基于时域统计特征的天然气管道泄漏检测方法

doi:10.7623/syxb201306022

石油学报 ›› 2013, Vol. 34 ›› Issue (6): 1195-1199.DOI: 10.7623/syxb201306022

基于时域统计特征的天然气管道泄漏检测方法

戚元华, 林伟国, 吴海燕

北京化工大学信息科学与技术学院北京 100029

收稿日期:2013-05-16 修回日期:2013-09-06 出版日期:2013-11-25 发布日期:2013-10-13
通讯作者: 林伟国，男，1968年2月生，1990年获中国矿业大学自动化专业学士学位，1999年获哈尔滨工业大学精密仪器与机械专业博士学位，现为北京化工大学信息科学与技术学院教授，主要从事生产过程智能检测与安全预警技术研究工作。Email：linwg@mail.buct.edu.cn
作者简介:戚元华，男，1990年4月生，2012年获山东大学自动化专业学士学位，现为北京化工大学信息科学与技术学院硕士研究生，主要从事检测技术与自动化装置的研究工作。Email：qiyuanhua0168@163.com

A leak detection method for natural gas pipelines based on time-domain statistical features

QI Yuanhua, LIN Weiguo, WU Haiyan

College of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2013-05-16 Revised:2013-09-06 Online:2013-11-25 Published:2013-10-13

摘要/Abstract

摘要：

根据管道动态压力信号在时域的幅值统计特性，提出一种基于时域统计特征的信号提取方法，实现对天然气管道的泄漏检测。通过每帧信号归一化的频率分布直方图（k-P图），提取动态压力信号时域幅值在均值上、下特定范围内波动的概率特征，使得时域的特征提取与信号幅值及波形无关，并且不受信号频率成分偏移的影响，具有较好的工况适应性。以PCA降维后的正常工况下动态压力信号时域统计特征向量为目标类样本，建立PCA-SVDD诊断模型，实现了对管道泄漏的可靠检测。历史数据的离线检验以及连续、实时的现场检验结果表明该方法可实现天然气管道的泄漏检测。

关键词: 天然气管道, 泄漏检测, 概率带宽, 特征提取, PCA-SVDD诊断模型

Abstract:

In view of the amplitude-value statistical feature of pipeline dynamic pressure signals in time domain, an extraction method of these signals based on time-domain statistical features was proposed which can dynamically detect a gas leak of pipelines. Through the normalized frequency distribution histogram (k-P diagram) of each frame signal, the probability bandwidth feature of amplitude values distributed near the average can be extracted from dynamic pressure signals in time domain, which is independent of the amplitude value and waveform of signals, and also unaffected by the frequency offset of signals, so it has a good adaptability. Taking the statistical feature vector of dynamic pressure signals in normal working conditions whose dimension is reduced by PCA as a target sample, a PCA-SVDD diagnostic model was established that can offer reliable detection of a pipeline leak. The results of off-line detection of historical data and a continuous on-line test showed that this method can detect a leak of gas pipelines effectively.

Key words: natural gas pipeline, leak detection, probability bandwidth, feature extraction, PCA-SVDD diagnostic model

中图分类号:

TE973.6

戚元华, 林伟国, 吴海燕. 基于时域统计特征的天然气管道泄漏检测方法[J]. 石油学报, 2013, 34(6): 1195-1199.

QI Yuanhua, LIN Weiguo, WU Haiyan. A leak detection method for natural gas pipelines based on time-domain statistical features[J]. ACTA PETROLEI SINICA, 2013, 34(6): 1195-1199.

参考文献

[1] Murvay P,Silea I.A survey on gas leak detection and localization techniques[J].Journal of Loss Prevention in the Process Industries,2012,25(6):966-973.
[2] 耿艳峰,张朝晖.气体长输管线泄漏检测技术[J].仪器仪表学报,2001,22(增刊2):328-330.
Geng Yanfeng,Zhang Zhaohui.Leak detection technology for the long gas pipeline[J].Chinese Journal of Scientific Instrument,2001,22(Supplement 2):328-330.
[3] 杨杰,王桂增.输气管道泄漏诊断技术综述[J].化工自动化及仪表,2004,31(3):1-5.
Jie Yang,Wang Guizeng.Leak detection and location methods for gas transport pipelines[J].Control and Instruments in Chemical Industry,2004,31(3):1-5.
[4] 林伟国,郑志受.基于动态压力信号的管道泄漏检测技术研究[J].仪器仪表学报,2006,27(8):907-910.
Lin Weiguo,Zheng Zhishou.Research on pipeline leak detection based on dynamic pressure signal[J].Chinese Journal of Scientific Instrument,2006,27(8):907-910.
[5] 张宇,靳世久,何静菁,等.基于动态压力信号的管道泄漏特征提取方法研究[J].石油学报,2010,31(2):338-342.
Zhang Yu,Jin Shijiu,He Jingjing,et al.Extraction method for pipeline leakage feature based on dynamic pressure signal[J].Acta Petrolei Sinica,2010,31(2):338-342.
[6] 王立坤,赵晋云,付松广,等.基于神经网络的管道泄漏声波信号特征识别[J].仪器仪表学报,2006,27(增刊3):2247-2249.
Wang Likun,Zhao Jinyun,Fu Songguang,et al.Recognizing characteristics of pipeline leakage acoustic signals based on neural network[J].Chinese Journal of Scientific Instrument,2006,27(Supplement 3):2247-2249.
[7] 王明达,张来斌,梁伟,等.基于独立分量分析和支持向量机的管道泄漏识别方法[J].石油学报,2010,31(4):659-663.
Wang Mingda,Zhang Laibin,Liang Wei,et al.Pipeline leakage detection method based on independent component analysis and support vector machine[J].Acta Petrolei Sinica,2010,31(4):659-663.
[8] Qu Zhigang,Feng Hao,Zeng Zhoumo,et al.A SVM-based pipeline leakage detection and pre-warning system[J].Measurement,2010,43(4):513-519.
[9] Hadad K,Jabbari M,Tabadar Z,et al.PCA-based ANN approach to leak classification in the main pipes of VVER-1000[J].Kerntechnik,2012,77(5):365-370.
[10] Meng Lingya,Li Yuxing,Wang Wuchang,et al.Experimental study on leak detection and location for gas pipeline based on acoustic method[J].Journal of Loss Prevention in the Process Industries,2012,25(1):90-102.
[11] Daubechies I.Ten lectures on wavelets[M].Philadelphia:Society for Industrial and Applied Mathematics,1992.
[12] Deng Yongjun,Wang Wei,Qian Chengchun,et al.Boundary-processing-technique in EMD method and Hilbert transform[J].Chinese Science Bulletin,2001,46(11):954-961.
[13] 杜陈艳,张榆锋,杨平,等.经验模态分解边缘效应抑制方法综述[J].仪器仪表学报,2009,30(1):56-59.
Du Chenyan,Zhang Yufeng,Yang Ping,et al.Approaches for the end effect restraint of empirical mode decomposition algorithm[J].Chinese Journal of Scientific Instrument,2009,30(1):56-59.
[14] Qi Keyu,He Zhengjia,Zi Yanyang.Cosine window-based boundary processing method for EMD and its application in rubbing fault diagnosis[J].Mechanical Systems and Signal Processing,2007,21(7):2750-2760.
[15] Jolliffe I T.Principal component analysis[M].New York:Springer Verlag,1989.
[16] Wang S W,Cui J T.Sensor-fault detection,diagnosis and estimation for centrifugal chiller systems using principal-component analysis method[J].Applied Energy,2005,82(3):197-213.
[17] Tax D M J,Duin R P W.Support vector domain description[J].Pattern Recognition Letters,1999,20(11/13):1191-1199.
[18] Tax D M J,Duin R P W.Support vector data description[J].Machine Learning,2004,54(1):45-66.
[19] Vapnik V N.The nature of statistical learning theory[M].New York:Springer Verlag,1995.
[20] Cho H W,Jeong M K,Kwon Y.Support vector data description for calibration monitoring of remotely located microrobotic system[J].Journal of Manufacturing Systems,2006,25(3):196-208.

基于时域统计特征的天然气管道泄漏检测方法

A leak detection method for natural gas pipelines based on time-domain statistical features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	林伟国, 王晓东, 戚元华, 吴海燕. 管道泄漏信号和干扰信号的数字化判别方法[J]. 石油学报, 2014, 35(6): 1197-1203.
[2]	赵利强　王建林　于　涛　苟武侯. 基于二代小波变换和多级假设检验的输油管道缓泄漏检测方法[J]. 石油学报, 2012, 33(5): 898-903.
[3]	蒋官澄吴雄军王晓军张卫行李洋洋王金树. 确定储层损害预测评价指标权值的层次分析法[J]. 石油学报, 2011, 32(6): 1037-1041.
[4]	孙良王建林赵利强. 负压波法在液体管道上的可检测泄漏率分析[J]. 石油学报, 2010, 31(4): 654-658.
[5]	王明达张来斌梁伟陈志刚. 基于独立分量分析和支持向量机的管道泄漏识别方法[J]. 石油学报, 2010, 31(4): 659-663.
[6]	张东领, 王树青, 张敏. 热输油管道泄漏定位技术研究[J]. 石油学报, 2007, 28(1): 131-133,138.
[7]	周琰, 靳世久, 张昀超, 孙立瑛. 分布式光纤管道泄漏检测和定位技术[J]. 石油学报, 2006, 27(2): 121-124.
[8]	崔谦, 靳世久, 王立坤, 魏茂安, 周琰. 基于序贯检验的管道泄漏检测方法[J]. 石油学报, 2005, 26(4): 123-126.
[9]	伦淑娴, 张化光, 冯健. 自适应模糊神经网络系统在管道泄漏检测中的应用[J]. 石油学报, 2004, 25(4): 101-104.