A variational-energy PINN with exact BC enforcement via output modification and transfer learning solves phase-field fracture problems on four test cases with higher accuracy than residual-based PINNs.
Deep hidden physics models: Deep learning of nonlinear partial differential equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Transfer learning enhanced physics informed neural network for phase-field modeling of fracture
A variational-energy PINN with exact BC enforcement via output modification and transfer learning solves phase-field fracture problems on four test cases with higher accuracy than residual-based PINNs.