Paper Titles
Effect of Pozzolanic Properties of Waste-Paper Pulp Ash in High Performance Concrete
p.1
Mechanical Properties of Sustainable Concrete Incorporating Steel-Binding Wire Wastes
p.17
Taguchi-Based Analysis of EPAC Constituents Affecting Natural Self-Healing in Non-Structural Concrete
p.35
Exponential Models of Concrete Block Produced with Coconut Shell and Coconut Shell-Ash for Strength Characterization and Structural Stability
p.53
Thermal and Mechanical Performance of Innovative Solid Olive Waste Composite for Use as Insulating Materials in Building
p.79
Real-Time Thermodynamic Analysis of Gas Turbines in Combined Cycle Power Plants
p.99
Energy Efficiency Optimization of Motor-Driven Pump Systems: A Case Study in a Moroccan Manufacturing Plant
p.117
Long Short-Term Memory-Autoencoder Model for Intelligent Oil-and-Gas Pipeline Anomaly Detection
p.141
Comparative Analysis of P&O and Fuzzy Logic MPPT Techniques for Photovoltaic Systems under Standard and Partial Shading Conditions Using DC-DC Converters
p.159

Long Short-Term Memory-Autoencoder Model for Intelligent Oil-and-Gas Pipeline Anomaly Detection

Article Preview

Abstract:

Pipelines are critical assets for transporting liquid and gaseous products in the oil and gas industry, and they are typically situated in challenging operational environments. Over time, adverse operational and environmental conditions lead to wear and tear of their structural components, resulting in structural anomalies that manifest as leak points. An effective pipeline anomaly and leakage detection mechanism is therefore crucial to maintaining the integrity of the product transportation system. This study develops a Long Short-Term Memory-AutoEncoder (LSTM-AE) model for real-time anomaly and leak detection in oil-and-gas production pipelines. The developed model uses an ensemble approach to adapt a multi-layer Long Short-Term Memory (LSTM) to improve the performance of an AutoEncoder (AE). The resulting hybrid LSTM-AE model composes an encoder, a repeat vector, and a decoder with a data-driven capability. The performance of the developed model is evaluated using publicly available oil-and-gas production data. Results indicate that the base AE model achieves accuracy, recall, and precision rates of 72%, 72%, and 100%, respectively, whilst the LSTM-AE model achieves improved rates of 88%, 100%, and 100% for the same respective metrics. The realized performance enhancement gives credence to the utility of the LSTM-AE model for effective intelligent anomaly detection in pipeline systems.

You might also be interested in these eBooks
International Journal of Engineering Research in Africa Vol. 75 View Preview

Info:

Periodical:

International Journal of Engineering Research in Africa (Volume 75)

Pages:

141-158

DOI:

https://doi.org/10.4028/p-TrVqP9

Citation:

Cite this paper

Online since:

October 2025

Authors:

Ojo Ayokunle Dolire*, Akaa Agbaeze Eteng, Stella Ifeoma Orakwue

Keywords:

AutoEncoder, Deep Learning, Long Short-Term Memory, Machine Learning, Pipeline, Recurrent Neural Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2025 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] Q. Li, Q. Li, H. Cao, J. Wu, F. Wang, Y. Wang, The Crack Propagation Behaviour of CO2 Fracturing Fluid in Unconventional Low Permeability Reservoirs: Factor Analysis and Mechanism Revelation, Processes 13 (2025) 1–18.

DOI: 10.3390/pr13010159

Google Scholar

[2] Q. Li, Q. Li, J. Wu, X. Li, H. Li, Y. Cheng, Wellhead Stability During Development Process of Hydrate Reservoir in the Northern South China Sea: Evolution and Mechanism, Processes 13 (2025) 1–27.

DOI: 10.3390/pr13010040

Google Scholar

[3] Q. Li, Q. Li, Y. Han, A Numerical Investigation on Kick Control with the Displacement Kill Method during a Well Test in a Deep-Water Gas Reservoir: A Case Study, Processes 12 (2024).

DOI: 10.3390/pr12102090

Google Scholar

[4] M.A. Adegboye, W. Fung, A. Karnik, Recent Advances in Pipeline Monitoring and Oil Leakage Detection Technologies : Principles and approaches, (2019).

DOI: 10.3390/s19112548

Google Scholar

[5] N. Venkata, S. Korlapati, F. Khan, Q. Noor, S. Mirza, Review and analysis of pipeline leak detection methods, J. Pipeline Sci. Eng. 2 (2022) 100074.

DOI: 10.1016/j.jpse.2022.100074

Google Scholar

[6] J. Yuan, W. Mao, C. Hu, J. Zheng, D. Zheng, Leak detection and localization techniques in oil and gas pipeline : A bibliometric and systematic review, Eng. Fail. Anal. 146 (2023) 107060.

DOI: 10.1016/j.engfailanal.2023.107060

Google Scholar

[7] M. Nikles, B. Vogel, F. Briffod, S. Grosswig, F. Sauser, Leakage detection using fiber optics distributed temperature monitoring, (2004).

DOI: 10.1117/12.540270

Google Scholar

[8] C. Hou, E. Zhang, Pipeline Leak Detection Based on Double Sensor Negative Pressure Wave, Appl. Mech. Mater. 313–314 (2013) 1225–1228.

DOI: 10.4028/www.scientific.net/AMM.313-314.1225

Google Scholar

[9] T. Barchyn, C. Hugenholtz, S. Myshak, J. Bauer, A UAV-based system for detecting natural gas leaks, J. Unmannered Veh. Syst. 6 (2017) 18–30.

DOI: 10.1139/juvs-2017-0018

Google Scholar

[10] R. Doshmanziari, H. Khaloozadeh, A. Nikoofard, Journal of Petroleum Science and Engineering Gas pipeline leakage detection based on sensor fusion under model-based fault detection framework, J. Pet. Sci. Eng. 184 (2020) 106581.

DOI: 10.1016/j.petrol.2019.106581

Google Scholar

[11] X. Diao, G. Shen, J. Jiang, Q. Chen, Z. Wang, L. Ni, Industries Leak detection and location in liquid pipelines by analyzing the fi rst transient pressure wave with unsteady friction, J. Loss Prev. Process Ind. 60 (2019) 303–310.

DOI: 10.1016/j.jlp.2019.04.017

Google Scholar

[12] W. Wang, Y. Gao, Pipeline leak detection method based on acoustic-pressure information fusion, Measurement 212 (2023) 112691.

DOI: 10.1016/j.measurement.2023.112691

Google Scholar

[13] M. Guerriero, F. Wheeler, Bayesian Data Fusion for Pipeline Leak Detection, 19th Int. Conf. Inf. Fusion , Proc. (FUSION 2016) (2016) 278–285.

Google Scholar

[14] J. Kim, M. Chae, J. Han, S. Park, Y. Lee, The development of leak detection model in subsea gas pipeline using machine learning, J. Nat. Gas Sci. Eng. 94 (2021) 104134.

DOI: 10.1016/j.jngse.2021.104134

Google Scholar

[15] K.O. Afebu, A.J. Abbas, G.G. Nasr, A. Kadir, U. Kingdom, Integrated Leak Detection in Gas Pipelines Using OLGA Simulator and and artificial neural networks, (2015).

DOI: 10.2118/177459-ms

Google Scholar

[16] R. Xiao, J. Li, Evaluation of acoustic techniques for leak detection in a complex low-pressure gas pipeline network, Eng. Fail. Anal. 143 (2023) 106897.

DOI: 10.1016/j.engfailanal.2022.106897

Google Scholar

[17] C. Spandonidis, P. Theodoropoulos, F. Giannopoulos, A Combined Semi-Supervised Deep Learning Method for Oil Leak Detection in Pipelines Using IIoT at the Edge, Sensors 22 (2022).

DOI: 10.3390/s22114105

Google Scholar

[18] Q. Tan, M. Fu, X. Chen, H. Yuan, G. Liang, J. Sun, A new leak recognition method for natural gas pipelines in the urban underground space based on probabilistic neural network, J. Loss Prev. Process Ind. (2023) 105162.

DOI: 10.1016/j.jlp.2023.105162

Google Scholar

[19] D. Karimanzira, Simultaneous Pipe Leak Detection and Localization Using Attention-Based Deep Learning Autoencoder, Electron. 12 (2023).

DOI: 10.3390/electronics12224665

Google Scholar

[20] P. Schneider, F. Xhafa, Anomaly Detection and Complex Event Processing over IoT Data Streams, in: 2022.

DOI: 10.1016/b978-0-12-823818-9.00013-4

Google Scholar

[21] M.G. Narasimhan, S. Sowmya Kamath, Dynamic video anomaly detection and localization using sparse denoising autoencoders, Multimed. Tools Appl. 77 (2018) 13173–13195.

DOI: 10.1007/s11042-017-4940-2

Google Scholar

[22] G. Bebis, R. Boyle, B. Parvin, D. Koracin, F. Porikli, S. Skaff, A. Entezari, J. Min, D. Iwai, A. Sadagic, C. Scheidegger, T. Isenberg, Abnormal event detection and localization in crowded scenes, Adv. Vis. Comput. 12th Int. Symp. ISVC 2016 Las Vegas, NV, USA, December 12–14, 2016 Proceedings, Part II 10073 LNCS (2016).

DOI: 10.1007/978-3-319-50832-0

Google Scholar

[23] D. Kucharski, P. Kleczek, J. Jaworek-korjakowska, G. Dyduch, M. Gorgon, Semi-Supervised Nests of Melanocytes Segmentation Method Using Convolutional Autoencoders, (2020) 1–19.

DOI: 10.3390/s20061546

Google Scholar

[24] K. Berahmand, F. Daneshfar, E.S. Salehi, Y. Li, Y. Xu, Autoencoders and their applications in machine learning: a survey, Artif. Intell. Rev. 57 (2024) 28.

DOI: 10.1007/s10462-023-10662-6

Google Scholar

[25] S. Chen, W. Guo, Auto-Encoders in Deep Learning—A Review with New Perspectives, Mathematics 11 (2023) 1–54.

DOI: 10.3390/math11081777

Google Scholar

[26] M. Said Elsayed, N.A. Le-Khac, S. Dev, A.D. Jurcut, Network Anomaly Detection Using LSTM Based Autoencoder, Q2SWinet 2020 - Proc. 16th ACM Symp. QoS Secur. Wirel. Mob. Networks (2020) 37–45.

DOI: 10.1145/3416013.3426457

Google Scholar

[27] A. Malekpour, Y. She, Real-time leak detection in oil pipelines using an Inverse Transient Analysis model, J. Loss Prev. Process Ind. 70 (2021) 104411.

DOI: 10.1016/j.jlp.2021.104411

Google Scholar

[28] O. Choura, C. Capponi, S. Meniconi, S. Elaoud, B. Brunone, A Nelder–Mead algorithm-based inverse transient analysis for leak detection and sizing in a single pipe, (2021) 1580–1593.

DOI: 10.2166/ws.2021.030

Google Scholar

[29] A.P. Ekong, G.G. James, I. Ohaeri, Oil and Gas Pipeline Leakage Detection using IoT and Deep Learning Algorithm, J. Inf. Syst. Informatics 6 (2024) 421–434.

DOI: 10.51519/journalisi.v6i1.652

Google Scholar

[30] Abimbola-ai, Oil-and-gas-pipeline-leakage, (2020). https://github.com/Abimbola-ai/Oil-and-gas-pipeline-leakage (accessed December 5, 2024).

Google Scholar

[31] S.S. Aljameel, D.M. Alomari, S. Alismail, F. Khawaher, A.A. Alkhudhair, F. Aljubran, R.M. Alzannan, An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning, Computation 10 (2022).

DOI: 10.3390/computation10080138

Google Scholar

[32] L.B.V. de Amorim, G.D.C. Cavalcanti, R.M.O. Cruz, The choice of scaling technique matters for classification performance, Appl. Soft Comput. 133 (2023) 1–37.

DOI: 10.1016/j.asoc.2022.109924

Google Scholar

[33] S.G.K. Patro, K.K. sahu, Normalization: A Preprocessing Stage, Iarjset (2015) 20–22.

DOI: 10.17148/iarjset.2015.2305

Google Scholar

[34] H. Chen, Y.H. Wang, C.H. Fan, A convolutional autoencoder-based approach with batch normalization for energy disaggregation, J. Supercomput. 77 (2021) 2961–2978.

DOI: 10.1007/s11227-020-03375-y

Google Scholar

[35] A. Mallak, M. Fathi, Sensor and component fault detection and diagnosis for hydraulic machinery integrating lstm autoencoder detector and diagnostic classifiers, Sensors (Switzerland) 21 (2021) 1–22.

DOI: 10.3390/s21020433

Google Scholar

[36] P. Mobtahej, X. Zhang, M. Hamidi, J. Zhang, An LSTM-Autoencoder Architecture for Anomaly Detection Applied on Compressors Audio Data, Comput. Math. Methods 2022 (2022) 1–22.

DOI: 10.1155/2022/3622426

Google Scholar

[37] Y. Shin, K.Y. Na, S.E. Kim, E.J. Kyung, H.G. Choi, J. Jeong, LSTM-Autoencoder Based Detection of Time-Series Noise Signals for Water Supply and Sewer Pipe Leakages, Water (Switzerland) 16 (2024) 1–22.

DOI: 10.3390/w16182631

Google Scholar

[38] M. Qiao, T. Wang, J. Li, C. Li, Z. Lin, H. Snoussi, Abnormal event detection based on deep autoencoder fusing optical flow, Chinese Control Conf. CCC (2017) 11098–11103.

DOI: 10.23919/ChiCC.2017.8029129

Google Scholar

[39] D. Gong, L. Liu, V. Le, B. Saha, M.R. Mansour, S. Venkatesh, A. Van Den Hengel, Memorizing normality to detect anomaly, Proc. IEEE Int. Conf. Comput. Vis. 2019-Octob (2019) 1705–1714.

DOI: 10.1109/iccv.2019.00179

Google Scholar

[40] T.T. Dien, S.H. Luu, N. Thanh-Hai, N. Thai-Nghe, Deep learning with data transformation and factor analysis for student performance prediction, Int. J. Adv. Comput. Sci. Appl. 11 (2020) 711–721.

DOI: 10.14569/IJACSA.2020.0110886

Google Scholar

[41] Y. Li, J. Li, Z. Lv, H. Li, Y. Wang, Z. Xu, GASTO: A Fast Adaptive Graph Learning Framework for Edge Computing Empowered Task Offloading, IEEE Trans. Netw. Serv. Manag. 20 (2023) 932–944. https://doi.org/.

DOI: 10.1109/TNSM.2023.3250395

Google Scholar

[42] H. Sun, Z. Lv, J. Li, Z. Xu, Z. Sheng, Will the Order Be Canceled? Order Cancellation Probability Prediction Based on Deep Residual Model, Transp. Res. Rec. 2677 (2023) 142–160. https://doi.org/.

DOI: 10.1177/03611981221144279

Google Scholar

[43] H. Sun, Z. Lv, J. Li, Z. Xu, Z. Sheng, Z. Ma, Prediction of Cancellation Probability of Online Car-Hailing Orders Based on Multi-source Heterogeneous Data Fusion, in: Wirel. Algorithms, Syst. Appl., 2022: p.168–180. https://doi.org/.

DOI: 10.1007/978-3-031-19214-2_14

Google Scholar