Traditional gas pipeline leak detection methods usually face challenges in that there are redundant data collected on account of the time-domain sampling theory and the valuable leakage information is hidden in the complex vibration signals. This paper put forward an intelligent aperture identification method for natural gas pipeline leakage. This method integrated the compression of monitoring data based on compressed sensing (CS) transformation and automatic feature extraction and identification based on deep neural networks, namely, denoising sparse autoencoder (DSAE). The compressed acquisition can greatly reduce the volume to be processed and effectively extract the aperture information. DSAE combined the merits of sparse auto-encoder (SAE), denoising coding and dropout to achieve robust feature extraction and aperture classification. Experimental results validate the effectiveness and good performance, and the proposed method can realize faster and more accurate identification of different leak sizes compared with the traditional methods.
MurvayP-SSileaL.A survey on gas leak detection and localization techniques. J Loss Prev Process Ind2012; 25(6): 966–973.
2.
LuHIseleyTBehbahaniS, et al. Leakage detection techniques for oil and gas pipelines: state-of-the-art. Tunnelling Underground Space Technol2020; 98: 103249.
3.
MahmoudMLyesKAbdelwahidA, et al. Leak detection systems in oil and gas fields: present trends and future prospects. Flow Meas Instrum2020; 75: 101772.
4.
DattaSSarkarS.A review on different pipeline fault detection methods. J Loss Prev Process Ind2016; 41(5): 97–106.
5.
BonnaudCCluzelVCorcolesP, et al. Experimental study and modelling of the consequences of small leaks on buried transmission gas pipeline. J Loss Prev Process Ind2018; 55: 303–312.
6.
AnYWangXYueB, et al. A novel method for natural gas pipeline safety online monitoring based on acoustic pulse compression. Process Safety Environ Protection2019; 130: 174–181.
7.
QuZWangHAnY, et al. Online monitoring method of hydrate agglomeration in natural gas pipelines based on acoustic active excitation. Measurement2016; 92: 11–18.
8.
LiuCLiYFangL, et al. Leakage monitoring research and design for natural gas pipelines based on dynamic pressure waves. J Process Control2017; 50: 66–76.
9.
SunJXiaoQWenJ, et al. Natural gas pipeline small leakage feature extraction and recognition based on LMD envelope spectrum entropy and SVM. Measurement2014; 55: 434–443.
10.
SunJXiaoQWenJ, et al. Natural gas pipeline leak aperture identification and location based on local mean decomposition analysis. Measurement2016; 79: 147–157.
11.
SunJPengZWenJ.Leakage aperture recognition based on ensemble local mean decomposition and sparse representation for classification of natural gas pipeline. Measurement2017; 108: 91–100.
12.
XiaoQLiJSunJ, et al. Natural-gas pipeline leak location using variational mode decomposition analysis and cross-time-frequency spectrum. Measurement2018; 124: 163–172.
13.
XiaoQLiJBai, et al. A small leak detection method based on VMD adaptive de-noising and ambiguity correlation classification intended for natural gas pipelines. Sensors2016; 16(12): 2116.
14.
AnYWangXBinYue, et al. Natural gas pipeline safety monitoring technique based on chaotic characteristics of the detected signals. Process Safety Environ Protection2018; 118: 279–284.
15.
QuZWangYYueH, et al. Study on the natural gas pipeline safety monitoring technique and the time-frequency signal analysis method. J Loss Prevention Process Ind2017; 47: 1–9.
16.
YuXLiangWZhangL, et al. Dual-tree complex wavelet transform and SVD based acoustic noise reduction and its application in leak detection for natural gas pipeline. Mech Syst Sig Process2016; 72–73: 266–285.
17.
WangFLinWLiuZ, et al. Pipeline leak detection by using time-domain statistical features. IEEE Sens J2017; 17(19): 6431–6442.
18.
SunJYuYWenJ.Compressed-sensing reconstruction based on block sparse bayesian learning in bearing-condition monitoring. Sensors2017; 17(6): 1454.
19.
SunJQiaoYWenJ.Intelligent aperture identification combining compressed data acquisition with sparse filtering-based deep learning towards natural gas pipeline leak. In: ChangF-KKopsaftopoulosF (eds.) Real-Time Material State Awareness and Data-Driven Safety Assurance, Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017, v 2, Structural Health Monitoring, 2017, pp. 2693–2700.
20.
DonohoDL.Compressed sensing. IEEE Trans Inf Theory2006; 52(4): 1289–1306.
21.
WangJMaYZhangL, et al. Deep learning for smart manufacturing: methods and applications. J Manuf Syst2018; 48(S1): 144–156.
22.
KhanSYairiT.A review on the application of deep learning in system health management. Mech Syst Sig Process2018; 107: 241–265.
23.
JiangGHeHXieP, et al. Stacked multilevel-denoising autoencoders: a new representation learning approach for wind turbine gearbox fault diagnosis. IEEE Trans Instrum Meas2017; 66(9): 2391–2402.
24.
SunJYanCWenJ.Intelligent bearing fault diagnosis method combining compressed data acquisition and deep learning. IEEE Trans Instrum Meas2018; 67(1): 185–195.
25.
ShaoHJiangHLiX, et al. Rolling bearing fault detection using continuous deep belief network with locally linear embedding. Comput Ind2018; 96: 27–39.
26.
JiaFLeiYGuoL, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing2018; 272: 619–628.
27.
SrivastavaNHintonGKrizhevskyA, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014; 15(1): 1929–1958.
28.
BaraniukRDavenportMDeVoreR, et al. A simple proof of the restricted isometry property for random matrices. Constr Approx2008; 28(3): 253–263.
29.
MamaghanianHKhaledNAtienzaD, et al. Compressed sensing for real-time energy-efficient ECG compression on wireless body sensor nodes. IEEE Trans Biomed Eng2011; 58(9): 2456–2466.
30.
ZhangZJungTMakeigS, et al. Compressed sensing for energy-efficient wireless telemonitoring of noninvasive fetal ECG via block sparse bayesian learning. IEEE Trans Biomed Eng2013; 60(2): 300–309.
31.
SunWJShaoSYZhaoR, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement2016; 89: 171–178.
32.
QiuYZhouWYuN, et al. Denoising sparse autoencoder-based Ictal EEG Classification. IEEE Trans Neural Syst Rehabilitation Eng2018; 26(9): 1717–1726.
33.
JiangGXiePHeH, et al. Wind turbine fault detection using a denoising autoencoder with temporal information. IEEE-ASME Trans Mech2018; 2(1): 89–100.
