journal article·2024-12Open access

Enhancing composite cathode manufacturing with machine learning for polymer electrolyte solid-state batteries

A. Gallo-Bueno, R.A.N. Hanifah, L. Fernandez-Diaz, L. Otaegui, A. Villaverde, M.C. Morant-Miñana, J. Carrasco

Abstract

Solid-state batteries (SSBs) represent a pivotal advancement in battery technology, poised to surpass lithium-ion batteries and drive the electrification of mobility. However, achieving cost-effective, scalable, and sustainable fabrication processes for SSB components remains a challenge. This study integrates machine learning (ML) techniques to optimize manufacturing processes of cathodes for polymer electrolyte based SSBs. The findings reveal strong predictive performance of regression models for active material loading, with support vector machine emerging as the top performer. Multiclassification models exhibit satisfactory precision, particularly in categorizing ideal electrode samples. Analysis of principal component and correlation circles highlight viscosity and wet thickness as critical variables for mixing and coating, respectively. Despite promising metrics, dataset imbalance and size limit model robustness. Further dataset augmentation is recommended before deployment in production. ML techniques offer promise in advancing battery manufacturing, paving the way for enhanced SSB performance and broader application across battery components. • Machine learning optimized cathode manufacturing for solid-state batteries. • Models achieved high predictive accuracy for active material loading. • Viscosity and wet thickness were key to improving electrode fabrication. • Key variables improved mixing and coating processes in electrode production.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Advanced Battery Materials and Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (37)

Show source-provided references
1. Performance and cost of materials for lithium-based rechargeable automotive batteries10.1038/s41560-018-0107-2 ↗
2. Thermal runaway mechanism of lithium ion battery for electric vehicles: a review10.1016/j.ensm.2017.05.013 ↗
3. A review of lithium-ion battery safety concerns: the issues, strategies, and testing standards10.1016/j.jechem.2020.10.017 ↗
4. Review—polymer electrolytes for rechargeable batteries: from nanocomposite to nanohybrid10.1149/1945-7111/ab7221 ↗
5. Lu · 2023 · vol. 13
6. A roadmap for solid-state batteries10.1002/aenm.202301886 ↗
7. https://www.blue-solutions.com/en/.
8. Challenges in speeding up solid-state battery development10.1038/s41560-023-01208-9 ↗
9. Electrode manufacturing for lithium-ion batteries—analysis of current and next generation processing10.1016/j.est.2019.100862 ↗
10. From laboratory innovations to materials manufacturing for lithium-based batteries10.1038/s41560-023-01221-y ↗
11. Artificial intelligence applied to battery research: hype or reality?10.1021/acs.chemrev.1c00108 ↗
12. Intensive dry and wet mixing influencing the structural and electrochemical properties of secondary lithium-ion battery cathodes10.1149/05026.0025ecst ↗
13. Mixing methods for solid state electrodes: techniques, fundamentals, recent advances, and perspectives10.1016/j.cej.2023.142469 ↗
14. Delaying the onset of Coulombic efficiency loss by adjusting the composite cathode processing parameters10.1016/j.jpowsour.2022.232372 ↗
15. The influence of slurry rheology on lithium-ion electrode processing
16. Efficiency of different dispersing devices for dispersing nanosized silica and alumina10.1016/j.powtec.2010.11.019 ↗
17. Relevance of the catholyte mixing method for solid-state composite cathodes10.1002/ente.202100479 ↗
18. Investigation of film solidification and binder migration during drying of Li-Ion battery anodes10.1016/j.jpowsour.2016.04.018 ↗
19. Feature analyses and modeling of lithium-ion battery manufacturing based on random forest classification10.1109/TMECH.2020.3049046 ↗
20. A Raman spectroscopic method to find binder distribution in electrodes during drying10.1007/s11998-013-9509-z ↗
21. Electrode microstructure controls localized electronic impedance in Li-ion batteries10.1016/j.electacta.2018.11.204 ↗
22. Machine learning in lithium-ion battery cell production: a comprehensive mapping study10.1002/batt.202300046 ↗
23. Interpretable machine learning for battery capacities prediction and coating parameters analysis10.1016/j.conengprac.2022.105202 ↗
24. Machine learning-assisted multi-objective optimization of battery manufacturing from synthetic data generated by physics-based simulations10.1016/j.ensm.2022.12.040 ↗
25. Random forest regression for online capacity estimation of lithium-ion batteries10.1016/j.apenergy.2018.09.182 ↗
26. Machine learning coupled multi-scale modeling for redox flow batteries
27. Scikit-learn: machine learning in Python. J
28. https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.PowerTransformer.html#sklearn.preprocessing.PowerTransformer.
29. https://gplearn.readthedocs.io/en/stable/index.html.
30. MLxtend: providing machine learning and data science utilities and extensions to Python's scientific computing stack10.21105/joss.00638 ↗
31. Bayesian inference of atomistic structure in functional materials10.1038/s41524-019-0175-2 ↗
32. Twiname · 2000
33. Drying of lithium-ion battery anodes for use in high-energy cells: influence of electrode thickness on drying time, adhesion, and crack formation10.1002/ente.201900722 ↗
34. Microstructure formation of lithium-ion battery electrodes during drying–An ex-situ study using cryogenic broad ion beam slope-cutting and scanning electron microscopy (Cryo-BIB-SEM)10.1016/j.jpowsour.2017.01.117 ↗
35. Data quantity governance for machine learning in materials science10.1093/nsr/nwad125 ↗
36. Generative artificial intelligence and its applications in materials science: current situation and future perspectives10.1016/j.jmat.2023.05.001 ↗
37. Multi‐layer feature selection incorporating weighted score‐based expert knowledge toward modeling materials with targeted properties, Adv