Accurate identification of gas-liquid two-phase flow patterns during oil and gas drilling is critical to analyzing bottom hole pressure, detecting overflows in time, and preventing blowout accidents. Since the gas-liquid two-phase flow has deformable interfaces, resulting in complex gas-liquid two-phase flow patterns, the existing gas-liquid two-phase flow patterns are limited in width in terms of pipe diameter and incline, leading to adaptation problems in experimental flow patterns and mechanistic models. Machine learning methods provide potential tools for solving gas-liquid two-phase flow pattern identification. In this paper, a sample database with 5879 data points was established by reviewing and organizing existing literature focusing on normal pressure and temperature, and air-water experimental conditions to provide a data-preparation for the relationship between gas and liquid velocities, pipe diameter and incline characteristics and flow pattern objectives. Four machine learning models, including K-Nearest Neighbor, Naïve Bayes, Decision Tree and Random Forest, were investigated, and each model was trained and tested using a sample database to reveal the performance of four types of supervised machine learning methods, representing similarity, probability, inductive inference and ensemble-learning principles, for gas-liquid two-phase flow pattern recognition, and the prediction accuracy was 0.86, Naïve Bayes is 0.56, Decision Tree is 0.89 and Random Forest 0.97. Comprehensive analysis of each model confusion matrix shows that the machine learning method has the best recognition of dispersed bubble flow, better recognition of slug flow, and the worst recognition of churn flow among the nine flow patterns which proves the controversial nature of the mechanism model in the transition from slug flow to churn flow. This paper uses experimental data as model input features, making the machine learning-based gas-liquid two-phase flow pattern identification model meaningful for practical engineering applications, and also demonstrating the feasibility of using supervised machine learning methods for gas-liquid two-phase flow pattern identification at normal pressure and temperature, wide-range of pipe diameter and incline.
Similar content being viewed by others
References
Baker, O., Simultaneous flow in oil and gas, Oil and Gas J, 1954, 53: 185–195.
Dune H.Jr., Ros N.C.J. Vertical Flow of Gas and Liquid Mixtures in WellsC. .Sixth World Petroleum Congress, Frankfurt am Main, Germany, 19-26 June 1963.
Govier, G.W. and Aziz, K. The Flow of Complex Mixtures in Pipes, Van Nostrand Reinhold, New York (1972).
Mandhane, J.M., Gregory, G.A., Aziz, K. A Flow Pattern Map for Gas-Liquid Flow in Horizontal Pipes, Int.J. Multiphase Flow, 1:537-553, (1974).
Y. Taitel, A.E. Dukler. A Model for Predicting Flow Regime Transitions in Horizontal and near Horizontal Gas-Liquid Flow, AIChE J., 22: 47-55, (1976).
Taitel, Y., Barnea D., Duckler A.E. Modeling Flow Pattern Transitions for Steady State Upward Gas-Liquid Flow in Vertical Tubes. AIChE J., (1980). 26:345–354.
Barnea D. Transition From Annular Flow And From Dispersed Bubble Flow-Unified Models For The Whole Range of Pipe Inclinations. int.J.Multiphase flow, 12(5): 733-734,(1986).
Barnea.D. A unified model for predicting flow-pattern transitions for the whole range of pipe inclinations.int. J. Multiphase flow. 13(1): 1-12 (1987).
Wallis, G., 1969. One-dimensional Two-phase Flow, McGraw-Hill. Weisman, J. & Kang, S.Y., 1981. Flow pattern transitions in vertical and upwardly inclined lines. International Journal of Multiphase Flow, 7(3): 271–291.
Hasan, A.R., Kabir, C.S. A Study of Multiphase Flow Behavior in Vertical Wells, SPEPE (May 1988) 263, Trans., AIME, 285.
D. Barnea, O. Shoham, Y. Taitel. Flow Pattern Transition for Vertical Downward Two Phase Flow. Chem. Eng. Sci., 37, 741-744 (1982).
Ansari A. M., Sylvester N. D., Sarica C., et al. A Comprehensive Mechanistic Model for Upward Two-Phase Flow in Welbores, SPEProd. Facil., May, P 143–152, (1994).
Osman, El-Sayed A. Artificial Neural Network Models for Identifying Flow Regimes and Predicting Liquid Holdup in Horizontal Multiphase Flow. Spe Production & Facilities 19 (2004): 33-40.
Trafalis T.B., Oladunni O., Papavassiliou D.V. Two-phase flow regime identification with a multiclassification support vector machine (SVM) model. Ind Eng Chem44: 4414–4426, (2005).
Mask G,Wu X,Ling K . An improved model for gas-liquid flow pattern prediction based on machine learning J. . Journal of Petroleum Science and Engineering, (2019), 183:106370.
Ala.AL-Dogail, Rahul.Gajbhiye, Abdullatif AlNajim, et al. Dimensionless Artificial Intelligence-Based Model for Multiphase Flow Pattern Recognition in Horizontal Pipe, 2022. SPE Production & Operations, 2022.5.
Kaushik Manikonda, Abu Rashid Hasan, Chinemerem Edmond Obi. Application of Machine Learning Classification Algorithms for Two-Phase Gas-Liquid Flow Regime Identification. the Abu Dhabi International Petroleum Exhibition & Conference, UAE, 15–18 November 2021.
Barnea D., Luninskl Y., Taitel Y. Flow pattern in horizontal and vertical two phase flow in small diameter pipes J. . Canadian Journal of Chemical Engineering, (1983),61:617-620.
Barnea, D., Shoham, O., Taitel, Y. et al. Gas-liquid flow in inclined tubes: flow pattern transitions for upward flow. Chemical Engineering Science,40, 131-136, (1985).
Vieira C., Kallager M., Vassmyr M., et al. Experimental investigation of two-phase flow regime in an inclined pipe. 11th North American Conference on Multiphase Production Technology. Banff, Canada:BHR Group,(2018).
Wu, H., Y. P. Zhao, H. J. Tan. A hybrid of fast K-nearest neighbor and improved directed acyclic graph support vector machine for large-scale supersonic inlet flow pattern recognition. Proceedings of the Institution of Mechanical Engineers, Part G. Journal of aerospace engineering 1(2022):236.
Omara, I., et al. A Hybrid Model Combining Learning Distance Metric and DAG Support Vector Machine for Multimodal Biometric Recognition. IEEE Access PP.99(2020):1-1.
Gu, Y., et al. A Layered KNN-SVM Approach to Predict Missing Values of Functional Requirements in Product Customization. Applied Sciences 11.5(2021):2420.
Zhang H.-Q. et al. Unified Model for Gas-Liquid Pipe Flow via Slug Dynamics—Part 1: Model Development. Journal of Energy Resources Technology, 125(4),p.266, (2003).
Ruz, G. A., D. T. Pham. NBSOM: The naive Bayes self-organizing map. Neural Computing & Applications 21.6(2012):1319-1330.
Yan, X., Q. Wu, V. S. Sheng. A Double Weighted Naive Bayes with Niching Cultural Algorithm for Multi-Label Classification. International Journal of Pattern Recognition and Artificial Intelligence, 30.6(2016):1650013.1-1650013.23.
Nur I., E. Uelker. A Novel Hybrid IoT Based IDS Using Binary Grey Wolf Optimizer (BGWO) and Naive Bayes (NB). (2020).
Mishan, M. T., et al. An analysis on business intelligence predicting business profitability model using Naive Bayes neural network algorithm. 2017 7th IEEE International Conference on System Engineering and Technology (ICSET) IEEE, 2017.
Shukla, Basu, and Tuninetti. Towards Closed-Loop Deep Brain Stimulation: Decision Tree-based Essential Tremor Patient’s State Classifier and Tremor Reappearance Predictor. IEEE ENG MED BIO (2014).
Ghaffari, A., G. Priestnall, M. L. Clarke. Artificial neural networks and decision tree classifier performance on medium resolution ASTER data to detect gully networks in southern Italy. Proceedings of SPIE - The International Society for Optical Engineering 6064(2006):0641Q-60641Q-9.
Wang S., et al. Human activity recognition with user-free accelerometers in the sensor networks. 2005 International Conference on Neural Networks and Brain IEEE, (2005).
Nisha R., et al. RFECS: A Random-Forest Based Algorithm for Enhancer Identification from Chromatin State. PLoS Computational Biology, 9,3(2013-3-14) 9.3(2013):e1002968.
Karpievitch, et al. An Introspective Comparison of Random Forest-Based Classifiers for the Analysis of Cluster-Correlated Data by Way of RF plus. PLOS ONE (2009).
Nadel et al. Random Forest (RF) Wrappers for Waveband Selection and Classification of Hyperspectral Data. Applied Spectroscopy Society for Applied Spectroscopy (2016).
Sheng L., et al. Classification of iron ores by laser-induced breakdown spectroscopy (LIBS) combined with random forest (RF). Journal of Analytical Atomic Spectrometry 30.2(2015):453-458.
Thome J.R. Encyclopedia of Two-Phase Heat Transfer and Flow I:Fundamentals and Methods (A 4-Volume Set), World Scientific PublishingCompany, (2015).
Ullmann A., Brauner N. Closure relations for two-fluid models for two-phase stratified smooth and stratified wavy flows. International Journal of Multiphase Flow, 32(1), pp.82–105, (2006).
Acknowledgments
This work was supported in part by the Sichuan Science and Technology Program under Grant 2023NSFSC1981.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Khimiya i Tekhnologiya Topliv i Masel, No. 5, pp. 121–126, September–October, 2023
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, J., Cai, M., Wei, N. et al. Supervised Machine Learning Mode for Predicting Gas-Liquid Flow Patterns in Upward Inclined Pipe. Chem Technol Fuels Oils 59, 1058–1069 (2023). https://doi.org/10.1007/s10553-023-01618-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10553-023-01618-1