Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework

Marcato, Agnese; Estrada Santos, Javier Andreas; Liu, Chaoyue; Boccardo, Gianluca; Marchisio, Daniele; Franco, Alejandro A.

doi:10.1016/j.ensm.2023.102927

Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework

Journal Article · Thu Aug 17 00:00:00 EDT 2023 · Energy Storage Materials

DOI:https://doi.org/10.1016/j.ensm.2023.102927· OSTI ID:1997186

Marcato, Agnese ^[1]; ^[2]; Liu, Chaoyue ^[3]; Boccardo, Gianluca ^[4]; Marchisio, Daniele ^[4]; ^[5]

Politecnico di Torino (Italy); Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Université de Picardie Jules Verne, Amiens (France); Hub de l'Energie, Amiens (France)
Politecnico di Torino (Italy)
Université de Picardie Jules Verne, Amiens (France); Hub de l'Energie, Amiens (France); Institut Universitaire de France, Paris (France)

The lithium-ion battery (LIB) field is moving towards the direction of investigating spatially resolved physical phenomena in the 3D porous microstructure of electrodes. These pore-scale simulations give new insights into the local dynamics of lithiation/de-lithiation and charge transport, Nevertheless, the computational time of these simulations limits the integration of these models in optimization workflows of cycling conditions or electrode manufacturing processes. Machine learning models present a way of assessing in real-time the performance of materials. While several successful techniques for replicating simulations with machine learning have been proposed, this case study presents a more demanding problem, due to the necessity of understanding the behavior of heterogeneous 3D local data, as it evolves in time: this poses both a scientific and a technical challenge. To this end, we propose an autoregressive multiscale convolutional neural network model to predict relevant quantities at the pore-scale in the solid phase: the lithium concentration (in the active material) and potential (in the active material and carbon binder). Here, these are ultimately used to reconstruct the battery discharge curve. 3D images of the electrode microstructures are the input to the network, trained with a dataset of finite element method simulations to predict the discharge behavior of the cathode side in lithium ion batteries. We propose this machine learning model as a proof-of-concept of the applicability of multiscale networks for time-dependent physics problems. The trained model exhibits very high accuracy (with errors lower than 2 %) in forecasting the discharge behavior of new unseen cathodes.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 1997186

Report Number(s):: LA-UR--23-29350

Journal Information:: Energy Storage Materials, Journal Name: Energy Storage Materials Vol. 63; ISSN 2405-8297

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (48)

Reconciling deep learning and first‐principle modelling for the investigation of transport phenomena in chemical engineering Marcato, Agnese; Marchisio, Daniele; Boccardo, Gianluca The Canadian Journal of Chemical Engineering, Vol. 101, Issue 6 https://doi.org/10.1002/cjce.24838	journal	February 2023
Influence of carbon binder domain on the performance of lithium‐ion batteries: Impact of size and fractal dimension Chauhan, Anshuman; Asylbekov, Ermek; Kespe, Susanne Electrochemical Science Advances, Vol. 3, Issue 1 https://doi.org/10.1002/elsa.202100151	journal	February 2022
Electrochemical transport modelling and open-source simulation of pore-scale solid–liquid systems Barnett, Robert; Municchi, Federico; King, John Engineering with Computers, Vol. 39, Issue 6 https://doi.org/10.1007/s00366-023-01828-5	journal	September 2023
Impact of geostatistical nonstationarity on convolutional neural network predictions Liu, Lei; Prodanović, Maša; Pyrcz, Michael J. Computational Geosciences, Vol. 27, Issue 1 https://doi.org/10.1007/s10596-022-10181-3	journal	November 2022
Computationally Efficient Multiscale Neural Networks Applied to Fluid Flow in Complex 3D Porous Media Santos, Javier E.; Yin, Ying; Jo, Honggeun Transport in Porous Media, Vol. 140, Issue 1 https://doi.org/10.1007/s11242-021-01617-y	journal	May 2021
Homogenization-Informed Convolutional Neural Networks for Estimation of Li-ion Battery Effective Properties Weber, Ross M.; Korneev, Svyatoslav; Battiato, Ilenia Transport in Porous Media, Vol. 145, Issue 2 https://doi.org/10.1007/s11242-022-01862-9	journal	October 2022
PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media Santos, Javier E.; Xu, Duo; Jo, Honggeun Advances in Water Resources, Vol. 138 https://doi.org/10.1016/j.advwatres.2020.103539	journal	April 2020
Deep neural networks for improving physical accuracy of 2D and 3D multi-mineral segmentation of rock micro-CT images Wang, Ying Da; Shabaninejad, Mehdi; Armstrong, Ryan T. Applied Soft Computing, Vol. 104 https://doi.org/10.1016/j.asoc.2021.107185	journal	June 2021
Prediction of local concentration fields in porous media with chemical reaction using a multi scale convolutional neural network Marcato, Agnese; Santos, Javier E.; Boccardo, Gianluca Chemical Engineering Journal, Vol. 455 https://doi.org/10.1016/j.cej.2022.140367	journal	January 2023
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales Thompson, Aidan P.; Aktulga, H. Metin; Berger, Richard Computer Physics Communications, Vol. 271 https://doi.org/10.1016/j.cpc.2021.108171	journal	February 2022
Three-dimensional particle-resolved models of Li-ion batteries to assist the evaluation of empirical parameters in one-dimensional models Goldin, Graham M.; Colclasure, Andrew M.; Wiedemann, Andreas H. Electrochimica Acta, Vol. 64 https://doi.org/10.1016/j.electacta.2011.12.119	journal	March 2012
Effects of three-dimensional cathode microstructure on the performance of lithium-ion battery cathodes Wiedemann, Andreas H.; Goldin, Graham M.; Barnett, Scott A. Electrochimica Acta, Vol. 88 https://doi.org/10.1016/j.electacta.2012.10.104	journal	January 2013
A Modified Multiphysics model for Lithium-Ion batteries with a LixNi1/3Mn1/3Co1/3O2 electrode Smekens, J.; Paulsen, J.; Yang, W. Electrochimica Acta, Vol. 174 https://doi.org/10.1016/j.electacta.2015.06.015	journal	August 2015
Tracking variabilities in the simulation of Lithium Ion Battery electrode fabrication and its impact on electrochemical performance Rucci, Alexis; Ngandjong, Alain C.; Primo, Emiliano N. Electrochimica Acta, Vol. 312 https://doi.org/10.1016/j.electacta.2019.04.110	journal	July 2019
Survey and sensitivity analysis of critical parameters in lithium-ion battery thermo-electrochemical modeling Lagnoni, Marco; Nicolella, Cristiano; Bertei, Antonio Electrochimica Acta, Vol. 394 https://doi.org/10.1016/j.electacta.2021.139098	journal	October 2021
An experimentally-validated 3D electrochemical model revealing electrode manufacturing parameters’ effects on battery performance Liu, Chaoyue; Lombardo, Teo; Xu, Jiahui Energy Storage Materials, Vol. 54 https://doi.org/10.1016/j.ensm.2022.10.035	journal	January 2023
Machine learning-assisted multi-objective optimization of battery manufacturing from synthetic data generated by physics-based simulations Duquesnoy, Marc; Liu, Chaoyue; Dominguez, Diana Zapata Energy Storage Materials, Vol. 56 https://doi.org/10.1016/j.ensm.2022.12.040	journal	February 2023
Modeling analysis of the effect of battery design on internal short circuit hazard in LiNi0.8Co0.1Mn0.1O2/SiOx-graphite lithium ion batteries Liu, Chaoyue; Li, Hang; Kong, Xiangbang International Journal of Heat and Mass Transfer, Vol. 153 https://doi.org/10.1016/j.ijheatmasstransfer.2020.119590	journal	June 2020
Finite-size effects on heat and mass transfer in porous electrodes Astaneh, Majid; Maggiolo, Dario; Ström, Henrik International Journal of Thermal Sciences, Vol. 179 https://doi.org/10.1016/j.ijthermalsci.2022.107610	journal	September 2022
Experiment and simulation of the fabrication process of lithium-ion battery cathodes for determining microstructure and mechanical properties Forouzan, Mehdi M.; Chao, Chien-Wei; Bustamante, Danilo Journal of Power Sources, Vol. 312 https://doi.org/10.1016/j.jpowsour.2016.02.014	journal	April 2016
Review of simplified Pseudo-two-Dimensional models of lithium-ion batteries Jokar, Ali; Rajabloo, Barzin; Désilets, Martin Journal of Power Sources, Vol. 327 https://doi.org/10.1016/j.jpowsour.2016.07.036	journal	September 2016
Modeling and simulation of inhomogeneities in a 18650 nickel-rich, silicon-graphite lithium-ion cell during fast charging Sturm, J.; Rheinfeld, A.; Zilberman, I. Journal of Power Sources, Vol. 412 https://doi.org/10.1016/j.jpowsour.2018.11.043	journal	February 2019
Lithium ion battery electrodes predicted from manufacturing simulations: Assessing the impact of the carbon-binder spatial location on the electrochemical performance Chouchane, Mehdi; Rucci, Alexis; Lombardo, Teo Journal of Power Sources, Vol. 444 https://doi.org/10.1016/j.jpowsour.2019.227285	journal	December 2019
Investigating electrode calendering and its impact on electrochemical performance by means of a new discrete element method model: Towards a digital twin of Li-Ion battery manufacturing Ngandjong, Alain C.; Lombardo, Teo; Primo, Emiliano N. Journal of Power Sources, Vol. 485 https://doi.org/10.1016/j.jpowsour.2020.229320	journal	February 2021
A review on electric vehicle battery modelling: From Lithium-ion toward Lithium–Sulphur Fotouhi, Abbas; Auger, Daniel J.; Propp, Karsten Renewable and Sustainable Energy Reviews, Vol. 56 https://doi.org/10.1016/j.rser.2015.12.009	journal	April 2016
Use of machine learning tools and NIR spectra to estimate residual moisture in freeze-dried products Massei, Ambra; Falco, Nunzia; Fissore, Davide Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, Vol. 293 https://doi.org/10.1016/j.saa.2023.122485	journal	May 2023
Charge transport modelling of Lithium-ion batteries Richardson, G. W.; Foster, J. M.; Ranom, R. European Journal of Applied Mathematics, Vol. 33, Issue 6 https://doi.org/10.1017/S0956792521000292	journal	October 2021
Solute transport and reaction in porous electrodes at high Schmidt numbers Maggiolo, Dario; Picano, Francesco; Zanini, Filippo Journal of Fluid Mechanics, Vol. 896 https://doi.org/10.1017/jfm.2020.344	journal	May 2020
Boosting Rechargeable Batteries R&D by Multiscale Modeling: Myth or Reality? Franco, Alejandro A.; Rucci, Alexis; Brandell, Daniel Chemical Reviews, Vol. 119, Issue 7 https://doi.org/10.1021/acs.chemrev.8b00239	journal	March 2019
From Computational Fluid Dynamics to Structure Interpretation via Neural Networks: An Application to Flow and Transport in Porous Media Marcato, Agnese; Boccardo, Gianluca; Marchisio, Daniele Industrial & Engineering Chemistry Research, Vol. 61, Issue 24 https://doi.org/10.1021/acs.iecr.1c04760	journal	March 2022
Dynamically Polarizable Force Fields for Surface Simulations via Multi-output Classification Neural Networks Di Pasquale, Nicodemo; Elliott, Joshua D.; Hadjidoukas, Panagiotis Journal of Chemical Theory and Computation, Vol. 17, Issue 7 https://doi.org/10.1021/acs.jctc.1c00360	journal	July 2021
Multiscale Simulation Platform Linking Lithium Ion Battery Electrode Fabrication Process with Performance at the Cell Level Ngandjong, Alain C.; Rucci, Alexis; Maiza, Mariem The Journal of Physical Chemistry Letters, Vol. 8, Issue 23 https://doi.org/10.1021/acs.jpclett.7b02647	journal	November 2017
Beneficial Effects of Three-Dimensional Structured Electrodes for the Fast Charging of Lithium-Ion Batteries De Lauri, Vittorio; Krumbein, Lukas; Hein, Simon ACS Applied Energy Materials, Vol. 4, Issue 12 https://doi.org/10.1021/acsaem.1c02621	journal	December 2021
Visualizing the Carbon Binder Phase of Battery Electrodes in Three Dimensions Daemi, Sohrab R.; Tan, Chun; Volkenandt, Tobias ACS Applied Energy Materials, Vol. 1, Issue 8 https://doi.org/10.1021/acsaem.8b00501	journal	July 2018
Probing the Role of Multi-scale Heterogeneity in Graphite Electrodes for Extreme Fast Charging Parmananda, Mukul; Norris, Chance; Roberts, Scott A. ACS Applied Materials & Interfaces, Vol. 14, Issue 16 https://doi.org/10.1021/acsami.1c25214	journal	April 2022
3D microstructure design of lithium-ion battery electrodes assisted by X-ray nano-computed tomography and modelling Lu, Xuekun; Bertei, Antonio; Finegan, Donal P. Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-15811-x	journal	April 2020
Machine-learning-revealed statistics of the particle-carbon/binder detachment in lithium-ion battery cathodes Jiang, Zhisen; Li, Jizhou; Yang, Yang Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-16233-5	journal	May 2020
Bridging nano- and microscale X-ray tomography for battery research by leveraging artificial intelligence Scharf, Jonathan; Chouchane, Mehdi; Finegan, Donal P. Nature Nanotechnology, Vol. 17, Issue 5 https://doi.org/10.1038/s41565-022-01081-9	journal	April 2022
Towards autonomous high-throughput multiscale modelling of battery interfaces Deng, Zeyu; Kumar, Vipin; Bölle, Felix T. Energy & Environmental Science, Vol. 15, Issue 2 https://doi.org/10.1039/D1EE02324A	journal	January 2022
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
Modeling of Galvanostatic Charge and Discharge of the Lithium/Polymer/Insertion Cell Doyle, Marc Journal of The Electrochemical Society, Vol. 140, Issue 6 https://doi.org/10.1149/1.2221597	journal	January 1993
Pore Network Modelling of Galvanostatic Discharge Behaviour of Lithium-Ion Battery Cathodes Khan, Zohaib Atiq; Agnaou, Mehrez; Sadeghi, Mohammad Amin Journal of The Electrochemical Society, Vol. 168, Issue 7 https://doi.org/10.1149/1945-7111/ac120c	journal	July 2021
Temperature and Concentration Dependence of the Ionic Transport Properties of Lithium-Ion Battery Electrolytes Landesfeind, Johannes; Gasteiger, Hubert A. Journal of The Electrochemical Society, Vol. 166, Issue 14 https://doi.org/10.1149/2.0571912jes	journal	January 2019
High Rate Capability of Li(Ni _1/3 Mn _1/3 Co _1/3 )O ₂ Electrode for Li-Ion Batteries Wu, Shao-Ling; Zhang, Wei; Song, Xiangyun Journal of The Electrochemical Society, Vol. 159, Issue 4 https://doi.org/10.1149/2.062204jes	journal	January 2012
Resolving the Discrepancy in Tortuosity Factor Estimation for Li-Ion Battery Electrodes through Micro-Macro Modeling and Experiment Usseglio-Viretta, Francois L. E.; Colclasure, Andrew; Mistry, Aashutosh N. Journal of The Electrochemical Society, Vol. 165, Issue 14 https://doi.org/10.1149/2.0731814jes	journal	January 2018
Aging of a Lithium-Metal/LFP Cell: Predictive Model and Experimental Validation Dessantis, Davide; Di Prima, Piera; Versaci, Daniele Batteries, Vol. 9, Issue 3 https://doi.org/10.3390/batteries9030146	journal	February 2023
Using Machine Learning to Predict Multiphase Flow through Complex Fractures Ting, Allen K.; Santos, Javier E.; Guiltinan, Eric Energies, Vol. 15, Issue 23 https://doi.org/10.3390/en15238871	journal	November 2022
Python Battery Mathematical Modelling (PyBaMM) Sulzer, Valentin; Marquis, Scott G.; Timms, Robert Journal of Open Research Software, Vol. 9 https://doi.org/10.5334/jors.309	journal	January 2021

Similar Records

Integrated Multiscale Model for Design of Robust 3D Solid-state Lithium Batteries

Technical Report · Tue Aug 29 00:00:00 EDT 2023 · OSTI ID:2202555

Data-driven design of electrolyte additives supporting high-performance 5 V LiNi0.5Mn1.5O4 positive electrodes

Journal Article · Thu Apr 10 00:00:00 EDT 2025 · Nature Communications · OSTI ID:2554071

Related Subjects

25 ENERGY STORAGE
Lithium-ion batteries
Machine learning
Neural networks

Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework

Citation Formats

References (48)

Similar Records

Related Subjects