Publicação

Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions

Ver documento

Detalhes bibliográficos
Resumo:Single-value prediction such as the End of Life and Remaining Useful Life is a common method of estimating the lifetime of Li-ion batteries. Information from such prediction is limited when the entire degradation pattern is needed for practical applications such as dynamic adjustment of battery warranty, improved maintenance scheduling, and battery stock management. In this research, a predictive, semi-parametric survival model called the Cox Proportional Hazards is proposed for the prediction of cell degradation in the form of survival probability (battery reliability) and cumulative hazard (battery risk) functions. Once this model is trained, the two functions can be obtained directly for a new cell without having to predict several cogent points. The model is trained on the first 50 cycles of only the voltage profile from either the charge or discharge data regime, implying that our methodology is data region agnostic. The signature method with both desirable mathematical and machine learning properties was adopted as a feature extraction technique. The developed models are tested rigorously using application-driven strategies involving model robustness to the number of cycles of data required for model training and prediction, different fractions of training samples, and systematic data sparsity. The codes for modeling and testing are publicly available.
Autores principais:Ibraheem, Rasheed
Outros Autores:Cannings, Timothy I.; Sell, Torben; dos Reis, Gonçalo
Assunto:Battery degradation Cox Proportional Hazards Cumulative hazard function Path signature methodology Reliability and risk functions Survival analysis Survival probability function Engineering (miscellaneous) General Energy Artificial Intelligence
Ano:2025
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_ 1868982375891861504
author Ibraheem, Rasheed
author2 Cannings, Timothy I.
Sell, Torben
dos Reis, Gonçalo
author2_role author
author
author
author_facet Ibraheem, Rasheed
Cannings, Timothy I.
Sell, Torben
dos Reis, Gonçalo
author_role author
contributor_name_str_mv CMA - Centro de Matemática e Aplicações
Faculdade de Ciências e Tecnologia (FCT)
Elsevier
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Ibraheem, Rasheed\"},{\"Person.name\":\"Cannings, Timothy I.\"},{\"Person.name\":\"Sell, Torben\"},{\"Person.name\":\"dos Reis, Gonçalo\"}]
datacite.contributors.contributor.contributorName.fl_str_mv CMA - Centro de Matemática e Aplicações
Faculdade de Ciências e Tecnologia (FCT)
Elsevier
RUN
datacite.creators.creator.creatorName.fl_str_mv Ibraheem, Rasheed
Cannings, Timothy I.
Sell, Torben
dos Reis, Gonçalo
datacite.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2025-07-15T21:17:15Z
datacite.date.embargoed.fl_str_mv 2025-07-15T21:17:15Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
datacite.titles.title.fl_str_mv Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
dc.contributor.none.fl_str_mv CMA - Centro de Matemática e Aplicações
Faculdade de Ciências e Tecnologia (FCT)
Elsevier
RUN
dc.creator.none.fl_str_mv Ibraheem, Rasheed
Cannings, Timothy I.
Sell, Torben
dos Reis, Gonçalo
dc.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
dc.date.available.fl_str_mv 2025-07-15T21:17:15Z
dc.date.embargoed.fl_str_mv 2025-07-15T21:17:15Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/185194
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 Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
dc.title.fl_str_mv Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Single-value prediction such as the End of Life and Remaining Useful Life is a common method of estimating the lifetime of Li-ion batteries. Information from such prediction is limited when the entire degradation pattern is needed for practical applications such as dynamic adjustment of battery warranty, improved maintenance scheduling, and battery stock management. In this research, a predictive, semi-parametric survival model called the Cox Proportional Hazards is proposed for the prediction of cell degradation in the form of survival probability (battery reliability) and cumulative hazard (battery risk) functions. Once this model is trained, the two functions can be obtained directly for a new cell without having to predict several cogent points. The model is trained on the first 50 cycles of only the voltage profile from either the charge or discharge data regime, implying that our methodology is data region agnostic. The signature method with both desirable mathematical and machine learning properties was adopted as a feature extraction technique. The developed models are tested rigorously using application-driven strategies involving model robustness to the number of cycles of data required for model training and prediction, different fractions of training samples, and systematic data sparsity. The codes for modeling and testing are publicly available.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/09c44d8a-447f-422a-a94b-f1ab7f098014/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_0e7c2fa01f5364a45e4bbd77c2668ca2
identifier.url.fl_str_mv http://hdl.handle.net/10362/185194
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:10362/185194
organization_str_mv urn:organizationAcronym:unl
person_str_mv Ibraheem, Rasheed
Cannings, Timothy I.
Sell, Torben
dos Reis, Gonçalo
publishDate 2025
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 engenSingle-value prediction such as the End of Life and Remaining Useful Life is a common method of estimating the lifetime of Li-ion batteries. Information from such prediction is limited when the entire degradation pattern is needed for practical applications such as dynamic adjustment of battery warranty, improved maintenance scheduling, and battery stock management. In this research, a predictive, semi-parametric survival model called the Cox Proportional Hazards is proposed for the prediction of cell degradation in the form of survival probability (battery reliability) and cumulative hazard (battery risk) functions. Once this model is trained, the two functions can be obtained directly for a new cell without having to predict several cogent points. The model is trained on the first 50 cycles of only the voltage profile from either the charge or discharge data regime, implying that our methodology is data region agnostic. The signature method with both desirable mathematical and machine learning properties was adopted as a feature extraction technique. The developed models are tested rigorously using application-driven strategies involving model robustness to the number of cycles of data required for model training and prediction, different fractions of training samples, and systematic data sparsity. The codes for modeling and testing are publicly available.application/pdfenRobust survival model for the prediction of Li-ion battery lifetime reliability and risk functionsIbraheem, RasheedCannings, Timothy I.Sell, Torbendos Reis, GonçaloCMA - Centro de Matemática e AplicaçõesFaculdade de Ciências e Tecnologia (FCT)ElsevierHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptISSNIsPartOf2666-5468URNIsPartOfPURE: 121823956URNIsPartOfPURE UUID: 995aa339-a381-44b9-95fd-2f95b4bcb2ebURNIsPartOfScopus: 85214489492URNIsPartOfWOS: 001397456600001DOIIsPartOf10.1016/j.egyai.2024.1004652025-07-15T21:17:15Z2025-012025-01-01T00:00:00ZHandlehttp://hdl.handle.net/10362/185194http://purl.org/coar/access_right/c_abf2open accessBattery degradationCox Proportional HazardsCumulative hazard functionPath signature methodologyReliability and risk functionsSurvival analysisSurvival probability functionEngineering (miscellaneous)General EnergyArtificial Intelligence3541706 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/09c44d8a-447f-422a-a94b-f1ab7f098014/download
spellingShingle Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
Ibraheem, Rasheed
Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
status SINGLETON
subject.fl_str_mv Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
title Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
title_full Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
title_fullStr Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
title_full_unstemmed Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
title_short Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
title_sort Robust survival model for the prediction of Li-ion battery lifetime reliability and risk functions
topic Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
topic_facet Battery degradation
Cox Proportional Hazards
Cumulative hazard function
Path signature methodology
Reliability and risk functions
Survival analysis
Survival probability function
Engineering (miscellaneous)
General Energy
Artificial Intelligence
url http://hdl.handle.net/10362/185194
visible 1