摘要
针对强干扰背景下管道泄漏声波检测产生的误报和漏报,提出一种基于同源性检验的干扰信号识别方法。将干扰信号和泄漏信号均作为异常信号,在基于迭代计算的异常信号自适应提取和一对一互相关延时估计的基础上,找出定位在站点的上下游异常信号并计算出相应的传播衰减特性。以同源信号的传播衰减频域特征和互相关系数为特征向量,建立异常信号同源性检验的支持向量数据描述(SVDD)诊断模型,实现站上干扰信号的识别和分离。对实际原油输送管线历史数据的离线测试结果表明:提出的方法能够可靠识别与分离干扰信号,有效减少系统的误报和漏报,并提高泄漏检测的可靠性和定位精度。
Aiming at false and missing alarms generated by pipeline leak acoustic wave detection under strong interference background,an approach for interference signal identification based on homology test is proposed.Interference and leak signals are all regarded as abnormal signals,on the basis of abnormal signal adaptive extraction of iterative computations and one to one cross-correlation time delay estimation,the abnormal signals from upstream and downstream,which located on the site with cross correlation are extracted,and the propagation damping characteristics are calculated. Use propagation damping frequency domain features and the crosscorrelation coefficient as the feature vector,a SVDD diagnostic model for homology test of abnormal signals is established. With the homology test diagnostic model,the identification and separation of interference signals can be implemented. The off-line test of historical field data collected from a crude oil transportation pipeline is conducted,test result shows that: the approach can reliably distinguish interference signals caused by site operation; false and missing alarms are effectively reduced,and the reliability of leak detection and the precision of localization are both improved.
引文
[1] Batzias F A,Siontorou C G,Spanidis P M P. Designing a reliable leak bio-detection system for natural gas pipelines[J]. Journal of Hazardous Materials,2011,186(1):35-58.
[2] Breton T,SanchezGheno J C,Alamilla J L,et al. Identification of failure type in corroded pipelines:A Bayesian probabilistic approach[J]. Journal of Hazardous Materials,2010,179(1-3):628-634.
[3] Yu X C,Liang W,Zhang L B,et al. Dual-tree complex wavelet transform and SVD based acoustic noise reduction and its application in leak detection for natural gas pipeline[J]. Mechanical Systems and Signal Processing,2016,72:266-285.
[4] Liu C W,Li Y X,Fu J T,et al. Experimental study on acoustic propagation-characteristics-based leak location method for natural gas pipelines[J]. Process Safety and Environmental Protection,2015,96:43-60.
[5]勒振宇,吴建德,范玉刚,等.基于MEMS加速度计的管道位移检测系统设计[J].传感器与微系统,2012,31(1):140-142.
[6] Zhang Y,Chen S L,Li J,et al. Leak detection monitoring system of long distance oil pipeline based on dynamic pressure transmitter[J]. Measurement,2014,49:382-389.
[7] Xu Q Q,Zhang L B,Liang W. Acoustic detection technology for gas pipeline leakage[J]. Process Safety and Environmental Protection,2013,91(4):253-261.
[8]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.
[9]靳世久,唐秀家,王立宁,等.原油管道泄漏检测与定位[J].仪器仪表学报,1997,18(4):343-348.
[10]林伟国,王晓东,戚元华,等.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.
[11] Lin W G,Wang X D,Wu H Y,et al. A dual-sensor-based method to recognize pipeline leakage and interference signals[J]. Journal of Loss Prevention in the Process Industries,2015,38:79-86.
[12]邵煜,葛传虎,叶昊,等.基于负压波的管道泄漏检测与定位系统评价[J].油气储运,2008,27(4):5-9.
[13] Liu C W,Li Y X,Yan Y K,et al. A new leak location method based on leakage acoustic waves for oil and gas pipelines[J].Journal of Loss Prevention in the Process Industries,2015,35:236-246.
[14] Zheng S F. Smoothly approximated support vector domain description[J]. Pattern Recognition. 2016,49:55-64.
[15] Guo S M,Chen L C,Tsai J S H. A boundary method for outlier detection based on support vector domain description[J]. Pattern Recognition,2009(1):77-83.
[16] Wang F,Lin W G,He Z Y,et al. Adaptive abnormal signal extraction based on iterative computations[C]∥The 28th Chinese Control and Decision Conference,2016:7261-7266.
[17]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.