Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning

Stavros X. Drakopoulos; Azarmidokht Gholamipour-Shirazi; Paul MacDonald; Robert C. Parini; Carl D. Reynolds; David L. Burnett; Ben Pye; Kieran B. O'Regan; Guanmei Wang; Thomas M. Whitehead; Gareth J. Conduit; Alexandru Cazacu; Emma Kendrick

doi:10.1016/j.xcrp.2021.100683

Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning

Stavros X. Drakopoulos, Azarmidokht Gholamipour-Shirazi, Paul MacDonald, Robert C. Parini, Carl D. Reynolds, David L. Burnett, Ben Pye, Kieran B. O'Regan, Guanmei Wang, Thomas M. Whitehead, Gareth J. Conduit, Alexandru Cazacu, Emma Kendrick^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

195 Downloads (Pure)

Abstract

Understanding the formulation and manufacturing parameters that lead to higher energy density and longevity is critical to designing energy-dense graphite electrodes for battery applications. A limited dataset that includes 27 different formulation, manufacturing protocols, and performance properties is reported. Input parameters from formulation and manufacturing are varied: slurry composition, mixing protocol, electrode coating gap size, drying temperature, coating speed, and calendering. Measurable outputs from the rheological characteristics, adhesion, and electrochemical testing are recorded. A database with the inputs and output parameters is populated and used to train an artificial intelligence model. Validation of the model is performed upon test data and an optimized electrode formulation and manufacturing process predicted. The electrode manufactured using the model process shows excellent cycle life and capacity agreement to prediction. The data model can be used to predict and design the formulation and manufacturing process to produce thick, high-coat-weight, graphite-based electrodes.

Original language	English
Article number	100683
Number of pages	20
Journal	Cell Reports Physical Science
Volume	2
Issue number	12
Early online date	7 Dec 2021
DOIs	https://doi.org/10.1016/j.xcrp.2021.100683
Publication status	Published - 22 Dec 2021

Bibliographical note

Funding Information:
All the authors would like to acknowledge the Innovate UK Faraday Challenge Competition for funding under project no. 133855 . C.D.R. and E.K. acknowledge financial support from The Faraday Institution , NEXTRODE project ( https://faraday.ac.uk ; EP/S003053/1), grant number FIRG015 . K.B.O. and E.K. acknowledge financial support from The Faraday Institution , MSM project ( https://faraday.ac.uk ; EP/S003053/1), grant numbers FITG011 and FIRG003 . G.J.C. acknowledges financial support from the Royal Society .

Publisher Copyright:
© 2021 The Author(s)

Keywords

artificial intelligence
electrode manufacturing
formulation
graphite
lithium-ion batteries
machine learning

ASJC Scopus subject areas

General Physics and Astronomy
General Materials Science
General Chemistry
General Energy
General Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.xcrp.2021.100683

DrakopoulosS2021FormulationFinal published version, 4.13 MBLicence: Creative Commons: Attribution (CC BY)

Cite this

Drakopoulos, S. X., Gholamipour-Shirazi, A., MacDonald, P., Parini, R. C., Reynolds, C. D., Burnett, D. L., Pye, B., O'Regan, K. B., Wang, G., Whitehead, T. M., Conduit, G. J., Cazacu, A., & Kendrick, E. (2021). Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning. Cell Reports Physical Science, 2(12), Article 100683. https://doi.org/10.1016/j.xcrp.2021.100683

@article{0844e81ca0634da2bd08bbc745fe9b86,

title = "Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning",

abstract = "Understanding the formulation and manufacturing parameters that lead to higher energy density and longevity is critical to designing energy-dense graphite electrodes for battery applications. A limited dataset that includes 27 different formulation, manufacturing protocols, and performance properties is reported. Input parameters from formulation and manufacturing are varied: slurry composition, mixing protocol, electrode coating gap size, drying temperature, coating speed, and calendering. Measurable outputs from the rheological characteristics, adhesion, and electrochemical testing are recorded. A database with the inputs and output parameters is populated and used to train an artificial intelligence model. Validation of the model is performed upon test data and an optimized electrode formulation and manufacturing process predicted. The electrode manufactured using the model process shows excellent cycle life and capacity agreement to prediction. The data model can be used to predict and design the formulation and manufacturing process to produce thick, high-coat-weight, graphite-based electrodes.",

keywords = "artificial intelligence, electrode manufacturing, formulation, graphite, lithium-ion batteries, machine learning",

author = "Drakopoulos, {Stavros X.} and Azarmidokht Gholamipour-Shirazi and Paul MacDonald and Parini, {Robert C.} and Reynolds, {Carl D.} and Burnett, {David L.} and Ben Pye and O'Regan, {Kieran B.} and Guanmei Wang and Whitehead, {Thomas M.} and Conduit, {Gareth J.} and Alexandru Cazacu and Emma Kendrick",

note = "Funding Information: All the authors would like to acknowledge the Innovate UK Faraday Challenge Competition for funding under project no. 133855 . C.D.R. and E.K. acknowledge financial support from The Faraday Institution , NEXTRODE project ( https://faraday.ac.uk ; EP/S003053/1), grant number FIRG015 . K.B.O. and E.K. acknowledge financial support from The Faraday Institution , MSM project ( https://faraday.ac.uk ; EP/S003053/1), grant numbers FITG011 and FIRG003 . G.J.C. acknowledges financial support from the Royal Society . Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2021",

month = dec,

day = "22",

doi = "10.1016/j.xcrp.2021.100683",

language = "English",

volume = "2",

journal = "Cell Reports Physical Science",

issn = "2666-3864",

publisher = "Elsevier",

number = "12",

}

Drakopoulos, SX, Gholamipour-Shirazi, A, MacDonald, P, Parini, RC, Reynolds, CD , Burnett, DL, Pye, B, O'Regan, KB, Wang, G, Whitehead, TM, Conduit, GJ, Cazacu, A & Kendrick, E 2021, 'Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning', Cell Reports Physical Science, vol. 2, no. 12, 100683. https://doi.org/10.1016/j.xcrp.2021.100683

TY - JOUR

T1 - Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning

AU - Drakopoulos, Stavros X.

AU - Gholamipour-Shirazi, Azarmidokht

AU - MacDonald, Paul

AU - Parini, Robert C.

AU - Reynolds, Carl D.

AU - Burnett, David L.

AU - Pye, Ben

AU - O'Regan, Kieran B.

AU - Wang, Guanmei

AU - Whitehead, Thomas M.

AU - Conduit, Gareth J.

AU - Cazacu, Alexandru

AU - Kendrick, Emma

N1 - Funding Information: All the authors would like to acknowledge the Innovate UK Faraday Challenge Competition for funding under project no. 133855 . C.D.R. and E.K. acknowledge financial support from The Faraday Institution , NEXTRODE project ( https://faraday.ac.uk ; EP/S003053/1), grant number FIRG015 . K.B.O. and E.K. acknowledge financial support from The Faraday Institution , MSM project ( https://faraday.ac.uk ; EP/S003053/1), grant numbers FITG011 and FIRG003 . G.J.C. acknowledges financial support from the Royal Society . Publisher Copyright: © 2021 The Author(s)

PY - 2021/12/22

Y1 - 2021/12/22

N2 - Understanding the formulation and manufacturing parameters that lead to higher energy density and longevity is critical to designing energy-dense graphite electrodes for battery applications. A limited dataset that includes 27 different formulation, manufacturing protocols, and performance properties is reported. Input parameters from formulation and manufacturing are varied: slurry composition, mixing protocol, electrode coating gap size, drying temperature, coating speed, and calendering. Measurable outputs from the rheological characteristics, adhesion, and electrochemical testing are recorded. A database with the inputs and output parameters is populated and used to train an artificial intelligence model. Validation of the model is performed upon test data and an optimized electrode formulation and manufacturing process predicted. The electrode manufactured using the model process shows excellent cycle life and capacity agreement to prediction. The data model can be used to predict and design the formulation and manufacturing process to produce thick, high-coat-weight, graphite-based electrodes.

AB - Understanding the formulation and manufacturing parameters that lead to higher energy density and longevity is critical to designing energy-dense graphite electrodes for battery applications. A limited dataset that includes 27 different formulation, manufacturing protocols, and performance properties is reported. Input parameters from formulation and manufacturing are varied: slurry composition, mixing protocol, electrode coating gap size, drying temperature, coating speed, and calendering. Measurable outputs from the rheological characteristics, adhesion, and electrochemical testing are recorded. A database with the inputs and output parameters is populated and used to train an artificial intelligence model. Validation of the model is performed upon test data and an optimized electrode formulation and manufacturing process predicted. The electrode manufactured using the model process shows excellent cycle life and capacity agreement to prediction. The data model can be used to predict and design the formulation and manufacturing process to produce thick, high-coat-weight, graphite-based electrodes.

KW - artificial intelligence

KW - electrode manufacturing

KW - formulation

KW - graphite

KW - lithium-ion batteries

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85121601065&partnerID=8YFLogxK

U2 - 10.1016/j.xcrp.2021.100683

DO - 10.1016/j.xcrp.2021.100683

M3 - Article

AN - SCOPUS:85121601065

SN - 2666-3864

VL - 2

JO - Cell Reports Physical Science

JF - Cell Reports Physical Science

IS - 12

M1 - 100683

ER -

Formulation and manufacturing optimization of lithium-ion graphite-based electrodes via machine learning

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this