Pipeline small leakage detection based on the EWT and AFCC
XIAO Qiyang1, LI Jian1, SUN Jiedi2, ZENG Zhoumo1
1. State Key Laboratory of Precision Measurement Technology and Instrument, Tianjin University, Tianjin, 300072,China ;
2. School of Information Science and Engineering, Yanshan University, Qin Huang Dao, Hebei Prov-ince 066004,China
Aiming at the small leakage detection in natural gas pipelines, a leak detection method based on the empirical wavelet transform (EWT) and ambiguity function correlation classification (AFCC) was proposed. The acquired signals from sensors were decomposed by the EWT, and then the kurtosis values of decomposition components were calculated. According to the kurtosis values, an adaptive denoising algorithm based on the EWT was proposed to process these noised components and the de-noised components were extracted and then reconstructed. The ambiguity function images were employed to analyze the de-noised signals. Combining with the correlation coefficient, the AFCC was proposed to detect the small leakage of pipelines. The experimental results show the proposed method can effectively detect the small leakage, and the result is better than that of the SVM or BP.
肖启阳1, 李健1, 孙洁娣2, 曾周末1. 基于EWT及模糊相关分类器的管道微小泄漏检测[J]. 振动与冲击, 2018, 37(14): 122-129.
XIAO Qiyang1, LI Jian1, SUN Jiedi2, ZENG Zhoumo1 . Pipeline small leakage detection based on the EWT and AFCC. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(14): 122-129.
[1] Sun J, Xiao Q, Wen J, et al. Natural gas leak location with K–L divergence-based adaptive selection of Ensemble Local Mean Decomposition components and high-order ambiguity function [J]. Journal of Sound and Vibration, 2015, 347: 232-245.
[2] Murvay P S, 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
[3] Sun J, Xiao Q, Wen J, et al.. Natural gas pipeline leak aperture identification and location based on local mean decomposition analysis[J]. Measurement, 79 (2016):147-157.
[4] 曲志刚,李健,靳世久,等. 基于EMD 的油气管道安全分布式光纤预警系统信号分析方法[J]. 天津大学学报, 2007, 40(1): 73-77.
Qu Zhigang,Li Jian,Jin Shijiu,et al. EMD-based sig-nal analysis method of distributed optical fiber pre-warning system for safety of oil and gas pipeline [J]. Journal of TianJin University, 2007, 40(1):73-77(in Chinese).
[5] Xiao.Q, Li .J, Bai. Zi, et al. A small leak detection method based on VMD adaptive de-noising and ambiguity corre-lation classification intended for natural gas pipelines [J]. Sensors, , 16(12)(2016): 2116
[6] Qu Z, Zhou Y, Zeng Z, et al. Detection of the abnormal events along the oil and gas pipeline and multi-scale chaotic character analysis of the detected signals [J]. Measurement Science and Technology, 2008, 19(2): 025301.
[7] Jin H, Zhang L, Liang W, et al. Integrated leakage detection and localization model for gas pipelines based on the acoustic wave method [J]. Journal of Loss Prevention in the Process Industries, 2014, 27: 74-88.
[8] Yen C L, Lu M C, Chen J L. Applying the self-organization feature map (SOM) algorithm to AE-based tool wear monitoring in micro-cutting [J]. Mechanical Systems and Signal Processing, 2013, 34(1): 353-366.
[9] Bin G F, Gao J J, Li X J, et al. Early fault diagnosis of rotating machinery based on wavelet packets—Empirical mode decomposition feature extraction and neural network [J]. Mechanical Systems and Signal Processing, 2012, 27: 696-711.
[10] Guo W, Peter W T. A novel signal compression method based on optimal ensemble empirical mode decomposition for bearing vibration signals [J]. Journal of sound and vibration, 2013, 332(2): 423-441.
[11] Davoodi S, Mostafapour A. Gas leak locating in steel pipe using wavelet transform and cross-correlation method [J]. The International Journal of Advanced Manufacturing Technology, 2014, 70(5-8): 1125-1135.
[12] Nguyen P, Kang M, Kim J M, et al. Robust condition monitoring of rolling element bearings using de-noising and envelope analysis with signal decomposition tech-niques[J]. Expert Systems with Applications, 2015, 42(22): 9024-9032.
[13] 易洪春, 刘树才, 贺克升, 等. 基于 EMD 去噪方法研究及其在地质勘探中的应用[J]. 物探与化探, 2013, 37(3): 533-537.
Yi Hongchun, Liu Shucai, He Kesheng, et al. Datadenois-ing based on EMD and its application to geological ex-ploration [J]. Geophysical & Geochemical Exploration, 2013, 37(3):533-537(in Chinese).
[14] 邵忍平, 曹精明, 李永龙. 基于 EMD 小波阈值去噪和时频分析的齿轮故障模式识别与诊断[J]. 振动与冲击, 2012, 31(8): 96-101。
Shao Renping, Cao Jingming, Li Yonglong. Gear fault pattern identification and diagnosis using time-frequency analysis and wavelet threshold de-noising based on EMD [J]. Journal of Vibration and Shock, 2012, 31(8): 96-101(in Chinese).
[15] Dragomiretskiy K, Zosso D. Variational mode decompo-sition [J]. Signal Processing, IEEE Transactions on, 2014, 62(3): 531-544.
[16] Yin A, Ren H. A propagating mode extraction algorithm for microwave waveguide using variational mode decom-position [J]. Measurement Science and Technology, 2015, 26(9): 095009.
[17] Kutyniok G. Ambiguity functions, Wigner distributions and Cohen's class for LCA groups[J]. Journal of mathe-matical analysis and applications, 2003, 277(2): 589-608.
[18] 李潇, 杨国安, 吴贞焕, 等. 基于声发射信号模糊函数综合相关系数的海洋平台各类损伤识别方法[J]. 机械工程学报, 2014, 50(22): 1-9.
Li Xiao, Yang Guoan, Wu Zhenhuan, et al. Damage iden-tification method of offshore platforms by ambiguity function integrated correlation coefficient of the acoustic emission signals [J]. Journal of Mechanical Engineering, 2014, 50 (22):1-9(in Chinese).
[19] Bonato P, Ceravolo R, De Stefano A, et al. Bilinear time-frequency transformations in the analysis of damaged structures[J]. Mechanical Systems and Signal Processing, 1997, 11(4): 509-527.