This paper proposes a novel data-based leakage diagnosis method for big datasets, which identifies the leak occurrence, its size, and its location. Different statistical features are used to express the changes in flow and pressure signals at different leakage scenarios. To improve the performances of the leakage diagnosis approach, factor analysis (FA) is employed for dimension reduction purposes. The optimal features of both pressure and flow signals are then fed as input vectors to a deep neural network (DNN) classifier. The proposed leakage diagnosis method has been applied to the first 20 km of the Golkhari-Binak oil pipeline, located in Iran. The leakage isolation accuracy has been compared with some related works. Simulation results show that the proposed method significantly outperforms others with the average correct classification rate (CCR) of about 98%.
AfebuKOAbbasAJNasrGGKadirA (2015) November. Integrated leak detection in gas pipelines using OLGA simulator and artificial neural networks. In: Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, UAE, 9–12 November 2015, pp. 1–22. Society of Petroleum Engineers.
2.
AgarapAF (2018) Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375.
3.
API 1149 (2015) Pipeline Variable Uncertainties and Their Effects Leak Detectability (2nd edn). Washington DC, USA: American Petroleum Institute.
4.
BaiYBaiQ (2014) Subsea Pipeline Integrity and Risk Management. USA: Gulf Professional Publishing.
5.
BishopCM (2006) Pattern Recognition and Machine Learning. New York, NY, USA: Springer.
6.
CaoLJChuaKSChongWK, et al. (2003) A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine. Neurocomputing55(1–2): 321–336.
7.
DattaSSarkarS (2016) A review on different pipeline fault detection methods. Journal of Loss Prevention in the Process Industries41: 97–106.
8.
DoshmanziariRKhaloozadehHNikoofardA (2020) Gas pipeline leakage detection based on sensor fusion under model-based fault detection framework. Journal of Petroleum Science and Engineering184: 106581.
9.
DudaROHartPEStorkDG (2012) Pattern Classification. San Jose, California, USA: John Wiley & Sons.
10.
El-ShiekhTM (2010) Leak detection methods in transmission pipelines. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects32(8): 715–726.
11.
El-ZahabSAbdelkaderEMZayedT (2018) An accelerometer-based leak detection system. Mechanical Systems and Signal Processing108: 276–291.
12.
FiedlerJ (2014) An overview of pipeline leak detection technologies. American School of Gas Measurement Technology (ASGMT), Peabody, MA, US.
13.
GopakumarVTiwariSRahmanI (2018) A deep learning based data driven soft sensor for bioprocesses. Biochemical Engineering Journal136: 28–39.
14.
JinquiuHLaibinZZhaohuiWWeiL (2007) Application of an improved ISODATA method to pipeline leak detection. Petroleum Science4(2): 97–104.
15.
KonersmannRKühlCLudwigJ (2009) On the risks of transporting liquid and gaseous fuels in pipelines. Berlin, Germany: BAM Federal Institute for Materials Research and Testing.
16.
LangXLiPHuZ, et al. (2017) Leak detection and location of pipelines based on LMD and least squares twin support vector machine. IEEE Access5: 8659–8668.
17.
LaurentysCABomfimCHDMMenezesBRCaminhasWM (2011) Design of a pipeline leakage detection using expert system: A novel approach. Applied Soft Computing11(1): 1057–1066.
18.
LiangWZhangL (2012) A wave change analysis (WCA) method for pipeline leak detection using Gaussian mixture model. Journal of Loss Prevention in the Process Industries25(1): 60–69.
19.
MandalSKChanFTTiwariMK (2012) Leak detection of pipeline: An integrated approach of rough set theory and artificial bee colony trained SVM. Expert Systems with Applications39(3): 3071–3080.
20.
MurphyKP (2012) Machine Learning: A Probabilistic Perspective. MIT Press.
21.
MurvayPSSileaI (2012) A survey on gas leak detection and localization techniques. Journal of Loss Prevention in the Process Industries25(6): 966–973.
22.
NiLJiangJPanYWangZ (2014) Leak location of pipelines based on characteristic entropy. Journal of Loss Prevention in the Process Industries30: 24–36.
23.
NicholasECarpenterPHenrieM (2015) May. RTTM based gas pipeline leak detection: A tutorial. In: PSIG Annual Meeting. Pipeline Simulation Interest Group.
24.
NikoofardAAarsnesUJFJohansenTAKaasaGO (2015) Estimation of states and parameters of a drift-flux model with unscented Kalman filter. IFAC-PapersOnLine48(6): 165–170.
25.
NwankpaCIjomahWGachaganAMarshallS (2018) Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378.
26.
PedamontiD (2018) Comparison of non-linear activation functions for deep neural networks on MNIST classification task. arXiv preprint arXiv:1804.02763.
27.
Santos-RuizIDLBermúdezJRLópez-EstradaFR, et al. (2018) Online leak diagnosis in pipelines using an EKF-based and steady-state mixed approach. Control Engineering Practice81: 55–64.
28.
Shwartz-ZivRTishbyN (2017) Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810.
29.
SongYJLiSZ (2018) Leak detection for galvanized steel pipes due to loosening of screw thread connections based on acoustic emission and neural networks. Journal of Vibration and Control24(18): 4122–4129.
30.
SunJXiaoQWenJWangF (2014) Natural gas pipeline small leakage feature extraction and recognition based on LMD envelope spectrum entropy and SVM. Measurement55: 434–443.
31.
ValizadehSMoshiriBSalahshoorK (2009) August. Multiphase pipeline leak detection based on fuzzy classification. In: AIP Conference Proceedings59(1): 72–80.
32.
WangFLinWLiuZ, et al. (2017) Pipeline leak detection by using time-domain statistical features. IEEE Sensors Journal17(19): 6431–6442.
33.
XiaoQLiJSunJ, et al. (2018) Natural-gas pipeline leak location using variational mode decomposition analysis and cross-time–frequency spectrum. Measurement124: 163–172.
34.
XiaoRHuQLiJ (2019) Leak detection of gas pipelines using acoustic signals based on wavelet transform and Support Vector Machine. Measurement146: 479–489.
35.
ZadkaramiMShahbazianMSalahshoorK (2016) Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN). Journal of Loss Prevention in the Process Industries43: 479–487.
36.
ZadkaramiMShahbazianMSalahshoorK (2017) Pipeline leak diagnosis based on wavelet and statistical features using Dempster–Shafer classifier fusion technique. Process Safety and Environmental Protection105: 156–163.
37.
ZamanDTiwariMKGuptaAKSenD (2019) A review of leakage detection strategies for pressurised pipeline in steady-state. Engineering Failure Analysis: 104–264.
38.
ZhaoZLiQHuangB, et al. (2015) Process monitoring based on factor analysis: Probabilistic analysis of monitoring statistics in presence of both complete and incomplete measurements. Chemometrics and Intelligent Laboratory Systems142: 18–27.
39.
ZhengYWangZFanX, et al. (2018) Localizing multiple software faults based on evolution algorithm. Journal of Systems and Software139: 107–123.
40.
ZhouMPanZLiuY, et al. (2019) Leak detection and location based on ISLMD and CNN in a Pipeline. IEEE Access7: 30457–30464.
