Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine
An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish t...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on power electronics 2016-03, Vol.31 (3), p.2226-2238 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2238 |
|---|---|
| container_issue | 3 |
| container_start_page | 2226 |
| container_title | IEEE transactions on power electronics |
| container_volume | 31 |
| creator | Meng, Jinhao Luo, Guangzhao Gao, Fei |
| description | An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish the battery model with limited initial training samples. The effectiveness of the moving window modeling method is validated by both simulations and lithium polymer battery experimental results. The measurement equation of the proposed AUKF method is established by the LSSVM battery model and AUKF has the advantage of adaptively adjusting noise covariance during the estimation process. In addition, the developed LSSVM model is continuously updated online with new samples during the battery operation, in order to minimize the influence of the changes in battery internal characteristics on modeling accuracy and estimation results after a period of operation. Finally, a comparison of accuracy and performance between the AUKF and UKF is made. Simulation and experiment results indicate that the proposed algorithm is capable of predicting lithium battery SOC with a limited number of initial training samples. |
| doi_str_mv | 10.1109/TPEL.2015.2439578 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_02380311v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7115185</ieee_id><sourcerecordid>3889178761</sourcerecordid><originalsourceid>FETCH-LOGICAL-c360t-eac55a6fb788f1857edc2403106828ba83193cf59f3e3ba91c02a356c32e87413</originalsourceid><addsrcrecordid>eNpdkUFv1DAQhS0EEkvhByAulrjQQxaPHSfOcVltKSKISm25Wl7vhHWVxMF2ivbf42irHjjNaPS9p3l6hLwHtgZgzee7m1275gzkmpeikbV6QVbQlFAwYPVLsmJKyUI1jXhN3sT4wBiUksGK_G1dOrp5oDe-Pw0Y6BeTEoYTvU0mYeG7Yns04TfSXUxuMMn5MSMRDzQvm4OZkntEej9Gi2PK1--mH8xIr1yfXagZD_R2niYfEv2FNvlAfxh7dCO-Ja8600d89zQvyP3V7m57XbQ_v37bbtrCioqlAo2V0lTdvlaqAyVrPFheMgGsUlztjRLQCNvJphMo9qYBy7gRsrKCo6pLEBfk8ux7NL2eQo4QTtobp683rV5ujAuV_eBxYT-d2Sn4PzPGpAeXc_W9GdHPUUNdK1ZKqHhGP_6HPvg5jDlJpspKKcUlyxScKRt8jAG75w-A6aU2vdSml9r0U21Z8-GscYj4zNcAMscX_wB135JV</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1746888250</pqid></control><display><type>article</type><title>Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine</title><source>IEEE Electronic Library (IEL)</source><creator>Meng, Jinhao ; Luo, Guangzhao ; Gao, Fei</creator><creatorcontrib>Meng, Jinhao ; Luo, Guangzhao ; Gao, Fei</creatorcontrib><description>An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish the battery model with limited initial training samples. The effectiveness of the moving window modeling method is validated by both simulations and lithium polymer battery experimental results. The measurement equation of the proposed AUKF method is established by the LSSVM battery model and AUKF has the advantage of adaptively adjusting noise covariance during the estimation process. In addition, the developed LSSVM model is continuously updated online with new samples during the battery operation, in order to minimize the influence of the changes in battery internal characteristics on modeling accuracy and estimation results after a period of operation. Finally, a comparison of accuracy and performance between the AUKF and UKF is made. Simulation and experiment results indicate that the proposed algorithm is capable of predicting lithium battery SOC with a limited number of initial training samples.</description><identifier>ISSN: 0885-8993</identifier><identifier>EISSN: 1941-0107</identifier><identifier>DOI: 10.1109/TPEL.2015.2439578</identifier><identifier>CODEN: ITPEE8</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Accuracy ; adaptive unscented Kalman filter (AUKF) ; Algorithms ; Automatic ; Batteries ; Computational efficiency ; Computer simulation ; Electric batteries ; Electric charge ; Electric power ; Engineering Sciences ; Estimating techniques ; Estimation ; Fluid mechanics ; Kalman filters ; least square support vector machine (LSSVM) ; Lithium ; Lithium polymer battery ; Mathematical model ; Mathematical models ; Measurement ; Mechanics ; modeling ; moving window method ; Physics ; Polymers ; Simulation ; state of charge (SOC) ; Support vector machines ; System-on-chip ; Thermics ; Training</subject><ispartof>IEEE transactions on power electronics, 2016-03, Vol.31 (3), p.2226-2238</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Mar 2016</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c360t-eac55a6fb788f1857edc2403106828ba83193cf59f3e3ba91c02a356c32e87413</citedby><cites>FETCH-LOGICAL-c360t-eac55a6fb788f1857edc2403106828ba83193cf59f3e3ba91c02a356c32e87413</cites><orcidid>0000-0001-9076-9718</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7115185$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,780,784,796,885,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7115185$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://hal.science/hal-02380311$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Meng, Jinhao</creatorcontrib><creatorcontrib>Luo, Guangzhao</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><title>Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine</title><title>IEEE transactions on power electronics</title><addtitle>TPEL</addtitle><description>An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish the battery model with limited initial training samples. The effectiveness of the moving window modeling method is validated by both simulations and lithium polymer battery experimental results. The measurement equation of the proposed AUKF method is established by the LSSVM battery model and AUKF has the advantage of adaptively adjusting noise covariance during the estimation process. In addition, the developed LSSVM model is continuously updated online with new samples during the battery operation, in order to minimize the influence of the changes in battery internal characteristics on modeling accuracy and estimation results after a period of operation. Finally, a comparison of accuracy and performance between the AUKF and UKF is made. Simulation and experiment results indicate that the proposed algorithm is capable of predicting lithium battery SOC with a limited number of initial training samples.</description><subject>Accuracy</subject><subject>adaptive unscented Kalman filter (AUKF)</subject><subject>Algorithms</subject><subject>Automatic</subject><subject>Batteries</subject><subject>Computational efficiency</subject><subject>Computer simulation</subject><subject>Electric batteries</subject><subject>Electric charge</subject><subject>Electric power</subject><subject>Engineering Sciences</subject><subject>Estimating techniques</subject><subject>Estimation</subject><subject>Fluid mechanics</subject><subject>Kalman filters</subject><subject>least square support vector machine (LSSVM)</subject><subject>Lithium</subject><subject>Lithium polymer battery</subject><subject>Mathematical model</subject><subject>Mathematical models</subject><subject>Measurement</subject><subject>Mechanics</subject><subject>modeling</subject><subject>moving window method</subject><subject>Physics</subject><subject>Polymers</subject><subject>Simulation</subject><subject>state of charge (SOC)</subject><subject>Support vector machines</subject><subject>System-on-chip</subject><subject>Thermics</subject><subject>Training</subject><issn>0885-8993</issn><issn>1941-0107</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkUFv1DAQhS0EEkvhByAulrjQQxaPHSfOcVltKSKISm25Wl7vhHWVxMF2ivbf42irHjjNaPS9p3l6hLwHtgZgzee7m1275gzkmpeikbV6QVbQlFAwYPVLsmJKyUI1jXhN3sT4wBiUksGK_G1dOrp5oDe-Pw0Y6BeTEoYTvU0mYeG7Yns04TfSXUxuMMn5MSMRDzQvm4OZkntEej9Gi2PK1--mH8xIr1yfXagZD_R2niYfEv2FNvlAfxh7dCO-Ja8600d89zQvyP3V7m57XbQ_v37bbtrCioqlAo2V0lTdvlaqAyVrPFheMgGsUlztjRLQCNvJphMo9qYBy7gRsrKCo6pLEBfk8ux7NL2eQo4QTtobp683rV5ujAuV_eBxYT-d2Sn4PzPGpAeXc_W9GdHPUUNdK1ZKqHhGP_6HPvg5jDlJpspKKcUlyxScKRt8jAG75w-A6aU2vdSml9r0U21Z8-GscYj4zNcAMscX_wB135JV</recordid><startdate>20160301</startdate><enddate>20160301</enddate><creator>Meng, Jinhao</creator><creator>Luo, Guangzhao</creator><creator>Gao, Fei</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><general>Institute of Electrical and Electronics Engineers</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>F28</scope><scope>1XC</scope><orcidid>https://orcid.org/0000-0001-9076-9718</orcidid></search><sort><creationdate>20160301</creationdate><title>Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine</title><author>Meng, Jinhao ; Luo, Guangzhao ; Gao, Fei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c360t-eac55a6fb788f1857edc2403106828ba83193cf59f3e3ba91c02a356c32e87413</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Accuracy</topic><topic>adaptive unscented Kalman filter (AUKF)</topic><topic>Algorithms</topic><topic>Automatic</topic><topic>Batteries</topic><topic>Computational efficiency</topic><topic>Computer simulation</topic><topic>Electric batteries</topic><topic>Electric charge</topic><topic>Electric power</topic><topic>Engineering Sciences</topic><topic>Estimating techniques</topic><topic>Estimation</topic><topic>Fluid mechanics</topic><topic>Kalman filters</topic><topic>least square support vector machine (LSSVM)</topic><topic>Lithium</topic><topic>Lithium polymer battery</topic><topic>Mathematical model</topic><topic>Mathematical models</topic><topic>Measurement</topic><topic>Mechanics</topic><topic>modeling</topic><topic>moving window method</topic><topic>Physics</topic><topic>Polymers</topic><topic>Simulation</topic><topic>state of charge (SOC)</topic><topic>Support vector machines</topic><topic>System-on-chip</topic><topic>Thermics</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Meng, Jinhao</creatorcontrib><creatorcontrib>Luo, Guangzhao</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Hyper Article en Ligne (HAL)</collection><jtitle>IEEE transactions on power electronics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Meng, Jinhao</au><au>Luo, Guangzhao</au><au>Gao, Fei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine</atitle><jtitle>IEEE transactions on power electronics</jtitle><stitle>TPEL</stitle><date>2016-03-01</date><risdate>2016</risdate><volume>31</volume><issue>3</issue><spage>2226</spage><epage>2238</epage><pages>2226-2238</pages><issn>0885-8993</issn><eissn>1941-0107</eissn><coden>ITPEE8</coden><abstract>An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish the battery model with limited initial training samples. The effectiveness of the moving window modeling method is validated by both simulations and lithium polymer battery experimental results. The measurement equation of the proposed AUKF method is established by the LSSVM battery model and AUKF has the advantage of adaptively adjusting noise covariance during the estimation process. In addition, the developed LSSVM model is continuously updated online with new samples during the battery operation, in order to minimize the influence of the changes in battery internal characteristics on modeling accuracy and estimation results after a period of operation. Finally, a comparison of accuracy and performance between the AUKF and UKF is made. Simulation and experiment results indicate that the proposed algorithm is capable of predicting lithium battery SOC with a limited number of initial training samples.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TPEL.2015.2439578</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-9076-9718</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0885-8993 |
| ispartof | IEEE transactions on power electronics, 2016-03, Vol.31 (3), p.2226-2238 |
| issn | 0885-8993 1941-0107 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_02380311v1 |
| source | IEEE Electronic Library (IEL) |
| subjects | Accuracy adaptive unscented Kalman filter (AUKF) Algorithms Automatic Batteries Computational efficiency Computer simulation Electric batteries Electric charge Electric power Engineering Sciences Estimating techniques Estimation Fluid mechanics Kalman filters least square support vector machine (LSSVM) Lithium Lithium polymer battery Mathematical model Mathematical models Measurement Mechanics modeling moving window method Physics Polymers Simulation state of charge (SOC) Support vector machines System-on-chip Thermics Training |
| title | Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T23%3A25%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Lithium%20Polymer%20Battery%20State-of-Charge%20Estimation%20Based%20on%20Adaptive%20Unscented%20Kalman%20Filter%20and%20Support%20Vector%20Machine&rft.jtitle=IEEE%20transactions%20on%20power%20electronics&rft.au=Meng,%20Jinhao&rft.date=2016-03-01&rft.volume=31&rft.issue=3&rft.spage=2226&rft.epage=2238&rft.pages=2226-2238&rft.issn=0885-8993&rft.eissn=1941-0107&rft.coden=ITPEE8&rft_id=info:doi/10.1109/TPEL.2015.2439578&rft_dat=%3Cproquest_RIE%3E3889178761%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1746888250&rft_id=info:pmid/&rft_ieee_id=7115185&rfr_iscdi=true |