Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/16412

Title: Artificial Neural Network (ANN) modelling of scale dependent dynamic capillary pressure effects in two-phase flow in porous media
Authors: Abidoye, Luqman K.
Das, Diganta Bhusan
Keywords: Multi-scale
Dynamic capillary pressure effects
Dynamic coefficient
ANN
Two-phase flow
Viscosity ratio
Porous media
Issue Date: 2015
Publisher: © IWA Publishing
Citation: ABIDOYE, L.K. and DAS, D.B., 2015. Artificial Neural Network (ANN) modelling of scale dependent dynamic capillary pressure effects in two-phase flow in porous media. Journal of Hydroinformatics, 17 (3), pp. 446–461.
Abstract: A number of numerical simulations and experimental investigations have reported the impact of specific domain size on the dynamic capillary pressure which is one of the forces that govern two-phase flow in porous media. These investigations are often achieved with time-consuming experiments and/or costly/complex computational methods. In view of this, a computationally efficient and simple alternative platform for the prediction of the domain scale dependence of the dynamic capillary pressure effects, defined in terms of a coefficient named as dynamic coefficient ( ), is developed using artificial neural network (ANN). The input parameters consist of the phase saturation, media permeability, capillary entry pressure, viscosity ratio, density ratio, temperature, pore size distribution index, porosity and domain volume with corresponding output obtained at different domain scales. Good generalization of the model was achieved by acquiring data from independent sources comprising experiments and numerical simulations. Different ANN configurations as well as linear and non-linear multivariate regression models were tested using a number of performance criteria. Findings in this work showed that the ANN structures with two hidden layers perform better than those with single hidden layer. In particular, the ANN configuration with 13 and 15 neurons in the first and second hidden layers, respectively, performed the best. Using this best-performing ANN, effects of increased domain size were predicted for three separate experimental results obtained from literature and our laboratory with different domain scales. Results showed increased magnitude of as the domain size increases for all the independent experimental data considered. This work shows the applicability and techniques of using ANN in the prediction of scale dependence of two-phase flow parameters.
Description: © IWA Publishing [2015]. The definitive peer-reviewed and edited version of this article is published in Journal of Hydroinformatics, 17 (3), pp. 446–461 doi: 10.2166/hydro.2014.079 and is available at www.iwapublishing.com
Version: Accepted for publication
DOI: 10.2166/hydro.2014.079
URI: https://dspace.lboro.ac.uk/2134/16412
Publisher Link: http://dx.doi.org/10.2166/hydro.2014.079
ISSN: 1464-7141
Appears in Collections:Published Articles (Chemical Engineering)

Files associated with this item:

File Description SizeFormat
ANN Paper_Re_Submitted_25_Oct_Cleaned.pdfAccepted version416.53 kBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.