Future Trends in Optimal Design in Electromagnetics

In computational electromagnetics, there are manyfold advantages when using machine learning methods because no mathematical formulation is required to solve the direct problem for given input geometry. Moreover, due to the inherent bidirectionality of a convolutional neural network, it can be train...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on magnetics 2022-09, Vol.58 (9), p.1-4
Main Author: Di Barba, Paolo
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Computational electromagnetics
Computational modeling
Computing costs
Convolutional neural networks
Deep neural network (DNN)
generative adversarial network (GAN)
Generative adversarial networks
Geometry
Machine learning
Magnetism
magnetostatic field
optimal shape synthesis
Optimization
Probability density function
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In computational electromagnetics, there are manyfold advantages when using machine learning methods because no mathematical formulation is required to solve the direct problem for given input geometry. Moreover, due to the inherent bidirectionality of a convolutional neural network, it can be trained to identify the geometry giving rise to the prescribed output field. All this puts the ground for neural meta-modeling of fields, despite different levels of cost and accuracy. For the sake of an example, a surrogate model of the field in a small device is shown. In particular, a concept of multi-fidelity model makes it possible to control both prediction accuracy and computational cost. Moreover, TEAM Problem 35 is solved and it is shown how a generative adversarial network can help multiobjective optimal design.
ISSN:0018-9464
1941-0069
DOI:10.1109/TMAG.2022.3164204