Gas liquid flow pattern prediction in horizontal and slightly inclined pipes: From mechanistic modelling to machine learning

• Published in: Applied mathematical modelling 2025-02, Vol.138, p.115748, Article 115748
• Main Authors: Guesmi, Montadhar, Manthey, Johannes, Unz, Simon, Schab, Richard, Beckmann, Michael
• Format: Article
• Language: English
• Subjects: Flow pattern prediction; Gas liquid two phase flow; Machine learning; Mechanistic modelling
• ISSN: 0307-904X
• DOI: 10.1016/j.apm.2024.115748

This paper investigates the prediction of two-phase gas-liquid flow regimes in both horizontal and slightly inclined pipes. For this purpose, the mechanistic model of Taitel et al. (1976) and the machine learning approach have been adopted. First, the mechanistic model was implemented, tested and optimised by introducing factors in the transition equations to determine the configuration that gives the highest prediction accuracy for a specific two-phase system for which experimental data points are available. Second, several machine learning models are trained, tested and additionally validated. This is done by splitting the experimental data set corresponding to the pipe inclination range (−10∘ to 10∘) into training, test and validation sets. The best classifier achieved an accuracy of 95.5% after the test step and up to 98.9% after the validation step. Finally, the Taitel et al. model with the optimal configuration and the best machine learning classifier (XGB classifier) are used to generate the two-dimensional flow regime map. •Gas-liquid flow prediction in horizontal and slightly inclined pipes (-10° to 10°).•Optimization of mechanistic model with introduced factors in transition equations.•Training, test and validation based on experimental data.•Accuracy of XGB classifier is 95.5% during testing and 98.9% after validation.•XGBClassifier used alongside the mechanistic model to generate a 2D flow regime map.