Pressure drop estimation in horizontal annuli for liquid–gas 2 phase flow: Comparison of mechanistic models and computational intelligence techniques

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

“…Persistent lack of physical comprehension continuously stymies preferable prediction performance of the key parameters in multiphase flow and reactor systems, although scientists have made systematic contributions to experimentally formulated correlations throughout the past decades. − The correlations of the key parameters in multiphase units are commonly expressed by gas/liquid/solid phase properties, operating conditions (e.g., phase concentration, velocity, and temperature), devices configurations (e.g., height and diameter), or a combination of them in dimensionless forms such as Archimedes, Froude, Nusselt, Reynolds, Sherwood, and Weber numbers. However, the prediction discrepancies between the existing empirical correlations of key parameters such as the particle entrainment and minimum fluidization velocity in gas-particle riser flows can reach several orders of magnitude. , Fortunately, the advanced research and development of flexible ML tools have the potential to complement the incomplete knowledge to boost the prediction ability of key multiphase field parameters such as mass flow rate/flux, − minimum fluidization velocity, , mixing rate/index, , overall/local hold-up, − pressure/pressure drop, − velocity, ,− temperature, − and other parameters − in multiphase/particulate flows and reactors. Note that interested readers may be referred to a relatively comprehensive list of the existing literature summarized in Table S4.…”

Gas–liquid flowing process in a horizontal well with premature liquid loading

“…Najmi et al (2015) conducted an experimental study to confirm the critical flow rates (resulting in stratified wavy flow) of gas and liquid necessary to keep particles moving in a horizontal flow line. Osgouei et al (2015) proposed a new model to estimate the frictional pressure losses for liquidegas multiphase flow in horizontal eccentric annulus. Also mechanism and model of stratified flow in inclined pipes are investigated by Li et al (2004), Lips and Meyer (2012), Xia and Lei (2012) and Xing et al (2013).…”

Machine Learning for Closure Models in Multiphase Flow Applications

“…Alizadehdakhel et al [1] and Osgouei et al [32] used physical experimental data to train neural networks to predict pressure drops in two-phase pipe flow. They related the superficial velocities to the spatially and temporally averaged pressure drop, like in the conventional approach, but used a neural network to construct the relation.…”