Application of statistical learning theory for thermodynamic modeling of natural gas hydrates

Abstract

The gas hydrate formation in pipelines of industries and chemical plants can cause various operational damages and can increase economic risks. Hence, the knowledge of hydrate formation conditions has become a critical research study to overcome the problems arising from the formation of hydrates. In this study, we applied an algorithm to develop an LSSVM model to predict the formation temperature of natural gas hydrate for a comprehensive range of data points. Total 188 experimental data points were applied from the literature for the development of the LSSVM model. The input parameter was finalized based on the structure of hydrates by each gas species. The results obtained by the LSSVM model have good accuracy as compared with empirical correlations available in the literature. This model gave the squared correlation coefficient (R²), and root mean square error of 0.9901 and 0.59974, respectively. The composition of gases may affect the phase equilibrium condition of gas hydrates. The applied algorithm revealed that the developed LSSVM model could become a good alternative for calculating the formation temperature of hydrate for the range of all data sets. The results showed that the proposed LSSVM model could be applicable for the prediction of hydrate formation temperature for all data points.

Keywords

Gas hydrate / LSSVM / Correlation / Hydrate formation temperature

Acknowledgements

The authors would like to acknowledge research grants from Gas Hydrate Research and Technology Centre (GHRTC), Panvel, Mumbai, India and Ministry of Human Resource Development (MHRD), India.

References

[1] J. Javanmardi, B. Partoon, F. Sabzi, Prediction of hydrate formation conditions based on the vdWP-type models at high pressures, Can. J. Chem. Eng. 89 (2011) 254-263.

[2] A. Kumari, S.H. Khan, A.K. Misra, C.B. Majumder, A. Arora, Hydrates of binary guest mixtures: fugacity model development and experimental validation, J. Non-Equilibrium Thermodyn. 45 (2020) 39-58, https://doi.org/10.1515/jnet-2019-0062.

[3] A. Arora Swaranjit Singh, C. Chandrajit, Natural Gas Hydrate (Clathrates) as an Untapped Resource of Natural Gas, 2015, https://doi.org/10.4172/2157-7463.1000234.

[4] M. Mesbah, E. Soroush, M. Rezakazemi,Modeling Dissociation Pressure of Semi-clathrate Hydrate Systems Containing CO 2, CH 4, N 2, and H 2 S in the Presence of Tetra-N-Butyl Ammonium Bromide, 2018.

[5] E.D. Sloan, C.A. Koh, clathrate-hydrates-of-natural-gases-third-edition-chemical-industries-series. pdf, 1998.

[6] E.G. Hammerschmidt, formation of gas hydrates in natural gas transmission lines, Ind. Eng. Chem. 26 (1934) 851-855, https://doi.org/10.1021/ie50296a010.

[7] D.L. Katz, Prediction of conditions for hydrate formation in natural gases, Trans. AIME. 160 (1945) 140-149.

[8] W.I. Wilcox, D.B. Carson, D.L. Katz, Natural gas hydrates, Ind. Eng. Chem. 33 (1941) 662-665.

[9] I.F. Makogon, Hydrates of Natural Gas, PennWell Books Tulsa, Oklahoma, 1981.

[10] B.K. Berge, Hydrate predictions on a microcomputer, in: Pet. Ind. Appl. Microcomput., Society of Petroleum Engineers, 1986.

[11] R. Kobayashi, K.Y. Song, E.D. Sloan, Phase behavior of water/hydrocarbon systems, Pet. Eng. Handb. 25 (1987) e13.

[12] M. Motiee, Estimate possibility of hydrates, Hydrocarb. Process. 70 (1991) 98-99.

[13] M. Safamirzaei, Predict Gas Hydrate Formation Temperature with a Simple Correlation, 2015, pp. 1-7.

[14] B.F. Towler, S. Mokhatab, Quickly estimate hydrate formation conditions in natural gases, Hydrocarb. Process. 84 (2005) 61-62.

[15] M. ali Ghayyem, M. Izadmehr, R. Tavakoli, Developing a simple and accurate correlation for initial estimation of hydrate formation temperature of sweet natural gases using an eclectic approach, J. Nat. Gas Sci. Eng. 21 (2014) 184-192, https://doi.org/10.1016/j.jngse.2014.08.003.

[16] S.O. Salufu, P. Nwakwo, New empirical correlation for predicting hydrate formation conditions, in: Soc. Pet. Eng. -37th Niger. Annu. Int. Conf. Exhib. NAICE 2013 -to Grow Africa's Oil Gas Prod. Required Policy, Funding, Technol., Tech. Capab., vol. 2, 2013, pp. 834-850, https://doi.org/10.2118/167571-ms.

[17] M. Mesbah, E. Soroush, M. Rezakazemi, Development of a least squares support vector machine model for prediction of natural gas hydrate formation temperature, Chin. J. Chem. Eng. 25 (2017) 1238-1248, https://doi.org/10.1016/j.cjche.2016.09.007.

[18] A. Baghban, S. Namvarrechi, L.T.K. Phung, M. Lee, A. Bahadori, T. Kashiwao, Phase equilibrium modelling of natural gas hydrate formation conditions using LSSVM approach, Petrol. Sci. Technol. 34 (2016) 1431-1438, https://doi.org/10.1080/10916466.2016.1202966.

[19] J.H. Vander Waals, J.C. Platteeuw, Clathrate solutions, Adv. Mater. Res. Chem. Phys. II (1958) 1-57.

[20] W.R. Parrish, J.M. Prausnitz, Dissociation pressures of gas hydrates formed by gas mixtures, Ind. Eng. Chem. Process Des. Dev. 11 (1972) 26-35, https://doi.org/10.1021/i260041a006.

[21] H.J. Ng, D.B. Robinson, The measurement and prediction of hydrate formation in liquid hydrocarbon-water systems, Ind. Eng. Chem. Fundam. 15 (1976) 293-298, https://doi.org/10.1021/i160060a012.

[22] V.T. John, G.D. Holder, Hydrates of methane + n-butane below the ice point, J. Chem. Eng. Data 27 (1982) 18-21.

[23] G.-J. Chen, T.-M. Guo, Thermodynamic modeling of hydrate formation based on new concepts, Fluid Phase Equil. 122 (1996) 43-65.

[24] G. D.H.V.T. John, K.D. Papadopoulos, V.T. John, K.D. Papadopoulos, G.D. Holder, A generalized model for predicting equilibrium conditions for gas hydrates, AIChE J. 31 (1985) 252-259, https://doi.org/10.1002/aic.690310212.

[25] H. Yarveicy, M.M. Ghiasi, Modeling of gas hydrate phase equilibria: extremely randomized trees and LSSVM approaches, J. Mol. Liq. 243 (2017) 533-541, https://doi.org/10.1016/j.molliq.2017.08.053.

[26] A.H. Mohammadi, A. Eslamimanesh, D. Richon, F. Gharagheizi, M. Yazdizadeh, J. Javanmardi, H. Hashemi, M. Zarifi, S. Babaee, Gas hydrate phase equilibrium in porous media: mathematical modeling and correlation, Ind. Eng. Chem. Res. 51 (2012) 1062-1072, https://doi.org/10.1021/ie201904r.

[27] M. Curilem, G. Acu-na, F. Cubillos, E. Vyhmeister, Neural networks and support vector machine models applied to energy consumption optimization in semiautogeneous grinding, Chem. Eng. Trans. 25 (2011) 761-766.

[28] J.A.K. Suykens, J. Vandewalle, Least squares support vector machine classifiers, Neural Process. Lett. 9 (1999) 293-300.

[29] C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn. 20 (1995) 273-297.

[30] E. Soroush, M. Mesbah, A. Shokrollahi, A. Bahadori, M.H. Ghazanfari, Prediction of methane uptake on different adsorbents in adsorbed natural gas technology using a rigorous model, Energy & Fuels 28 (2014) 6299-6314.

[31] H. Wang, D. Hu, Comparison of SVM and LS-SVM for regression, in: 2005 Int. Conf. Neural Networks Brain, IEEE, 2005, pp. 279-283.

[32] J.A.K. Suykens, J. De Brabanter, L. Lukas, J. Vandewalle, Weighted least squares support vector machines: robustness and sparse approximation, Neurocomputing 48 (2002) 85-105.

[33] K. Pelckmans, J.A.K. Suykens, T. Van Gestel, J. De Brabanter, L. Lukas, B. Hamers, B. De Moor, J. Vandewalle, Ls-SVMlab, A Matlab/c Toolbox for Least Squares Support Vector Machines, Tutorial, KULeuven-ESAT., Leuven, Belgium, 2002, p. 142.

[34] D.L.V. Katz, Handbook of Natural Gas Engineering, McGraw-Hill, 1959.