Learning Unknown Physics of non-Newtonian Fluids
This work addresses the challenge of modeling complex fluid behaviors for applications in materials science and engineering, representing an incremental extension of PINNs to non-Newtonian systems.
The authors tackled the problem of learning viscosity models for non-Newtonian fluids using physics-informed neural networks (PINNs) from velocity measurements, achieving agreement with empirical models for high shear rates but identifying deviations near zero shear rates due to singularities in analytical models.
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.