Convolution-Based Model-Solving Method for Three-Dimensional, Unsteady, Partial Differential Equations

Neural networks are increasingly used widely in the solution of partial differential equations (PDEs). This letter proposes 3D-PDE-Net to solve the three-dimensional PDE. We give a mathematical derivation of a three-dimensional convolution kernel that can approximate any order differential operator...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural computation 2022-01, Vol.34 (2), p.518-540
Hauptverfasser:	Zha, Wenshu, Zhang, Wen, Li, Daolun, Xing, Yan, He, Lei, Tan, Jieqing
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Convolution Neural networks Operators (mathematics) Partial differential equations Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!