Research Papers: Multiphase Flows

An Optimized Artificial Neural Network Unifying Model for Steady-State Liquid Holdup Estimation in Two-Phase Gas–Liquid Flow

[+] Author and Article Information
Majdi Chaari

Department of Electrical and
Computer Engineering,
University of Louisiana at Lafayette,
P.O. Box 43890,
Lafayette, LA 70504-3890
e-mail: mxc0798@louisiana.edu

Abdennour C. Seibi

Department of Petroleum Engineering,
University of Louisiana at Lafayette,
P.O. Box 44690,
Lafayette, LA 70504
e-mail: acs9955@louisiana.edu

Jalel Ben Hmida

Department of Mechanical Engineering,
University of Louisiana at Lafayette,
P.O. Box 43678,
Lafayette, LA 70504
e-mail: jxb9360@louisiana.edu

Afef Fekih

Department of Electrical and
Computer Engineering,
University of Louisiana at Lafayette,
P.O. Box 43890,
Lafayette, LA 70504-3890
e-mail: afef.fekih@louisiana.edu

1Corresponding author.

Contributed by the Fluids Engineering Division of ASME for publication in the JOURNAL OF FLUIDS ENGINEERING. Manuscript received October 5, 2017; final manuscript received March 7, 2018; published online May 2, 2018. Assoc. Editor: Riccardo Mereu.

J. Fluids Eng 140(10), 101301 (May 02, 2018) (11 pages) Paper No: FE-17-1640; doi: 10.1115/1.4039710 History: Received October 05, 2017; Revised March 07, 2018

Simplifying assumptions and empirical closure relations are often required in existing two-phase flow modeling based on first-principle equations, hence limiting its prediction accuracy and in some instances compromising safety and productivity. State-of-the-art models used in the industry still include correlations that were developed in the sixties, whose prediction performances are at best acceptable. To better improve the prediction accuracy and encompass all pipe inclinations and flow patterns, we propose in this paper an artificial neural network (ANN)-based model for steady-state two-phase flow liquid holdup estimation in pipes. Deriving the best input combination among a large reservoir of dimensionless Π groups with various fluid properties, pipe characteristics, and operating conditions is a laborious trial-and-error procedure. Thus, a self-adaptive genetic algorithm (GA) is proposed in this work to both ease the computational complexity associated with finding the elite ANN model and lead to the best prediction accuracy of the liquid holdup. The proposed approach was implemented using the Stanford multiphase flow database (SMFD), chosen for being among the largest and most complete databases in the literature. The performance of the proposed approach was further compared to that of two prominent models, namely a standard empirical correlation-based model and a mechanistic model. The obtained results along with the comparison analysis confirmed the enhanced accuracy of the proposed approach in predicting liquid holdup for all pipe inclinations and fluid flow patterns.

Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.


Diener, R. , and Friedel, L. , 1998, “ Reproductive Accuracy of Selected Void Fraction Correlations for Horizontal and Vertical Upflow,” Forsch. Ingenieurwes., 64(4–5), pp. 87–97. [CrossRef]
Woldesemayat, M. A. , and Ghajar, A. J. , 2007, “ Comparison of Void Fraction Correlations for Different Flow Patterns in Horizontal and Upward Inclined Pipes,” Int. J. Multiphase Flow, 33(4), pp. 347–370. [CrossRef]
Abdul-Majeed, G. H. , 1996, “ Liquid Holdup in Horizontal Two-Phase Gas-Liquid Flow,” J. Pet. Sci. Eng., 15(2–4), pp. 271–280. [CrossRef]
Zhao, H. D. , Lee, K. C. , and Freeston, D. H. , 2000, “ Geothermal Two-Phase Flow in Horizontal Pipes,” World Geothermal Congress, Tokyo, Japan, May 28–June 10, pp. 3349–3353.
Rouhani, S. Z. , and Axelsson, E. , 1970, “ Calculation of Void Volume Fraction in the Subcooled and Quality Boiling Regions,” Int. J. Heat Mass Transfer, 13(2), pp. 383–393. [CrossRef]
Hughmark, G. A. , 1962, “ Holdup in Gas Liquid Flow,” Chem. Eng. Prog., 58(4), pp. 62–64.
Gomez, L. E. , Shoham, O. , and Taitel, Y. , 2000, “ Prediction of Slug Liquid Holdup: Horizontal to Upward Vertical Flow,” Int. J. Multiphase Flow, 26(3), pp. 517–521. [CrossRef]
Beggs, H. D. , and Brill, J. P. , 1973, “ A Study of Two-Phase Flow in Inclined Pipes,” J. Pet. Technol., 25(5), pp. 607–617. [CrossRef]
Mukherjee, H. , and Brill, J. P. , 1983, “ Liquid Holdup Correlations for Inclined Two-Phase Flow,” J. Pet. Technol., 35(5), pp. 1003–1008. [CrossRef]
Duns, H. J. , and Ros, N. , 1963, “ Vertical Flow of Gas and Liquid Mixtures in Wells,” Sixth World Petroleum Congress, Frankfurt am Main, Germany, June 19–26, pp. 451–465.
Taitel, Y. , and Dukler, A. E. , 1976, “ A Model for Predicting Flow Regime Transitions in Horizontal and Near Horizontal Gas–Liquid Flow,” AIChE J., 22(1), pp. 47–55. [CrossRef]
Ansari, A. M. , Sylvester, N. D. , Sarica, C. , Shoham, O. , and Brill, J. P. , 1994, “ A Comprehensive Mechanistic Model for Upward Two-Phase Flow in Wellbores,” SPE Prod. Facil., 9(2), pp. 143–151. [CrossRef]
Taitel, Y. , Bornea, D. , and Dukler, A. , 1980, “ Modelling Flow Pattern Transitions for Steady Upward Gas-Liquid Flow in Vertical Tubes,” AIChE J., 26(3), pp. 345–354. [CrossRef]
Petalas, N. , and Aziz, K. , 2000, “ A Mechanistic Model for Multiphase Flow in Pipes,” J. Can. Pet. Technol., 39(6), pp. 43–55. [CrossRef]
Kazi, S. N. , 1999, An Overview of Heat Transfer Phenomena, InTech, London. [PubMed] [PubMed]
Awad, M. M. , and Muzychka, Y. S. , 2008, “ Effective Property Models for Homogeneous Two-Phase Flows,” Exp. Therm. Fluid Sci., 33(1), pp. 106–113. [CrossRef]
Lockhart, R. W. , and Martinelli, R. C. , 1949, “ Proposed Correlation of Data for Isothermal Two-Phase, Two-Component Flow in Pipes,” Chem. Eng. Prog. Symp. Ser., 45(1), pp. 39–48.
Zivi, S. M. , 1964, “ Estimation of Steady-State Void Fraction by Means of the Principle of Minimum Energy Production,” ASME J. Heat Transfer, 86(2), pp. 247–252. [CrossRef]
Wallis, G. B. , 1969, One-Dimensional Two-Phase Flow, McGraw-Hill, New York.
Franca, F. , and Lahey, R. T. , 1992, “ The Use of Drift-Flux Techniques for the Analysis of Horizontal Two-Phase Flows,” Int. J. Multiphase Flow, 18(6), pp. 787–801. [CrossRef]
Shi, H. , Holmes, J. , Diaz, L. , Durlofsky, L. , and Aziz, K. , 2005, “ Drift-Flux Modeling of Two-Phase Flow in Wellbores,” SPE J., 10(1), pp. 24–33. [CrossRef]
Hasan, A. R. , Kabir, C. S. , and Sayarpour, M. , 2007, “ A Basic Approach to Wellbore Two-Phase Flow Modeling,” SPE Annual Technical Conference and Exhibition, Anaheim, CA, Nov. 11–14, SPE Paper No. SPE-109868-MS.
Mishima, K. , and Ishii, M. , 1984, “ Flow Regime Transition Criteria for Upward Two-Phase Flow in Vertical Tubes,” Int. J. Heat Mass Transfer, 27(5), pp. 723–737. [CrossRef]
Ishii, M. , 1987, “ Two-Fluid Model for Two-Phase Flow,” Multiphase Sci. Technol., 5(1), pp. 1–63.
De Sampaio, P. A. B. , Faccini, J. L. H. , and Su, J. , 2008, “ Modelling of Stratified Gas–Liquid Two-Phase Flow in Horizontal Circular Pipes,” Int. J. Heat Mass Transfer, 51(11–12), pp. 2752–2761. [CrossRef]
Taha, T. , and Cui, Z. F. , 2006, “ CFD Modelling of Slug Flow in Vertical Tubes,” Chem. Eng. Sci., 61(2), pp. 676–687. [CrossRef]
Liu, Y. , Cui, J. , and Li, W. Z. , 2011, “ A Two-Phase, Two-Component Model for Vertical Upward Gas–Liquid Annular Flow,” Int. J. Heat Fluid Flow, 32(4), pp. 796–804. [CrossRef]
Shuard, A. M. , Mahmud, H. B. , and King, A. J. , 2016, “ Comparison of Two-Phase Pipe Flow in OpenFOAM With a Mechanistic Model,” IOP Conf. Ser.: Mater. Sci. Eng., 121(Conf. 1), p. 012018. [CrossRef]
Shippen, M. E. , and Scott, S. L. , 2004, “ A Neural Network Model for Prediction of Liquid Holdup in Two-Phase Horizontal Flow,” SPE Prod. Facil., 19(2), pp. 67–76. [CrossRef]
El-Sayed, A. O. , 2004, “ Artificial Neural Network Models for Identifying Flow Regimes and Predicting Liquid Holdup in Horizontal Multiphase Flow,” SPE Prod. Facil., 19(1), pp. 33–40. [CrossRef]
Park, H. J. , and Kang, J. M. , 2006, “ Polynomial Neural Network Approach for Prediction of Liquid Holdup in Horizontal Two-Phase Flow,” Energy Sources, Part A, 28(9), pp. 845–853. [CrossRef]
Meribout, M. , Al-Rawahi, N. Z. , Al-Naamany, A. M. , Al-Bimani, A. , Al-Busaidi, K. , and Meribout, A. , 2010, “ A Multisensory Intelligent Device for Real-Time Multiphase Flow Metering in Oil Fields,” IEEE Trans. Instrum. Meas., 59(6), pp. 1507–1519. [CrossRef]
Ozbayoglu, A. M. , and Yuksel, H. E. , 2011, “ Estimation of Multiphase Flow Properties Using Computational Intelligence Models,” Procedia Comput. Sci., 6, pp. 493–498. [CrossRef]
Ling, J. , Kurzawski, A. , and Templeton, J. , 2016, “ Reynolds Averaged Turbulence Modelling Using Deep Neural Networks With Embedded Invariance,” J. Fluid Mech., 807, pp. 155–166. [CrossRef]
Kutz, J. N. , 2017, “ Deep Learning in Fluid Dynamics,” J. Fluid Mech., 814, pp. 1–4. [CrossRef]
Mohammadi, M. , 2006, “ A Comprehensive Neural Network Model for Predicting Two-Phase Liquid Holdup Under Various Angles of Pipe Inclinations,” Canadian International Petroleum Conference, Calgary, AB, Canada, June 13–15, Paper No. PETSOC-2006-048.
Liao, K. , Yao, Q. , Wu, X. , and Jia, W. , 2012, “ A Numerical Corrosion Rate Prediction Method for Direct Assessment of Wet Gas Gathering Pipelines Internal Corrosion,” Energies, 5(10), pp. 3892–3907. [CrossRef]
Zhang, D. , and Xia, B. , 2014, “ Soft Measurement of Water Content in Oil-Water Two-Phase Flow Based on RS-SVM Classifier and GA-NN Predictor,” Meas. Sci. Rev., 14(4), pp. 219–226. [CrossRef]
Porto, M. P. , Pedro, H. T. C. , Machado, L. , Koury, R. N. N. , Lima, C. U. S. , and Coimbra, C. F. M. , 2014, “ Genetic Optimization of Heat Transfer Correlations for Evaporator Tube Flows,” Int. J. Heat Mass Transfer, 70, pp. 330–339. [CrossRef]
Hassoun, M. H. , 1995, Fundamentals of Artificial Neural Networks, MIT Press, Cambridge, MA, Chap. 5.
Hornik, K. , Stinchcombe, M. , and White, H. , 1990, “ Universal Approximation of an Unknown Mapping and Its Derivatives Using Multilayer Feedforward Networks,” Neural Networks, 3(5), pp. 551–560. [CrossRef]
Goldberg, D. E. , 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA.
Blickle, T. , and Thiele, L. , 1995, “ A Comparison of Selection Schemes Used in Genetic Algorithms,” Computer Engineering and Communication Networks Lab (TIK), Swiss Federal Institute of Technology (ETH), Zürich, Switzerland, Technical Report No. 11.
De Jong, K. A. , 1976, “Analysis of the Behavior of a Class of Genetic Adaptive Systems,” Ph.D. thesis, University of Michigan, Ann Arbor, MI.
Hong, T. P. , Wang, H. S. , Lin, W. Y. , and Lee, W. Y. , 2002, “ Evolution of Appropriate Crossover and Mutation Operators in a Genetic Process,” Appl. Intell., 16(1), pp. 7–17. [CrossRef]
Lin, W. Y. , Lee, W. Y. , and Hong, T. P. , 2003, “ Adapting Crossover and Mutation Rates in Genetic Algorithms,” J. Inf. Sci. Eng., 19, pp. 889–903.
Alves, G. E. , 1954, “ Co-Current Liquid-Gas Flow in a Pipeline Contractor,” Chem. Eng. Prog., 50(9), pp. 449–456.
Green, D. W. , 1959, M.Sc. thesis, University of Oklahoma, Norman, OK.
Govier, G. W. , Radford, B. A. , and Dunn, J. S. C. , 1957, “ The Upwards Vertical Flow of Air-Water Mixtures—I: Effect of Air and Water Rates on Flow Pattern, Holdup and Pressure Drop,” Can. J. Chem. Eng., 35, pp. 58–70.
Govier, G. W. , and Omer, M. M. , 1962, “ The Horizontal Pipeline Flow of Air–Water Mixtures,” Can. J. Chem. Eng., 40(3), pp. 93–104.
Agrawal, S. S. , 1971, “Horizontal Two-Phase Stratified Flow in Pipes,” M.Sc. thesis, University of Calgary, Calgary, AB, Canada.
Yu, C. , 1972, “Horizontal Flow of Air-Oil Mixtures in the Elongated Bubble Flow Pattern,” M.Sc. thesis, University of Calgary, Calgary, AB, Canada.
Eaton, B. A. , 1966, “The Prediction of Flow Patterns, Liquid Holdup and Pressure Losses,” Ph.D. thesis, University of Texas, Austin, TX.
Vermeulen, L. R. , 1968, “Two-Phase Slug Flow in Horizontal and Inclined Tubes,” M.Sc. thesis, University of Alberta, Edmonton, AB, Canada.
Mattar, L. , 1973, “Slug Flow Uphill in an Inclined Pipe,” M.Sc. thesis, University of Calgary, Calgary, AB, Canada.
Griffith, P. , Lau, C. W. , Hon, P. C. , and Pearson, J. F. , 1973, “Two Phase Pressure Drop in Inclined and Vertical Pipes,” Massachusetts Institute of Technology, Cambridge, MA, Technical Report No. DSR 80063-81.
Nicholson, M. K. , Aziz, K. , and Gregory, G. A. , 1978, “ Intermittent Two Phase Flow in Horizontal Pipes: Predictive Models,” Can. J. Chem. Eng., 56(6), pp. 653–663. [CrossRef]
Mukherjee, H. , 1979, “An Experimental Study of Inclined Two-Phase Flow,” Ph.D. thesis, University of Tulsa, Tulsa, OK.
Nguyen, V. T. , 1975, “Two Phase Gas–Liquid Co-Current Flow. An Investigation of Holdup, Pressure Drop and Flow Pattern in a Pipe at Various Inclinations,” Ph.D. thesis, University of Auckland, Auckland, New Zealand.
Gregory, G. A. , Nicholson, M. K. , and Aziz, K. , 1978, “ Correlation of the Liquid Volume Fraction in the Slug for Horizontal Gas-Liquid Slug Flow,” Int. J. Multiphase Flow, 4(1), pp. 33–39. [CrossRef]
Chaari, M. , Fekih, A. , and Seibi, A. C. , 2018, “ A Frequency Domain Approach to Improve ANNs Generalization Quality Via Proper Initialization,” Neural Networks (in press).
Maren, A. J. , Harston, C. T. , and Pap, R. M. , 1990, Handbook of Neural Computing Applications, Academic Press, San Diego, CA, Chap. 15.
Hagan, M. T. , and Menhaj, M. B. , 1994, “ Training Feedforward Networks With the Marquardt Algorithm,” IEEE Trans. Neural Networks, 5(6), pp. 989–993. [CrossRef]
Chaari, M. , Ben Hmida, J. , Seibi, A. C. , and Fekih, A. , 2017, “ Steady-State Pressure Drop for Two-Phase Flow in Pipelines: An Integrated Genetic Algorithm–Artificial Neural Network Approach,” ASME Paper No. IMECE2017-71854.
Bäck, T. , and Hoffmeister, F. , 1991, “ Extended Selection Mechanisms in Genetic Algorithms,” Fourth International Conference on Genetic Algorithms, San Diego, July 13–16, pp. 92–99.
Kumar, R. , and Jyotishree , 2012, “ Effect of Annealing Selection Operators in Genetic Algorithms on Benchmark Test Functions,” Int. J. Comput. Appl., 40(3), pp. 38–46.
Krogh, A. , and Hertz, J. A. , 1991, “ A Simple Weight Decay Can Improve Generalization,” Advances in Neural Information Processing Systems, Vol. 4, Morgan Kaumann Publishers, San Mateo CA, pp. 950–957.
Meziou, A. , Chaari, M. , Franchek, M. , Borji, R. , Grigoriadis, K. , and Tafreshi, R. , 2016, “ Low-Dimensional Modeling of Transient Two-Phase Flow in Pipelines,” ASME J. Dyn. Syst. Meas. Control, 138(10), p. 101008.


Grahic Jump Location
Fig. 1

Architecture of an m-input single-output three-layered perceptron

Grahic Jump Location
Fig. 2

Flowchart of the ANN input selection approach

Grahic Jump Location
Fig. 3

m-input selector encoding solution

Grahic Jump Location
Fig. 4

Two-point crossover of five-one-valued-bit individuals: (a) successful crossover and (b) unsuccessful crossover

Grahic Jump Location
Fig. 5

Mutation of a five-one-valued-bit individual

Grahic Jump Location
Fig. 6

Observed flow patterns

Grahic Jump Location
Fig. 7

Evolution of the best fitness for different initial pc and pm: (a) m = 5, (b) m = 6, and (c) m = 7

Grahic Jump Location
Fig. 8

(a) Evolution of the best fitness for various numbers of inputs m and (b) evolution of pc and pm for m = 6

Grahic Jump Location
Fig. 9

Experimental and predicted liquid holdup parity charts: (a) elite ANN model, (b) Beggs and Brill's model, and (c) Petalas and Aziz's model (solid line represents parity line)

Grahic Jump Location
Fig. 10

Absolute relative error of the elite ANN model



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In