Finite-Element-based Methodology for Training Neural Network Surrogate Models
Comparison between FEM and predicted FE-PINN solutions for x-displacement, ux and y-displacement, uy.
The finite element method (FEM) has emerged as a powerful technique for modeling physical problems in various disciplines. Such models can be very accurate and fully interpretable, but usually have relatively larger computational...
Inventor(s): Ryan Sills
Category(s): Technology Classifications > Physical Sciences & Engineering, Technology Classifications > Software & Algorithms