油气站场典型设备的焊缝缺陷检测与识别方法

doi:10.16265/j.cnki.issn 1003-3033.2020.11.016

中国安全科学学报 ›› 2020, Vol. 30 ›› Issue (11): 108-113.doi: 10.16265/j.cnki.issn 1003-3033.2020.11.016

油气站场典型设备的焊缝缺陷检测与识别方法

武琳玉, 梁伟^** 教授, 沙夺林

中国石油大学(北京) 安全与海洋工程学院,北京 102249

收稿日期:2020-08-29 修回日期:2020-10-12 出版日期:2020-11-28 发布日期:2021-07-15
通讯作者: **梁伟(1978—),男,陕西绥德人,博士,教授,博士生导师,主要从事油气管道安全监测、场站设备诊断与可靠性评估等研究。E-mail: lw@cup.edu.cn。
作者简介:武琳玉 (1995—),女,河南南阳人,博士研究生,主要研究方向为机械设备故障诊断、管道缺陷检测与诊断。E-mail:2019310517@student.cup.edu.cn。
基金资助:
国家重点研发计划课题(2017YFC0805804)。

Weld defect detection and identification method of typical equipment in oil-gas station

WU Linyu, LIANG Wei, SHA Duolin

School of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China

Received:2020-08-29 Revised:2020-10-12 Online:2020-11-28 Published:2021-07-15

摘要/Abstract

摘要： 基于双向励磁下的三线圈检测技术,检测油气站场内典型设备的焊缝缺陷,提出一种基于焊缝状态辨识和特征子集优选的裂纹缺陷分类识别方法。首先,采用非线性特征分析的方法分析焊缝信号特性,用Lemper-Ziv分析信号的复杂度,辨识焊缝类别;然后,基于改进的最大相关最小冗余特征选择方法,对提取的特征参数进行降维;最后,将不同权重因子下的优选特征子集作为支持向量机(SVM)的输入构建分类器,识别油气站场内的实测信号缺陷。结果表明:根据Lemper-Ziv复杂度大小分布,可以实现对焊缝类型较精确的区分;经过现场试验验证,基于特征子集优选的识别方法对焊缝的纵向缺陷和横向缺陷均有较高的识别精度,且总体识别准确率最大可达到83.33%。

关键词: 油气站场, 焊缝缺陷, 涡流检测(ECT), Lemper-Ziv复杂度, 特征选择, 支持向量机(SVM)

Abstract: Based on three-coil detection technology under bidirectional excitation, a method to identify weld defect types building on weld state identification and feature subset optimization was proposed in this paper. Firstly, characteristics and complexity of weld signals were analyzed by utilizing non-linear characteristic analysis method and Lemper-Ziv complexity value so as to identify weld category. Then, extracted features were reduced in dimension based on improved maximum relevance minimum redundancy feature selection method. Finally, optimal feature subset under different weight factors were used as input of SVM to identify defects of tested signals in oil-gas station. The results indicate that Lemper-Ziv complexity-based distribution can help accurately distinguish weld types. And it is verified by tests that recognition method based on feature subset optimization has high recognition accuracy for both longitudinal defects and transverse defects of welds, and its overall accuracy can reach as high as 83.33%.

Key words: oil-gas station, weld defect, eddy current testing(ECT), Lemper-Ziv complexity value, feature selection, support vector machine(SVM)

中图分类号:

X937

武琳玉, 梁伟, 沙夺林. 油气站场典型设备的焊缝缺陷检测与识别方法[J]. 中国安全科学学报, 2020, 30(11): 108-113.

WU Linyu, LIANG Wei, SHA Duolin. Weld defect detection and identification method of typical equipment in oil-gas station[J]. China Safety Science Journal, 2020, 30(11): 108-113.

参考文献

[1] 赵俊茹,白伟,陈靖,等. 油气罐区安全水平影响因子SD仿真分析[J]. 中国安全科学学报,2017,27(6): 43-48.
ZHAO Junru,BAI Wei,CHEN Jing,et al.SD simulation analysis of factors influencing safety levels in oil-gas storage tank area[J].China Safety Science Journal,2017,27(6): 43-48.
[2] 李育忠,郑宏丽,贾世民,等. 国内外油气管道检测监测技术发展现状[J]. 石油科技论坛,2012,31(2): 30-35.
LI Yuzhong,ZHENG Hongli,JIA Shimin,et al. Status of oil & gas pipeline inspection and monitoring both at home and abroad [J]. Oil Forum,2012,31(2): 30-35.
[3] KALAISELVI V,ARAVINDHAR D J. An non destructive test for the detection of weld defects using image processing[J]. Indonesian Journal of Electrical Engineering and Computer Science,2018,9(3): 764-770.
[4] HEBER M,LENZ M,MATTHIAS R,et al. Weld seam tracking and panorama image generation for on-line quality assurance[J]. International Journal of Advanced Manufacturing Technology,2013,65(9/10/11/12): 1 371-1 382.
[5] 林东,高建忠,黄磊. 钢管母材边缘缺陷对焊缝超声波探伤的影响[J]. 焊管,2018,41(2): 61-64.
LIN Dong,GAO Jianzhong,HUANG Lei. Impact of steel pipe body edge defect on ultrasonic flaw detection of welds [J]. Welded Pipe and Tube,2018,41(2): 61-64.
[6] 唐炜,张莉,葛向兵. 涡流检测焊缝裂纹缺陷的有限元仿真[J]. 仪表技术与传感器,2011(12): 72-74.
TANG Wei,ZHANG Li,GE Xiangbing. Finite element simulation of welding crack defect based on eddy current testing [J]. Instrument Technique and Sensor,2011(12): 72-74.
[7] 刘迎来,王鹏,王高峰. 钢管与法兰对接环焊缝开裂分析[J]. 管道技术与设备,2013(3): 30-32,35.
LIU Yinglai,WANG Peng,WANG Gaofeng. Cracking analysis of circumferential weld for steel pipe and flange butt joint [J]. Pipeline Technique and Equipment,2013(3): 30-32,35.
[8] 陈福真, 张明广, 王妍,等. 油气储罐区多米诺事故耦合效应风险分析[J]. 中国安全科学学报, 2017, 27(10): 115-120.
CHEN Fuzhen,ZHANG Mingguang,WANG Yan,et al.Risk analysis of coupling domino effect in petroliferous tank farm [J].China Safety Science Journal,2017,27(10): 111-116.
[9] 张颖,张维,徐磊,等. 大型储罐底板焊缝缺陷非接触式自动检测仪的研制[J]. 中国安全科学学报,2018,28(10): 71-76.
ZHANG Ying,ZHANG Wei,XU Lei,et al. Development of non-contact automatic detector for defects in large tank bottom weld seam [J]. China Safety Science Journal,2018,28(10): 71-76.
[10] RAO B P C,RAJ B,JAYAKUMAR T,et al. An artificial neural network for eddy current testing of austenitic stainless steel welds[J]. Ndt & E International,2002,35(6): 393-398.
[11] REN Junjie,MA Weifeng,HE Xueliang. Mechanical properties of girth weld with different butt materials severed for natural gas station[J]. Materials science forum,2019,944: 821-827.
[12] 杨叠,杨柳青,白世武,等. X80钢管自保护药芯焊丝环焊缝成分及组织研究[J]. 焊接技术,2016,45(12): 28-31.
[13] 万本例,胡斌,赵泓,等. 管板焊缝结构涡流检测端部效应抑制仿真试验[J]. 无损检测,2018,40(4): 19-25.
WAN Benli,HU Bin,ZHAO Hong,et al. Simulation research on restraining end effect of eddy current testing for fillet welds in tube sheets [J]. Nondestructive Testing,2018,40(4): 19-25.
[14] 戈浩,金南辉,钟丰平. 某型涡流检测仪特殊缺陷信号特征的形成原因[J]. 无损检测,2018,40(1): 55-60.
GE Hao,JIN Nanhui,ZHONG Fengping. Cause of special defect signal characteristics of an eddy current detector [J]. Nondestructive Testing,2018,40(1): 55-60.
[15] HENCH K W,CHRISTENSEN W,LOPEZ A A,et al. An optimization technique for the evaluation of eddy current inspection data to determine weld quality[C]. IEEE International Conference on Systems,Man and Cybernetics,2006: 1 535-1 539.
[16] TODOROV E,NAGY B,LEVESQUE S,et al. Inspection of laser welds with array eddy current technique[C]. AIP Conference Proceedings,2013: 1 065-1 072.
[17] JAVIER G M,JAIME G G,ERNESTO V S. Non-destructive techniques based on eddy current testing[J]. Sensors,2011,11(3): 2 525-2 565.
[18] YUSA N,MACHIDA E,JANOUSEK L,et al. Application of eddy current inversion technique to the sizing of defects in Inconel welds with rough surfaces[J]. Nuclear Engineering and Design,2005,235(14): 1 469-1 480.
[19] HOSHIKAWA H,KOYAMA K,MIZOGUCHI K. Eddy current non-destructive surface testing of weld coated with anticorrosion painting[J]. Welding in the World,Le Soudage Dans Le Monde,2013,49(7/8): 28-32.
[20] 侯威,封国林,董文杰. 基于复杂度分析logistic映射和Lorenz模型的研究[J]. 物理学报,2005,54(8): 3 940-3 946.
HOU Wei,FENG Guolin,DONG Wenjie. Investigation about the Lorenz model and logistic equation based on the complexity [J]. Acta Physica Sinica,2005,54(8): 3 940-3 946.
[21] 侯建忠. 钢结构焊接缺陷及预防措施[J]. 化工管理,2016(8): 285.
[22] 李扬,顾雪平. 基于改进最大相关最小冗余判据的暂态稳定评估特征选择[J]. 中国电机工程学报,2013,33(34): 179-186,27.
LI Yang,GU Xueping. Feature selection for transient stability assessment based on improved maximal relevance and minimal redundancy criterion[J]. Proceedings of the CSEE,2013,33(34): 179-186,27.

油气站场典型设备的焊缝缺陷检测与识别方法

Weld defect detection and identification method of typical equipment in oil-gas station

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨文臣, 周燕宁, 田毕江, 郭凤香, 胡澄宇. 基于聚类分析和SVM的二级公路交通事故严重度预测[J]. 中国安全科学学报, 2022, 32(5): 163-169.
[2]	丁茜, 赵晓东, 吴鑫俊, 张泰丽, 徐振涛. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200.
[3]	吴孟龙, 叶义成, 胡南燕, 王其虎, 李文, 江慧敏. 基于模糊信息粒化的矿业安全生产态势区间预测^*[J]. 中国安全科学学报, 2021, 31(9): 119-127.
[4]	赵挺生, 庞奇志, 姜雯茜. 基于数据库与支持向量机的施工升降机安全风险预测[J]. 中国安全科学学报, 2021, 31(4): 11-17.
[5]	刘阳, 张建经, 罗宏森, 于海莹, 向波. 基于贝叶斯网络的Fuzzy-SVM路基震害预测模型^*[J]. 中国安全科学学报, 2021, 31(11): 171-178.
[6]	郑晓亮, 来文豪, 薛生. MI和SVM算法在煤与瓦斯突出预测中的应用[J]. 中国安全科学学报, 2021, 31(1): 75-80.
[7]	王旭, 帅健, 王宇, 罗雨菲, 单克. 考虑材料特性的管道环焊缝缺陷评估方法[J]. 中国安全科学学报, 2020, 30(7): 78-84.
[8]	马辉, 吕航, 栾瑞斌. 基于空间单元分析的装配式建筑施工安全预警模型[J]. 中国安全科学学报, 2020, 30(5): 27-32.
[9]	马英楠, 吕子阳, 高星, 王勇毅. 基于SVM的居家老人跌倒预测方法研究[J]. 中国安全科学学报, 2019, 29(6): 43-48.
[10]	马杰, 刘琪, 张春玮, 刘克中, 张煜. 基于AIS的数据时空分析及船舶会遇态势提取方法[J]. 中国安全科学学报, 2019, 29(5): 111-116.
[11]	楚文慧, 吴超仲, 张晖, 杨曼, 李思瑶. 基于个性化行为模型的驾驶疲劳识别方法[J]. 中国安全科学学报, 2018, 28(6): 43-48.
[12]	王岩韬, 赵嶷飞. 基于多算法协作的航班运行风险辨识研究[J]. 中国安全科学学报, 2018, 28(6): 166-172.
[13]	邵良杉, 周玉. QGA-RFR模型在导水裂隙带高度预测中的应用[J]. 中国安全科学学报, 2018, 28(3): 19-24.
[14]	毛志勇, 黄春娟, 路世昌. 基于PSO-SVM的砂土地震液化预测模型[J]. 中国安全科学学报, 2018, 28(3): 25-30.
[15]	王杰, 罗周全, 秦亚光, 赵爽. 基于随机森林理论的采场稳定性预测研究[J]. 中国安全科学学报, 2018, 28(3): 155-160.