Remaining-capacity estimation of lithium-ion batteries using heatmap-based denoising autoencoder and vision transformer algorithm

Lithium-ion batteries, which are valued for their high energy density and reusability, gradually lose capacity as charge–discharge cycles accumulate. Remaining capacity—the usable charge expressed in ampere-hours—is a direct, real-time indicator of state of health (SOH) and is critical for safe, eff...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:JOURNAL OF POWER ELECTRONICS Jg. 25; H. 9; S. 1745 - 1760
Hauptverfasser: Jang, Yunseo, Park, Joung-Hu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Singapore Springer Nature Singapore 01.09.2025
Springer Nature B.V
전력전자학회
Schlagworte:
ISSN:1598-2092, 2093-4718
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Lithium-ion batteries, which are valued for their high energy density and reusability, gradually lose capacity as charge–discharge cycles accumulate. Remaining capacity—the usable charge expressed in ampere-hours—is a direct, real-time indicator of state of health (SOH) and is critical for safe, efficient battery management. We propose a deep learning framework that transforms multichannel time-series measurements into correlation heatmaps, which are then fed into a denoising autoencoder (DAE) to suppress sensor noise while preserving electrochemical patterns. These image-based representations are subsequently processed by a vision transformer (ViT) to estimate the remaining capacity. The ViT architecture captures complex spatial–temporal dependencies through self-attention mechanisms. Experiments on the NASA lithium-ion benchmark dataset show that the proposed heatmap-based DAE-ViT model achieves lower root mean square error and mean absolute error compared with recurrent neural networks, one-dimensional transformer encoders trained on DAE features, support vector regression, and XGBoost. To further validate the proposed model, we apply it to the CALCE CS2 dataset, where it also demonstrates robust performance under different degradation scenarios. Results demonstrate that image-based self-attention can deliver scalable, high-precision remaining-capacity estimation for lithium-ion battery management systems.
AbstractList Lithium-ion batteries, which are valued for their high energy density and reusability, gradually lose capacity as charge–discharge cycles accumulate. Remaining capacity—the usable charge expressed in ampere-hours—is a direct, real-time indicator of state of health (SOH) and is critical for safe, efficient battery management. We propose a deep learning framework that transforms multichannel time-series measurements into correlation heatmaps, which are then fed into a denoising autoencoder (DAE) to suppress sensor noise while preserving electrochemical patterns. These image-based representations are subsequently processed by a vision transformer (ViT) to estimate the remaining capacity. The ViT architecture captures complex spatial–temporal dependencies through self-attention mechanisms. Experiments on the NASA lithium-ion benchmark dataset show that the proposed heatmap-based DAE-ViT model achieves lower root mean square error and mean absolute error compared with recurrent neural networks, one-dimensional transformer encoders trained on DAE features, support vector regression, and XGBoost. To further validate the proposed model, we apply it to the CALCE CS2 dataset, where it also demonstrates robust performance under different degradation scenarios. Results demonstrate that image-based self-attention can deliver scalable, high-precision remaining-capacity estimation for lithium-ion battery management systems.
Lithium-ion batteries, which are valued for their high energy density and reusability, gradually lose capacity as charge–discharge cycles accumulate. Remaining capacity—the usable charge expressed in ampere-hours—is a direct, real-time indicator of state of health (SOH) and is critical for safe, efficient battery management. We propose a deep learning framework that transforms multichannel time-series measurements into correlation heatmaps, which are then fed into a denoising autoencoder (DAE) to suppress sensor noise while preserving electrochemical patterns. These image-based representations are subsequently processed by a vision transformer (ViT) to estimate the remaining capacity. The ViT architecture captures complex spatial–temporal dependencies through self-attention mechanisms. Experiments on the NASA lithium-ion benchmark dataset show that the proposed heatmap-based DAE-ViT model achieves lower root mean square error and mean absolute error compared with recurrent neural networks, one-dimensional transformer encoders trained on DAE features, support vector regression, and XGBoost. To further validate the proposed model, we apply it to the CALCE CS2 dataset, where it also demonstrates robust performance under different degradation scenarios. Results demonstrate that image-based selfattention can deliver scalable, high-precision remaining-capacity estimation for lithium-ion battery management systems. KCI Citation Count: 0
Author Jang, Yunseo
Park, Joung-Hu
Author_xml – sequence: 1
  givenname: Yunseo
  surname: Jang
  fullname: Jang, Yunseo
  organization: Department of Electrical Engineering, Soongsil University
– sequence: 2
  givenname: Joung-Hu
  orcidid: 0000-0002-5694-417X
  surname: Park
  fullname: Park, Joung-Hu
  email: wait4u@ssu.ac.kr
  organization: Department of Electrical Engineering, Soongsil University
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003244219$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNp9UU1r3DAUFCWFbtP8gZ4MvRXUPEleSz6G0I9AoBDSs3i25I2atbSV5JIc-8_7dl3oLRcNGmaGx8xbdhZT9Iy9F_BJAOjL0iqpOg5yy0EI1fKnV2wjoVe81cKcsY3Y9oYTId-wi1LCAC1IaQyYDftz52cMMcQdH_GAY6jPjS81zFhDik2amn2oD2GZ-fE7YK0-B1-apZClefBYZzzwAYt3jfMxhROPS00-jsn53GB0zW-iyV4zxjKlPB_p_S5lip7fsdcT7ou_-Ifn7MeXz_fX3_jt968311e3fFSgK-9x7ISGocVpawbdK9mL1gg3eDAK-lG73jhCQHoGp7XrtAM0nWu1l6JX5-zjmhvzZB_HYBOGE-6Sfcz26u7-xgrQ2w4UkPjDKj7k9GuhQuzPtORI91klO91qKlORSq6qMadSsp_sIVNz-ZmC7HEau05jaRp7msY-kUmtpkLiuPP5f_QLrr_AgpXD
Cites_doi 10.1016/j.energy.2024.131173
10.1109/TII.2019.2941747
10.1016/j.apenergy.2019.113626
10.1016/j.jpowsour.2017.03.042
10.1016/j.egypro.2017.03.583
10.1016/j.energy.2024.130790
10.1038/s41560-019-0356-8
10.3390/batteries8110229
10.1016/j.ress.2022.108821
10.1016/j.rser.2020.110015
10.1016/j.est.2025.115512
10.1109/ACCESS.2019.2905740
10.55981/j.mev.2024.905
10.1016/j.ress.2015.07.013
10.1016/j.est.2023.107322
10.3390/batteries11020058
10.1016/j.jpowsour.2013.03.158
10.1016/j.jpowsour.2010.12.102
10.1016/j.jpowsour.2021.230892
10.1016/j.rser.2019.109254
10.1016/j.rser.2023.114077
10.1016/j.dib.2022.107995
10.5194/gmd-7-1247-2014
10.1016/j.apenergy.2014.04.077
10.3390/app15073747
10.3390/en11092323
10.1016/j.rser.2015.11.042
10.1016/j.est.2024.113388
10.1038/s41467-023-38458-w
10.28945/4184
10.1007/s43236-022-00526-7
10.1016/j.microrel.2013.03.010
ContentType Journal Article
Copyright The Author(s) under exclusive licence to The Korean Institute of Power Electronics 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
The Author(s) under exclusive licence to The Korean Institute of Power Electronics 2025.
Copyright_xml – notice: The Author(s) under exclusive licence to The Korean Institute of Power Electronics 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
– notice: The Author(s) under exclusive licence to The Korean Institute of Power Electronics 2025.
DBID AAYXX
CITATION
ACYCR
DOI 10.1007/s43236-025-01134-x
DatabaseName CrossRef
Korean Citation Index
DatabaseTitle CrossRef
DatabaseTitleList


DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2093-4718
EndPage 1760
ExternalDocumentID oai_kci_go_kr_ARTI_10756030
10_1007_s43236_025_01134_x
GrantInformation_xml – fundername: Korea Society
  grantid: 2019R1A2C1084605
  funderid: http://dx.doi.org/10.13039/100005960
GroupedDBID 0R~
406
5GY
9ZL
AACDK
AAHNG
AAJBT
AASML
AATNV
AAYYP
ABAKF
ABBRH
ABDBE
ABECU
ABFSG
ABMQK
ABRTQ
ABTEG
ABTKH
ACAOD
ACDTI
ACHSB
ACOKC
ACPIV
ACSTC
ACZOJ
ADTPH
ADYFF
AEFQL
AEMSY
AENEX
AESKC
AEZWR
AFDZB
AFHIU
AGMZJ
AGQEE
AHPBZ
AHWEU
AIGIU
AILAN
AIXLP
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
AMXSW
ATHPR
AYFIA
BGNMA
DBRKI
DPUIP
EBLON
EBS
FIGPU
FNLPD
GW5
IKXTQ
IWAJR
JDI
JZLTJ
LLZTM
M4Y
MZR
NPVJJ
NQJWS
NU0
OK1
P2P
PT4
ROL
RSV
SJYHP
SNE
SNPRN
SOHCF
SOJ
SRMVM
SSLCW
TDB
UOJIU
UTJUX
ZMTXR
ZZE
AAYXX
CITATION
ACYCR
ID FETCH-LOGICAL-c307t-9ac6170b4af58b793291481dbe08309c7d98d09c0a09cbd77d67d0a86d47e2193
IEDL.DBID RSV
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001546919200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1598-2092
IngestDate Sun Sep 21 03:10:33 EDT 2025
Sun Nov 02 05:02:36 EST 2025
Sat Nov 29 07:33:21 EST 2025
Sat Sep 06 07:29:23 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 9
Keywords Lithium-ion battery
Vision transformer
Denoising autoencoder
Correlation heatmap
Battery dataset
Remaining capacity
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c307t-9ac6170b4af58b793291481dbe08309c7d98d09c0a09cbd77d67d0a86d47e2193
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
https://link.springer.com/article/10.1007/s43236-025-01134-x
ORCID 0000-0002-5694-417X
PQID 3267470923
PQPubID 7435055
PageCount 16
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_10756030
proquest_journals_3267470923
crossref_primary_10_1007_s43236_025_01134_x
springer_journals_10_1007_s43236_025_01134_x
PublicationCentury 2000
PublicationDate 20250900
2025-09-00
20250901
2025-09
PublicationDateYYYYMMDD 2025-09-01
PublicationDate_xml – month: 9
  year: 2025
  text: 20250900
PublicationDecade 2020
PublicationPlace Singapore
PublicationPlace_xml – name: Singapore
PublicationTitle JOURNAL OF POWER ELECTRONICS
PublicationTitleAbbrev J. Power Electron
PublicationYear 2025
Publisher Springer Nature Singapore
Springer Nature B.V
전력전자학회
Publisher_xml – name: Springer Nature Singapore
– name: Springer Nature B.V
– name: 전력전자학회
References Y Chen (1134_CR4) 2024; 99
X Cai (1134_CR13) 2025; 15
RR Richardson (1134_CR15) 2023; 14
N-T Pham (1134_CR2) 2022; 22
W Duan (1134_CR3) 2023; 65
Z Chen (1134_CR17) 2022; 521
Y Li (1134_CR25) 2019; 113
D Yang (1134_CR16) 2017; 105
J Peng (1134_CR10) 2022; 8
Z Chen (1134_CR21) 2013; 240
KA Severson (1134_CR24) 2019; 4
1134_CR8
Y Wang (1134_CR20) 2020; 131
C Hu (1134_CR29) 2014; 129
G Pozzato (1134_CR6) 2022; 41
X Feng (1134_CR18) 2018; 11
1134_CR9
RR Richardson (1134_CR26) 2024; 296
Y Zheng (1134_CR11) 2024; 536
AR Yuliani (1134_CR14) 2024; 15
L Zhou (1134_CR7) 2025; 108
Y Wang (1134_CR12) 2022; 228
A Botchkarev (1134_CR34) 2019; 14
T Chai (1134_CR33) 2014; 7
Y Liu (1134_CR27) 2019; 7
X Zheng (1134_CR28) 2015; 144
D Liu (1134_CR23) 2013; 53
N-T Pham (1134_CR1) 2025; 11
M Berecibar (1134_CR31) 2016; 56
G Ma (1134_CR22) 2019; 253
Y Zhang (1134_CR5) 2024
K Liu (1134_CR19) 2020; 16
D Andre (1134_CR30) 2011; 196
C Pastor-Fernández (1134_CR32) 2017; 360
References_xml – ident: 1134_CR8
– volume: 296
  start-page: 131173
  year: 2024
  ident: 1134_CR26
  publication-title: Energy
  doi: 10.1016/j.energy.2024.131173
– volume: 16
  start-page: 3767
  issue: 6
  year: 2020
  ident: 1134_CR19
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2019.2941747
– volume: 253
  start-page: 113626
  year: 2019
  ident: 1134_CR22
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2019.113626
– volume: 360
  start-page: 301
  year: 2017
  ident: 1134_CR32
  publication-title: J. Power. Sources
  doi: 10.1016/j.jpowsour.2017.03.042
– volume: 105
  start-page: 2059
  year: 2017
  ident: 1134_CR16
  publication-title: Energy Procedia
  doi: 10.1016/j.egypro.2017.03.583
– volume: 536
  start-page: 232215
  year: 2024
  ident: 1134_CR11
  publication-title: J. Power. Sources
  doi: 10.1016/j.energy.2024.130790
– volume: 4
  start-page: 383
  issue: 5
  year: 2019
  ident: 1134_CR24
  publication-title: Nat. Energy
  doi: 10.1038/s41560-019-0356-8
– volume: 8
  start-page: 229
  year: 2022
  ident: 1134_CR10
  publication-title: Batteries
  doi: 10.3390/batteries8110229
– volume: 228
  start-page: 108821
  year: 2022
  ident: 1134_CR12
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2022.108821
– volume: 131
  start-page: 110015
  year: 2020
  ident: 1134_CR20
  publication-title: Renew. Sustain. Energy Rev.
  doi: 10.1016/j.rser.2020.110015
– volume: 108
  start-page: 115512
  year: 2025
  ident: 1134_CR7
  publication-title: J. Energy Storage
  doi: 10.1016/j.est.2025.115512
– volume: 7
  start-page: 39474
  year: 2019
  ident: 1134_CR27
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2905740
– volume: 15
  start-page: 93
  year: 2024
  ident: 1134_CR14
  publication-title: Mechatron. Electr. Power Veh. Technol.
  doi: 10.55981/j.mev.2024.905
– volume: 144
  start-page: 74
  year: 2015
  ident: 1134_CR28
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2015.07.013
– volume: 65
  start-page: 107322
  year: 2023
  ident: 1134_CR3
  publication-title: J. Energy Storage
  doi: 10.1016/j.est.2023.107322
– volume: 11
  start-page: 58
  issue: 2
  year: 2025
  ident: 1134_CR1
  publication-title: Batteries
  doi: 10.3390/batteries11020058
– ident: 1134_CR9
– volume: 240
  start-page: 184
  year: 2013
  ident: 1134_CR21
  publication-title: J. Power. Sources
  doi: 10.1016/j.jpowsour.2013.03.158
– volume: 196
  start-page: 5334
  issue: 12
  year: 2011
  ident: 1134_CR30
  publication-title: J. Power. Sources
  doi: 10.1016/j.jpowsour.2010.12.102
– volume: 521
  start-page: 230892
  year: 2022
  ident: 1134_CR17
  publication-title: J. Power. Sources
  doi: 10.1016/j.jpowsour.2021.230892
– volume: 113
  start-page: 109254
  year: 2019
  ident: 1134_CR25
  publication-title: Renew. Sustain. Energy Rev.
  doi: 10.1016/j.rser.2019.109254
– year: 2024
  ident: 1134_CR5
  publication-title: Renew. Sustain. Energy Rev.
  doi: 10.1016/j.rser.2023.114077
– volume: 41
  start-page: 107995
  year: 2022
  ident: 1134_CR6
  publication-title: Data Brief
  doi: 10.1016/j.dib.2022.107995
– volume: 7
  start-page: 1247
  issue: 3
  year: 2014
  ident: 1134_CR33
  publication-title: Geosci. Model. Dev.
  doi: 10.5194/gmd-7-1247-2014
– volume: 129
  start-page: 49
  year: 2014
  ident: 1134_CR29
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2014.04.077
– volume: 15
  start-page: 3747
  year: 2025
  ident: 1134_CR13
  publication-title: Appl. Sci.
  doi: 10.3390/app15073747
– volume: 11
  start-page: 2323
  issue: 9
  year: 2018
  ident: 1134_CR18
  publication-title: Energies
  doi: 10.3390/en11092323
– volume: 56
  start-page: 572
  year: 2016
  ident: 1134_CR31
  publication-title: Renew. Sustain. Energy Rev.
  doi: 10.1016/j.rser.2015.11.042
– volume: 99
  start-page: 113388
  issue: Part B
  year: 2024
  ident: 1134_CR4
  publication-title: J. Energy Storage
  doi: 10.1016/j.est.2024.113388
– volume: 14
  start-page: 2665
  year: 2023
  ident: 1134_CR15
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-023-38458-w
– volume: 14
  start-page: 45
  year: 2019
  ident: 1134_CR34
  publication-title: Interdiscip. J. Info. Knowl. Manag.
  doi: 10.28945/4184
– volume: 22
  start-page: 2092
  year: 2022
  ident: 1134_CR2
  publication-title: J. Power Electron.
  doi: 10.1007/s43236-022-00526-7
– volume: 53
  start-page: 832
  issue: 6
  year: 2013
  ident: 1134_CR23
  publication-title: Microelectron. Reliab.
  doi: 10.1016/j.microrel.2013.03.010
SSID ssib040228808
ssj0003009991
Score 2.3504446
Snippet Lithium-ion batteries, which are valued for their high energy density and reusability, gradually lose capacity as charge–discharge cycles accumulate. Remaining...
SourceID nrf
proquest
crossref
springer
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 1745
SubjectTerms Aging
Back propagation
Batteries
Datasets
Deep learning
Electrical Machines and Networks
Engineering
Kalman filters
Lithium
Lithium-ion batteries
Machine learning
Maintenance costs
Noise reduction
Original Article
Parameter identification
Power Electronics
Power management
Real time
Recurrent neural networks
Support vector machines
전기공학
Title Remaining-capacity estimation of lithium-ion batteries using heatmap-based denoising autoencoder and vision transformer algorithm
URI https://link.springer.com/article/10.1007/s43236-025-01134-x
https://www.proquest.com/docview/3267470923
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003244219
Volume 25
WOSCitedRecordID wos001546919200001&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
ispartofPNX Journal of Power Electronics, 2025, 25(9), , pp.1745-1760
journalDatabaseRights – providerCode: PRVAVX
  databaseName: SpringerLink Journals
  customDbUrl:
  eissn: 2093-4718
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003009991
  issn: 1598-2092
  databaseCode: RSV
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8QwEA66etCDb3F1lYDeNLBtsm16FFEURMQX3kJeXVfdVrpd8eo_d5K2vtCDXhqatinNTGa-ITNfEdrRqsciiEuITg0ljKuQSGk1UVyqWAYmVNwXCp_GZ2f89jY5r4vCRk22e7Ml6S31e7EboyF1CbMu2SygjABynAJ3x91yvLi8abSIOUYXXjPW3HvM71GQJ05NnFokYV098_OwXzzUZFakX8Dnt_1S74aO5v_3AQtoroadeL_Sk0U0YbMlNPuJjHAZvV7YYfW7CKLBg2qA59hRcFS1jThPMSD2u8F4SNyp8rycEGZjlznfx86mD-UTcV7RYDBm-cD3y3GZO65MYwssM4OrWnZcNnjZdT_28wKGHq6g66PDq4NjUv-ggWgwDSVJpHZ87orJtMcVrPQwgegqMMoCsOsmOjYJN9B2JRyUiWMTxaYreWRYbMFU0lXUyvLMriEsUyVtQI2NIsV4z_I07FGZBioIUsssa6PdRijiqeLhEO-My35iBUys8BMrXtpoG-QmHvRAOPps1_Zz8VAICBJO4KEYcB7ttlGnkauoV-5IAJyFCAt0hLbRXiPHj8u_v3P9b7dvoJnQq4JLV-ugVlmM7Saa1s_lYFRseY1-A_yn8m4
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9wwEB1RQCo9lFKKui0US-VWLG1ib-Icq6oIxLKqKCBulr-y3dJNUDaLuPLPGTsJLQgO9BIrTuIonsnMG3nmGWDH6AFPMC6hJreMcqFjqpQzVAulUxXZWItQKDxMRyNxfp79aIvCZl22e7ckGSz1XbEbZzHzCbM-2SxinCJyXOLosXwi3_HPs06LuGd0ES1jze-A-QMKCsSpmVeLLG6rZx4f9p6HelFU-T3w-WC9NLihvdX_-4A38LqFneRroydrsOCKt_DqHzLCdbg5dtNmuwhq0IMahOfEU3A0tY2kzAki9l-T-ZT6Ux14OTHMJj5zfky8TZ-qS-q9oiVozMpJ6FfzuvRcmdZVRBWWNLXspO7wsu_-My4rHHr6Dk73vp9826ftBg3UoGmoaaaM53PXXOUDofFPjzOMriKrHQK7fmZSmwmLbV_hQds0tUlq-0oklqcOTSXbgMWiLNx7ICrXykXMuiTRXAycyOMBU3mkoyh33PEefOmEIi8bHg55x7gcJlbixMowsfK6B59RbvLCTKSnz_btuJQXlcQg4QAfShHnsX4PNju5yvbPnUmEsxhhoY6wHux2cvx7-el3fnje7dvwcv_kaCiHB6PDj7ASB7XwqWubsFhXc7cFy-aqnsyqT0G7bwFhKPVS
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagRYgeaIEiti1gCW5gdRN7E-dYASsqqlVVHurN8nO7LZus0mzVa_95Z5yktAgOiEusOImjeCYz38gznwl5a81IZBCXMBscZ0KalGntLTNSm1wnLjUyFgof5JOJPD4uDm9V8cds935Jsq1pQJamstlduLB7U_gmeMoxeRYTzxIuGKDIVYGbBmG8_vVHr1EC2V1kx15zGvF_RESRRLVAFSnSrpLmz8Pe8Vb3yzrcAaK_rZ1GlzRe__-P2SCPOzhK91r9eULu-fIpWbtFUviMXB35ebuNBLPgWS3AdorUHG3NI60CBSR_MlvOGZ6ayNcJ4TfFjPopRVs_1wuG3tJRMHLVLPbrZVMhh6bzNdWlo22NO216HI3dP6dVDUPPN8n38advHz6zbuMGZsFkNKzQFnnejdBhJA1YgLSAqCtxxgPgGxY2d4V00A41HIzLc5flbqhl5kTuwYTy52SlrEr_glAdjPYJdz7LjJAjL0M64jokJkmCF14MyLteQGrR8nOoGybmOLEKJlbFiVWXA_IGZKjO7EwhrTa200qd1QqCh314KAf8x4cDstPLWHV_9LkCmAuRF-gLH5D3vUx_Xf77O7f-7fbX5OHhx7E62J982SaP0qgVmNG2Q1aaeulfkgf2opmd16-iol8DnIP-Ng
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=Remaining-capacity+estimation+of+lithium-ion+batteries+using+heatmap-based+denoising+autoencoder+and+vision+transformer+algorithm&rft.jtitle=JOURNAL+OF+POWER+ELECTRONICS&rft.au=Jang%2C+Yunseo&rft.au=Park%2C+Joung-Hu&rft.date=2025-09-01&rft.pub=Springer+Nature+Singapore&rft.issn=1598-2092&rft.eissn=2093-4718&rft.volume=25&rft.issue=9&rft.spage=1745&rft.epage=1760&rft_id=info:doi/10.1007%2Fs43236-025-01134-x&rft.externalDocID=10_1007_s43236_025_01134_x
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1598-2092&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1598-2092&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1598-2092&client=summon