Publicação
Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling
| Resumo: | Lithium-ion batteries have found applications in many parts of our daily lives. Predicting their remaining useful life (RUL) is thus essential for management and prognostics. Most approaches look at early life prediction of RUL in the context of designing charging profiles or optimising cell design. While critical, said approaches are not directly applicable to the regular testing of cells used in applications. This article focuses on a class of models called ‘one-cycle’ models which are suitable for this task and characterized by versatility (in terms of online prediction frameworks and model combinations), prediction from limited input, and cells’ history independence. Our contribution is fourfold. First, we show the wider deployability of the so-called one-cycle model for a different type of battery data, thus confirming its wider scope of use. Second, reflecting on how prediction models can be leveraged within battery management cloud solutions, we propose a universal Exponential-smoothing (e-forgetting) mechanism that leverages cycle-to-cycle prediction updates to reduce prediction variance. Third, we use this new model as a second-life assessment tool by proposing a knee region classifier. Last, using model ensembling, we build a “model of models”. We show that it outperforms each underpinning model (from in-cycle variability, cycle-to-cycle variability, and empirical models). This ‘ensembling’ strategy allows coupling explainable and black-box methods, thus giving the user extra control over the final model. |
|---|---|
| Autores principais: | Strange, Calum |
| Outros Autores: | Ibraheem, Rasheed; dos Reis, Gonçalo |
| Assunto: | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| Ano: | 2023 |
| País: | Portugal |
| Tipo de documento: | artigo |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| _version_ | 1868983113358508032 |
|---|---|
| author | Strange, Calum |
| author2 | Ibraheem, Rasheed dos Reis, Gonçalo |
| author2_role | author author |
| author_facet | Strange, Calum Ibraheem, Rasheed dos Reis, Gonçalo |
| author_role | author |
| contributor_name_str_mv | CMA - Centro de Matemática e Aplicações MDPI - Multidisciplinary Digital Publishing Institute RUN |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Strange, Calum\"},{\"Person.name\":\"Ibraheem, Rasheed\"},{\"Person.name\":\"dos Reis, Gonçalo\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | CMA - Centro de Matemática e Aplicações MDPI - Multidisciplinary Digital Publishing Institute RUN |
| datacite.creators.creator.creatorName.fl_str_mv | Strange, Calum Ibraheem, Rasheed dos Reis, Gonçalo |
| datacite.date.Accepted.fl_str_mv | 2023-04-06T00:00:00Z |
| datacite.date.available.fl_str_mv | 2023-07-13T22:18:37Z |
| datacite.date.embargoed.fl_str_mv | 2023-07-13T22:18:37Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| datacite.titles.title.fl_str_mv | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| dc.contributor.none.fl_str_mv | CMA - Centro de Matemática e Aplicações MDPI - Multidisciplinary Digital Publishing Institute RUN |
| dc.creator.none.fl_str_mv | Strange, Calum Ibraheem, Rasheed dos Reis, Gonçalo |
| dc.date.Accepted.fl_str_mv | 2023-04-06T00:00:00Z |
| dc.date.available.fl_str_mv | 2023-07-13T22:18:37Z |
| dc.date.embargoed.fl_str_mv | 2023-07-13T22:18:37Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://hdl.handle.net/10362/155253 |
| dc.language.none.fl_str_mv | eng |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| dc.title.fl_str_mv | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_6501 |
| description | Lithium-ion batteries have found applications in many parts of our daily lives. Predicting their remaining useful life (RUL) is thus essential for management and prognostics. Most approaches look at early life prediction of RUL in the context of designing charging profiles or optimising cell design. While critical, said approaches are not directly applicable to the regular testing of cells used in applications. This article focuses on a class of models called ‘one-cycle’ models which are suitable for this task and characterized by versatility (in terms of online prediction frameworks and model combinations), prediction from limited input, and cells’ history independence. Our contribution is fourfold. First, we show the wider deployability of the so-called one-cycle model for a different type of battery data, thus confirming its wider scope of use. Second, reflecting on how prediction models can be leveraged within battery management cloud solutions, we propose a universal Exponential-smoothing (e-forgetting) mechanism that leverages cycle-to-cycle prediction updates to reduce prediction variance. Third, we use this new model as a second-life assessment tool by proposing a knee region classifier. Last, using model ensembling, we build a “model of models”. We show that it outperforms each underpinning model (from in-cycle variability, cycle-to-cycle variability, and empirical models). This ‘ensembling’ strategy allows coupling explainable and black-box methods, thus giving the user extra control over the final model. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | article |
| fulltext.url.fl_str_mv | https://run.unl.pt/bitstreams/1224f4fc-3a0c-41fe-ab52-c82883a7641c/download |
| funder_facet_str_mv | FCT{{{_:::_}}}Fundação para a Ciência e a Tecnologia |
| funding.funder.alternateName_str_mv | FCT |
| funding.funder.identifier_str_mv | http://doi.org/10.13039/501100001871 |
| funding.funder.name_str_mv | Fundação para a Ciência e a Tecnologia |
| funding.name_str_mv | 6817 - DCRRNI ID |
| id | run_e842f486594de1ffd5b83f8a0217db62 |
| identifier.url.fl_str_mv | http://hdl.handle.net/10362/155253 |
| inst_facet_str | urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa |
| instacron_str | unl |
| institution | Universidade Nova de Lisboa |
| instname_str | Universidade Nova de Lisboa |
| language | eng |
| network_acronym_str | run |
| network_name_str | Repositório Institucional da UNL |
| oai_identifier_str | oai:run.unl.pt:10362/155253 |
| organization_str_mv | urn:organizationAcronym:unl |
| person_str_mv | Strange, Calum Ibraheem, Rasheed dos Reis, Gonçalo |
| publishDate | 2023 |
| repo_facet_str | urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL |
| reponame_str | Repositório Institucional da UNL |
| repository_id_str | urn:repositoryAcronym:run |
| service_str_mv | urn:repositoryAcronym:run |
| spelling | engenLithium-ion batteries have found applications in many parts of our daily lives. Predicting their remaining useful life (RUL) is thus essential for management and prognostics. Most approaches look at early life prediction of RUL in the context of designing charging profiles or optimising cell design. While critical, said approaches are not directly applicable to the regular testing of cells used in applications. This article focuses on a class of models called ‘one-cycle’ models which are suitable for this task and characterized by versatility (in terms of online prediction frameworks and model combinations), prediction from limited input, and cells’ history independence. Our contribution is fourfold. First, we show the wider deployability of the so-called one-cycle model for a different type of battery data, thus confirming its wider scope of use. Second, reflecting on how prediction models can be leveraged within battery management cloud solutions, we propose a universal Exponential-smoothing (e-forgetting) mechanism that leverages cycle-to-cycle prediction updates to reduce prediction variance. Third, we use this new model as a second-life assessment tool by proposing a knee region classifier. Last, using model ensembling, we build a “model of models”. We show that it outperforms each underpinning model (from in-cycle variability, cycle-to-cycle variability, and empirical models). This ‘ensembling’ strategy allows coupling explainable and black-box methods, thus giving the user extra control over the final model.application/pdfenOnline Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model EnsemblingStrange, CalumIbraheem, Rasheeddos Reis, GonçaloCMA - Centro de Matemática e AplicaçõesMDPI - Multidisciplinary Digital Publishing InstituteHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptISSNIsPartOf1996-1073URNIsPartOfPURE: 66169186URNIsPartOfPURE UUID: 53f4b863-6be7-4c13-91c1-e1e1ac059937URNIsPartOfScopus: 85152772082URNIsPartOfWOS: 000969555400001DOIIsPartOf10.3390/en160732732023-07-13T22:18:37Z2023-04-062023-04-06T00:00:00ZHandlehttp://hdl.handle.net/10362/155253http://purl.org/coar/access_right/c_abf2open accesscloud computingensemble modelsmachine learningprediction of full degradation curveremaining-useful-lifeRenewable Energy, Sustainability and the EnvironmentFuel TechnologyEngineering (miscellaneous)Energy Engineering and Power TechnologyEnergy (miscellaneous)Control and OptimizationElectrical and Electronic EngineeringSDG 7 - Affordable and Clean Energy755321 bytesFundação para a Ciência e a TecnologiaCenter for Mathematics and Applications6817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871literaturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/1224f4fc-3a0c-41fe-ab52-c82883a7641c/download |
| spellingShingle | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling Strange, Calum cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| status | SINGLETON |
| subject.fl_str_mv | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| title | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| title_full | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| title_fullStr | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| title_full_unstemmed | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| title_short | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| title_sort | Online Lifetime Prediction for Lithium-Ion Batteries with Cycle-by-Cycle Updates, Variance Reduction, and Model Ensembling |
| topic | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| topic_facet | cloud computing ensemble models machine learning prediction of full degradation curve remaining-useful-life Renewable Energy, Sustainability and the Environment Fuel Technology Engineering (miscellaneous) Energy Engineering and Power Technology Energy (miscellaneous) Control and Optimization Electrical and Electronic Engineering SDG 7 - Affordable and Clean Energy |
| url | http://hdl.handle.net/10362/155253 |
| visible | 1 |