Using statistical learning to close two-fluid multiphase flow equations for a simple bubbly system
- 1 September 2015
- journal article
- conference paper
- Published by AIP Publishing in Physics of Fluids
- Vol. 27 (9) , 092101
Abstract
Direct numerical simulations of bubbly multiphase flows are used to find closure terms for a simple model of the average flow, using Neural Networks (NNs). The flow considered consists of several nearly spherical bubbles rising in a periodic domain where the initial vertical velocity and the average bubble density are homogeneous in two directions but non-uniform in one of the horizontal directions. After an initial transient motion the average void fraction and vertical velocity become approximately uniform. The NN is trained on a dataset from one simulation and then used to simulate the evolution of other initial conditions. Overall, the resulting model predicts the evolution of the various initial conditions reasonably well.Keywords
Funding Information
- National Science Foundation (CBET-1335913)
This publication has 38 references indexed in Scilit:
- A NEURAL NETWORK ALGORITHM FOR DENSITY MEASUREMENT OF MULTIPHASE FLOWMultiphase Science and Technology, 2012
- Apparent damage accumulation in cancellous bone using neural networksJournal of the Mechanical Behavior of Biomedical Materials, 2011
- Neural networks as material models within a multiscale approachComputers & Structures, 2009
- Coupling of scales in a multiscale simulation using neural networksComputers & Structures, 2008
- Effect of bubble deformability in turbulent bubbly upflow in a vertical channelPhysics of Fluids, 2008
- Neural network modelling for mean velocity and turbulence intensities of steep channel flowsHydrological Processes, 2007
- Numerical simulation of behavior of gas bubbles using a 3‐D front‐tracking methodAIChE Journal, 2005
- Neural network based multi-criterion optimization image reconstruction technique for imaging two- and three-phase flow systems using electrical capacitance tomographyMeasurement Science and Technology, 2001
- Neural Networks Tools for Improving Tacite Hydrodynamic Simulation of Multiphase Flow Behavior in PipelinesOil & Gas Science and Technology – Revue d’IFP Energies nouvelles, 2001
- The simulation and interpretation of free turbulence with a cognitive neural systemPhysics of Fluids, 2000