View in EDS

SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network.

Saved in:
Bibliographic Details
Title: SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network.
Authors: Hannan, M. A.1 (AUTHOR) hannan@uniten.edu.my, How, D. N. T.1 (AUTHOR) dickson@uniten.edu.my, Lipu, M. S. Hossain1 (AUTHOR) lipu@ukm.edu.my, Ker, Pin Jern1 (AUTHOR) pinjern@uniten.edu.my, Dong, Z. Y.1 (AUTHOR) joe.dong@unsw.edu.au, Mansur, M.1 (AUTHOR) muhamadm@uniten.edu.my, Blaabjerg, Frede1 (AUTHOR) fbl@et.aau.dk
Source: IEEE Transactions on Power Electronics. Jul2021, Vol. 36 Issue 7, p7349-7353. 5p.
Subjects: Deep learning, Lithium-ion batteries, Standard deviations, Lithium cells
Abstract: In this letter, we train deep learning (DL) models to estimate the state-of-charge (SOC) of lithium-ion (Li-ion) battery directly from voltage, current, and battery temperature values. The deep fully convolutional network model is proposed for its novel architecture with learning rate optimization strategies. The proposed model is capable of estimating SOC at constant and varying ambient temperature on different drive cycles without having to be retrained. The model also outperformed other commonly used DL models such as the LSTM, GRU, and CNN on an open source Li-ion battery dataset. The model achieves 0.85% root mean squared error (RMSE) and 0.7% mean absolute error (MAE) at 25 °C and 2.0% RMSE and 1.55% MAE at varying ambient temperature (–20–25 °C). [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Power Electronics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 149122601
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hannan%2C+M%2E+A%2E%22">Hannan, M. A.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hannan@uniten.edu.my</i><br /><searchLink fieldCode="AR" term="%22How%2C+D%2E+N%2E+T%2E%22">How, D. N. T.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> dickson@uniten.edu.my</i><br /><searchLink fieldCode="AR" term="%22Lipu%2C+M%2E+S%2E+Hossain%22">Lipu, M. S. Hossain</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lipu@ukm.edu.my</i><br /><searchLink fieldCode="AR" term="%22Ker%2C+Pin+Jern%22">Ker, Pin Jern</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> pinjern@uniten.edu.my</i><br /><searchLink fieldCode="AR" term="%22Dong%2C+Z%2E+Y%2E%22">Dong, Z. Y.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> joe.dong@unsw.edu.au</i><br /><searchLink fieldCode="AR" term="%22Mansur%2C+M%2E%22">Mansur, M.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> muhamadm@uniten.edu.my</i><br /><searchLink fieldCode="AR" term="%22Blaabjerg%2C+Frede%22">Blaabjerg, Frede</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> fbl@et.aau.dk</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Power+Electronics%22">IEEE Transactions on Power Electronics</searchLink>. Jul2021, Vol. 36 Issue 7, p7349-7353. 5p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Lithium-ion+batteries%22">Lithium-ion batteries</searchLink><br /><searchLink fieldCode="DE" term="%22Standard+deviations%22">Standard deviations</searchLink><br /><searchLink fieldCode="DE" term="%22Lithium+cells%22">Lithium cells</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this letter, we train deep learning (DL) models to estimate the state-of-charge (SOC) of lithium-ion (Li-ion) battery directly from voltage, current, and battery temperature values. The deep fully convolutional network model is proposed for its novel architecture with learning rate optimization strategies. The proposed model is capable of estimating SOC at constant and varying ambient temperature on different drive cycles without having to be retrained. The model also outperformed other commonly used DL models such as the LSTM, GRU, and CNN on an open source Li-ion battery dataset. The model achieves 0.85% root mean squared error (RMSE) and 0.7% mean absolute error (MAE) at 25 °C and 2.0% RMSE and 1.55% MAE at varying ambient temperature (–20–25 °C). [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Power Electronics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=149122601
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TPEL.2020.3041876
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 5
        StartPage: 7349
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Lithium-ion batteries
        Type: general
      – SubjectFull: Standard deviations
        Type: general
      – SubjectFull: Lithium cells
        Type: general
    Titles:
      – TitleFull: SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hannan, M. A.
      – PersonEntity:
          Name:
            NameFull: How, D. N. T.
      – PersonEntity:
          Name:
            NameFull: Lipu, M. S. Hossain
      – PersonEntity:
          Name:
            NameFull: Ker, Pin Jern
      – PersonEntity:
          Name:
            NameFull: Dong, Z. Y.
      – PersonEntity:
          Name:
            NameFull: Mansur, M.
      – PersonEntity:
          Name:
            NameFull: Blaabjerg, Frede
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 08858993
          Numbering:
            – Type: volume
              Value: 36
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: IEEE Transactions on Power Electronics
              Type: main
ResultId 1