Material Design with Topology Optimization Based on the Neural Network
Abstract
This paper describes a neural network (NN)-based topology optimization approach for designing microstructures. The design variables are the NN weights and biases used to describe the density field, which is independent of element meshes. The number of design variables and gray elements is reduced substantially, and no filtering is necessary. Three numerical examples are provided to demonstrate the efficacy of the proposed method, namely, maximum shear modulus, maximum bulk modulus, and negative Poisson's ratio.
Details
- Organisationseinheit(en)
-
Institut für Photonik
- Externe Organisation(en)
-
Tongji University
- Typ
- Artikel
- Journal
- International Journal of Computational Methods
- Band
- 19
- Anzahl der Seiten
- 15
- ISSN
- 0219-8762
- Publikationsdatum
- 01.10.2022
- Publikationsstatus
- Veröffentlicht
- Peer-reviewed
- Ja
- ASJC Scopus Sachgebiete
- Informatik (sonstige), Computational Mathematics
- Elektronische Version(en)
-
https://doi.org/10.1142/S0219876221420135 (Zugang:
Geschlossen
)
Zitieren
Laden...
