Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons

The development of innovative materials, based on the modern technologies and processes, is the key factor to improve the energetic sustainability and reduce the environmental impact of electrical equipment. In particular, the modeling of magnetic hysteresis is crucial for the design and constructio...

Full description

Saved in:
Bibliographic Details
Main Authors: Silvia Licciardi, Guido Ala, Elisa Francomano, Fabio Viola, Michele Lo Giudice, Alessandro Salvini, Fausto Sargeni, Vittorio Bertolini, Andrea Di Schino, Antonio Faba
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/21/3363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173318738083840
author Silvia Licciardi
Guido Ala
Elisa Francomano
Fabio Viola
Michele Lo Giudice
Alessandro Salvini
Fausto Sargeni
Vittorio Bertolini
Andrea Di Schino
Antonio Faba
author_facet Silvia Licciardi
Guido Ala
Elisa Francomano
Fabio Viola
Michele Lo Giudice
Alessandro Salvini
Fausto Sargeni
Vittorio Bertolini
Andrea Di Schino
Antonio Faba
author_sort Silvia Licciardi
collection DOAJ
description The development of innovative materials, based on the modern technologies and processes, is the key factor to improve the energetic sustainability and reduce the environmental impact of electrical equipment. In particular, the modeling of magnetic hysteresis is crucial for the design and construction of electrical and electronic devices. In recent years, additive manufacturing techniques are playing a decisive role in the project and production of magnetic elements and circuits for applications in various engineering fields. To this aim, the use of the deep learning paradigm, integrated with the most common models of the magnetic hysteresis process, has become increasingly present in recent years. The intent of this paper is to provide the features of a wide range of deep learning tools to be applied to magnetic hysteresis context and beyond. The possibilities of building neural networks in hybrid form are innumerable, so it is not plausible to illustrate them in a single paper, but in the present context, several neural networks used in the scientific literature, integrated with various hysteretic mathematical models, including the well-known Preisach model, are compared. It is shown that this hybrid approach not only improves the modeling of hysteresis by significantly reducing computational time and efforts, but also offers new perspectives for the analysis and prediction of the behavior of magnetic materials, with significant implications for the production of advanced devices.
format Article
id doaj-art-719b66f0344242f39b866e811da45ac9
institution Kabale University
issn 2227-7390
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-719b66f0344242f39b866e811da45ac92024-11-08T14:37:39ZengMDPI AGMathematics2227-73902024-10-011221336310.3390/math12213363Neural Network Architectures and Magnetic Hysteresis: Overview and ComparisonsSilvia Licciardi0Guido Ala1Elisa Francomano2Fabio Viola3Michele Lo Giudice4Alessandro Salvini5Fausto Sargeni6Vittorio Bertolini7Andrea Di Schino8Antonio Faba9Department of Electrical Engineering, University of Palermo, Viale delle Scienze, 90128 Palermo, ItalyDepartment of Electrical Engineering, University of Palermo, Viale delle Scienze, 90128 Palermo, ItalyDepartment of Electrical Engineering, University of Palermo, Viale delle Scienze, 90128 Palermo, ItalyDepartment of Electrical Engineering, University of Palermo, Viale delle Scienze, 90128 Palermo, ItalyDepartment of Civil, Computer Science and Aeronautical Technologies Engineering, University of Rome Tre, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Civil, Computer Science and Aeronautical Technologies Engineering, University of Rome Tre, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Electronic Engineering, University of Rome Tor Vergata, Via del Politecnico 1, 00133 Rome, ItalyDepartment of Engineering, University of Perugia, Via G. Duranti 93, 06123 Perugia, ItalyDepartment of Engineering, University of Perugia, Via G. Duranti 93, 06123 Perugia, ItalyDepartment of Engineering, University of Perugia, Via G. Duranti 93, 06123 Perugia, ItalyThe development of innovative materials, based on the modern technologies and processes, is the key factor to improve the energetic sustainability and reduce the environmental impact of electrical equipment. In particular, the modeling of magnetic hysteresis is crucial for the design and construction of electrical and electronic devices. In recent years, additive manufacturing techniques are playing a decisive role in the project and production of magnetic elements and circuits for applications in various engineering fields. To this aim, the use of the deep learning paradigm, integrated with the most common models of the magnetic hysteresis process, has become increasingly present in recent years. The intent of this paper is to provide the features of a wide range of deep learning tools to be applied to magnetic hysteresis context and beyond. The possibilities of building neural networks in hybrid form are innumerable, so it is not plausible to illustrate them in a single paper, but in the present context, several neural networks used in the scientific literature, integrated with various hysteretic mathematical models, including the well-known Preisach model, are compared. It is shown that this hybrid approach not only improves the modeling of hysteresis by significantly reducing computational time and efforts, but also offers new perspectives for the analysis and prediction of the behavior of magnetic materials, with significant implications for the production of advanced devices.https://www.mdpi.com/2227-7390/12/21/3363deep learningLSTM architectureshybrid neural networks architecturesmagnetic hysteresisPreisach modelnumerical methods
spellingShingle Silvia Licciardi
Guido Ala
Elisa Francomano
Fabio Viola
Michele Lo Giudice
Alessandro Salvini
Fausto Sargeni
Vittorio Bertolini
Andrea Di Schino
Antonio Faba
Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
Mathematics
deep learning
LSTM architectures
hybrid neural networks architectures
magnetic hysteresis
Preisach model
numerical methods
title Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
title_full Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
title_fullStr Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
title_full_unstemmed Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
title_short Neural Network Architectures and Magnetic Hysteresis: Overview and Comparisons
title_sort neural network architectures and magnetic hysteresis overview and comparisons
topic deep learning
LSTM architectures
hybrid neural networks architectures
magnetic hysteresis
Preisach model
numerical methods
url https://www.mdpi.com/2227-7390/12/21/3363
work_keys_str_mv AT silvialicciardi neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT guidoala neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT elisafrancomano neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT fabioviola neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT michelelogiudice neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT alessandrosalvini neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT faustosargeni neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT vittoriobertolini neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT andreadischino neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons
AT antoniofaba neuralnetworkarchitecturesandmagnetichysteresisoverviewandcomparisons