An online real-time estimation tool of leakage parameters for hazardous liquid pipelines

Abstract Hazardous liquid pipeline (HLP) leaks not only result in energy waste and environmental pollution, but also pose a threat to people's lives and property. The estimation of leakage parameters is an essential part of risk assessment and environment pollution assessment. However, current common leak detection methods are mainly based on physical models with assumptions and are susceptible to noise. Limited historical leakage data render it impossible to develop a leak model in advance. To address this problem, this study establishes a pipeline digital twin model that simulates a pipeline leak to generate leakage data. A conditional variational auto-encoder (CVAE) framework is proposed to estimate the leakage parameters based on data detected by upstream and downstream meters once the HLP leak occurs. CVAE can treat the high-dimensional detected data as labels to overcome the dimensionality problem. Based on the CVAE framework, an online real-time leakage parameter estimation tool for HLP is formed. To qualify the performance of the approach, a sensitivity analysis for the structure of the CVAE framework is evaluated. Finally, four examples demonstrate the effectiveness, stability, and applicability of the proposed method.

[1]  Zhang Laibin,et al.  Data Mining Technology Based Leak Detection Method for Crude Oil Pipeline , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[2]  Subrata Bhowmik.  Digital Twin of Subsea Pipelines: Conceptual Design Integrating IoT, Machine Learning and Data Analytics , 2019 .

[3]  Svetlana Lazebnik,et al.  Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space , 2017, NIPS.

[4]  Bo Kong,et al.  Multipoint hoop strain measurement based pipeline leakage localization with an optimized support vector regression approach , 2019, Journal of Loss Prevention in the Process Industries.

[5]  Haoran Zhang,et al.  Improved PSO-Based Method for Leak Detection and Localization in Liquid Pipelines , 2018, IEEE Transactions on Industrial Informatics.

[6]  Feng Li,et al.  A method for simulating the entire leaking process and calculating the liquid leakage volume of a damaged pressurized pipeline. , 2017, Journal of hazardous materials.

[7]  Zhihong Qian,et al.  A novel location algorithm for pipeline leakage based on the attenuation of negative pressure wave , 2019, Process Safety and Environmental Protection.

[8]  Jiheon Kang,et al.  Novel Leakage Detection by Ensemble CNN-SVM and Graph-Based Localization in Water Distribution Systems , 2018, IEEE Transactions on Industrial Electronics.

[9]  B. Zhao.  Qingdao pipeline explosion: introductions and reflections , 2014, Natural Hazards.

[10]  Zhirong Wang,et al.  Leak detection and location in liquid pipelines by analyzing the first transient pressure wave with unsteady friction , 2019, Journal of Loss Prevention in the Process Industries.

[11]  Ioan Silea,et al.  A survey on gas leak detection and localization techniques , 2012 .

[12]  L. I. Minchala,et al.  Leak Detection and Location in Great Longitude Pipelines through Speed Propagation of the Negative Pressure Wave , 2012, 2012 VI Andean Region International Conference.

[13]  Yongtu Liang,et al.  A hybrid computational approach for detailed scheduling of products in a pipeline with multiple pump stations , 2017 .

[14]  Xiaofeng Hu,et al.  A probabilistic analysis model of oil pipeline accidents based on an integrated Event-Evolution-Bayesian (EEB) model , 2018, Process Safety and Environmental Protection.

[15]  Zhirong Wang,et al.  Leak location of pipelines based on characteristic entropy , 2014 .

[16]  Yuxing Li,et al.  A new leak location method based on leakage acoustic waves for oil and gas pipelines , 2015 .

[17]  Stefan Boschert,et al.  Digital Twin—The Simulation Aspect , 2016 .

[18]  Didem Ozevin,et al.  Novel leak localization in pressurized pipeline networks using acoustic emission and geometric connectivity , 2012 .

[19]  Minghai Xu,et al.  An integrated detection and location model for leakages in liquid pipelines , 2019, Journal of Petroleum Science and Engineering.

[20]  Qiyang Xiao,et al.  Natural gas pipeline leak aperture identification and location based on local mean decomposition analysis , 2016 .

[21]  Khe Chai Sim,et al.  Learning utterance-level normalisation using Variational Autoencoders for robust automatic speech recognition , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[22]  S. Shirazi,et al.  Failure analysis and simulation model of pinhole corrosion of the refined oil pipeline , 2019 .

[23]  Jian Li,et al.  A small leakage detection approach for oil pipeline using an inner spherical ball , 2019, Process Safety and Environmental Protection.

[24]  Shubi Kaijage,et al.  An overview of pipeline leak detection and location systems , 2014, Proceedings of the 2nd Pan African International Conference on Science, Computing and Telecommunications (PACT 2014).

[25]  Hong-Nan Li,et al.  Pipeline Leak Localization Based on FBG Hoop Strain Sensors Combined with BP Neural Network , 2018 .

[26]  Ye Hao.  Oil pipeline leak detection and location based on image processing , 2005 .

[27]  Hongwei Zhu,et al.  Quantitative risk analysis on leakage failure of submarine oil and gas pipelines using Bayesian network , 2016 .

[28]  Kyunghyun Cho,et al.  Conditional molecular design with deep generative models , 2018, J. Chem. Inf. Model..

[29]  Shuaiyong Li,et al.  Leak location in gas pipelines using cross-time–frequency spectrum of leakage-induced acoustic vibrations , 2014 .

[30]  Yongtu Liang,et al.  Environmental consequence analysis of oil spills from onshore pipelines with parametric uncertainty , 2020 .

[31]  Yongtu Liang,et al.  A leakage risk assessment method for hazardous liquid pipeline based on Markov chain Monte Carlo , 2019, Int. J. Crit. Infrastructure Prot..

[32]  Xiaodong Xu,et al.  Long range pipeline leak detection and localization using discrete observer and support vector machine , 2019, AIChE Journal.

[33]  Feng Jian,et al.  Oil pipeline leak detection and location using double sensors pressure gradient method , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[34]  Chunlong Ma,et al.  Negative pressure wave-flow testing gas pipeline leak based on wavelet transform , 2010, 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering.

[35]  Guangquan Lu,et al.  Multi-task learning using variational auto-encoder for sentiment classification , 2020, Pattern Recognit. Lett..

[36]  V. Cozzani,et al.  Assessment of the risk related to environmental damage following major accidents in onshore pipelines , 2018, Journal of Loss Prevention in the Process Industries.

[37]  Roland Rosen,et al.  About The Importance of Autonomy and Digital Twins for the Future of Manufacturing , 2015 .

[38]  Xiangdong Xie,et al.  A new analytical method of strain and deformation of pipeline under fault movement , 2019, International Journal of Pressure Vessels and Piping.

[39]  Xiaobo Qiu,et al.  Pipeline Leak Detection by Using Time-Domain Statistical Features , 2017, IEEE Sensors Journal.

[40]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.