Preprint
Aug 2026
Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains
Finite basis PINNs (FBPINNs), which are based on domain decomposition and localisation principles, are used together with hard boundary constraints that efficiently encode perforation-related boundary conditions, thereby providing an efficient and highly parallelisable neural network framework.
Jeeeun Lee, Denis Korolev, M. Duhovic et al.
· 0 citations