Application of domain-adaptive convolutional variational autoencoder for stress-state prediction

Applying data-driven methods such as deep learning in material mechanics is challenging because producing a sufficiently large, labeled dataset is costly resource-wise. This paper outlines a new approach to overcoming this difficulty by transferring knowledge from a source domain of finite-element-a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Knowledge-based systems Jg. 248; S. 108827
Hauptverfasser:	Lee, Sang Min, Park, Sang-Youn, Choi, Byoung-Ho
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Amsterdam Elsevier B.V 19.07.2022 Elsevier Science Ltd
Schlagworte:	Aluminum base alloys Convolutional neural network Data Deep learning Domains Finite element method Four-point bending Imagery Knowledge management Labeling Mathematical models Mechanics (physics) Predictions Scarcity Stainless steels Stress analysis Unsupervised domain adaptation Variational autoencoder Deep learning Unsupervised domain adaptation Variational autoencoder Stress analysis Convolutional neural network Four-point bending
ISSN:	0950-7051, 1872-7409
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!