Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics

Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental da...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Duquesnoy, Marc, Lombardo, Teo, Caro, Fernando, Haudiquez, Florent, Ngandjong, Alain C, Xu, Jiahui, Oularbi, Hassan, Franco, Alejandro A
Format: Artikel
Sprache: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 Duquesnoy, Marc
Lombardo, Teo
Caro, Fernando
Haudiquez, Florent
Ngandjong, Alain C
Xu, Jiahui
Oularbi, Hassan
Franco, Alejandro A
description Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental data, is typically time and resources consuming In this work, we tackled this issue by proposing a functional data-driven framework combining Functional Principal Component Analysis and K-Nearest Neighbors algorithms. This aims first to recover the early numerical values of a mechanistic electrode manufacturing simulation to predict if the observable being calculated is prone to match or not, \textit{i.e} screening step. In a second step it recovers additional numerical values of the ongoing mechanistic simulation iterations to predict the mechanistic simulation result, \textit{i.e} forecasting step. We demonstrated this approach in context of LIB manufacturing through non-equilibrium molecular dynamics (NEMD) simulations, aiming to capture the rheological behavior of electrode slurries. We discuss in full details our novel methodology and we report that the expected mechanistic simulation results can be obtained 11 times faster with respect to running the complete mechanistic simulation, while being accurate enough from an experimental point of view, with a $F1_{score}$ equals to 0.90, and a $R^2_{score}$ equals to 0.96 for the learnings validation. This paves the way towards a powerful tool to drastically reduce the utilization of computational resources while running mechanistic simulations of battery manufacturing electrodes.
doi_str_mv 10.48550/arxiv.2201.04394
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2201_04394</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2201_04394</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-7daff38b71bc9d927a4f04d23a9f4af81e244e2e0440302f2c7822d1654fa2fc3</originalsourceid><addsrcrecordid>eNotj81Og0AUhdm4MNUHcOV9AXCYGQosTSlq0sbEdk8u81MnDoy5QJW3F6urc07y5SRfFN2lLJFFlrEHpG93TjhnacKkKOV1RPXUq9GFHj1UOGJckTubHmrCznwF-gAbCGocRqgDGbUU158gWNh6o0YK2sDBT0QzvL2b4MNphoPrJo-j0dDOsA8Lt0yCau6xc2q4ia4s-sHc_ucqOtbb4-Y53r0-vWwedzGucxnnGq0VRZunrSp1yXOUlknNBZZWoi1Sw6U03DApmWDccpUXnOt0nUmL3Cqxiu7_bi_SzSe5DmlufuWbi7z4AeGjVnE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics</title><source>arXiv.org</source><creator>Duquesnoy, Marc ; Lombardo, Teo ; Caro, Fernando ; Haudiquez, Florent ; Ngandjong, Alain C ; Xu, Jiahui ; Oularbi, Hassan ; Franco, Alejandro A</creator><creatorcontrib>Duquesnoy, Marc ; Lombardo, Teo ; Caro, Fernando ; Haudiquez, Florent ; Ngandjong, Alain C ; Xu, Jiahui ; Oularbi, Hassan ; Franco, Alejandro A</creatorcontrib><description>Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental data, is typically time and resources consuming In this work, we tackled this issue by proposing a functional data-driven framework combining Functional Principal Component Analysis and K-Nearest Neighbors algorithms. This aims first to recover the early numerical values of a mechanistic electrode manufacturing simulation to predict if the observable being calculated is prone to match or not, \textit{i.e} screening step. In a second step it recovers additional numerical values of the ongoing mechanistic simulation iterations to predict the mechanistic simulation result, \textit{i.e} forecasting step. We demonstrated this approach in context of LIB manufacturing through non-equilibrium molecular dynamics (NEMD) simulations, aiming to capture the rheological behavior of electrode slurries. We discuss in full details our novel methodology and we report that the expected mechanistic simulation results can be obtained 11 times faster with respect to running the complete mechanistic simulation, while being accurate enough from an experimental point of view, with a $F1_{score}$ equals to 0.90, and a $R^2_{score}$ equals to 0.96 for the learnings validation. This paves the way towards a powerful tool to drastically reduce the utilization of computational resources while running mechanistic simulations of battery manufacturing electrodes.</description><identifier>DOI: 10.48550/arxiv.2201.04394</identifier><language>eng</language><subject>Mathematics - Functional Analysis ; Physics - Chemical Physics</subject><creationdate>2022-01</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2201.04394$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2201.04394$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Duquesnoy, Marc</creatorcontrib><creatorcontrib>Lombardo, Teo</creatorcontrib><creatorcontrib>Caro, Fernando</creatorcontrib><creatorcontrib>Haudiquez, Florent</creatorcontrib><creatorcontrib>Ngandjong, Alain C</creatorcontrib><creatorcontrib>Xu, Jiahui</creatorcontrib><creatorcontrib>Oularbi, Hassan</creatorcontrib><creatorcontrib>Franco, Alejandro A</creatorcontrib><title>Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics</title><description>Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental data, is typically time and resources consuming In this work, we tackled this issue by proposing a functional data-driven framework combining Functional Principal Component Analysis and K-Nearest Neighbors algorithms. This aims first to recover the early numerical values of a mechanistic electrode manufacturing simulation to predict if the observable being calculated is prone to match or not, \textit{i.e} screening step. In a second step it recovers additional numerical values of the ongoing mechanistic simulation iterations to predict the mechanistic simulation result, \textit{i.e} forecasting step. We demonstrated this approach in context of LIB manufacturing through non-equilibrium molecular dynamics (NEMD) simulations, aiming to capture the rheological behavior of electrode slurries. We discuss in full details our novel methodology and we report that the expected mechanistic simulation results can be obtained 11 times faster with respect to running the complete mechanistic simulation, while being accurate enough from an experimental point of view, with a $F1_{score}$ equals to 0.90, and a $R^2_{score}$ equals to 0.96 for the learnings validation. This paves the way towards a powerful tool to drastically reduce the utilization of computational resources while running mechanistic simulations of battery manufacturing electrodes.</description><subject>Mathematics - Functional Analysis</subject><subject>Physics - Chemical Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81Og0AUhdm4MNUHcOV9AXCYGQosTSlq0sbEdk8u81MnDoy5QJW3F6urc07y5SRfFN2lLJFFlrEHpG93TjhnacKkKOV1RPXUq9GFHj1UOGJckTubHmrCznwF-gAbCGocRqgDGbUU158gWNh6o0YK2sDBT0QzvL2b4MNphoPrJo-j0dDOsA8Lt0yCau6xc2q4ia4s-sHc_ucqOtbb4-Y53r0-vWwedzGucxnnGq0VRZunrSp1yXOUlknNBZZWoi1Sw6U03DApmWDccpUXnOt0nUmL3Cqxiu7_bi_SzSe5DmlufuWbi7z4AeGjVnE</recordid><startdate>20220112</startdate><enddate>20220112</enddate><creator>Duquesnoy, Marc</creator><creator>Lombardo, Teo</creator><creator>Caro, Fernando</creator><creator>Haudiquez, Florent</creator><creator>Ngandjong, Alain C</creator><creator>Xu, Jiahui</creator><creator>Oularbi, Hassan</creator><creator>Franco, Alejandro A</creator><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20220112</creationdate><title>Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics</title><author>Duquesnoy, Marc ; Lombardo, Teo ; Caro, Fernando ; Haudiquez, Florent ; Ngandjong, Alain C ; Xu, Jiahui ; Oularbi, Hassan ; Franco, Alejandro A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-7daff38b71bc9d927a4f04d23a9f4af81e244e2e0440302f2c7822d1654fa2fc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Mathematics - Functional Analysis</topic><topic>Physics - Chemical Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Duquesnoy, Marc</creatorcontrib><creatorcontrib>Lombardo, Teo</creatorcontrib><creatorcontrib>Caro, Fernando</creatorcontrib><creatorcontrib>Haudiquez, Florent</creatorcontrib><creatorcontrib>Ngandjong, Alain C</creatorcontrib><creatorcontrib>Xu, Jiahui</creatorcontrib><creatorcontrib>Oularbi, Hassan</creatorcontrib><creatorcontrib>Franco, Alejandro A</creatorcontrib><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Duquesnoy, Marc</au><au>Lombardo, Teo</au><au>Caro, Fernando</au><au>Haudiquez, Florent</au><au>Ngandjong, Alain C</au><au>Xu, Jiahui</au><au>Oularbi, Hassan</au><au>Franco, Alejandro A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics</atitle><date>2022-01-12</date><risdate>2022</risdate><abstract>Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental data, is typically time and resources consuming In this work, we tackled this issue by proposing a functional data-driven framework combining Functional Principal Component Analysis and K-Nearest Neighbors algorithms. This aims first to recover the early numerical values of a mechanistic electrode manufacturing simulation to predict if the observable being calculated is prone to match or not, \textit{i.e} screening step. In a second step it recovers additional numerical values of the ongoing mechanistic simulation iterations to predict the mechanistic simulation result, \textit{i.e} forecasting step. We demonstrated this approach in context of LIB manufacturing through non-equilibrium molecular dynamics (NEMD) simulations, aiming to capture the rheological behavior of electrode slurries. We discuss in full details our novel methodology and we report that the expected mechanistic simulation results can be obtained 11 times faster with respect to running the complete mechanistic simulation, while being accurate enough from an experimental point of view, with a $F1_{score}$ equals to 0.90, and a $R^2_{score}$ equals to 0.96 for the learnings validation. This paves the way towards a powerful tool to drastically reduce the utilization of computational resources while running mechanistic simulations of battery manufacturing electrodes.</abstract><doi>10.48550/arxiv.2201.04394</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2201.04394
ispartof
issn
language eng
recordid cdi_arxiv_primary_2201_04394
source arXiv.org
subjects Mathematics - Functional Analysis
Physics - Chemical Physics
title Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T18%3A08%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Functional%20Data-Driven%20Framework%20for%20Fast%20Forecasting%20of%20Electrode%20Slurry%20Rheology%20Simulated%20by%20Molecular%20Dynamics&rft.au=Duquesnoy,%20Marc&rft.date=2022-01-12&rft_id=info:doi/10.48550/arxiv.2201.04394&rft_dat=%3Carxiv_GOX%3E2201_04394%3C/arxiv_GOX%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