IDM-Net: A Multi-Task Supported Encoder-Decoder Framework for Magnetic Field Inverse Design

We propose an end-to-end framework for inversely designing permanent magnets named IDM-Net. It utilizes a fundamental encoder-decoder architecture to handle multiple tasks. In more detail, the encoder is responsible for deeply extracting features of the magnetic field and categorizing different type...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on applied superconductivity Ročník 34; číslo 8; s. 1 - 5
Hlavní autori: Wang, Jiaqi, Zhang, Qiankun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.11.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1051-8223, 1558-2515
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract We propose an end-to-end framework for inversely designing permanent magnets named IDM-Net. It utilizes a fundamental encoder-decoder architecture to handle multiple tasks. In more detail, the encoder is responsible for deeply extracting features of the magnetic field and categorizing different types of magnet shapes. The decoder focuses on inferring significant properties of each specific type of magnet shape, including size, position, and magnetization intensity. Such architecture breaks the critical limitation of designing only a single type of magnet in literature. Further, it allows for flexible choices of encoders' networks, such as convolutional neural networks (CNNs) or transformers, which are widely used in various computer vision tasks. Our experimental results demonstrate that the ResNet50-based and ViT-B/16-based IDM-Nets achieve accuracies of 93.8% and 91.4% in magnet shapes classification and errors of 0.31% and 0.33% in predicting magnetic properties, respectively.
AbstractList We propose an end-to-end framework for inversely designing permanent magnets named IDM-Net. It utilizes a fundamental encoder-decoder architecture to handle multiple tasks. In more detail, the encoder is responsible for deeply extracting features of the magnetic field and categorizing different types of magnet shapes. The decoder focuses on inferring significant properties of each specific type of magnet shape, including size, position, and magnetization intensity. Such architecture breaks the critical limitation of designing only a single type of magnet in literature. Further, it allows for flexible choices of encoders' networks, such as convolutional neural networks (CNNs) or transformers, which are widely used in various computer vision tasks. Our experimental results demonstrate that the ResNet50-based and ViT-B/16-based IDM-Nets achieve accuracies of 93.8% and 91.4% in magnet shapes classification and errors of 0.31% and 0.33% in predicting magnetic properties, respectively.
Author Wang, Jiaqi
Zhang, Qiankun
Author_xml – sequence: 1
  givenname: Jiaqi
  orcidid: 0009-0002-9836-2933
  surname: Wang
  fullname: Wang, Jiaqi
  email: jiaqiqaq@hust.edu.cn
  organization: School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
– sequence: 2
  givenname: Qiankun
  orcidid: 0000-0002-8034-2689
  surname: Zhang
  fullname: Zhang, Qiankun
  email: qiankun@hust.edu.cn
  organization: School of Cyber Science and Engineering, Huazhong University of Science and Technology, Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, Wuhan, China
BookMark eNpNkMtOwzAQRS1UJNrCByCxsMTaxc_EYVf1AZVaWLSsWFhJPKnSRxzsBMTfk1IWrO5odO6MdAaoV7kKELpldMQYTR424_VkxCmXIyEjJWJ9gfpMKU24YqrXzVQxojkXV2gQwo5SJrVUffS-mK7ICzSPeIxX7aEpySYNe7xu69r5BiyeVbmz4MkUfhPPfXqEL-f3uHAer9JtBU2Z43kJB4sX1Sf4AHgKodxW1-iySA8Bbv5yiN7ms83kmSxfnxaT8ZLkXEYNAaFzlqUxg5hlXORWSMVkllguNdWZsppGtttynhTKJrbQqRBcFIWKIqsjJobo_ny39u6jhdCYnWt91b00gjGe8CSWqqPYmcq9C8FDYWpfHlP_bRg1J4fm5NCcHJo_h13n7twpAeAfH3XuEiV-ALy6bbI
CODEN ITASE9
Cites_doi 10.48550/arXiv.2010.11929
10.1109/APCAP56600.2022.10069102
10.1016/j.asoc.2018.10.054
10.1109/CVPR.2016.90
10.1109/ICCV48922.2021.00041
10.1109/TMAG.2017.2658027
10.1177/0309524X20949526
10.4324/9781410605337-29
10.1109/ICCV48922.2021.00986
10.1109/ACCESS.2022.3206368
10.1038/s41598-018-37952-2
10.3390/en14154642
10.1016/j.patrec.2019.11.020
10.1109/ICCV48922.2021.00061
10.1063/9.0000076
10.1109/TPAMI.2017.2699184
10.1038/s41598-021-04246-z
10.1109/TMAG.2021.3082431
10.1002/aisy.201900110
10.1109/TPAMI.2016.2644615
10.1109/CVPR.2016.308
10.1109/CVPR.2017.243
10.1007/978-3-319-05549-7
10.1109/TMAG.2019.2899304
10.1103/PhysRevApplied.14.054004
10.1126/science.aat2663
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/TASC.2024.3465378
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Solid State and Superconductivity Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1558-2515
EndPage 5
ExternalDocumentID 10_1109_TASC_2024_3465378
10684595
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Hubei Province
  grantid: 2023AFB258
  funderid: 10.13039/501100003819
– fundername: Ministry of Education
  grantid: KLCS20240401
  funderid: 10.13039/100010449
– fundername: Open Foundation of Key Laboratory of Cyberspace Security
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
DU5
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PZZ
RIA
RIE
RNS
TN5
VH1
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c246t-e38c1ba71e71b23cd34514b9d24808b5d806dcd3229f5d9df8a3323ff566d8613
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001329038100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1051-8223
IngestDate Mon Jun 30 10:22:20 EDT 2025
Sat Nov 29 06:16:27 EST 2025
Wed Aug 27 02:18:43 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c246t-e38c1ba71e71b23cd34514b9d24808b5d806dcd3229f5d9df8a3323ff566d8613
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8034-2689
0009-0002-9836-2933
PQID 3112929745
PQPubID 85434
PageCount 5
ParticipantIDs proquest_journals_3112929745
crossref_primary_10_1109_TASC_2024_3465378
ieee_primary_10684595
PublicationCentury 2000
PublicationDate 2024-11-01
PublicationDateYYYYMMDD 2024-11-01
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-11-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on applied superconductivity
PublicationTitleAbbrev TASC
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
ref30
ref11
ref10
ref2
ref1
ref16
ref19
ref18
Simonyan (ref29) 2015
ref24
ref23
ref26
ref20
Tashli (ref17) 2022
ref22
ref21
Touvron (ref25) 2021
ref28
ref27
ref8
ref7
ref9
ref4
ref6
ref5
Chaudhary (ref3) 2015; 3
References_xml – volume: 3
  start-page: 63
  issue: 3
  year: 2015
  ident: ref3
  article-title: A perspective on the future of the magnetic hard disk drive (HDD) technology
  publication-title: Int. J. Tech. Res. Appl.
– ident: ref28
  doi: 10.48550/arXiv.2010.11929
– ident: ref19
  doi: 10.1109/APCAP56600.2022.10069102
– ident: ref8
  doi: 10.1016/j.asoc.2018.10.054
– ident: ref27
  doi: 10.1109/CVPR.2016.90
– ident: ref26
  doi: 10.1109/ICCV48922.2021.00041
– ident: ref9
  doi: 10.1109/TMAG.2017.2658027
– ident: ref1
  doi: 10.1177/0309524X20949526
– ident: ref20
  doi: 10.4324/9781410605337-29
– ident: ref23
  doi: 10.1109/ICCV48922.2021.00986
– ident: ref10
  doi: 10.1109/ACCESS.2022.3206368
– start-page: 1
  volume-title: Proc. 3rd Int. Conf. Learn. Representations
  year: 2015
  ident: ref29
  article-title: Very deep convolutional networks for large-scale image recognition
– ident: ref14
  doi: 10.1038/s41598-018-37952-2
– ident: ref7
  doi: 10.3390/en14154642
– start-page: 10347
  volume-title: Proc. Int. Conf. Mach. Learn.
  year: 2021
  ident: ref25
  article-title: Training data-efficient image transformers & distillation through attention
– ident: ref5
  doi: 10.1016/j.patrec.2019.11.020
– ident: ref24
  doi: 10.1109/ICCV48922.2021.00061
– start-page: 202
  year: 2022
  ident: ref17
  article-title: Prediction of electric fields induced by transcranial magnetic stimulation in the brain using a deep encoder-decoder convolutional neural network
  publication-title: bioRxiv
– ident: ref2
  doi: 10.1063/9.0000076
– ident: ref22
  doi: 10.1109/TPAMI.2017.2699184
– ident: ref11
  doi: 10.1038/s41598-021-04246-z
– ident: ref15
  doi: 10.1109/TMAG.2021.3082431
– ident: ref4
  doi: 10.1002/aisy.201900110
– ident: ref16
  doi: 10.1109/TPAMI.2016.2644615
– ident: ref30
  doi: 10.1109/CVPR.2016.308
– ident: ref21
  doi: 10.1109/CVPR.2017.243
– ident: ref6
  doi: 10.1007/978-3-319-05549-7
– ident: ref18
  doi: 10.1109/TMAG.2019.2899304
– ident: ref12
  doi: 10.1103/PhysRevApplied.14.054004
– ident: ref13
  doi: 10.1126/science.aat2663
SSID ssj0014845
Score 2.398191
Snippet We propose an end-to-end framework for inversely designing permanent magnets named IDM-Net. It utilizes a fundamental encoder-decoder architecture to handle...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Artificial neural networks
Computer vision
Decoding
Deep learning
design optimization
encoder-decoder
Encoders-Decoders
Inverse design
Magnetic confinement
magnetic field
Magnetic fields
Magnetic properties
Magnetic resonance imaging
Magnetosphere
Permanent magnets
Shape
Superconducting magnets
Title IDM-Net: A Multi-Task Supported Encoder-Decoder Framework for Magnetic Field Inverse Design
URI https://ieeexplore.ieee.org/document/10684595
https://www.proquest.com/docview/3112929745
Volume 34
WOSCitedRecordID wos001329038100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2515
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014845
  issn: 1051-8223
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB50UdCDj1VxdZUcPAnRNknT1NuyDxTcRXAVwUNpk1REqLJd_f1m0q4siAcvbSl9kWk633S-bwbgLIhsIaRWVGouqeCBpi4OyWiBvj93Qa71vQ4fb-PJRD09JXeNWN1rYay1nnxmL3DT5_LNu_7EX2VuhksloiRahdU4lrVY6ydlIJTvSOzwQuhux3iTwgyD5HLau--7UJCJC47lxLCl2pIT8l1Vfn2KvX8Zbf_zyXZgqwGSpFdbfhdWbNmGzaXygm1Y9_ROXe3B881gTCd2fkV6xEtu6TSr3gi29ESyrSHDErXtMzqwfk1GC84WcaCWjLOXEsWOZIR8N4K1OWaVJQPP_tiHh9Fw2r-mTVsFqpmQc2q50mGexaGNw5xxbbhwqClPDBMqUHlkVCCN28tYUkQmMYXKOGe8KBzyM8q5_wNole-lPQSCaVnGtJYOl4giZ1niIQd3y9zIKOzA-WKc04-6ekbqo44gSdEoKRolbYzSgX0c2KUD6zHtQHdhmrSZYFXKEScyFwxFR3-cdgwbePVaN9iF1nz2aU9gTX_NX6vZqX93vgHV0r5j
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED50KuqDv8Xp1Dz4JETbJO1S34ZbUdyG4BTBh9ImqYhQZd38-82lnQzEB1_aUlpS7prmu9599wGceYHJRagkDRUPqeCeojYOSWmOa39mg1zjtA6f-u3hUD4_R_c1Wd1xYYwxrvjMXOChy-XrDzXFX2V2hodSBFGwCEsonVXTtX6SBkI6TWKLGHw7ION1EtP3ostR5-HaBoNMXHBsKIaianPLkNNV-fUxditMvPnPZ9uCjRpKkk7l-21YMMUOrM81GNyBFVfgqcpdeLntDujQTK5IhzjSLR2l5TtBUU8st9WkVyC7fUy7xu1JPKvaIhbWkkH6WiDdkcRY8UawO8e4NKTr6j_24DHuja5vaC2sQBUT4YQaLpWfpW3ftP2McaW5sLgpizQT0pNZoKUXanuWsSgPdKRzmXLOeJ5b7KelBQD70Cg-CnMABBOzjCkVWmQi8oylkQMd3G4zHQZ-E85ndk4-q_4ZiYs7vChBpyTolKR2ShP20LBzF1Y2bUJr5pqknmJlwhEpMhsOBYd_3HYKqzejQT_p3w7vjmANR6pYhC1oTMZTcwzL6mvyVo5P3Hv0DfE1waw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=IDM-Net%3A+A+Multi-Task+Supported+Encoder-Decoder+Framework+for+Magnetic+Field+Inverse+Design&rft.jtitle=IEEE+transactions+on+applied+superconductivity&rft.au=Wang%2C+Jiaqi&rft.au=Zhang%2C+Qiankun&rft.date=2024-11-01&rft.pub=IEEE&rft.issn=1051-8223&rft.volume=34&rft.issue=8&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FTASC.2024.3465378&rft.externalDocID=10684595
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8223&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8223&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8223&client=summon