Magnetic Properties Identification by Using a Bi-Objective Optimal Multi-Fidelity Neural Network

In order to identify the magnetic properties of magnetic steel, the synergy between the data arising from the experimental activity, an FE model, and the use of a multi-fidelity surrogate could relieve the burden of the total cost. A neural network, with as many outputs as fidelity levels, is adopte...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on magnetics 2021-06, Vol.57 (6), p.1-4
Main Authors: Baldan, Marco, Barba, Paolo Di, Nacke, Bernard
Format: Article
Language:English
Subjects:
Accuracy
Bi-objective optimality
Conjugates
Forward problem
Hafnium
inverse problem
magnetic permeability
Magnetic properties
Magnetism
Metamodels
multi-fidelity
neural network
Neural networks
Optimization
Permeability
Temperature dependence
Training
Windings
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 order to identify the magnetic properties of magnetic steel, the synergy between the data arising from the experimental activity, an FE model, and the use of a multi-fidelity surrogate could relieve the burden of the total cost. A neural network, with as many outputs as fidelity levels, is adopted in quality of metamodel to describe the forward problem [forward neural network (FNN)]. FNN is trained using multiple losses aiming at getting a robust surrogate that is poorly sensitive to the chosen norm. This makes it bi-objective optimal since several error metrics are simultaneously minimized. In addition, a conjugate, inverse net (INN CJ ) is built, which is a ready-to-use tool for inverse properties identification, since no optimization runs are required. Its performances are compared to those obtained with a transfer learning-based approach (INN TR ) and a single-fidelity inverse neural network (INN SF ). Finally, a real B - H curve identification task has been solved, thereby validating the conjugate inverse net.
ISSN:0018-9464
1941-0069
DOI:10.1109/TMAG.2021.3068705