基于二维阻抗特征的管道环焊缝缺陷涡流检测

发布时间：2018-01-23 13:29

本文关键词： 管道内表面环焊缝缺陷涡流无损检测图像处理神经网络　出处：《仪器仪表学报》2017年09期 　论文类型：期刊论文

【摘要】：油气长输管道环焊缝处缺陷对管道安全的危害性巨大,管道缺陷造成的事故大部分发生在管道焊接处。目前,对管道进行无损检测(NTD)是预测事故隐患、保证管道安全运行的常用手段,但传统无损检测方法无法有效识别位于环焊缝处等表面形貌复杂位置的缺陷。为了克服传统检测方法的缺点,提出一种基于图像处理和神经网络的嵌入式涡流检测系统。从涡流信号合成的二维阻抗图入手,对其进行霍夫变换和轮廓提取得到特征分量,使用类内散布矩阵筛选分类特性好的特征用以训练基于FPGA加速的神经网络,实现在焊缝基底噪声较大的情况下对缺陷的自动分类与识别。实验结果表明,本系统可以有效识别位于环焊缝处等形貌复杂位置的缺陷信号,正确率可达92%,且系统体积小、功耗低,适合应用于管道内检测环境。
[Abstract]:The defects in the girth weld of long distance oil and gas pipeline are very harmful to the safety of the pipeline, and the accidents caused by the defects of the pipeline mostly occur in the welding of the pipeline. At present, the nondestructive testing of the pipeline is the hidden trouble to predict the accident. In order to overcome the shortcomings of the traditional detection methods, the conventional nondestructive testing method can not effectively identify the defects in the complex position of the surface morphology at the circumferential weld seam in order to overcome the shortcomings of the traditional detection methods in order to overcome the shortcomings of the traditional detection methods. An embedded eddy current detection system based on image processing and neural network is proposed. Based on the two-dimensional impedance diagram of eddy current signal synthesis, the feature components are obtained by Hough transform and contour extraction. In order to train the neural network based on FPGA acceleration, the defects can be automatically classified and identified when the weld substrate noise is high. The experimental results show that the proposed method can be used to identify the defects. The system can effectively identify the defect signals located in complex positions such as girth welds, and the accuracy can reach 92%. The system is small in size and low in power consumption, so it is suitable for pipeline detection environment.
【作者单位】：天津大学精密测试技术及仪器国家重点实验室;中国石油管道科技研究中心中国石油天然气集团公司油气储运重点实验室;
【基金】：天津市自然科学基金(14JCQNJC04900) 教育部博士点基金(20130032120066)项目资助
【分类号】：TE973.3;TG441.7;TP391.41
【正文快照】： 0引言随着经济、社会的高速发展,管道运输成为一种高效且经济的物料运输方式。由于管道运输行业的大规模发展、管道里程的不断增长,如何保证管道安全运行成为越来越重要的问题。针对管道缺陷的定期检测以及安全评估对预测和及时消除管道的安全隐患有着重要的意义[1]。由于管道

【相似文献】