|本期目录/Table of Contents|

[1]徐鲁帅,董绍华,陈思雅,等.基于AOA-XGBOOST模型的管道缺陷漏磁信号量化研究*[J].中国安全生产科学技术,2024,20(12):75-81.[doi:10.11731/j.issn.1673-193x.2024.12.010]
　XU Lushuai,DONG Shaohua,CHEN Siya,et al.Research on quantification of magnetic flux leakage signals of pipeline defect based on AOA-XGBOOST Model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(12):75-81.[doi:10.11731/j.issn.1673-193x.2024.12.010]
点击复制

基于AOA-XGBOOST模型的管道缺陷漏磁信号量化研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年12期
页码:
75-81
栏目:
职业安全卫生管理与技术
出版日期:
2024-12-30

文章信息/Info

Title:
Research on quantification of magnetic flux leakage signals of pipeline defect based on AOA-XGBOOST Model
文章编号:
1673-193X(2024)-12-0075-07
作者:
徐鲁帅; 董绍华; 陈思雅; 魏昊天; 孙伟栋; 郭永
（1.中国石油大学（北京） 人工智能学院，北京 102249；
2.应急管理部油气生产安全与应急技术重点实验室，北京 102249；
3.中国石油大学（北京） 安全与海洋工程学院，北京 102249；
4.国家石油天然气管网集团有限公司华南分公司，广东 广州 510655；
5.管网集团（徐州）管道检验检测有限公司，江苏 徐州 221008；
6.国家管网集团西部管道有限责任公司塔里木输油气分公司，新疆 库尔勒 841000）
Author(s):
XU Lushuai;  DONG Shaohua;  CHEN Siya;  WEI Haotian;  SUN Weidong;  GUO Yong
关键词:
油气管道; 漏磁检测; 缺陷深度量化; 机器学习
Keywords:
oil and gas pipeline;  magnetic flux leakage detection;  defect depth quantification;  machine learning
分类号:
X937
DOI:
10.11731/j.issn.1673-193x.2024.12.010
文献标志码:
A
摘要:
为提升管道漏磁检测管道缺陷深度的量化精度，对长输管道外腐蚀状态进行准确把控，搭建管道漏磁信号采集实验平台，开展管道漏磁内检测牵拉实验，提取120组管道内外部缺陷的三轴漏磁信号。建立基于AOA-XGBOOST的管道漏磁检测缺陷深度预测模型，使用BPNN、SVR、XGBOOST模型作为对照组进行验证计算。研究结果表明：AOA-XGBOOST模型对漏磁内检测信号量化精度具有更好的准确性和优越性，可解决漏磁内检测信号的管道缺陷深度量化难题，有效提升管体状态检测精度。研究结果可为管道漏磁检测信号的智能分析提供技术参考。
Abstract:
To enhance the quantitative accuracy of pipeline magnetic flux leakage (MFL) detection for pipeline defect depth and precisely control the external corrosion state of long-distance pipelines,an experimental platform of pipeline MFL signal acquisition was constructed.The pipeline MFL internal detection pulling experiments were conducted,and 120 groups of triaxial MFL signals of internal and external pipeline defects were extracted.A prediction model on the defect depth of pipeline MFL detection based on AOA-XGBOOST was established,and BPNN,SVR,and XGBOOST models were used as the control group for verification calculation.The results show that the AOA-XGBOOST model exhibits better accuracy and superiority for the quantification accuracy of the internal MFL detection signal,which can resolve the quantification issue of internal MFL detection signal forthe pipeline defect depth,and effectively enhance the detection accuracy of pipeline state.The research results can provide technical reference for the intelligent analysis of pipeline MFL detection signals.

参考文献/References:

［1］刘延雷,陈涛,杨志军,等.可变径管道漏磁检测有限元仿真与实验研究［J］.中国安全生产科学技术,2016,12(12):42-47. LIU Yanlei,CHEN Tao,YANG Zhijun,et al.Finite element simulation and experimental research on diameter-variable pipeline magnetic flux leakage testing［J］.Journal of Safety Science and Technology,2016,12(12):42-47.
［2］PENG X,ANYAOHA U,LIU Z,et al.Analysis of magnetic-flux leakage (MFL) data for pipeline corrosion assessment［J］.IEEE Transactions on Magnetics,2020,56(6):1-15.
［3］MAAZAZ Z,HUBERT O,ZEMMOURI E.Inverse identification of pipeline steel mechanical state by means of coupled magnetic measurements and artificial neural networks［J］.NDT & E International,2023,134:102782.
［4］WILLIAM M V A,RAMESH S,CEP R,et al.MFO tunned SVR models for analyzing dimensional characteristics of cracks developed on steam generator tubes［J］.Applied Sciences,2022,12(23):12375.
［5］ZHANG H,WANG L,WANG J,et al.A pipeline defect inversion method with erratic MFL signals based on cascading abstract features［J］.IEEE Transactions on Instrumentation and Measurement,2022,71:1-11.
［6］崔国宁,杨理践,耿浩,等.基于卷积神经网络的管道缺陷量化识别方法［J］.仪表技术与传感器,2022(10):99-103. CUl Guoning,YANG Lijian,GENG Hao,et al.Quantitative identification method of pipeline defects based on convolutional neural network［J］.Instrument Technique and Sensor,2022(10):99-103.
［7］卢森骧,神祥凯,张俊楠,等.基于三轴融合的漏磁内检测数据缺陷反演方法研究［J］.仪器仪表学报,2021,42(12):245-253. LU Senxiang,SHEN Xiangkai,ZHANG Junnan,et al.Research on defect inversion method of magnetic flux leakage internal inspection data based on triaxial fusion［J］.Chinese Journal of Scientific Instrument,2021,42(12):245-253.
［8］LIU B,LUO N,FENG G.Quantitative study on MFL signal of sipeline composite defect based on improved magnetic charge model［J］.Sensors,2021,21(10):3412.
［9］LI H,LIU X,WU B,et al.Accurate 3D reconstruction of complex defects based on combined method of MFL and MFDs［J］.Measurement Science and Technology,2021,32(7):075402.
［10］莫丽,雍浩,李长俊,等.油气管道组合缺陷漏磁检测信号数值模拟研究［J］.中国安全生产科学技术,2024,20(1):5-10. MO Li,YONG Hao,Ll Changjun,et al.Numerical simulation study on magnetic flux leakage testing signals of combined defects in oil and gas pipelines［J］.Journal of Safety Science and Technology,2024,20(1):5-10.
［11］缪立恒,潘峰,彭丽莎,等.基于漏磁信号深度特性的缺陷深度轮廓迭代优化方法［J］.中国电机工程学报,2022,42(8):3077-3086. MIU Liheng,PAN Feng,PENG Lisha,et al.Iterative optimization method of defect depth profile based on depth characteristics of MFL signal［J］.Proceedings of the CSEE,2022,42(8):3077-3086.
［12］HAN W,QUE P.Defect reconstruction of submarine oil pipeline from MFL signals using genetic simulated annealing algorithm［J］.Journal of the Japan Petroleum Institute,2006,49(3):145-150.
［13］LI F,FENG J,ZHANG H,et al.Quick reconstruction of arbitrary pipeline defect profiles from MFL measurements employing modified harmony search algorithm［J］.IEEE Transactions on Instrumentation and Measurement,2018,67(9):2200-2213.
［14］YANG L J,SUN X,GAO S W.MFL detection defect reconstruction of pipeline based on conjugate gradient methods［C］//Advanced Materials Research.Trans Tech PublicationsLtd,2012,490:1066-1070.
［15］NALLURI M,PENTELA M,ELURI N R.Ascalable tree boosting system:XGBoost［J］.International Journal of Research Studies in Science,Engineering and Technology,2020,7(12):36-51.
［16］BENESTY J,CHEN J,HUANG Y,et al.Pearson correlation coefficient［M］//Noise reduction in speech processing.Springer,Berlin,Heidelberg,2009:1-4.
［17］ABUALIGAH L,DIABAT A,MIRJALILI S,et al.The arithmetic optimization algorithm［J］.Computer methods in applied mechanics and engineering,2021,376:113609.
［18］俞进,唐建华,神祥凯,等.基于Faster R-CNN的海底管道智能检测方法［J］.中国安全科学学报,2023,33(6):80-87. YU Jin,TANG Jianhua,SHEN Xiangkai,et al.Intelligent detection method for submarine pipelines based on faster R-CNN［J］.China Safety Science Journal,2023,33(6):80-87.
［19］董绍华,田中山,赖少川,等.新一代超高清亚毫米级管道内检测技术的研发与应用［J］.油气储运,2022,41(1):34-41. DONG Shaohua,TIAN Zhongshan,LAI Shaochuan,et al.Research and application of a new generation of ultra-high-definition inline detection technology with sub-milimeter precision［J］.Oil & Gas Storage and Transportation,2022,41(1):34-41.
［20］郗涛,王通,王莉静,等.基于AOA-LSTM的施工升降机电机轴承剩余寿命预测［J］.中国工程机械学报,2023,21(6):600-606. XI Tao,WANG Tong,WANG Lijing,et al.Prediction of remaining life of rolling bearing based on AOA-LSTM［J］.Chinese Journal of Construction Machinery,2023,21(6):600-606.

相似文献/References:

[1]辜冬梅,姚安林,尹旭东,等.基于层次-模糊评价法的山区油气管道 地质灾害易发性研究[J].中国安全生产科学技术,2012,8(5):52.
　GU Dong mei,YAO An lin,YIN Xu dong,et al.Study on occurrence of geological hazards for oil and gas pipelines through the mountains based on AHPfuzzy evaluation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(12):52.
[2]郑登锋,蒋金生,王明勇.基于风险矩阵和LOPA的风险评价系统在油气管道 的应用研究[J].中国安全生产科学技术,2012,8(10):76.
　ZHENG Deng feng,JIANG Jin sheng,WANG Ming yong.Study on application of risk evaluation system based on risk matrix and LOPA in oil and gas pipeline system[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(12):76.
[3]王全国,贺帅斌,党文义.油气管道安全预警技术性能评估研究[J].中国安全生产科学技术,2013,9(1):98.
　WANG Quan guo,HE Shuai bin,et al.Study on performance evaluation of safety prewarning technology on oil and gas pipeline[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(12):98.
[4]康乐,姚安林,关惠平,等.急倾斜煤层采空区地表移动盆地对油气管道安全影响分析[J].中国安全生产科学技术,2013,9(9):102.[doi:10.11731/j.issn.1673-193x.2013.09.019]
　KANG Le,YAO An lin,GUAN Hui pin,et al.Safety influence analysis of subsidence trough on oil & gas pipeline in steeply inclined coalmining area[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(12):102.[doi:10.11731/j.issn.1673-193x.2013.09.019]
[5]樊文有,陈 叶,李云海.基于地理信息系统的油气管道安全管理研究[J].中国安全生产科学技术,2009,5(4):175.
　FAN Wen you,CHEN Ye,Li Yun hai.Study on safety management system of gasoil pipeline based on GIS[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2009,5(12):175.
[6]姜好,张鹏,王大庆.超声波和漏磁检测结果的对比分析[J].中国安全生产科学技术,2014,10(11):128.[doi:10.11731/j.issn.1673-193x.2014.11.022]
　JIANG Hao,ZHANG Peng,WANG Da-qing.Comparative analysis on testing results of ultrasonic and magnetic flux leakage[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(12):128.[doi:10.11731/j.issn.1673-193x.2014.11.022]
[7]鲜涛,姚安林,李熠辰,等.基于属性识别理论的油气管道施工质量风险评价[J].中国安全生产科学技术,2015,11(4):95.[doi:10.11731/j.issn.1673-193X.2015.04.015]
　XIAN Tao,YAO An-lin,LI Yi-chen,et al.Risk assessment on constructing quality of oil & gas pipeline based on attribute recognition theory[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(12):95.[doi:10.11731/j.issn.1673-193X.2015.04.015]
[8]王如君.灰色-马尔科夫链模型在埋地油气管道腐蚀预测中的应用[J].中国安全生产科学技术,2015,11(4):102.[doi:10.11731/j.issn.1673-193X.2015.04.016]
　WANG Ru-jun,WANG Tian-yu.Application of grey Markov chain model in corrosion forecast of buried oil and gas pipelines[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(12):102.[doi:10.11731/j.issn.1673-193X.2015.04.016]
[9]张杰,梁政,韩传军,等.落石冲击作用下架设油气管道响应分析[J].中国安全生产科学技术,2015,11(7):11.[doi:10.11731/j.issn.1673-193x.2015.07.002]
　ZHANG Jie,LIANG Zheng,HAN Chuan-jun,et al.Analysis on response of overhead oil and gas pipeline impacted by rock-fall[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(12):11.[doi:10.11731/j.issn.1673-193x.2015.07.002]
[10]冯晓东,张圣柱,王如君,等.加拿大油气管道安全管理体系及其启示[J].中国安全生产科学技术,2016,12(6):180.[doi:10.11731/j.issn.1673-193x.2016.06.032]
　FENG Xiaodong,ZHANG Shengzhu,WANG Rujun,et al.Study on safety management system of oil and gas pipeline in Canada and its implications[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(12):180.[doi:10.11731/j.issn.1673-193x.2016.06.032]

备注/Memo

备注/Memo:
收稿日期： 2024-06-23
* 基金项目： “一带一路”海外长输管道完整性关键技术研究与应用项目（ZLZX2020-05）
作者简介： 徐鲁帅，博士研究生，主要研究方向为智慧管网技术。
通信作者： 董绍华，博士，教授，主要研究方向为管道完整性管理。
更新日期/Last Update: 2024-12-28