MACHINE LEARNING PREDICTION OF VOLUME FRACTION OF GAS-HYDRATES IN NATURAL GAS PIPELINES IN OFFSHORE NIGER DELTA
Abstract
This study employs multiphase simulations with OLGA software to investigate volume fractions of hydrate in an offshore gas system and develops machine-learning models to predict these fractions. Annually, substantial operating expenditures are allocated to hydrate prevention, with significant costs associated with inhibition (Wang et al., 2022). Hydrate formation along natural gas pipelines is recognized as a critical threat to the success of gas field operations. Despite the importance, no machine learning model has been validated for predicting volume fractions of hydrate in the Niger Delta study area, making this development crucial. Key findings indicate significant hydrate jamming risks in Niger Delta offshore flowlines and risers, with a peak volume fraction of 0.54, highlighting the need for proactive management strategies. Hydrate formation begins at 750 m where fluid temperatures fall below formation thresholds, with a sudden increase in volume at 2971 m, peaking at 3022 m before declining. Machine Learning model comparisons show Random Forest's superior accuracy (correlation coefficient of 0.9391, mean absolute error of 0.0271), while Linear Regression provides interpretable insights for future predictions. All models perform well, with Random Forest leading in accuracy. Regression analysis reveals relationships between volume fractions of hydrate and various parameters, guiding management strategies. The Random Forest and Linear Regression models are valuable for estimating hydrate volumes and enhancing management approaches in natural gas pipelines due to their accuracy and interpretability. These findings underscore the importance of proactive hydrate management in offshore gas systems and the potential of Machine Learning models to optimize these strategies.
References
Barker, J. W. (1989). Formation of Hydrates during Deep water Drilling Operations, . SPE/ADC 16130, presented at the 1987 SPE/LADC Drilling Conference. New Orleans, LA.: SPE/ADC.
Dorstewitz F. Mewes, D. (1995). Hydrate Formation in Pipelines. Presented at the Fifth International Offshore and Polar Engineering Conference
Garapati, B. J., N. A. (2014). Statistical thermodynamics model and empirical correlations for predicting mixed hydrate phase equilibria. Fluid Phase Equilibria, 373(NA), 20–28. https://doi.org/10.1016/j.fluid.2014.03.010 DOI: https://doi.org/10.1016/j.fluid.2014.03.010
Gbaruko, B. C. (2004). Asphaltenes, oil recovery and down-hole upgrading in the Nigerian petroleum industry. In ACS National Meeting Book of Abstracts (Vol. 228, Issue 2). 228 ACS National meeting.
Hackeling, G. (2014). Mastering Machine Learning with scikit-learn. Birmingham: Packt Publishing.
Infochem, Technologies. (2015). Multiflash for Windows. Surrey: KBC Advanced Technologies Ltd.
Kaplan, A., & Haenlein, M. (2019). Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Business Horizons, 62(1), 15–25. https://doi.org/10.1016/j.bushor.2018.08.004 DOI: https://doi.org/10.1016/j.bushor.2018.08.004
Kummamuru P.; Lenaerts, Silvia, N. B. . P. (2021). A New Generalized Empirical Correlation for Predicting Methane Hydrate Equilibrium Conditions in Pure Water. Industrial & Engineering Chemistry Research, 60(8), 3474–3483. https://doi.org/10.1021/acs.iecr.0c05833
Moradi, E., G. K. (2013). Modeling of hydrate formation conditions for CH4, C2H6, C3H8, N2, CO2 and their mixtures using the PRSV2 equation of state and obtaining the Kihara potential parameters for these components. Fluid Phase Equilibria, 38(NA), 179–187. https://doi.org/10.1016/j.fluid.2012.11.010 DOI: https://doi.org/10.1016/j.fluid.2012.11.010
NAPIMS. (2023). Crude Oil Reserves/ Production. http://www.napims.com/crudeoil.html .
Nazifi, S., O. G. (2024). Crop Yield Prediction Using Selected Machine Learning Algorithms. FUDMA Journal of Sciences (FJS), 61 - 68. DOI: https://doi.org/10.33003/fjs-2024-0801-2220
Odutola, T. (2022). Engineering and Scientific Research ( UJESR ) Comparing the Effectiveness of Methanol , Ethanol and Monoethylene Glycol at Preventing Hydrate Formation in a Hydrate Flow Loop. 6(2), 6–13.
Odutola, T. O., Ikiensikimama, S. S., & Ajienka, J. A. (2015). Effective Hydrate Management during Gas Expansion. Effective Hydrate Management during Gas Expansion Conference Paper at Nigeria Annual International Conference and Exhibition (2015) Society of Petroleum Engineers/2015/ SPE 178342.
Patrice, K., & Lenaerts, S. N. (2021). A New Generalized Empirical Correlation for Predicting Methane Hydrate Equilibrium Conditions in Pure Water. Industrial & Engineering Chemistry Research, 60 (8) , 3474–3483. DOI: https://doi.org/10.1021/acs.iecr.0c05833
Qin, H. (2020). Hydrate Film Growth and Risk Management in Oil/Gas Pipelines using Experiments, Simulations, and Machine Learning.
Saeed, Z. and E. A. (2021). Modelling the Formation of Gas Hydrate in the Pipelines. Petroleum & Petrochemical Engineering Journal, 5(1), 1–14. https://doi.org/10.23880/ppej-16000259 DOI: https://doi.org/10.23880/ppej-16000259
Schlumberger. (2022). Release notes. Schlumberger.
Seo, Y., Kim, B., Lee, J., & Lee, Y. (2021). Development of ai-based diagnostic model for the prediction of hydrate in gas pipeline. Energies, 14(8), 1–22. https://doi.org/10.3390/en14082313 DOI: https://doi.org/10.3390/en14082313
Srivastava, V. (2018). Quantitative Risk Modeling of Hydrate Bedding Using Mechanistic,
Statistical, and Artifical Neural Network Frameworks.
Swamynathan, M. (2017). Mastering Machine Learning with Python in Six Steps. Bangalore, Karnataka, India: Freepik. DOI: https://doi.org/10.1007/978-1-4842-2866-1
Wang, J., Wang, Q., Meng, Y., Yao, H., Zhang, L., Jiang, B., Liu, Z., Zhao, J., & Song, Y. (2022). Flow characteristic and blockage mechanism with hydrate formation in multiphase transmission pipelines: In-situ observation and machine learning predictions. Fuel, 330(August), 125669. https://doi.org/10.1016/j.fuel.2022.125669 DOI: https://doi.org/10.1016/j.fuel.2022.125669
Yu, Z., & Tian, H. (2022). Application of Machine Learning in Predicting Formation Condition of Multi-Gas Hydrate. Energies, 15(13). https://doi.org/10.3390/en15134719 DOI: https://doi.org/10.3390/en15134719
Zarei Mostafa; Mohammadi, Amir H.; Moosavi, Ali, M. M. H. (2021). Model development for estimating calcium sulfate dihydrate, hemihydrate, and anhydrite solubilities in multicomponent acid and salt containing aqueous solutions over wide temperature ranges. Journal of Molecular Liquids, 328(NA), 115473-NA. https://doi.org/10.1016/j.molliq.2021.115473 DOI: https://doi.org/10.1016/j.molliq.2021.115473
Zerpa, L.E., E. S. (2012). Hydrate Risk Assessment and RestartProcedure Optimization of an Offshore Well. Offshore Technology Conference Brasil (pp. 49-56). Rio de Janeiro: Society of Petroleum Engineers. DOI: https://doi.org/10.2118/160578-PA
Zhong Qi-Long; Wang, Yu; He, Yufa; Li, Zi-Han, H.-Q. Y. (2019). A Graphical Alternating Conditional Expectation to Predict Hydrate Phase Equilibrium Conditions for Sweet and Sour Natural Gases. Mathematical Problems in Engineering, 2019(NA), 1–15. https://doi.org/10.1155/2019/2383961 DOI: https://doi.org/10.1155/2019/2383961
Copyright (c) 2024 FUDMA JOURNAL OF SCIENCES
This work is licensed under a Creative Commons Attribution 4.0 International License.
FUDMA Journal of Sciences
