A soft computing approach for prediction of P-ρ-T behavior of natural gas using adaptive neuro-fuzzy inference system

Abstract

Density is an important property of natural gas required for the design of gas processing and reservoir simulation. Due to expensive measurement of density, industry tends to predict gas density through an EOS. However, all EOS are associated with uncertainties, especially at high-pressure conditions. Also, using sophisticated EOS in commercial software renders simulation highly time-consuming. This work aims to evaluate performance of adaptive neuro-fuzzy inference system (ANFIS) as a widely-accepted intelligent model for prediction of P-ρ-T behavior of natural gas. Using experimental data reported in the literature, our inference system was trained with 95 data of natural gas densities in the temperature range of (250-450)K and pressures up to 150 MPa. Additionally, prediction by ANFIS was compared with those of AGA8 and GERG04 which both are leading industrial EOS for calculation of natural gas density. It was observed that ANFIS predicts natural gas density with AARD% of 1.704; and is able to estimate gas density as accurate as sophisticated EOS. The proposed model is applicable for predicting gas density in the range of (250-450) K, (10-150) MPa and also for sweet gases, i.e., containing a low concentration of N₂ and CO₂.

Keywords

Natural gas / Density / Fuzzy inference system / Intelligent modelling / Equation of state

References

[1] A.M. Elsharkawy, Predicting volumetric and transport properties of sour gases and gas condensates using EOSs, corresponding state models, and empirical correlations, Pet. Sci. Technol. 21 (2003) 1759-1787.

[2] Y. Guo, B. Sun, K. Zhao, H. Zhang, A prediction method of natural gas hydrate formation in deepwater gas well and its application, Petroleum 2 (3) (2016) 296-300.

[3] X. Yang, W. Zhu, A theoretical model for the density and temperature dependent viscosity of hydrocarbon gases, Pet. Sci. Technol. 34 (2016) 765-770.

[4] J. Shanshool, E.T. Hashim, A.A. Hassaballah, Prediction of liquefied natural gas density using PengeRobinson equation of state, Pet. Sci. Technol. 22 (2004) 415-422.

[5] A. AlQuraishi, E. Shokir, Viscosity and density correlations for hydrocarbon gases and pure and impure gas mixtures, Pet. Sci. Technol. 27 (2009) 1674-1689.

[6] S. Masoumi, A. Helalizadeh, M. Bahrami, The performance of various injecting gases into fractured retrograde gas reservoirs for revaporization of liquid drop-out, Pet. Sci. Technol. 29 (2011) 2536-2544.

[7] M. Farzaneh-Gord, A. Khamforoush, S. Hashemi, H. Pourkhadem, Computing thermal properties of natural gas by utilizing AGA8 equation of state, Int. J. Chem. Eng. Appl. 1 (2010) 20.

[8] A.H.S. Dehaghani, M.H. Badizad, Thermodynamic modeling of gas hydrate formation in presence of thermodynamic inhibitors with a new association equation of state, Fluid Phase Equilibria 427 (2016) 328-339.

[9] O. Kunz, W. Wagner, The GERG-2008 wide-range equation of state for natural gases and other mixtures: an expansion of GERG-2004, J. Chem. Eng. data 57 (2012) 3032-3091.

[10] A.H. Saeedi Dehaghani, M.H. Badizad, Experimental study of Iranian heavy crude oil viscosity reduction by diluting with heptane, methanol, toluene, gas condensate and naphtha, Petroleum (2016), http://dx.doi.org/10.1016/j.petlm.2016.08.012 (accepted).

[11] M.H. Badizad, A.R. Zanganeh, A.H.S.D. Dehaghani, Simulation and assessment of surfactant injection in fractured reservoirs: a sensitivity analysis of some uncertain parameters, Iran. J. Oil Gas Sci. Technol. 5 (2016) 13-26.

[12] M.M. Shadman, A.H.S. Dehaghani, M.H. Badizad, How much do you know about the methods for determining onset of asphaltene precipitation? Petroleum (accepted) (2016) http://dx.doi.org/10.1016/j.petlm.2016.08.011.

[13] A. Kamari, A.H. Mohammadi, M. Lee, T. Mahmood, A. Bahadori, Decline curve based models for predicting natural gas well performance, Petroleum (2016), http://dx.doi.org/10.1016/j.petlm.2016.06.006.

[14] R. Arabjamaloei, S. Shadizadeh, Modeling and optimizing rate of penetration using intelligent systems in an iranian southern oil field (Ahwaz Oil Field), Pet. Sci. Technol. 29 (2011) 1637-1648.

[15] A. Tatar, S. Naseri, M. Bahadori, J. Rozyn, M. Lee, T. Kashiwao, A. Bahadori, Evaluation of different artificial intelligent models to predict reservoir formation water density, Pet. Sci. Technol. 33 (2015) 1749-1756.

[16] L.A. Zadeh, Fuzzy sets Inf. Control 8 (1965) 338-353.

[17] L.A. Zadeh, Fuzzy logic=computing with words, IEEE Trans. Fuzzy Syst. 4 (1996) 103-111.

[18] L.A. Zadeh, Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic, Fuzzy Sets Syst. 90 (1997) 111-127.

[19] A. Hamam, N.D. Georganas,A comparison of Mamdani and Sugeno fuzzy inference systems for evaluating the quality of experience of Hapto-Audio-Visual applications, in: Haptic Audio Visual Environments and Games, 2008. HAVE 2008. IEEE International Workshop on, IEEE, 2008.

[20] J.-S.R. Jang, C.-T. Sun, E. Mizutani, Neuro-fuzzy and Soft Computing; a Computational Approach to Learning and Machine Intelligence, 1997.

[21] M. Sugeno, G. Kang, Structure identification of fuzzy model, Fuzzy Sets Syst. 28 (1988) 15-33.

[22] 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.

[23] L.-X. Wang,Fuzzy systems are universal approximators, in: Fuzzy Systems, 1992., IEEE International Conference on, IEEE, 1992.

[24] M. Atilhan, S. Aparicio, S. Ejaz, D. Cristancho, I. Mantilla, K. Hall, pereT behavior of three lean synthetic natural gas mixtures using a magnetic suspension densimeter and isochoric apparatus from (250 to 450) K with pressures up to 150 MPa: Part II, J. Chem. Eng. Data 56 (2011) 3766-3774.

[25] M. Atilhan, S. Aparicio, S. Ejaz, D. Cristancho, K. Hall, P r T behavior of a lean synthetic natural gas mixture using magnetic suspension densimeters and an isochoric apparatus: Part I, J. Chem. Eng. Data 56 (2011) 212-221.

[26] G.A. Barreto, A.F. Araujo, Identification and control of dynamical systems using the self-organizing map, IEEE Trans. Neural Netw. 15 (2004) 1244-1259.

[27] X.-Z. Wang, C.-R. Dong, Improving generalization of fuzzy ifethen rules by maximizing fuzzy entropy, IEEE Trans. fuzzy Syst. 17 (2009) 556-567.

[28] M. Davanipoor, M. Zekri, F. Sheikholeslam, Fuzzy wavelet neural network with an accelerated hybrid learning algorithm, IEEE Trans. Fuzzy Syst. 20 (2012) 463-470.

[29] S. Esfahani, S. Baselizadeh, A. Hemmati-Sarapardeh, On determination of natural gas density: least square support vector machine modeling approach, J. Nat. Gas Sci. Eng. 22 (2015) 348-358.

[30] A. Fayazi, A.M. Arabloo, A.H. Mohammadi, Efficient estimation of natural gas compressibility factor using a rigorous method, J. Nat. Gas Sci. Eng. 16 (2014) 8-17.

[31] H. Hayer, R. Haghbakhsh, S. Keshtkari, S. Raeissi, Support vector machine and CPA EoS for the prediction of high-pressure liquid densities of normal alkanols, J. Taiwan Inst. Chem. Eng. 45 (2014) 2888-2898.

[32] R. Haghbakhsh, H. Adib, P. Keshavarz, M. Koolivand, S. Keshtkari, Development of an artificial neural network model for the prediction of hydrocarbon density at high-pressure, high-temperature conditions, Thermochim. Acta 551 (2013) 124-130.

[33] M. Moosavi, N. Soltani, Prediction of hydrocarbon densities using an artificial neural networkegroup contribution method up to high temperatures and pressures, Thermochim. Acta 556 (2013) 89-96.

[34] M. Atilhan, S. Aparicio, F. Karadas, K.R. Hall, R. Alcalde, Isothermal PrT measurements on Qatar's North Field type synthetic natural gas mixtures using a vibrating-tube densimeter, J. Chem. Thermodyn. 53 (2012) 1-8.