成签到,获得积分10
2秒前
凤凰完成签到,获得积分10
3秒前
3秒前
3秒前
冲就完了发布了新的文献求助10
3秒前
1518发布了新的文献求助10
3秒前
3秒前
Leef完成签到,获得积分10
3秒前
4秒前
恰好发布了新的文献求助10
4秒前
彭于晏的应助被躺赢的猴哥采纳,获得10
4秒前
李梦凡完成签到,获得积分20
4秒前
科研通AI6.2的应助被嵐拾壹采纳,获得10
4秒前
莫望完成签到,获得积分10
4秒前
泰山球迷完成签到,获得积分10
4秒前
4秒前
dbyte完成签到,获得积分10
4秒前
5秒前
ZetaGundam完成签到,获得积分10
5秒前
5秒前
欢呼的雅琴完成签到 ,获得积分10
5秒前
缓慢元彤完成签到,获得积分10
5秒前
Emilia0707完成签到,获得积分10
6秒前
诸乘风完成签到,获得积分10
6秒前
城北徐公完成签到,获得积分10
6秒前
Coco完成签到,获得积分10
6秒前
雪白炎彬完成签到,获得积分10
6秒前
右想完成签到,获得积分10
6秒前
Leoitch完成签到,获得积分10
7秒前
wendy_1006完成签到 ,获得积分10
7秒前
独特的夏蓉完成签到,获得积分10
7秒前
6666666666666666完成签到,获得积分10
7秒前
石榴发布了新的文献求助10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180407
求助须知:如何正确求助?哪些是违规求助? 9570403
关于积分的说明 21811831
捐赠科研通 7776452
什么是DOI,文献DOI怎么找? 3433277
关于科研通互助平台的介绍 2557499
邀请新用户注册赠送积分活动 2479105