Deep learning methods for predicting fluid forces in dense particle suspensions

Neil Raj Ashwin, Ze Cao, Nikhil Muralidhar, Danesh Tafti, Anuj Karpatne

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

Two deep learning methods, Multi-Layer Perceptron (MLP) network and Convolution Neural Network (CNN) are evaluated to predict drag forces in dense suspensions of ellipsoidal particles using data from Particle Resolved Simulations (PRS). The MLP is trained on the mean flow Reynolds number, solid fraction of the suspension, the aspect ratio of the particle, and orientation to flow direction. The CNN is given an additional 3D spatial map of the particle of interest and its immediate neighborhood via a distance function. The prediction capability of the trained networks is tested at different levels of complexity: on an unseen particle arrangement (Level 1), to all arrangements of an unseen numerical experiment (Level 2), and finally to all experiments of an unseen Reynolds number, solid fraction or aspect ratio (Level 3). The CNN is shown to perform better than the MLP for all testing levels except when testing on an unseen aspect ratio.

Original languageEnglish
Article number117303
JournalPowder Technology
Volume401
DOIs
StatePublished - Mar 2022

Keywords

  • Convolution neural network (CNN)
  • Drag force
  • Ellipsoidal particle suspension
  • Machine learning
  • Multi-layer perceptron (MLP)

Fingerprint

Dive into the research topics of 'Deep learning methods for predicting fluid forces in dense particle suspensions'. Together they form a unique fingerprint.

Cite this