Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation

Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AIP advances 2023-07, Vol.13 (7), p.075113-075113-12
Hauptverfasser: Liu, Xin, Yang, Changbo, Meng, Yanmei, Zhu, Jihong, Duan, Yijian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 075113-12
container_issue 7
container_start_page 075113
container_title AIP advances
container_volume 13
creator Liu, Xin
Yang, Changbo
Meng, Yanmei
Zhu, Jihong
Duan, Yijian
description Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of charge/discharge cycles lead to insufficient historical data and inaccurate capacity estimation. In order to improve the adaptability as well as accuracy under different operating conditions, this paper proposes a lithium-ion battery capacity estimation model based on Transformer-Adversarial Discriminative Domain Adaptation (T-ADDA). The model takes charging voltage, charging current, and charging temperature as inputs and uses a transformer network to extract the time series features from the data. Then, adversarial domain adaptation is trained on the source and target domain data by the domain discrimination network of the ADDA model so as to find the domain invariant features between the source and target domains. Finally, the regression network of ADDA is used to achieve cross-domain prediction for the target domain data. The experimental results show that the T-ADDA model can accurately achieve cross-domain prediction and that the average error of prediction under different operating conditions is only 3.9225%. Therefore, the T-ADDA model has good adaptability and accuracy, and it can significantly improve the performance of lithium-ion battery capacity estimation.
doi_str_mv 10.1063/5.0152038
format Article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_proquest_journals_2836064690</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_5edc25534aa5440f9524e1be5a5eacf5</doaj_id><sourcerecordid>2836064690</sourcerecordid><originalsourceid>FETCH-LOGICAL-c353t-a80693af8dc31a76aba559501423b1ec891653d6b95c3effa9da3c8c7e4933b13</originalsourceid><addsrcrecordid>eNp9kU1LAzEQhhdRUKoH_8GCJ4XVZJNJN0cpfkHBi57DbD4kpd2sSSz03xu7RTyZywzDw5Phnaq6pOSWEsHu4JZQaAnrjqqzlkLXsLYVx3_60-oipRUpj0tKOn5WfSxwRO3zrrYp-w1mH4Y6uHrpm5-ux5xt3JWarKnLIEcckgtxY2ODZmtjwuhxXRufdPQbPxTD1tYmbNAPNRoc8955Xp04XCd7caiz6v3x4W3x3Cxfn14W98tGM2C5wY4IydB1RjOKc4E9AkgglLesp1Z3kgpgRvQSNLPOoTTIdKfnlktWCDarXiavCbhSY1kJ404F9Go_CPFDYcxer60Ca3QLwDgicE6chJZb2ltAsKgdFNfV5Bpj-Pwq-ahV-IpDWV-1HRNEcCFJoa4nSseQUrTu91dK1M9ZFKjDWQp7M7GpRL7P5R_4G4HRjWA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2836064690</pqid></control><display><type>article</type><title>Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation</title><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Alma/SFX Local Collection</source><source>Free Full-Text Journals in Chemistry</source><creator>Liu, Xin ; Yang, Changbo ; Meng, Yanmei ; Zhu, Jihong ; Duan, Yijian</creator><creatorcontrib>Liu, Xin ; Yang, Changbo ; Meng, Yanmei ; Zhu, Jihong ; Duan, Yijian</creatorcontrib><description>Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of charge/discharge cycles lead to insufficient historical data and inaccurate capacity estimation. In order to improve the adaptability as well as accuracy under different operating conditions, this paper proposes a lithium-ion battery capacity estimation model based on Transformer-Adversarial Discriminative Domain Adaptation (T-ADDA). The model takes charging voltage, charging current, and charging temperature as inputs and uses a transformer network to extract the time series features from the data. Then, adversarial domain adaptation is trained on the source and target domain data by the domain discrimination network of the ADDA model so as to find the domain invariant features between the source and target domains. Finally, the regression network of ADDA is used to achieve cross-domain prediction for the target domain data. The experimental results show that the T-ADDA model can accurately achieve cross-domain prediction and that the average error of prediction under different operating conditions is only 3.9225%. Therefore, the T-ADDA model has good adaptability and accuracy, and it can significantly improve the performance of lithium-ion battery capacity estimation.</description><identifier>ISSN: 2158-3226</identifier><identifier>EISSN: 2158-3226</identifier><identifier>DOI: 10.1063/5.0152038</identifier><identifier>CODEN: AAIDBI</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Adaptation ; Charging ; Electric vehicles ; Lithium ; Lithium-ion batteries ; Rechargeable batteries ; Transformers</subject><ispartof>AIP advances, 2023-07, Vol.13 (7), p.075113-075113-12</ispartof><rights>Author(s)</rights><rights>2023 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c353t-a80693af8dc31a76aba559501423b1ec891653d6b95c3effa9da3c8c7e4933b13</cites><orcidid>0000-0001-5242-4508 ; 0000-0002-3615-9465</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,860,2096,27901,27902</link.rule.ids></links><search><creatorcontrib>Liu, Xin</creatorcontrib><creatorcontrib>Yang, Changbo</creatorcontrib><creatorcontrib>Meng, Yanmei</creatorcontrib><creatorcontrib>Zhu, Jihong</creatorcontrib><creatorcontrib>Duan, Yijian</creatorcontrib><title>Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation</title><title>AIP advances</title><description>Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of charge/discharge cycles lead to insufficient historical data and inaccurate capacity estimation. In order to improve the adaptability as well as accuracy under different operating conditions, this paper proposes a lithium-ion battery capacity estimation model based on Transformer-Adversarial Discriminative Domain Adaptation (T-ADDA). The model takes charging voltage, charging current, and charging temperature as inputs and uses a transformer network to extract the time series features from the data. Then, adversarial domain adaptation is trained on the source and target domain data by the domain discrimination network of the ADDA model so as to find the domain invariant features between the source and target domains. Finally, the regression network of ADDA is used to achieve cross-domain prediction for the target domain data. The experimental results show that the T-ADDA model can accurately achieve cross-domain prediction and that the average error of prediction under different operating conditions is only 3.9225%. Therefore, the T-ADDA model has good adaptability and accuracy, and it can significantly improve the performance of lithium-ion battery capacity estimation.</description><subject>Adaptation</subject><subject>Charging</subject><subject>Electric vehicles</subject><subject>Lithium</subject><subject>Lithium-ion batteries</subject><subject>Rechargeable batteries</subject><subject>Transformers</subject><issn>2158-3226</issn><issn>2158-3226</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNp9kU1LAzEQhhdRUKoH_8GCJ4XVZJNJN0cpfkHBi57DbD4kpd2sSSz03xu7RTyZywzDw5Phnaq6pOSWEsHu4JZQaAnrjqqzlkLXsLYVx3_60-oipRUpj0tKOn5WfSxwRO3zrrYp-w1mH4Y6uHrpm5-ux5xt3JWarKnLIEcckgtxY2ODZmtjwuhxXRufdPQbPxTD1tYmbNAPNRoc8955Xp04XCd7caiz6v3x4W3x3Cxfn14W98tGM2C5wY4IydB1RjOKc4E9AkgglLesp1Z3kgpgRvQSNLPOoTTIdKfnlktWCDarXiavCbhSY1kJ404F9Go_CPFDYcxer60Ca3QLwDgicE6chJZb2ltAsKgdFNfV5Bpj-Pwq-ahV-IpDWV-1HRNEcCFJoa4nSseQUrTu91dK1M9ZFKjDWQp7M7GpRL7P5R_4G4HRjWA</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Liu, Xin</creator><creator>Yang, Changbo</creator><creator>Meng, Yanmei</creator><creator>Zhu, Jihong</creator><creator>Duan, Yijian</creator><general>American Institute of Physics</general><general>AIP Publishing LLC</general><scope>AJDQP</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-5242-4508</orcidid><orcidid>https://orcid.org/0000-0002-3615-9465</orcidid></search><sort><creationdate>20230701</creationdate><title>Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation</title><author>Liu, Xin ; Yang, Changbo ; Meng, Yanmei ; Zhu, Jihong ; Duan, Yijian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c353t-a80693af8dc31a76aba559501423b1ec891653d6b95c3effa9da3c8c7e4933b13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Adaptation</topic><topic>Charging</topic><topic>Electric vehicles</topic><topic>Lithium</topic><topic>Lithium-ion batteries</topic><topic>Rechargeable batteries</topic><topic>Transformers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Xin</creatorcontrib><creatorcontrib>Yang, Changbo</creatorcontrib><creatorcontrib>Meng, Yanmei</creatorcontrib><creatorcontrib>Zhu, Jihong</creatorcontrib><creatorcontrib>Duan, Yijian</creatorcontrib><collection>AIP Open Access Journals</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>AIP advances</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Xin</au><au>Yang, Changbo</au><au>Meng, Yanmei</au><au>Zhu, Jihong</au><au>Duan, Yijian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation</atitle><jtitle>AIP advances</jtitle><date>2023-07-01</date><risdate>2023</risdate><volume>13</volume><issue>7</issue><spage>075113</spage><epage>075113-12</epage><pages>075113-075113-12</pages><issn>2158-3226</issn><eissn>2158-3226</eissn><coden>AAIDBI</coden><abstract>Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of charge/discharge cycles lead to insufficient historical data and inaccurate capacity estimation. In order to improve the adaptability as well as accuracy under different operating conditions, this paper proposes a lithium-ion battery capacity estimation model based on Transformer-Adversarial Discriminative Domain Adaptation (T-ADDA). The model takes charging voltage, charging current, and charging temperature as inputs and uses a transformer network to extract the time series features from the data. Then, adversarial domain adaptation is trained on the source and target domain data by the domain discrimination network of the ADDA model so as to find the domain invariant features between the source and target domains. Finally, the regression network of ADDA is used to achieve cross-domain prediction for the target domain data. The experimental results show that the T-ADDA model can accurately achieve cross-domain prediction and that the average error of prediction under different operating conditions is only 3.9225%. Therefore, the T-ADDA model has good adaptability and accuracy, and it can significantly improve the performance of lithium-ion battery capacity estimation.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0152038</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-5242-4508</orcidid><orcidid>https://orcid.org/0000-0002-3615-9465</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2158-3226
ispartof AIP advances, 2023-07, Vol.13 (7), p.075113-075113-12
issn 2158-3226
2158-3226
language eng
recordid cdi_proquest_journals_2836064690
source DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Alma/SFX Local Collection; Free Full-Text Journals in Chemistry
subjects Adaptation
Charging
Electric vehicles
Lithium
Lithium-ion batteries
Rechargeable batteries
Transformers
title Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T21%3A30%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Capacity%20estimation%20of%20Li-ion%20battery%20based%20on%20transformer-adversarial%20discriminative%20domain%20adaptation&rft.jtitle=AIP%20advances&rft.au=Liu,%20Xin&rft.date=2023-07-01&rft.volume=13&rft.issue=7&rft.spage=075113&rft.epage=075113-12&rft.pages=075113-075113-12&rft.issn=2158-3226&rft.eissn=2158-3226&rft.coden=AAIDBI&rft_id=info:doi/10.1063/5.0152038&rft_dat=%3Cproquest_doaj_%3E2836064690%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2836064690&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_5edc25534aa5440f9524e1be5a5eacf5&rfr_iscdi=true