基于Feature Boosting的管道电磁内检测多传感信号缺陷解析算法  

Feature Boosting Framework for Pipeline Multi-sensing Defects Inspection Using an Intelligent Pig System

作　　者：傅杨 张跃 毛颖 唐小华 陈祖高 徐和武 杨雨沛 高斌[1] 田贵云[1,4] FU Yang;ZHANG Yue;MAO Ying;TANG Xiaohua;CHEN Zugao;XU Hewu;YANG Yupei;GAO Bin;TIAN Guiyun(School of Automation Engineering,University of Electronic Science and Technology,Chengdu 611731;PetroChina Zhejiang Oilfield Company,Yibin 645200;Sichuan Deyuan Pipeline Technology Co.,Ltd.,Chengdu 610041;School of Electrical and Electronic Engineering,Newcastle University,Newcastle,NE17RU UK)

机构地区：[1]电子科技大学自动化工程学院,成都611731 [2]中国石油浙江油田分公司,宜宾645200 [3]四川德源管道科技股份有限公司,成都610041 [4]纽卡斯尔大学电气与电子工程学院,英国纽卡斯尔NE17RU

出　　处：《机械工程学报》2024年第20期51-67,共17页Journal of Mechanical Engineering

基　　金：国家自然科学基金(61971093);四川德源管道科技股份有限公司(231236)资助项目。

摘　　要：随着管道在能源运输中发挥越来越重要的作用,管道的健康管理势在必行。管道内检测是一种常用的管道寿命维护方法。在管道内部环境极其复杂的地方,内部检测得到的信号含有较强的噪声和干扰。因此,如何准确地识别缺陷信号是一个难题。基于管道内检测器的多传感检测信号,提出了一种基于Feature Boosting的信号解析缺陷检测算法框架。该框架通过加强特征构建和层次分类,不仅可以对管道内检测各种复杂信号进行正确分类,还可以实现缺陷信号的准确识别。同时,为了展示检测算法框架的高灵活性和鲁棒性,在实验室环境、模拟环境和实际环境三种不同环境下对标本进行了试验和验证。在实际环境检测信号的分类中,与不同算法进行了比较,并使用f评分进行了定量评价,验证了所提框架的有效性。As pipelines take an increasingly important role in energy transportation,their health management is necessary.In-pipe inspection is a common pipeline life maintains method.The signal obtained through internal inspection contains strong noise and interference where the internal environment of the pipeline is extremely complicated.Thus,it is challenging to accurately identify the defect signal.A defect detection algorithm framework based on feature boosting is proposed by using the multi sensing pipeline pig as the detection signals.Through boosting construction of features and hierarchical classification,the framework can not only correctly classify various signals in the internal detection signals but also realize the accurate identification of defect signals.Concurrently,in order to demonstrate the high flexibility and robustness of the detection framework,experiments and verifications have been carried out on specimens in three different environments i.e.laboratory environment,simulated environment and actual environment.In the classification of actual environmental detection signals,comparisons with different algorithms have been undertaken and quantitatively evaluated using the F-score and demonstrated the effectiveness of the proposed framework.

关 键 词：管道内检测 缺陷检测及定位 多传感融合 Feature Boosting 

分 类 号：TG156[金属学及工艺—热处理]