Artificial Neural Network to Determine Dynamic Effect in Capillary Pressure Relationship for Two-Phase Flow in Porous Media with Micro-Heterogeneities
详细信息 查看全文
- 作者：Diganta B. Das ; Thanit Thirakulchaya ; Lipika Deka…
- 关键词：Artificial neural network (ANN) ; Two phase flow ; Porous media ; Dynamic coefficient ; Dynamic capillary pressure ; Porous medium heterogeneity ; Micro ; heterogeneity
- 刊名：Environmental Processes
- 出版年：2015
- 出版时间：March 2015
- 年：2015
- 卷：2
- 期：1
- 页码：1-18
- 全文大小：960KB
- 参考文献：Abidoye LK, Das DB (2014) Scale dependent dynamic capillary pressure effect for two-phase flow in porous media. Adv Water Resour. doi:10.-016/?j.?advwatres.-014.-9.-09
Akratos CS, Papaspyros JNE, Tsihrintzis VA (2008) An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands. Chem Eng J 143(1-):96-10CrossRef
Ataie-Ashtiani B, Hassanizadeh SM, Celia MA (2002) Effects of heterogeneities on capillary pressure–saturation–relative permeability relationships. J Contam Hydrol 56(3):175-92CrossRef
Ataie-Ashtiani B, Hassanizadeh SM, Oung O, Weststrate FA, Bezuijen A (2003) Numerical modelling of two-phase flow in a geocentrifuge. Environ Model Softw 18(3):231-41CrossRef
Baldwin JL. (1991) Proceedings of the SPE annual technical conference and exhibition, 273-286
Bear J (1972) Dynamics of fluids in porous media. Dover, New York
Boadu FK (2001) Predicting oil saturation from velocities using petrophysical models and artificial neural networks. J Pet Sci Eng 30:143-54CrossRef
Bottero S, Hassanizadeh SM, Kleingeld PJ, Heimovaara TJ, (2011) Non-equilibrium capillarity effects in two-phase flow through porous media at different scales. Water Resources Research 47: W10505, DOI: 10.-029/-011WR010887
Brooks RH, Corey AT (1964) Hydraulic properties of porous media, Hydrol. Pap. 3, Colo. State Univ., Fort Collins
Corey A (1994) Mechanics of immiscible fluids in porous media. Water Resources Publications, Highlands Ranch, Colorado
Dahle HK, Celia MA, Hassanizadeh SM (2005) Bundle-of-tubes model for calculating dynamic effects in the capillary-pressure–saturation relationship. Transp Porous Media 58(1):5-2CrossRef
Das, DB, Hassanizadeh, SM, Rotter, BE, Ataie Ashtiani, B (2004) A Numerical Study of Micro-Heterogeneity Effects on Upscaled Properties of Two-Phase Flow in Porous Media. Transport in Porous Media 56: 329-50
Das DB, Mirzaei M (2012) Dynamic effects in capillary pressure relationships for two-phase flow in porous media: experiments and numerical analyses. AIChE J 58(12):3891-903CrossRef
Das DB, Mirzaei M (2013) Experimental measurement of dynamic effect in capillary pressure relationship for two-phase flow in weakly layered porous media. AIChE J 59(5):1723-734CrossRef
Das, DB, Mirzaei, M, Widdows, N (2006) Non-uniqueness in capillary pressure-saturation-relative permeability relationships for two-phase flow in porous media. Interplay between distribution and intensity of micro-heterogeneity. Chemical Engineering Science 61: 6786-803
Das DB, Gauldie R, Mirzaei M (2007) Dynamic effects in capillary pressure relationships for two-phase flow in porous media: implications of fluid properties. AIChE J 53(10):2505-520CrossRef
Das DB, Gill GS, Abidoye LK, Khudaida K (2014) A numerical study of dynamic capillary pressure effect for supercritical carbon dioxide-water flow in porous domain. AIChE J. doi:10.-002/?aic.-4577
Deka L, Quddus M (2014) Network-level accident-mapping: distance based pattern matching using artificial neural network. Accid Anal Prev 65:105-13CrossRef
Demuth H, Beale M, Hogan M (2008) Neural network toolbox 6: user’s guide, Math Works, Inc., Version 6.0.1, 1-24
Elkamel A, Karkoub K, Gharbi R (1996) A neural network prediction model of fluid displacements in porous media. Comput Chem Eng 20(1):515-20CrossRef
Gharbi R, Karkoub M, Elkamel A (1995) An artificial neural network for the prediction of immiscible flood performance. Energy Fuel 9(5):894-96CrossRef
Graupe D (2007) Principles of artificial neural networks advanced series on circuits and systems, vol 6. World Scientific, United Stated of America
Hanspal N, Das DB (2012) Dynamic effects on capillary pressure-saturation relationships for two-phase porous flow: implications of temperature. AIChE J 58:1951-965CrossRef
Hanspal N, Allison BA, Deka L, Das DB (2013) Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous medial. J Hydroinf 15(2):540-54CrossRef
Hassanizadeh S, Celia M, Dahle C (2002) Dynamic effect in the capillary pressure-saturation relationship and its impact on unsaturated flow. Vadose Zone J 1(1):38-0
Haykin S (1999) Neural networks - a comprehensive foundation, 2nd edn. Englewood Cliffs, NJ
Hou L, Sleep BE, Kibbey TCG (2014) The influence of unavoidable saturation averaging on the experimental measurement of dynamic capillary effects: a numerical simulation study. Adv Water Resour 66:43-1CrossRef
Jain A, Varshney AK, Joshi UC (2001) Short-term water demand forecast modelling at IIT Kanpur using artificial neural networks. Water Resour Manag 15(5):299-21CrossRef
Jensen J (1991) Use of the geometric average for effective permeability estimation. Math Geol 23(6):883-85CrossRef
Juanes R (2009) Nonequilibrium effects in models of three-phase flow in porous media. Adv Water Resour 31:661- - 作者单位：Diganta B. Das (1)
Thanit Thirakulchaya (1)
Lipika Deka (2)
Navraj S. Hanspal (3)
1. Chemical Engineering Department, Loughborough University, Loughborough, LE11 3TU, UK
2. School of Civil and Building Engineering, Loughborough University, Loughborough, LE11 3TU, UK
3. Ansys, Inc., 2645 Zanker Road, San Jose, CA, 95134, USA - 刊物类别：Environmental Science and Engineering; Environmental Management; Waste Management/Waste Technology;
- 刊物主题：Environmental Science and Engineering; Environmental Management; Waste Management/Waste Technology; Water Quality/Water Pollution;
- 出版者：Springer International Publishing
- ISSN：2198-7505
文摘
An artificial neural network (ANN) is presented for computing a parameter of dynamic two-phase flow in porous media with water as wetting phase, namely, dynamic coefficient (τ), by considering micro-heterogeneity in porous media as a key parameter. τ quantifies the dependence of time derivative of water saturation on the capillary pressures and indicates the rates at which a two-phase flow system may reach flow equilibrium. Therefore, τ is of importance in the study of dynamic two-phase flow in porous media. An attempt has been made in this work to reduce computational and experimental effort by developing and applying an ANN which can predict the dynamic coefficient through the “learning-from available data. The data employed for testing and training the ANN have been obtained from computational flow physics-based studies. Six input parameters have been used for the training, performance testing and validation of the ANN which include water saturation, intensity of heterogeneity, average permeability depending on this intensity, fluid density ratio, fluid viscosity ratio and temperature. It is found that a 15 neuron, single hidden layer ANN can characterize the relationship between media heterogeneity and dynamic coefficient and it ensures a reliable prediction of the dynamic coefficient as a function of water saturation. Keywords Artificial neural network (ANN) Two phase flow Porous media Dynamic coefficient Dynamic capillary pressure Porous medium heterogeneity Micro-heterogeneity