A physics-induced surrogate modeling framework for lithium-ion battery electrode manufacturing
Source abstract
Abstract
The manufacturing of lithium-ion battery electrodes is a complex, multi-step process. The selection of manufacturing parameters at each stage directly affects the final microstructure of the electrode and, consequently, the electrochemical performance of the cell. Here, we demonstrate the application of our Physics-Induced Electrode (PIE) framework, comprising a set of Machine Learning (ML) models that represent key manufacturing steps: slurry, drying, and calendering. For each step, the ML model uses the coordinates of the particles (representing the active material and carbon-binder aggregates at the mesoscale), along with geometrical descriptors with physical properties, to predict the resulting particle displacement. The model predictions were evaluated using statistical metrics and were found to be significantly accurate. The predicted electrode microstructures were further assessed in terms of their properties and exhibited good agreement with those obtained from purely physics-based simulations. To enhance interpretability, SHapley Additive exPlanations (SHAP) were used to analyze the contribution of the input features to the model predictions. The SHAP analysis showed that the ML predictions capture trends consistent with physical intuition for the manufacturing step analyzed. The PIE framework offers a scalable and interpretable approach that can be integrated into digital solutions to support battery electrode manufacturing pilot lines.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advancements in Battery Materials · Advanced Battery Technologies Research · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (48)
Show source-provided references
1. Circular economy: the concept and its limitations10.1016/j.ecolecon.2017.06.041 ↗
2. Integration of lithium-ion battery recycling into manufacturing through digitalization: a perspective10.1016/j.jpowsour.2024.236158 ↗
3. Beyond Li-ion batteries: performance, materials diversification, and sustainability10.1016/j.oneear.2022.02.014 ↗
4. A review of lithium-ion battery for electric vehicle applications and beyond10.1016/j.egypro.2019.01.783 ↗
5. 2024 roadmap for sustainable batteries
6. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science10.1063/1.4946894 ↗
7. A contemporary approach to the MSE paradigm powered by artificial intelligence from a review focused on polymer matrix composites10.1080/15376494.2021.1886379 ↗
8. Artificial intelligence applied to battery research: hype or reality?10.1021/acs.chemrev.1c00108 ↗
9. Accelerated optimization methods for force‐field parametrization in battery electrode manufacturing modeling10.1002/batt.202000049 ↗
10. Data specifications for battery manufacturing digitalization: current status, challenges, and opportunities10.1002/batt.202200224 ↗
11. Multiscale modelling and numerical simulation of rechargeable lithium ion batteries: concepts, methods and challenges10.1039/c3ra23502e ↗
12. Experimental-numerical studies on thermal conductivity anisotropy of lithium-ion batteries10.1016/j.est.2024.114139 ↗
13. Prediction of battery thermal behaviour in the presence of a constructal theory-based heat pipe (CBHP): a multiphysics model and pattern-based machine learning approach10.1016/j.est.2022.103963 ↗
14. A numerically efficient method of solving the full-order pseudo-2-dimensional (P2D) Li-ion cell model10.1016/j.jpowsour.2021.229571 ↗
15. Numerical simulation of electrochemical systems by coupling analytical calculation of the diffuse double layer and finite element description of solution bulk10.1002/elan.202200257 ↗
16. A fast numerical method with non-iterative source term for pseudo-two-dimension lithium-ion battery model10.1016/j.jpowsour.2023.233258 ↗
17. A computational workflow for the simulation of solid state battery electrodes from manufacturing to electrochemical performance
18. Understanding mechanical stresses upon solid-state battery electrode cycling using discrete element method
19. Effect of external pressure and internal stress on battery performance and lifespan10.1016/j.ensm.2022.07.034 ↗
20. Transfer learning assessment of small datasets relating manufacturing parameters with electrochemical energy cell component properties10.1038/s44334-025-00024-1 ↗
21. Machine learning-assisted multi-objective optimization of battery manufacturing from synthetic data generated by physics-based simulations10.1016/j.ensm.2022.12.040 ↗
22. Deconvoluting the benefits of porosity distribution in layered electrodes on the electrochemical performance of Li-ion batteries10.1016/j.ensm.2022.01.058 ↗
23. The ARTISTIC battery manufacturing digitalization initiative: from fundamental research to industrialization
24. A microstructure-resolved model of sodium-ion battery hard carbon electrodes10.1016/j.jpowsour.2025.237878 ↗
25. Elucidating Pt/C and ionomer aggregation dynamics in the manufacturing of fuel cell catalyst layers: a discrete element method approach10.1016/j.jpowsour.2025.238238 ↗
26. Multiscale simulation platform linking lithium ion battery electrode fabrication process with performance at the cell level10.1021/acs.jpclett.7b02647 ↗
27. Tracking variabilities in the simulation of Lithium Ion Battery electrode fabrication and its impact on electrochemical performance10.1016/j.electacta.2019.04.110 ↗
28. 3D resolved computational modeling to simulate the electrolyte wetting of a lithium‐ion battery cell with 18650 format10.1002/batt.202500434 ↗
29. Digital correlation analysis and optimization of microporous layer through a machine learning workflow for PEMFC applications10.1016/j.jpowsour.2025.237522 ↗
30. Machine learning-driven optimization of gas diffusion layer microstructure for PEM fuel cells10.1016/j.jpowsour.2024.235583 ↗
31. A hybrid modelling approach coupling physics-based simulation and deep learning for battery electrode manufacturing simulations
32. Surrogate modeling of lithium‐ion battery electrode manufacturing by combining physics‐based simulation and deep learning10.1002/batt.202500433 ↗
33. Physics-Assisted machine learning for the simulation of the slurry drying in the manufacturing process of battery electrodes: a hybrid time-dependent VGG16-DEM model10.1021/acsami.4c23103 ↗
34. Microrheological modeling of lithium ion battery anode slurry10.1016/j.jpowsour.2019.226994 ↗
35. Impact of formulation and slurry properties on Lithium‐ion electrode manufacturing10.1002/batt.202300396 ↗
36. Modeling and optimizing the drying process of electrode manufacturing for lithium‐ion batteries10.1002/ente.202401146 ↗
37. Study of an industrial electrode dryer of a lithium-ion battery manufacturing plant: dynamic modelling
38. Process modeling of the electrode calendering of lithium-ion batteries regarding variation of cathode active materials and mass loadings10.1016/j.est.2018.05.018 ↗
39. Modeling of unit pressure distribution and roll stress analysis during lithium-ion battery electrode calendering10.1016/j.est.2025.118698 ↗
40. Perspective: machine learning potentials for atomistic simulations10.1063/1.4966192 ↗
41. Machine learning interatomic potentials as emerging tools for materials science10.1002/adma.201902765 ↗
42. Understanding physics-informed neural networks: techniques, applications, trends, and challenges10.3390/ai5030074 ↗
43. Physics-guided, physics-informed, and physics-encoded neural networks and operators in scientific computing: fluid and solid mechanics10.1115/1.4064449 ↗
44. Lithium ion battery electrode manufacturing model accounting for 3D realistic shapes of active material particles10.1016/j.jpowsour.2022.232294 ↗
45. 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 manufacturing10.1016/j.jpowsour.2020.229320 ↗
46. Understanding the calendering processability of Li (Ni0. 33Mn0. 33Co0. 33) O2-based cathodes10.1016/j.jpowsour.2020.229361 ↗
47. Generalized neural-network representation of high-dimensional potential-energy surfaces10.1103/PhysRevLett.98.146401 ↗
48. Random forests10.1023/A:1010933404324 ↗