In EDS ansehen

Active-learning-driven error control for data-driven state of charge estimation across the lithium battery lifecycle

Gespeichert in:
Bibliographische Detailangaben
Titel: Active-learning-driven error control for data-driven state of charge estimation across the lithium battery lifecycle
Autoren: Xue, Jinwei, Du, Xuzhi, Zhao, Lei, Yang, Zhigang, Xia, Chao, 1988, Ma, Yuan, Hoque, Muhammad Jahidul, Fu, Wuchen, Yan, Xiao, Miljkovic, N.
Quelle: Energy and AI. 21
Schlagwörter: Deep learning, Battery aging, State of charge (SOC), Closed-loop correction, data-driven SOC estimation, Active learning, Lithium-ion battery
Beschreibung: Accurate estimation of lithium-ion battery state of charge (SOC) is crucial for the safe and efficient operation of electric vehicles (EVs). However, both data-driven and model-driven SOC estimation methods face significant challenges under battery aging, which alters internal resistance and electrochemical properties, especially across complex aging trajectories. Most existing deep learning and model-based approaches operate in an open-loop manner, lacking mechanisms for uncertainty quantification, accuracy prediction, or adaptive correction—leading to uncontrolled estimation errors during aging. To address this, we propose an innovative closed-loop SOC estimation framework that integrates active learning with uncertainty-aware correction into deep learning networks, enabling real-time feedback on SOC prediction confidence levels without the need for additional sensors or reference data. Specifically, we quantify the performance degradation of mainstream data-driven methods, including long short-term memory (LSTM) networks and Gaussian process regression (GPR), under complex aging paths. We demonstrate that our model-disagreement-based active learning correction strategy maintains robustness throughout the battery lifecycle. Experimental results show that with only four active retraining sessions over the full aging process, our method reduces average SOC estimation error to below 1.5 %, and maximum cycle-based average error to below 2 %. This work establishes a path toward uncertainty-informed, lifecycle-resilient, and data-efficient SOC estimation, marking a significant advancement in battery management systems for real-world EV applications.
Dateibeschreibung: electronic
Zugangs-URL: https://research.chalmers.se/publication/547533
https://research.chalmers.se/publication/547533/file/547533_Fulltext.pdf
Datenbank: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/547533#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=26665468&ISBN=&volume=21&issue=&date=20250101&spage=&pages=&title=Energy and AI&atitle=Active-learning-driven%20error%20control%20for%20data-driven%20state%20of%20charge%20estimation%20across%20the%20lithium%20battery%20lifecycle&aulast=Xue%2C%20Jinwei&id=DOI:10.1016/j.egyai.2025.100549
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Xue%20J
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.5db74641.8b47.4389.af87.234834220f86
RelevancyScore: 1065
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1064.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Active-learning-driven error control for data-driven state of charge estimation across the lithium battery lifecycle
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xue%2C+Jinwei%22">Xue, Jinwei</searchLink><br /><searchLink fieldCode="AR" term="%22Du%2C+Xuzhi%22">Du, Xuzhi</searchLink><br /><searchLink fieldCode="AR" term="%22Zhao%2C+Lei%22">Zhao, Lei</searchLink><br /><searchLink fieldCode="AR" term="%22Yang%2C+Zhigang%22">Yang, Zhigang</searchLink><br /><searchLink fieldCode="AR" term="%22Xia%2C+Chao%22">Xia, Chao</searchLink>, 1988<br /><searchLink fieldCode="AR" term="%22Ma%2C+Yuan%22">Ma, Yuan</searchLink><br /><searchLink fieldCode="AR" term="%22Hoque%2C+Muhammad+Jahidul%22">Hoque, Muhammad Jahidul</searchLink><br /><searchLink fieldCode="AR" term="%22Fu%2C+Wuchen%22">Fu, Wuchen</searchLink><br /><searchLink fieldCode="AR" term="%22Yan%2C+Xiao%22">Yan, Xiao</searchLink><br /><searchLink fieldCode="AR" term="%22Miljkovic%2C+N%2E%22">Miljkovic, N.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Energy and AI</i>. 21
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Battery+aging%22">Battery aging</searchLink><br /><searchLink fieldCode="DE" term="%22State+of+charge+%28SOC%29%22">State of charge (SOC)</searchLink><br /><searchLink fieldCode="DE" term="%22Closed-loop+correction%22">Closed-loop correction</searchLink><br /><searchLink fieldCode="DE" term="%22data-driven+SOC+estimation%22">data-driven SOC estimation</searchLink><br /><searchLink fieldCode="DE" term="%22Active+learning%22">Active learning</searchLink><br /><searchLink fieldCode="DE" term="%22Lithium-ion+battery%22">Lithium-ion battery</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Accurate estimation of lithium-ion battery state of charge (SOC) is crucial for the safe and efficient operation of electric vehicles (EVs). However, both data-driven and model-driven SOC estimation methods face significant challenges under battery aging, which alters internal resistance and electrochemical properties, especially across complex aging trajectories. Most existing deep learning and model-based approaches operate in an open-loop manner, lacking mechanisms for uncertainty quantification, accuracy prediction, or adaptive correction—leading to uncontrolled estimation errors during aging. To address this, we propose an innovative closed-loop SOC estimation framework that integrates active learning with uncertainty-aware correction into deep learning networks, enabling real-time feedback on SOC prediction confidence levels without the need for additional sensors or reference data. Specifically, we quantify the performance degradation of mainstream data-driven methods, including long short-term memory (LSTM) networks and Gaussian process regression (GPR), under complex aging paths. We demonstrate that our model-disagreement-based active learning correction strategy maintains robustness throughout the battery lifecycle. Experimental results show that with only four active retraining sessions over the full aging process, our method reduces average SOC estimation error to below 1.5 %, and maximum cycle-based average error to below 2 %. This work establishes a path toward uncertainty-informed, lifecycle-resilient, and data-efficient SOC estimation, marking a significant advancement in battery management systems for real-world EV applications.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/547533" linkWindow="_blank">https://research.chalmers.se/publication/547533</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/547533/file/547533_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/547533/file/547533_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.5db74641.8b47.4389.af87.234834220f86
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.egyai.2025.100549
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Battery aging
        Type: general
      – SubjectFull: State of charge (SOC)
        Type: general
      – SubjectFull: Closed-loop correction
        Type: general
      – SubjectFull: data-driven SOC estimation
        Type: general
      – SubjectFull: Active learning
        Type: general
      – SubjectFull: Lithium-ion battery
        Type: general
    Titles:
      – TitleFull: Active-learning-driven error control for data-driven state of charge estimation across the lithium battery lifecycle
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xue, Jinwei
      – PersonEntity:
          Name:
            NameFull: Du, Xuzhi
      – PersonEntity:
          Name:
            NameFull: Zhao, Lei
      – PersonEntity:
          Name:
            NameFull: Yang, Zhigang
      – PersonEntity:
          Name:
            NameFull: Xia, Chao
      – PersonEntity:
          Name:
            NameFull: Ma, Yuan
      – PersonEntity:
          Name:
            NameFull: Hoque, Muhammad Jahidul
      – PersonEntity:
          Name:
            NameFull: Fu, Wuchen
      – PersonEntity:
          Name:
            NameFull: Yan, Xiao
      – PersonEntity:
          Name:
            NameFull: Miljkovic, N.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 26665468
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 21
          Titles:
            – TitleFull: Energy and AI
              Type: main
ResultId 1