版权所有@2014 《油气储运》杂志社 冀ICP备号:0000000
地址:河北省廊坊市金光道51号(065000);电话:0316-2177193 / 0316-2176753; 传真:0316-2177392; 网址:yqcy.paperonce.org
技术支持:西安三才科技实业有限公司 029-88222991
基于支持向量机的带包覆层油气管道剩余壁厚反演研究
Research on residual wall thickness inversion of oil and gas pipeline with cladding based on support vector machine
cladding
; pulsed eddy current; residual wall thickness inversion; late signal slope; support vector machine油田现场的油气管道外壁通常带有一定厚度的包覆层,脉冲涡流检测技术可实现不拆包覆层 条件下的壁厚检测,可节约大量的包覆层拆装成本。但包覆层的存在使得脉冲涡流检测传感器与管 道之间存在提离距离,导致传感器的等效电阻和电感发生变化,进而对脉冲涡流检测电压信号产生 影响,降低剩余壁厚反演的精度。基于此,采用支持向量机方法(Support Vector Machine,SVM)建 立了提离距离、检测电压信号晚期段斜率与管道壁厚之间的定量化反演模型。利用该模型对壁厚范 围5~21 mm 的阶梯试件开展了0~10 cm 提离距离条件下的剩余壁厚反演测试,反演结果的误差 控制在7%以内,验证了所得反演模型的有效性,并具有较高的实用价值,可为带包覆层的管道剩余 壁厚检测提供参考。(图4,表5,参20)
The oil and gas pipelines in the oil field are usually equipped with a layer of cladding in certain thickness, and the pulsed eddy current testing technology can be adopted to measure the wall thickness without removing the cladding, which saves a lot of costs for the removal and assembly of the cladding. However, as a result of cladding, distance exists between the pulsed eddy current sensor and the pipeline, which leads to the variation of the equivalent resistance and inductance of the sensor, and further affects the voltage signal of the pulsed eddy current detection, reducing the accuracy of the residual wall thickness inversion. In order to solve this problem, a quantitative inversion model of lift-off, slope of late detection voltage signal and pipe wall thickness was established with a support vector machine (SVM), and inversion test of the residual wall thickness of the step specimen with the wall thickness of 5-21 mm was carried out with this model under the condition of 0-10 cm lift-off, with the error of the inversion result controlled within 7%. Thereby, the inversion model is verified to be valid with high practical value, and certain reference could be provided for the measurement of the residual wall thickness of the pipeline with cladding. (4 Figures, 5 Tables, 20 References)
[1] 徐志远. 带包覆层管道壁厚减薄脉冲涡流检测理论与方法[D]. 武汉:华中科技大学,2012:66-79.
XU Z Y. Pulse eddy current testing theory and method for wall thinning of insulated pipe with cladding layer[D]. Wuhan: Huazhong University of Science and Technology, 2012: 66-79.
[2] 沈功田. 中国无损检测与评价技术的进展[J]. 无损检测,2008(11): 787-793.
SHEN G T. Progress of nondestructive testing and evaluation in China[J]. Non-Destructive Testing, 2008(11): 787-793.
[3] 江山. 基于脉冲涡流检测技术的实验研究[D]. 桂林:广西师范 大学,2016:1-9.
JIANG S. Experimental research based on pulsed eddy current testing technology[D]. Guilin: Guangxi Normal University, 2016: 1-9.
[4] 武新军,张卿,沈功田. 脉冲涡流无损检测技术综述[J]. 仪器仪 表学报,2016,37(8):1698-1712.
WU X J, ZHANG Q, SHEN G T. Review on advances in pulsed eddy current nondestructive testing technology[J]. Chinese Journal of Scientific Instrument, 2016, 37(8): 1698-1712.
[5] 侯春明. 基于脉冲涡流海底管道无损检测理论与技术研究[D]. 大连:大连理工大学,2017:1-35.
HOU C M. Research on theory and technology for nondestructive testing of submarine pipeline based on pulsed eddy current[D]. Dalian: Dalian University of Technology, 2017: 1-35.
[6] FAN M B, CAO B H, YANG P P, LI W, TIAN G Y.
Elimination of liftoff effect using a model-based method for eddy current characterization of a plate[J]. NDT & E International, 2015, 74: 66-71.
[7] 胡冠华,赵晶亮,张波涛,薛丹丹. 基于磁阻传感器的铁磁体探 测系统设计[J]. 传感器世界,2011,17(8):26-29.
HU G H, ZHAO J L, ZHANG B T, XUE D D. Ferromagnetic detection system based on magnetic resistance sensors[J]. Sensor World, 2011, 17(8): 26-29.
[8] 韩昊轩,张国峰,张雪,梁恬恬,应利良,王永良,等. 低噪声超导 量子干涉器件磁强计设计与制备[J]. 物理学报,2019,68(13): 295-300.
HAN H X, ZHANG G F, ZHANG X, LIANG T T, YING L L, WANG Y L, et al. Design and fabrication of low-noise superconducting quantum interference device magnetometer[J]. Acta Physica Sinica, 2019, 68(13): 295-300.
[9] XIE S J, CHEN Z M, TAKAGI T, UCHIMOTO T. Quantitative non-destructive evaluation of wall thinning defect in double-layer pipe of nuclear power plants using pulsed ECT method[J]. NDT & E International, 2015, 75: 87-95.
[10] YANG H C, TAI C C. The interaction of pulsed eddy current with metal surface crack for various coils[J]. AIP Conference Proceedings, 2002, 615(1): 409-414.
[11] 徐志远,武新军,康宜华,李建. 脉冲涡流检测集总参数模型[J]. 华中科技大学学报(自然科学版),2013,41(5):1-5.
XU Z Y, WU X J, KANG Y H, LI J. Lumped-parameter model for pulsed eddy current testing[J]. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2013, 41(5): 1-5.
[12] 张卿. 带金属保护层构件脉冲涡流检测解析模型及应用[D]. 武汉:华中科技大学,2018:1-17.
ZHANG Q. Analytical model and application for pulsed eddy current testing of equipments with metallic claddings[D]. Wuhan: Huazhong University of Science and Technology, 2018: 1-17.
[13] YIN W L, XU K. A novel triple-coil electromagnetic sensor for thickness measurement immune to lift-off variations[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(1): 164-169.
[14] 叶波,黄平捷,周泽魁. 涡流检测探头提离变化对阻抗的影响 及消除技术[J]. 仪器仪表学报,2005,26(8):2535-2537,2540.
YE B, HUANG P J, ZHOU Z K. Impedance variations caused by probe coil lift-off and elimination technique in eddy current testing[J]. Chinese Journal of Scientific Instrument, 2005, 26(8): 2535-2537, 2540.
[15] 高春法,宋凯,唐继红. 涡流检测传感器提离效应的抑制[J]. 无 损检测,2003,25(12):606-608,619.
GAO C F, SONG K, TANG J H. Restrain of the lift-off effect of eddy current sensor[J]. Non-Destructive Testing, 2003, 25(12): 606-608, 619.
[16] 徐志远,伍权. 基于维纳滤波和主成分分析的脉冲涡流检测信 号降噪方法[J]. 传感技术学报,2019,32(3):411-417.
XU Z Y, WU Q. Pulsed eddy current signal de-noising method based on wiener filtering and PCA[J]. Chinese Journal of Sensors and Actuators, 2019, 32(3): 411-417.
[17] 柯海,徐志远,黄琛,武新军. 基于信号斜率的铁磁材料脉冲涡 流测厚研究[J]. 仪器仪表学报,2011,32(10):2376-2381.
KE H, XU Z Y, HUANG C, WU X J. Research on thickness measurement of ferromagnetic materials using pulsed eddy current based on signal slopes[J]. Chinese Journal of Scientific Instrument, 2011, 32(10): 2376-2381.
[18] 柯海. 脉冲涡流测厚信号斜率法研究[D]. 武汉:华中科技大 学,2013:7-37.
KE H. Research on signal slope method of pulse eddy current thickness measurement[D]. Wuhan: Huazhong University of Science and Technology, 2013: 7-37.
[19] 李立刚,万勇,王宇,杨勇,戴永寿. 基于支持向量机和磁记 忆技术的管道缺陷深度的定量化反演研究[J]. 腐蚀与防护, 2020,41(1):29-34,40.
LI L G, WAN Y, WANG Y, YANG Y, DAI Y S. Quantitative inversion of pipeline defect depth based on support vector machine and magnetic memory technology[J]. Corrosion and Protection, 2020, 41(1): 29-34, 40.
[20] 左宪章,胡德洲,常东,钱苏敏. 钢板局部腐蚀的脉冲涡流热成 像定量检测[J]. 腐蚀与防护,2015,36(7):652-658.
ZUO X Z, HU D Z, CHANG D, QIAN S M. Quantitative detection of steel local corrosion using pulse eddy current thermography[J]. Corrosion and Protection, 2015, 36(7): 652-658.
[1]周煊勇 刘半藤 徐菲 周莹 吕何新 陈树越.基于AIC-RBF 的油气管柱挤压形变估计方法[J].油气储运,2021,40(01):1.
ZHOU Xuanyong,LIU Banteng,XU Fei,et al.Extrusion deformation estimation method of oil and gas string basedon AIC-RBF[J].Oil & Gas Storage and Transportation,2021,40(01):1.
[2]郝宪锋 宫昊 孙国健 王安泉 戴永寿.基于支持向量机的带包覆层油气管道剩余壁厚反演研究[J].油气储运,2021,40(01):1.
HAO Xianfeng,GONG Hao,SUN Guojian,et al.Research on residual wall thickness inversion of oil and gas pipelinewith cladding based on support vector machine[J].Oil & Gas Storage and Transportation,2021,40(01):1.
基金项目:国家重点研发计划项目“临海油气管道检测、监控技 术研究与仪器装备研制”,2016YFC0802302。
作者简介:郝宪锋,男,1980 年生,高级工程师,2014 年硕士毕业 于中国石油大学(华东)电子通信工程专业,现主要从事信号分析与 处理专业方向的研究工作。地址:山东省青岛市黄岛区长江西路 66 号,266580。电话:18678460769。Email:haoxf@upc.edu.cn