Lithium battery health state monitoring method based on state attenuation and interactive learning
The invention relates to a lithium battery health state monitoring method based on state attenuation and interactive learning, and belongs to the technical field of batteries. The method comprises the following steps: constructing a missing data vector; extracting features of missing data of the lit...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | MAO YAN LI PENGHUA GAO DAILIN HOU JIE DENG ZHONGWEI YANG ZHELIN XIANG SHENG XIE LIRONG LIU SHENGWEI |
| description | The invention relates to a lithium battery health state monitoring method based on state attenuation and interactive learning, and belongs to the technical field of batteries. The method comprises the following steps: constructing a missing data vector; extracting features of missing data of the lithium battery sequence; multi-resolution time feature extraction is carried out; and proportional fusion of the multi-scale features. A lithium battery time sequence belongs to one-dimensional data, various curves objectively and abstractly reflect working conditions of a lithium battery, and people cannot directly utilize a traditional data filling method to destroy nonlinearity of data. According to the research, DEC-LSTM and CIN are used as core modules, a hybrid neural network meeting SOH, RUL and other tasks is constructed, and accurate monitoring of the lithium battery health state is realized. According to the method, the authenticity of a data source and the accuracy of model prediction are both considered, |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117590241A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117590241A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117590241A3</originalsourceid><addsrcrecordid>eNqNjE0KwjAQRrNxIeodxgMIxh_EpRTFhbhyX6btaAaSSUmmgrc3Qg_g6oPHe9_UNDdWx0OABlUpfcARenWQFZUgRGGNieUFgdTFrmiZOogyCr9IBlQuBKUDlnKCrfKbwBMmKencTJ7oMy3GnZnl5fyorivqY025x5aEtK7u1h72x_VmZ0_bf5wvsQU-xA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Lithium battery health state monitoring method based on state attenuation and interactive learning</title><source>esp@cenet</source><creator>MAO YAN ; LI PENGHUA ; GAO DAILIN ; HOU JIE ; DENG ZHONGWEI ; YANG ZHELIN ; XIANG SHENG ; XIE LIRONG ; LIU SHENGWEI</creator><creatorcontrib>MAO YAN ; LI PENGHUA ; GAO DAILIN ; HOU JIE ; DENG ZHONGWEI ; YANG ZHELIN ; XIANG SHENG ; XIE LIRONG ; LIU SHENGWEI</creatorcontrib><description>The invention relates to a lithium battery health state monitoring method based on state attenuation and interactive learning, and belongs to the technical field of batteries. The method comprises the following steps: constructing a missing data vector; extracting features of missing data of the lithium battery sequence; multi-resolution time feature extraction is carried out; and proportional fusion of the multi-scale features. A lithium battery time sequence belongs to one-dimensional data, various curves objectively and abstractly reflect working conditions of a lithium battery, and people cannot directly utilize a traditional data filling method to destroy nonlinearity of data. According to the research, DEC-LSTM and CIN are used as core modules, a hybrid neural network meeting SOH, RUL and other tasks is constructed, and accurate monitoring of the lithium battery health state is realized. According to the method, the authenticity of a data source and the accuracy of model prediction are both considered,</description><language>chi ; eng</language><subject>MEASURING ; MEASURING ELECTRIC VARIABLES ; MEASURING MAGNETIC VARIABLES ; PHYSICS ; TESTING</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240223&DB=EPODOC&CC=CN&NR=117590241A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240223&DB=EPODOC&CC=CN&NR=117590241A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MAO YAN</creatorcontrib><creatorcontrib>LI PENGHUA</creatorcontrib><creatorcontrib>GAO DAILIN</creatorcontrib><creatorcontrib>HOU JIE</creatorcontrib><creatorcontrib>DENG ZHONGWEI</creatorcontrib><creatorcontrib>YANG ZHELIN</creatorcontrib><creatorcontrib>XIANG SHENG</creatorcontrib><creatorcontrib>XIE LIRONG</creatorcontrib><creatorcontrib>LIU SHENGWEI</creatorcontrib><title>Lithium battery health state monitoring method based on state attenuation and interactive learning</title><description>The invention relates to a lithium battery health state monitoring method based on state attenuation and interactive learning, and belongs to the technical field of batteries. The method comprises the following steps: constructing a missing data vector; extracting features of missing data of the lithium battery sequence; multi-resolution time feature extraction is carried out; and proportional fusion of the multi-scale features. A lithium battery time sequence belongs to one-dimensional data, various curves objectively and abstractly reflect working conditions of a lithium battery, and people cannot directly utilize a traditional data filling method to destroy nonlinearity of data. According to the research, DEC-LSTM and CIN are used as core modules, a hybrid neural network meeting SOH, RUL and other tasks is constructed, and accurate monitoring of the lithium battery health state is realized. According to the method, the authenticity of a data source and the accuracy of model prediction are both considered,</description><subject>MEASURING</subject><subject>MEASURING ELECTRIC VARIABLES</subject><subject>MEASURING MAGNETIC VARIABLES</subject><subject>PHYSICS</subject><subject>TESTING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjE0KwjAQRrNxIeodxgMIxh_EpRTFhbhyX6btaAaSSUmmgrc3Qg_g6oPHe9_UNDdWx0OABlUpfcARenWQFZUgRGGNieUFgdTFrmiZOogyCr9IBlQuBKUDlnKCrfKbwBMmKencTJ7oMy3GnZnl5fyorivqY025x5aEtK7u1h72x_VmZ0_bf5wvsQU-xA</recordid><startdate>20240223</startdate><enddate>20240223</enddate><creator>MAO YAN</creator><creator>LI PENGHUA</creator><creator>GAO DAILIN</creator><creator>HOU JIE</creator><creator>DENG ZHONGWEI</creator><creator>YANG ZHELIN</creator><creator>XIANG SHENG</creator><creator>XIE LIRONG</creator><creator>LIU SHENGWEI</creator><scope>EVB</scope></search><sort><creationdate>20240223</creationdate><title>Lithium battery health state monitoring method based on state attenuation and interactive learning</title><author>MAO YAN ; LI PENGHUA ; GAO DAILIN ; HOU JIE ; DENG ZHONGWEI ; YANG ZHELIN ; XIANG SHENG ; XIE LIRONG ; LIU SHENGWEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117590241A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>MEASURING</topic><topic>MEASURING ELECTRIC VARIABLES</topic><topic>MEASURING MAGNETIC VARIABLES</topic><topic>PHYSICS</topic><topic>TESTING</topic><toplevel>online_resources</toplevel><creatorcontrib>MAO YAN</creatorcontrib><creatorcontrib>LI PENGHUA</creatorcontrib><creatorcontrib>GAO DAILIN</creatorcontrib><creatorcontrib>HOU JIE</creatorcontrib><creatorcontrib>DENG ZHONGWEI</creatorcontrib><creatorcontrib>YANG ZHELIN</creatorcontrib><creatorcontrib>XIANG SHENG</creatorcontrib><creatorcontrib>XIE LIRONG</creatorcontrib><creatorcontrib>LIU SHENGWEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MAO YAN</au><au>LI PENGHUA</au><au>GAO DAILIN</au><au>HOU JIE</au><au>DENG ZHONGWEI</au><au>YANG ZHELIN</au><au>XIANG SHENG</au><au>XIE LIRONG</au><au>LIU SHENGWEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Lithium battery health state monitoring method based on state attenuation and interactive learning</title><date>2024-02-23</date><risdate>2024</risdate><abstract>The invention relates to a lithium battery health state monitoring method based on state attenuation and interactive learning, and belongs to the technical field of batteries. The method comprises the following steps: constructing a missing data vector; extracting features of missing data of the lithium battery sequence; multi-resolution time feature extraction is carried out; and proportional fusion of the multi-scale features. A lithium battery time sequence belongs to one-dimensional data, various curves objectively and abstractly reflect working conditions of a lithium battery, and people cannot directly utilize a traditional data filling method to destroy nonlinearity of data. According to the research, DEC-LSTM and CIN are used as core modules, a hybrid neural network meeting SOH, RUL and other tasks is constructed, and accurate monitoring of the lithium battery health state is realized. According to the method, the authenticity of a data source and the accuracy of model prediction are both considered,</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117590241A |
| source | esp@cenet |
| subjects | MEASURING MEASURING ELECTRIC VARIABLES MEASURING MAGNETIC VARIABLES PHYSICS TESTING |
| title | Lithium battery health state monitoring method based on state attenuation and interactive learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T18%3A21%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=MAO%20YAN&rft.date=2024-02-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117590241A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |