Application of machine learning to viscoplastic flow modeling

TL;DR

This paper introduces a machine learning-based reduced-order modeling approach for viscoplastic duct flows, combining POD and neural networks to achieve fast and accurate approximations of flow solutions.

Contribution

It presents a novel integration of proper orthogonal decomposition and neural networks for efficient viscoplastic flow modeling.

Findings

The method achieves significant speed-up in solution evaluation.

The approximation maintains reasonable accuracy.

The approach is applicable to Bingham media flows.

Abstract

We present a method to construct reduced-order models for duct flows of Bingham media. Our method is based on proper orthogonal decomposition (POD) to find a low-dimensional approximation to the velocity and artificial neural network to approximate the coefficients of a given solution in the constructed POD basis. We use well-established augmented Lagrangian method and finite-element discretization in the "offline" stage. We show that the resulting approximation has a reasonable accuracy, but the evaluation of the approximate solution several orders of magnitude times faster.