Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems

We propose a conservative physics-informed neural network (cPINN) on discrete domains for nonlinear conservation laws. Here, the term discrete domain represents the discrete sub-domains obtained after division of the computational domain, where PINN is applied and the conservation property of cPINN...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Computer methods in applied mechanics and engineering Ročník 365; číslo C; s. 113028
Hlavní autori:	Jagtap, Ameya D., Kharazmi, Ehsan, Karniadakis, George Em
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Amsterdam Elsevier B.V 15.06.2020 Elsevier BV Elsevier
Predmet:	Activation Algorithms Artificial neural networks Compressibility Computational fluid dynamics Conservation laws cPINN Domain decomposition Euler-Lagrange equation Fluxes Inverse problems Machine learning Mortar PINN Neural networks Optimization Parallel processing Training Conservation laws Inverse problems cPINN Mortar PINN Domain decomposition Machine learning
ISSN:	0045-7825, 1879-2138
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!