Towards Particle-Resolved Accuracy in Euler-Lagrange Simulations of Multiphase Flow Using Machine Learning and Pairwise Interaction Extended Point-particle (PIEP) Approximation

TL;DR

This paper develops machine learning models to accurately predict hydrodynamic forces on particles in multiphase flow, combining physics-based flow modeling with neural networks to improve over traditional methods.

Contribution

It introduces a hybrid approach that integrates physics-based flow predictions with machine learning to enhance particle force modeling in multiphase flow simulations.

Findings

Flow prediction using linear regression is effective for wake modeling.

ANN models tend to overfit due to limited training data.

Hybrid models improve force prediction accuracy significantly.

Abstract

This study presents two different machine learning approaches for the modeling of hydrodynamic force on particles in a particle-laden multiphase flow. Results from particle-resolved direct numerical simulations (PR-DNS) of flow over a random array of stationary particles for eight combinations of particle Reynolds number ($Re$) and volume fraction ($\phi$) are used in the development of the models. The first approach follows a two step process. In the first flow prediction step, the perturbation flow due to a particle is obtained as an axisymmetric superposable wake using linear regression. In the second force prediction step, the force on a particle is evaluated in terms of the perturbation flow induced by all its neighbors using the generalized Fax\'en form of the force expression. In the second approach, the force data on all the particles from the PR-DNS simulations is used to develop an artificial neural network (ANN) model for direct prediction of force on a particle. Due to the unavoidable limitation on the number of fully resolved particles in the PR-DNS simulations, direct force prediction with the ANN model tends to over-fit the data and performs poorly in the prediction of test data. In contrast, due to the millions of grid points used in the PR-DNS simulations, accurate flow prediction is possible, which then allows accurate prediction of particle force. This hybridization of multiphase physics and machine learning is particularly important, since it blends the strength of each, and the resulting pairwise interaction extended point-particle (PIEP) model cannot be developed by either physics or machine learning alone.