Prediction of pressure gradient for oil-water flow: A comprehensive analysis on the performance of machine learning algorithms

Abstract Pressure gradient (PG) in liquid-liquid flow is one of the key components to design an energy-efficient transportation system for wellbores. This study aims to develop five robust machine learning (ML) algorithms and their fusions for a wide range of flow patterns (FP) regimes. The MLs include Support Vector Machine (SVM), Gaussian Process (GP), Random Forest (RF), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), and fusions of these five MLs. A total of eleven hundred experimental data points for nine FPs (two stratified and seven dispersed patterns) in horizontal wellbores are used to develop the MLs. The MLs' performance is evaluated using the metrics including mean absolute percentage error (MAPE), median absolute percentage error (MdAPE), coefficient of variation of root mean squared error (CV-RMSE), and adjusted coefficient of determination. The evaluation metrics are cross-validated using a repeated train-test split strategy. Seven important predictor variables are identified using a supervised feature selection approach: oil and water velocities, FP, input diameter, oil and water density, and oil viscosity. The results show that the high PG prediction accuracy can be achieved using GP compared to other MLs except for the ML-fusions (p

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  A. S. Olawale,et al.  Experimental investigation on flow patterns and pressure gradient through two pipe diameters in horizontal oil–water flows , 2014 .

[3]  B. Adhikari,et al.  Artificial neural networks: a new tool for prediction of pressure drop of non-Newtonian fluid foods through tubes , 2000 .

[4]  Yahya Al-Wahaibi,et al.  Effect of oil viscosity on the flow structure and pressure gradient in horizontal oil–water flow , 2012 .

[5]  Alessandro E. P. Villa,et al.  Artificial Neural Networks and Machine Learning – ICANN 2016 , 2016, Lecture Notes in Computer Science.

[6]  Suhaib Umer Ilyas,et al.  Machine Learning Methods for Herschel–Bulkley Fluids in Annulus: Pressure Drop Predictions and Algorithm Performance Evaluation , 2020, Applied Sciences.

[7]  Alireza Bahadori,et al.  Application of a radial basis function neural network to estimate pressure gradient in water–oil pipelines , 2016 .

[8]  H. Lilliefors.  On the Kolmogorov-Smirnov Test for Normality with Mean and Variance Unknown , 1967 .

[9]  E. Pereyra,et al.  Pressure gradient correlations analysis for liquid-liquid flow in horizontal pipes , 2018, Journal of Petroleum Science and Engineering.

[10]  Julius U. Akpabio,et al.  Artificial intelligence techniques and their applications in drilling fluid engineering: A review , 2018, Journal of Petroleum Science and Engineering.

[11]  O. J. Dunn.  Multiple Comparisons among Means , 1961 .

[12]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[13]  Cem Sarica,et al.  Characterization of Oil/Water Flows in Horizontal Pipes , 2008 .

[14]  Evgeny Burnaev,et al.  A Predictive Model for Steady-State Multiphase Pipe Flow: Machine Learning on Lab Data , 2019, Journal of Petroleum Science and Engineering.

[15]  G. W. Milligan,et al.  A study of standardization of variables in cluster analysis , 1988 .

[16]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[17]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[18]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[19]  Ahmad Shamsul Izwan Ismail,et al.  Review of oil-water through pipes , 2015 .

[20]  Md Ferdous Wahid,et al.  Prediction of Pressure Drops in Liquid-Liquid Two-Phase Flow Across Circular Channels , 2021, Volume 4: Pipelines, Risers, and Subsea Systems.

[21]  R. Manabe,et al.  Analysis of Oil-Water Flow Tests in Horizontal, Hilly-Terrain, and Vertical Pipes , 2006 .

[22]  Subhabrata Ray,et al.  Pressure Drop in Liquid‐liquid Two Phase Horizontal Flow: Experiment and Prediction , 2005 .

[23]  Zilong Liu,et al.  Prediction of Pressure Gradient in Two and Three-phase Flows in Horizontal Pipes Using an Artificial Neural Network Model , 2019 .

[24]  Anand B. Desamala,et al.  Correlations for Prediction of Pressure Gradient of Liquid-Liquid Flow Through a Circular Horizontal Pipe , 2014 .

[25]  A. Al-Ajmi,et al.  Effect of low interfacial tension on flow patterns, pressure gradients and holdups of medium-viscosity oil/water flow in horizontal pipe , 2015 .

[26]  Oscar Mauricio Hernandez Rodriguez,et al.  Experimental investigation on liquid–liquid–gas flow: Flow patterns and pressure-gradient , 2009 .

[27]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[28]  A. Fichera,et al.  A neural tool for the prediction of the experimental dynamics of two-phase flows , 2017 .

[29]  Geir Elseth,et al.  An Experimental Study of Oil/Water Flow in Horizontal Pipes , 2001 .

[30]  B. John,et al.  Liquid – Liquid horizontal pipe flow – A review , 2018, Journal of Petroleum Science and Engineering.

[31]  D. Wolpert,et al.  No Free Lunch Theorems for Search , 1995 .

[32]  Farouq S. Mjalli,et al.  PREDICTION OF HORIZONTAL OIL-WATER FLOW PRESSURE GRADIENT USING ARTIFICIAL INTELLIGENCE TECHNIQUES , 2014 .

[33]  Panagiota Angeli,et al.  Experimental studies on the dual continuous flow pattern in oil-water flows , 2004 .

[34]  Oscar Mauricio Hernandez Rodriguez,et al.  Experimental study on oil–water flow in horizontal and slightly inclined pipes , 2006 .

[35]  D. Mewes,et al.  Flow induced emulsification in the flow of two immiscible liquids in horizontal pipes , 1997 .

[36]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .

[37]  H. Karimi,et al.  An Artificial Neural Network Model for Predicting the Pressure Gradient in Horizontal Oil–Water Separated Flow , 2015 .

[38]  Panagiota Angeli,et al.  Pressure gradient in horizontal liquid-liquid flows , 1999 .

[39]  Eva Ocelíková,et al.  Multi-criteria decision making methods , 2005 .

[40]  Jacob Cohen,et al.  Applied multiple regression/correlation analysis for the behavioral sciences , 1979 .

[41]  Neima Brauner,et al.  ANALYTICAL SOLUTION FOR LAMINAR-LAMINAR TWO-PHASE STRATIFIED FLOW IN CIRCULAR CONDUITS , 1996 .