Data driven methodology for model selection in flow pattern prediction

Abstract

The determination of multiphase flow parameters such as flow pattern, pressure drop and liquid holdup, is a very challenging and valuable problem in chemical, oil and gas industries, especially during transportation. There are two main approaches to solve this problem in literature: data based algorithms and mechanistic models. Although data based methods may achieve better prediction accuracy, they fail to explain the two-phase characteristics (i.e. pressure gradient, holdup, gas and liquid local velocities, etc.). Recently, many approaches have been made for establishing a unified mechanistic model for steady-state two-phase flow to predict accurately the mentioned properties. This paper proposes a novel data-driven methodology for selecting closure relationships from the models included in the unified model. A decision tree based model is built based on a data driven methodology developed from a 27670 points data set and later tested for flow pattern prediction in a set made of 9224 observations. The closure relationship selection model achieved high accuracy in classifying flow regimes for a wide range of two-phase flow conditions. Intermittent flow registering the highest accuracy (86.32%) and annular flow the lowest (49.11%). The results show that less than 10% of global accuracy is lost compared to direct data based algorithms, which is explained by the worse performance presented for atypical values and zones close to boundaries between flow patterns.

Machine learning applications to predict two-phase flow patterns

“…Previous work on the classification of two-phase flow pattern using the 12 databases to be used in the experiments of this paper reported an accuracy of: 74.71% for the classification of six flow patterns, 79.02% for the classification of five flow patterns, and 82.29% for the classification of three flow patterns, using a mechanistic model ( Pereyra et al, 2012 ); 74.84% for the classification of six flow patterns using a tree-based model ( Hernandez et al, 2019 ); and 95% for the classification of six flow patterns, 95% for the classification of five flow patterns, and 97% for the classification of three flow patterns using a SVM approach ( Guillen-Rondon et al, 2018 ).…”

“…Due to the nature of the spatial distribution, there have been disagreements about where a different pattern begins and ends. However, there are flow patterns, and they must be classified correctly ( Hernandez et al, 2019 ; Figueiredo et al, 2020 ; Liu, Tan & Dong, 2021 ). Today it is possible to design powerful artificial intelligence models as an excellent tool to predict the flow pattern despite the different changes in the variables involved ( Roshani et al, 2021 ; Cerqueira & Paladino, 2021 ; de Castro Teixeira Carvalho, de Melo Freire Figueiredo & Serpa, 2020 ).…”

Machine Learning Algorithms for Flow Pattern Classification in Pulsating Heat Pipes

“…Most efforts focused on common heat pipes and two-phase systems. Hernandez et al [38] developed a decision-tree-based classifier to identify flow regimes and select appropriate predictive models for several two-phase flow systems. Zhang et al [39] proposed two different machine learning classification algorithms for two-phase nuclear systems.…”

Machine Learning Augmented Two-Fluid Model for Segregated Flow

“…Multiple other studies are based on fluid property experimental data using support vector machines, neural networks, or deep learning as a machine learning tool. Some of the related work was conducted by Osman (2004) 2020) [30][31][32][33][34][35][36]. The studies prove machine learning is an effective tool for predicting flow patterns based on pipe characteristics, superficial velocities, and other fluid properties.…”