The authors explore the possibility of simulating the grade-two fluid model in a geometry related to a contraction rheometer, and provide details on several key aspects of the computation. They show how the results can be used to determine the viscosity ν from experimental data, and explore the identifiability of the grade-two parameters α1 and α2 from experimental data.
The core message of this paper is to design a helicity-conservative physics-informed neural network (PINN) model for solving the incompressible Navier-Stokes equations, which can exactly preserve the fluid helicity without any discretization error.