Learning Unknown Physics of non-Newtonian Fluids

TL;DR

This paper extends physics-informed neural networks (PINNs) to learn viscosity models of non-Newtonian fluids like polymer melts and suspensions using velocity data, revealing new insights near zero shear rates.

Contribution

It introduces a PINN-based approach to infer viscosity models of non-Newtonian fluids solely from velocity measurements, addressing limitations of traditional models.

Findings

PINN-inferred viscosity models match empirical data at high shear rates.

Deviations occur near zero shear rates where traditional models have singularities.

PINNs can solve flow equations using learned viscosity models and boundary conditions.

Abstract

We extend the physics-informed neural network (PINN) method to learn viscosity models of two non-Newtonian systems (polymer melts and suspensions of particles) using only velocity measurements. The PINN-inferred viscosity models agree with the empirical models for shear rates with large absolute values but deviate for shear rates near zero where the analytical models have an unphysical singularity. Once a viscosity model is learned, we use the PINN method to solve the momentum conservation equation for non-Newtonian fluid flow using only the boundary conditions.