A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation

Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Ionics 2024-05, Vol.30 (5), p.2609-2625
Hauptverfasser: Wang, Yangtao, Wang, Shunli, Fan, Yongcun, Zhang, Hansheng, Xie, Yanxin, Fernandez, Carlos
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2625
container_issue 5
container_start_page 2609
container_title Ionics
container_volume 30
creator Wang, Yangtao
Wang, Shunli
Fan, Yongcun
Zhang, Hansheng
Xie, Yanxin
Fernandez, Carlos
description Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is proposed to achieve the high-precision lithium-ion battery capacity estimation. By re-selecting each activation function, the proposed algorithm avoids the low estimation accuracy caused by the fixed activation function of the long short-term memory (LSTM) algorithm, and meanwhile, it can effectively speed up the convergence. The algorithm inputs consider two correlation coefficients so that the health factor with the highest correlation coefficient is chosen as the network input. The experimental data used for the experimental validation is the NASA public battery data under different temperature operating conditions. The validation results show that the estimation accuracy of the VAF-LSTM algorithm under different training sets is greatly improved compared with the traditional LSTM algorithm and the back propagation (BP) algorithm, and the average estimation accuracy can reach more than 97.5%. The improvement of estimation accuracy is also clearly demonstrated under the MAE, MSE, and RMSE. Therefore, the capacity estimation model will provide an important reference role in high-precision battery management systems.
doi_str_mv 10.1007/s11581-024-05475-8
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3053165198</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3053165198</sourcerecordid><originalsourceid>FETCH-LOGICAL-c270t-459117d73ca9afe327b0ac15b632fa0cbbdc2962b43c60ec4a9f3cb132921933</originalsourceid><addsrcrecordid>eNp9kM1OwzAQhC0EEqXwApwscTas7SROjlXFn4TEpXfLcZ3GJYmD7RTlAXhvkhaJG6edw3wzq0HolsI9BRAPgdI0pwRYQiBNREryM7SgecYIiAzO0QKKRBABibhEVyHsAbKMMrFA3yvcuYNp8EF5q8rGYKWjPahoXYerodOzII3rdjjUzkcSjW9xa1rnR9yZwatmOvHL-Q9cOY9ru6tJ7422YU5obKzt0JJZlypO8Ii16pW2ccQmRNsem67RRaWaYG5-7xJtnh436xfy9v78ul69Ec0ERJKkBaViK7hWhaoMZ6IEpWlaZpxVCnRZbjUrMlYmXGdgdKKKiuuSclYwWnC-RHen2N67z2Gql3s3-G5qlBxSTrOUFvnkYieX9i4EbyrZ--lPP0oKcl5bntaW09ryuLacIX6CwmTudsb_Rf9D_QBy_oYK</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3053165198</pqid></control><display><type>article</type><title>A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation</title><source>SpringerNature Journals</source><creator>Wang, Yangtao ; Wang, Shunli ; Fan, Yongcun ; Zhang, Hansheng ; Xie, Yanxin ; Fernandez, Carlos</creator><creatorcontrib>Wang, Yangtao ; Wang, Shunli ; Fan, Yongcun ; Zhang, Hansheng ; Xie, Yanxin ; Fernandez, Carlos</creatorcontrib><description>Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is proposed to achieve the high-precision lithium-ion battery capacity estimation. By re-selecting each activation function, the proposed algorithm avoids the low estimation accuracy caused by the fixed activation function of the long short-term memory (LSTM) algorithm, and meanwhile, it can effectively speed up the convergence. The algorithm inputs consider two correlation coefficients so that the health factor with the highest correlation coefficient is chosen as the network input. The experimental data used for the experimental validation is the NASA public battery data under different temperature operating conditions. The validation results show that the estimation accuracy of the VAF-LSTM algorithm under different training sets is greatly improved compared with the traditional LSTM algorithm and the back propagation (BP) algorithm, and the average estimation accuracy can reach more than 97.5%. The improvement of estimation accuracy is also clearly demonstrated under the MAE, MSE, and RMSE. Therefore, the capacity estimation model will provide an important reference role in high-precision battery management systems.</description><identifier>ISSN: 0947-7047</identifier><identifier>EISSN: 1862-0760</identifier><identifier>DOI: 10.1007/s11581-024-05475-8</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Accuracy ; Algorithms ; Back propagation networks ; Chemistry ; Chemistry and Materials Science ; Condensed Matter Physics ; Correlation coefficients ; Electrochemistry ; Energy Storage ; Lithium ; Lithium-ion batteries ; Management systems ; Neural networks ; Optical and Electronic Materials ; Power management ; Rechargeable batteries ; Renewable and Green Energy</subject><ispartof>Ionics, 2024-05, Vol.30 (5), p.2609-2625</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. 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.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c270t-459117d73ca9afe327b0ac15b632fa0cbbdc2962b43c60ec4a9f3cb132921933</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11581-024-05475-8$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11581-024-05475-8$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>315,781,785,27929,27930,41493,42562,51324</link.rule.ids></links><search><creatorcontrib>Wang, Yangtao</creatorcontrib><creatorcontrib>Wang, Shunli</creatorcontrib><creatorcontrib>Fan, Yongcun</creatorcontrib><creatorcontrib>Zhang, Hansheng</creatorcontrib><creatorcontrib>Xie, Yanxin</creatorcontrib><creatorcontrib>Fernandez, Carlos</creatorcontrib><title>A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation</title><title>Ionics</title><addtitle>Ionics</addtitle><description>Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is proposed to achieve the high-precision lithium-ion battery capacity estimation. By re-selecting each activation function, the proposed algorithm avoids the low estimation accuracy caused by the fixed activation function of the long short-term memory (LSTM) algorithm, and meanwhile, it can effectively speed up the convergence. The algorithm inputs consider two correlation coefficients so that the health factor with the highest correlation coefficient is chosen as the network input. The experimental data used for the experimental validation is the NASA public battery data under different temperature operating conditions. The validation results show that the estimation accuracy of the VAF-LSTM algorithm under different training sets is greatly improved compared with the traditional LSTM algorithm and the back propagation (BP) algorithm, and the average estimation accuracy can reach more than 97.5%. The improvement of estimation accuracy is also clearly demonstrated under the MAE, MSE, and RMSE. Therefore, the capacity estimation model will provide an important reference role in high-precision battery management systems.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Back propagation networks</subject><subject>Chemistry</subject><subject>Chemistry and Materials Science</subject><subject>Condensed Matter Physics</subject><subject>Correlation coefficients</subject><subject>Electrochemistry</subject><subject>Energy Storage</subject><subject>Lithium</subject><subject>Lithium-ion batteries</subject><subject>Management systems</subject><subject>Neural networks</subject><subject>Optical and Electronic Materials</subject><subject>Power management</subject><subject>Rechargeable batteries</subject><subject>Renewable and Green Energy</subject><issn>0947-7047</issn><issn>1862-0760</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kM1OwzAQhC0EEqXwApwscTas7SROjlXFn4TEpXfLcZ3GJYmD7RTlAXhvkhaJG6edw3wzq0HolsI9BRAPgdI0pwRYQiBNREryM7SgecYIiAzO0QKKRBABibhEVyHsAbKMMrFA3yvcuYNp8EF5q8rGYKWjPahoXYerodOzII3rdjjUzkcSjW9xa1rnR9yZwatmOvHL-Q9cOY9ru6tJ7422YU5obKzt0JJZlypO8Ii16pW2ccQmRNsem67RRaWaYG5-7xJtnh436xfy9v78ul69Ec0ERJKkBaViK7hWhaoMZ6IEpWlaZpxVCnRZbjUrMlYmXGdgdKKKiuuSclYwWnC-RHen2N67z2Gql3s3-G5qlBxSTrOUFvnkYieX9i4EbyrZ--lPP0oKcl5bntaW09ryuLacIX6CwmTudsb_Rf9D_QBy_oYK</recordid><startdate>20240501</startdate><enddate>20240501</enddate><creator>Wang, Yangtao</creator><creator>Wang, Shunli</creator><creator>Fan, Yongcun</creator><creator>Zhang, Hansheng</creator><creator>Xie, Yanxin</creator><creator>Fernandez, Carlos</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240501</creationdate><title>A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation</title><author>Wang, Yangtao ; Wang, Shunli ; Fan, Yongcun ; Zhang, Hansheng ; Xie, Yanxin ; Fernandez, Carlos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c270t-459117d73ca9afe327b0ac15b632fa0cbbdc2962b43c60ec4a9f3cb132921933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Back propagation networks</topic><topic>Chemistry</topic><topic>Chemistry and Materials Science</topic><topic>Condensed Matter Physics</topic><topic>Correlation coefficients</topic><topic>Electrochemistry</topic><topic>Energy Storage</topic><topic>Lithium</topic><topic>Lithium-ion batteries</topic><topic>Management systems</topic><topic>Neural networks</topic><topic>Optical and Electronic Materials</topic><topic>Power management</topic><topic>Rechargeable batteries</topic><topic>Renewable and Green Energy</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Yangtao</creatorcontrib><creatorcontrib>Wang, Shunli</creatorcontrib><creatorcontrib>Fan, Yongcun</creatorcontrib><creatorcontrib>Zhang, Hansheng</creatorcontrib><creatorcontrib>Xie, Yanxin</creatorcontrib><creatorcontrib>Fernandez, Carlos</creatorcontrib><collection>CrossRef</collection><jtitle>Ionics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Yangtao</au><au>Wang, Shunli</au><au>Fan, Yongcun</au><au>Zhang, Hansheng</au><au>Xie, Yanxin</au><au>Fernandez, Carlos</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation</atitle><jtitle>Ionics</jtitle><stitle>Ionics</stitle><date>2024-05-01</date><risdate>2024</risdate><volume>30</volume><issue>5</issue><spage>2609</spage><epage>2625</epage><pages>2609-2625</pages><issn>0947-7047</issn><eissn>1862-0760</eissn><abstract>Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is proposed to achieve the high-precision lithium-ion battery capacity estimation. By re-selecting each activation function, the proposed algorithm avoids the low estimation accuracy caused by the fixed activation function of the long short-term memory (LSTM) algorithm, and meanwhile, it can effectively speed up the convergence. The algorithm inputs consider two correlation coefficients so that the health factor with the highest correlation coefficient is chosen as the network input. The experimental data used for the experimental validation is the NASA public battery data under different temperature operating conditions. The validation results show that the estimation accuracy of the VAF-LSTM algorithm under different training sets is greatly improved compared with the traditional LSTM algorithm and the back propagation (BP) algorithm, and the average estimation accuracy can reach more than 97.5%. The improvement of estimation accuracy is also clearly demonstrated under the MAE, MSE, and RMSE. Therefore, the capacity estimation model will provide an important reference role in high-precision battery management systems.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s11581-024-05475-8</doi><tpages>17</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0947-7047
ispartof Ionics, 2024-05, Vol.30 (5), p.2609-2625
issn 0947-7047
1862-0760
language eng
recordid cdi_proquest_journals_3053165198
source SpringerNature Journals
subjects Accuracy
Algorithms
Back propagation networks
Chemistry
Chemistry and Materials Science
Condensed Matter Physics
Correlation coefficients
Electrochemistry
Energy Storage
Lithium
Lithium-ion batteries
Management systems
Neural networks
Optical and Electronic Materials
Power management
Rechargeable batteries
Renewable and Green Energy
title A novel variable activation function-long short-term memory neural network for high-precision lithium-ion battery capacity estimation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T17%3A23%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20novel%20variable%20activation%20function-long%20short-term%20memory%20neural%20network%20for%20high-precision%20lithium-ion%20battery%20capacity%20estimation&rft.jtitle=Ionics&rft.au=Wang,%20Yangtao&rft.date=2024-05-01&rft.volume=30&rft.issue=5&rft.spage=2609&rft.epage=2625&rft.pages=2609-2625&rft.issn=0947-7047&rft.eissn=1862-0760&rft_id=info:doi/10.1007/s11581-024-05475-8&rft_dat=%3Cproquest_cross%3E3053165198%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3053165198&rft_id=info:pmid/&rfr_iscdi=true