Autoencoder Based Optimization for Electromagnetics Problems

In this work a novel approach is presented for topology optimization of electromagnetic devices. In particular a surrogate model based on Deep Neural Networks with encoder-decoder architecture is introduced. A first autoencoder learns to represent the input images that describe the topology, i.e., g...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied Computational Electromagnetics Society journal Jg. 34; H. 12; S. 1875
Hauptverfasser: Barmada, S, Fontana, N, Thomopulos, D, Tucci, M
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Pisa River Publishers 2019
Schlagworte:
Algorithms
Artificial neural networks
Encoders-Decoders
Network topologies
Neural networks
Numerical analysis
Optimization
Topology optimization
ISSN:1054-4887, 1943-5711
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this work a novel approach is presented for topology optimization of electromagnetic devices. In particular a surrogate model based on Deep Neural Networks with encoder-decoder architecture is introduced. A first autoencoder learns to represent the input images that describe the topology, i.e., geometry and materials. The novel idea is to use the low dimensional latent space (i.e., the output space of the encoder) as the search space of the optimization algorithm, instead of using the higher dimensional space represented by the input images. A second neural network learns the relationship between the encoder outputs and the objective function (i.e., an electromagnetic quantity that is crucial for the design of the device) which is calculated by means of a numerical analysis. The calculation time for the optimization is greatly improved by reducing the dimensionality of the search space, and by introducing the surrogate model, whereas the quality of the result is slightly affected.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1054-4887
1943-5711