Predicting wax deposition using robust machine learning techniques

Abstract

Accurate prediction of wax deposition is of vital interest in digitalized systems to avoid many issues that interrupt the flow assurance during production of hydrocarbon fluids. The present investigation aims at establishing rigorous intelligent schemes for predicting wax deposition under extensive production conditions. To do so, multilayer perceptron (MLP) optimized with Levenberg-Marquardt algorithm (MLP-LMA) and Bayesian Regularization algorithm (MLP-BR) were taught using 88 experimental measurements. These latter were described by some independent variables, namely temperature (in K), specific gravity, and compositions of C1-C3, C4-C7, C8-C15, C16-C22, C23-C29 and C30+. The obtained results showed that MLP-LMA achieved the best performance with an overall root mean square error of 0.2198 and a coefficient of determination (R²) of 0.9971. The performance comparison revealed that MLP-LMA outperforms the prior approaches in the literature.

Keywords

Wax deposition / Multilayer perceptron / Levenberg-marquardt algorithm / Flow assurance

References

[1] C. Benamara, M. Nait Amar, K. Gharbi, B. Hamada, Modeling wax disappearance temperature using advanced intelligent frameworks, Energy Fuels 33 (2019) 10959-10968, https://doi.org/10.1021/acs.energyfuels.9b03296.

[2] A.M. Elsharkawy, T.A. Al-Sahhaf, M.A. Fahim, Wax deposition from Middle East crudes, Fuel 79 (2000) 1047-1055, https://doi.org/10.1016/S0016-2361(99)00235-5.

[3] C. Benamara, K. Gharbi, M. Nait Amar, B. Hamada, Prediction of wax appearance temperature using artificial intelligent techniques, Arabian J. Sci. Eng. 45 (2020) 1319-1330, https://doi.org/10.1007/s13369-019-04290-y.

[4] H.Y. Ji, B. Tohidi, A. Danesh, A.C. Todd, Wax phase equilibria: developing a thermodynamic model using a systematic approach, Fluid Phase Equil. 216 (2004) 201-217, https://doi.org/10.1016/j.fluid.2003.05.011.

[5] A. Kamari, A. Khaksar-Manshad, F. Gharagheizi, A.H. Mohammadi, S. Ashoori, Robust model for the determination of wax deposition in oil systems, Ind. Eng. Chem. Res. 52 (2013) 15664-15672.

[6] M.J. Jalalnezhad, V. Kamali, Development of an intelligent model for wax deposition in oil pipeline, J. Pet. Explor. Prod. Technol. 6 (2016) 129-133, https://doi.org/10.1007/s13202-015-0160-3.

[7] E. Bell, Y. Lu, N. Daraboina, C. Sarica, Experimental Investigation of active heating in removal of wax deposits, J. Petrol. Sci. Eng. 200 (2021) 108346.

[8] Z. Wang, J. Li, H.-Q. Zhang, Y. Liu, W. Li, Treatment on oil/water gel deposition behavior in non-heating gathering and transporting process with polymer flooding wells, Environ. Earth Sci. 76 (2017) 326.

[9] M.A. Theyab, Wax deposition process: mechanisms, affecting factors and mitigation methods, Open Access J. Sci. 2 (2018), https://doi.org/10.15406/oajs.2018.02.00054.

[10] M. del C. Garcia, L. Carbognani, Asphaltene-paraffin structural interactions. Effect on crude oil stability, Energy Fuels 15 (2001) 1021-1027.

[11] D. Neto, B. Neto, Determination of wax appearance temperature (wat) in paraffin/solvent systems by photoelectric signal and viscosimetry a, Brazilian J. Pet. Gas. 3 (4) (2009).

[12] B. Jiang, L. Qiu, X. Li, S. Yang, K. Li, H. Chen, Measurement of the wax appearance temperature of waxy oil under the reservoir condition with ultrasonic method, Petrol. Explor. Dev. 41 (2014) 509-512, https://doi.org/10.1016/S1876-3804(14)60059-8.

[13] M. Mansourpoor, R. Azin, S. Osfouri, A.A. Izadpanah, Experimental measurement and modeling study for estimation of wax disappearance temperature, J. Dispersion Sci. Technol. 40 (2019) 161-170, https://doi.org/10.1080/01932691.2018.1461635.

[14] J. Chen, J. Zhang, H. Li, Determining the wax content of crude oils by using differential scanning calorimetry, Thermochim. Acta 410 (2004) 23-26, https://doi.org/10.1016/S0040-6031(03)00367-8.

[15] Z. Wang, Y. Bai, H. Zhang, Y. Liu, Investigation on gelation nucleation kinetics of waxy crude oil emulsions by their thermal behavior, J. Petrol. Sci. Eng. 181 (2019) 106230.

[16] H. Saxena, A. Majhi, B. Behera, Prediction of wax content in crude oil and petroleum fraction by proton NMR, Petrol. Sci. Technol. 37 (2019) 226-233, https://doi.org/10.1080/10916466.2018.1536713.

[17] M.M. El-Dalatony, B.H. Jeon, E.S. Salama, M. Eraky, W.B. Kim, J. Wang, T. Ahn, Occurrence and characterization of paraffin wax formed in developing wells and pipelines, Energies 12 (2019), https://doi.org/10.3390/en12060967.

[18] F. Alnaimat, M. Ziauddin, Wax deposition and prediction in petroleum pipelines, J. Petrol. Sci. Eng. 184 (2020), https://doi.org/10.1016/j.petrol.2019.106385.

[19] J.H. Hansen, A. Fredenslund, K.S. Pedersen, H.P. Rønningsen, A thermodynamic model for predicting wax formation in crude oils, AIChE J. 34 (1988) 1937-1942, https://doi.org/10.1002/aic.690341202.

[20] C. Lira-Galeana, A. Firoozabadi, J.M. Prausnitz, Thermodynamics of wax precipitation in petroleum mixtures, AIChE J. 42 (1996) 239-248, https://doi.org/10.1002/aic.690420120.

[21] J.A.P. Coutinho, Predictive UNIQUAC: a new model for the description of multiphase solid-liquid equilibria in complex hydrocarbon mixtures, Ind. Eng. Chem. Res. 37 (1998) 4870-4875, https://doi.org/10.1021/ie980340h.

[22] A. Kamari, A. Khaksar-Manshad, F. Gharagheizi, A.H. Mohammadi, S. Ashoori, Robust model for the determination of wax deposition in oil systems, Ind. Eng. Chem. Res. (2013) 15664-15672, https://doi.org/10.1021/ie402462q.

[23] M. Nait Amar, Prediction of hydrate formation temperature using gene expression programming, J. Nat. Gas Sci. Eng. 89 (2021) 103879, https://doi.org/10.1016/j.jngse.2021.103879.

[24] M. Nait Amar, Modeling solubility of sulfur in pure hydrogen sulfide and sour gas mixtures using rigorous machine learning methods, Int. J. Hydrogen Energy 45 (2020) 33274-33287, https://doi.org/10.1016/j.ijhydene.2020.09.145.

[25] M. Nait Amar, M.A. Ghriga, H. Ouaer, On the evaluation of solubility of hydrogen sulfide in ionic liquids using advanced committee machine intelligent systems, J. Taiwan Inst. Chem. Eng. 118 (2021) 159-168, https://doi.org/10.1016/j.jtice.2021.01.007.

[26] A. Hemmati-Sarapardeh, R. Alipour-Yeganeh-Marand, A. Naseri, A. Safiabadi, F. Gharagheizi, P. Ilani-Kashkouli, A.H. Mohammadi, Asphaltene precipitation due to natural depletion of reservoir: determination using a SARA fraction based intelligent model, Fluid Phase Equil. 354 (2013) 177-184.

[27] A. Hemmati-Sarapardeh, B. Dabir, M. Ahmadi, A.H. Mohammadi, M.M. Husein, Modelling asphaltene precipitation titration data: a committee of machines and a group method of data handling, Can. J. Chem. Eng. 97 (2019) 431-441.

[28] X.Q. Bian, J.H. Huang, Y. Wang, Y.B. Liu, D.T. Kaushika Kasthuriarachchi, L.J. Huang, Prediction of wax disappearance temperature by intelligent models, Energy Fuels 33 (2019) 2934-2949, https://doi.org/10.1021/acs.energyfuels.8b04286.

[29] E.O. Obanijesu, E.O. Omidiora, Artificial neural network's prediction of wax deposition potential of Nigerian crude oil for pipeline safety, Petrol. Sci. Technol. 26 (2008) 1977-1991, https://doi.org/10.1080/10916460701399485.

[30] Z.Q. Chu, J. Sasanipour, M. Saeedi, A. Baghban, H. Mansoori, Modeling of wax deposition produced in the pipelines using PSO-ANFIS approach, Petrol. Sci. Technol. 35 (2017) 1974-1981, https://doi.org/10.1080/10916466.2017.1374405.

[31] A. Gholami, H.R. Ansari, S. Ahmadi, Combining of intelligent models through committee machine for estimation of wax deposition, J. Chin. Chem. Soc. 65 (2018) 925-931, https://doi.org/10.1002/jccs.201700329.

[32] Y. Xie, Y. Xing, A prediction method for the wax deposition rate based on a radial basis function neural network, Petroleum 3 (2017) 237-241, https://doi.org/10.1016/j.petlm.2016.08.003.

[33] A. Hemmati-Sarapardeh, A. Varamesh, M.M. Husein, K. Karan, On the evaluation of the viscosity of nanofluid systems: modeling and data assessment, Renew. Sustain. Energy Rev. 81 (2018) 313-329.

[34] M. Nait Amar, N. Zeraibi, K. Redouane, Bottom hole pressure estimation using hybridization neural networks and grey wolves optimization, Petroleum 4 (2018) 419-429, https://doi.org/10.1016/j.petlm.2018.03.013.

[35] S. Haykin, Neural Networks and Learning Machines, third ed., Pearson, Upper Saddle River, NJ, USA, 2001 https://doi.org/10.1002/1521-3773(20010316)40:6<9823::AID-ANIE9823>3.3.CO;2-C.

[36] A. Hemmati-Sarapardeh, M. Nait Amar, M.R. Soltanian, Z. Dai, X. Zhang, Modeling CO₂ solubility in water at high pressure and temperature conditions, Energy Fuels 34 (2020) 4761-4776, https://doi.org/10.1021/acs.energyfuels.0c00114.

[37] W. Batsberg Pedersen, A. Baltzer Hansen, E. Larsen, A.B. Nielsen, H.P. Roenningsen, Wax precipitation from North Sea crude oils. 2. Solid-phase content as function of temperature determined by pulsed NMR, Energy Fuels 5 (1991) 908-913.

[38] K. Schou Pedersen, P. Skovborg, H.P. Roenningsen, Wax precipitation from North Sea crude oils. 4. Thermodynamic modeling, Energy Fuels 5 (1991) 924-932.

[39] A. Baltzer Hansen, E. Larsen, W. Batsberg Pedersen, A.B. Nielsen, H.P. Roenningsen, Wax precipitation from North Sea crude oils. 3. Precipitation and dissolution of wax studied by differential scanning calorimetry, Energy Fuels 5 (1991) 914-923.

[40] M. Lashkarbolooki, A. Seyfaee, F. Esmaeilzadeh, D. Mowla, Experimental investigation of wax deposition in Kermanshah crude oil through a monitored flow loop apparatus, Energy Fuels 24 (2010) 1234-1241.

[41] W. Wang, Q. Huang, C. Wang, S. Li, W. Qu, J. Zhao, M. He, Effect of operating conditions on wax deposition in a laboratory flow loop characterized with DSC technique, J. Therm. Anal. Calorim. 119 (2015) 471-485.

[42] S. Ravichandran, Mechanistic Study of Wax Deposition-Effect of Super Saturation, The University of Tulsa, 2018.

[43] A. Janamatti, Y. Lu, S. Ravichandran, C. Sarica, N. Daraboina, Influence of operating temperatures on long-duration wax deposition in flow lines, J. Petrol. Sci. Eng. 183 (2019) 106373.

[44] A. Dubey, Investigation of the Effects of Operating Conditions and Inhibitors on Paraffin Deposition, The University of Tulsa, 2016.