Prediction of Interfacial Tension Between CO<sub>2</sub> and Brine With the Wavelet Neural Network Method

JIANG An; LIU Ping-li; LI Nian-yin; ZHANG Yun-fei; DU Xin-wei

doi:10.21656/1000-0887.370339

Volume 38 Issue 10

Turn off MathJax

Article Contents

Article Navigation > Applied Mathematics and Mechanics > 2017 > 38(10): 1136-1145

JIANG An, LIU Ping-li, LI Nian-yin, ZHANG Yun-fei, DU Xin-wei. Prediction of Interfacial Tension Between CO2 and Brine With the Wavelet Neural Network Method[J]. Applied Mathematics and Mechanics, 2017, 38(10): 1136-1145. doi: 10.21656/1000-0887.370339

Citation:

JIANG An, LIU Ping-li, LI Nian-yin, ZHANG Yun-fei, DU Xin-wei. Prediction of Interfacial Tension Between CO₂ and Brine With the Wavelet Neural Network Method[J]. Applied Mathematics and Mechanics, 2017, 38(10): 1136-1145. doi: 10.21656/1000-0887.370339

Citation:

PDF( 1250 KB)

Prediction of Interfacial Tension Between CO₂ and Brine With the Wavelet Neural Network Method

doi: 10.21656/1000-0887.370339

¹CNOOC EnerTech-Drilling & Production Co., Tianjin 300452, P.R.China; ²Southwest Petroleum University, Chengdu 610500, P.R.China; ³WestEast Gas Pipeline Company of CNPC, Changzhou, Jiangshu 213251, P.R.China

Funds: The National Natural Science Foundation of China(General Program)（51574197）

Received Date: 2016-11-07
Rev Recd Date: 2016-12-20
Publish Date: 2017-10-15

Abstract

Abstract

Interfacial tension (IFT) between CO₂ and formation water is one of the most important parameters for CO₂ capture and storage, for it controls the transport properties of both phases in the formation. In order to rapidly and accurately predict the IFT of the CO₂-brine system, 1 677 sets of measured IFT data from previous studies were acquired. A wavelet neural network (WNN) prediction model was proposed in view of 6 parameters including the pressure, the temperature, the CH₄ molality and the N₂ molality in CO₂ gas, the monovalent cation (Na⁺ and K⁺) concentration and the bivalent cation (Ca²⁺ and Mg²⁺) concentration. The simulation results show that a 3-layer (6-16-1) WNN model comes out of 839 data as the training datasets. The mean absolute error (M_MAE), the mean relative error (M_MARE), the root mean squared error(M_MSE) and the determination coefficient (R²) of the WNN model were 1.23 mN/m, 3.30%, 2.30 mN²/m² and 0.988, respectively. The performance of the WNN model was further compared with one newly proposed multivariate fitting model and the BP neural network model. The comparison results suggest that the WNN model is better than the other 2.
- wavelet neural network,
- interfacial tension,
- CO₂-brine system

FullText(HTML)

References(32)

References

[1]	ZHANG Ji-yuan, FENG Qi-hong, WANG Shu-hua, et al. Estimation of CO2-brine interfacial tension using an artificial neural network[J]. The Journal of Supercritical Fluids,2016,107(1): 31-37.
[2]	余迎松. 液气界面张力垂直分量引起的基底弹性变形[J]. 应用数学和力学, 2012,33(9): 1025-1042.(YU Yin-song. Substrate elastic deformation due to vertical component of liquid-vapor interfacial tension[J]. Applied Mathematics and Mechanics,2012,33(9): 1025-1042.(in Chinese))
[3]	Hebach A, Oberhof A, Dahmen N, et al. Interfacial tension at elevated pressures—measurements and correlations in the water+carbon dioxide system[J]. Journal of Chemical & Engineering Data,2002,47(6): 1540-1546.
[4]	Chalbaud C, Robin M, Lombard J-M, et al. Interfacial tension measurements and wettability evaluation for geological CO₂ storage[J]. Advances in Water Resources,2009,32(1): 98-109.
[5]	Aggelopoulos C A, Robin M, Vizika O. Interfacial tension between CO₂ and brine (NaCl+CaCl₂) at elevated pressures and temperatures: the additive effect of different salts[J]. Advances in Water Resources,2011,34(4): 505-511.
[6]	Massoudi R, King Jr A D. Effect of pressure on the surface tension of water. Adsorption of low molecular weight gases on water at 25°[J]. The Journal of Physical Chemistry,1974,78(22): 2262-2266.
[7]	Chun B S, Wilkinson G T. Interfacial tension in high-pressure carbon dioxide mixtures[J]. Industrial & Engineering Chemistry Research,1995,34(12): 4371-4377.
[8]	Wesch A, Dahmen N, Ebert K, et al. Grenzflchenspannungen, tropfengren und kontaktwinkel im zweiphasensystem H₂O/CO₂ bei temperaturen von 298 bis 333 K und drücken bis 30 MPa[J]. Chemie Ingenieur Technik,1997,69(7): 942-946.
[9]	Bennion D B, Bachu S. Correlations for the interfacial tension between supercritical phase CO₂ and equilibrium brines at in situ conditions[C]// SPE Annual Technical Conference and Exhibition.Colorado, USA, 2008: 1-13.
[10]	Georgiadis A, Maitland G, Trusler J P M, et al. Interfacial tension measurements of the (H₂O+CO₂) system at elevated pressures and temperatures[J]. Journal of Chemical & Engineering Data,2010,55(10): 4168-4175.
[11]	LI Xue-song, Boek E, Maitland G C, et al. Interfacial tension of (brines+CO2): (0.864 NaCl+0.136 KCl) at temperatures between (298 and 448) K, pressures between (2 and 50) MPa, and total molalities of (1 to 5) mol·kg^-1[J]. Journal of Chemical & Engineering Data,2012,57(4): 1078-1088.
[12]	LI Zhao-min, WANG Shu-hua, LI Song-yan, et al. Accurate determination of the CO₂-brine interfacial tension using graphical alternating conditional expectation[J]. Energy & Fuels,2013,28(1): 624-635.
[13]	任双双, 杨胜来, 沈飞. BP神经网络预测最小混相压力[J]. 断块油气田, 2010,17(2): 216-218.(REN Shuang-shuang, YANG Sheng-lai, SHEN Fei. Prediction minimum miscibility pressure with BP neural network[J]. Fault-Block Oil & Gas Field,2010,17(2): 216-218.(in Chinese))
[14]	韩晋, 杨岳, 陈峰, 等. 基于非等时距加权灰色模型与神经网络的组合预测算法[J]. 应用数学和力学, 2013,34(4): 408-419.(HAN Jin, YANG Yue, CHEN Feng, et al. Combination forecasting algorithm based on non-equal interval weighted grey model and neural network[J]. Applied Mathematics and Mechanics,2013,34(4): 408-419.(in Chinese))
[15]	盛仲飙, 同晓荣. BP神经网络在曲线拟合中的应用[J]. 科学技术与工程, 2011,11(28): 6998-7000.(SHENG Zhong-biao, TONG Xiao-rong. The application of BP neutral network in curve fitting[J].Science Technology and Engineering,2011,11(28): 6998-7000.(in Chinese))
[16]	黄海萍. 基于BP神经网络的中国电力需求预测[J]. 科学技术与工程, 2007,7(4): 612-616.(HUANG Hai-ping. Combination estimate for electric demand of China[J]. Science Technology and Engineering,2007,7(4): 612-616.(in Chinese))
[17]	曹成涛, 崔凤, 林晓辉. 基于神经网络的交通状态模糊判别方法[J]. 科学技术与工程, 2010,10(21): 5195-5199.(CAO Cheng-tao, CUI Feng, LIN Xiao-hui. Traffic condition fuzzy recognition based on neural network[J]. Science Technology and Engineering,2010,10(21): 5195-5199.(in Chinese))
[18]	REN Quan-yuan, CHEN Guang-jin, YAN Wei, et al. Interfacial tension of (CO₂+CH₄)+water from 298 K to 373 K and pressures up to 30 MPa[J].Journal of Chemical & Engineering Data,2000,45(4): 610-612.
[19]	YAN Wei, ZHAO Guo-ying, CHEN Guang-jin, et al. Interfacial tension of (methane+nitrogen)+water and (carbon dioxide+nitrogen)+water systems[J]. Journal of Chemical &Engineering Data,2001,46(6): 1544-1548.
[20]	Hebach A, Oberhof A, Dahmen N, et al. Interfacial tension at elevated pressures measurements and correlations in the water+carbon dioxide system[J]. Journal of Chemical & Engineering Data,2002,47(6): 1540-1546.
[21]	Chiquet P, Daridon J L, Broseta D, et al. CO₂/water interfacial tensions under pressure and temperature conditions of CO₂ geological storage[J]. Energy Conversion and Management,2007,48(3): 736-744.
[22]	Bachu S, Bennion D B. Interfacial tension between CO₂, freshwater, and brine in the range of pressure from (2 to 27) MPa, temperature from (20 to 125) ℃, and water salinity from (0 to 334 000) mg·L^-1[J]. Journal of Chemical & Engineering Data,2008,54(3): 765-775.
[23]	Bachu S, Bennion D B. Dependence of CO₂-brine interfacial tension on aquifer pressure, temperature and water salinity[J]. Energy Procedia,2009,1(1): 3157-3164.
[24]	Chalbaud C A, Robin M, Egermann P. Interfacial tension data and correlations of brine-CO₂ systems under reservoir conditions[C]// SPE Annual Technical Conference and Exhibition.Texas, USA, 2006: 1-18.
[25]	Aggelopoulos C A, Robin M, Perfetti E, et al. CO₂/CaCl₂ solution interfacial tensions under CO₂ geological storage conditions: influence of cation valence on interfacial tension[J]. Advances in Water Resources,2010,33(6): 691-697.
[26]	Bikkina P K, Shoham O, Uppaluri R. Equilibrated interfacial tension data of the CO₂-water system at high pressures and moderate temperatures[J]. Journal of Chemical & Engineering Data,2011,56(10): 3725-3733.
[27]	LI Xue-song, Boek E S, Maitland G C, et al. Interfacial tension of (brines+CO₂): CaCl₂(aq), MgCl₂(aq), and Na₄SO₂(aq) at temperatures between (343 and 423) K, pressures between (2 and 50) MPa, and molalities of (0.5 to 5) mol·kg^-1[J].Journal of Chemical & Engineering Data,2012,57(5): 1369-1375.
[28]	Kvamme B, Kuznetsova T, Hebach A, et al. Measurements and modelling of interfacial tension for water+carbon dioxide systems at elevated pressures[J]. Computational Materials Science,2007,38(3): 506-513.
[29]	LIU Hui, TIAN Hong-qi, LI Yan-feng, et al. Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions[J].Energy Conversion and Management,2015,92(1): 67-81.
[30]	叶峰. 运用MATLAB软件进行回归分析建模[J]. 成都航空职业技术学院学报, 2007,23(2): 44-47.(YE Feng. Multiple regression modeling by using MATLAB software[J]. Journal of Chengdu Aeronautic Vocational and Technical College,2007,23(2): 44-47.(in Chinese))
[31]	周荣义, 李树清, 牛会永. 小波神经网络在矿井安全管理评价中的应用[J]. 煤炭科学技术, 2006,34(5): 67-70.(ZHOU Rong-yi, LI Shu-qing, NIU Hui-yong. Application of wavelet neural network in mine safety management assessment[J]. Coal Science and Technology,2006,34(5): 67-70.(in Chinese))
[32]	Jung S, Kwon S D. Weighted error functions in artificial neural networks for improved wind energy potential estimation[J]. Applied Energy,2013,111: 778-790.