Mesoscale Machine Learning Analytics for Electrode Property Estimation
Source abstract
Abstract
The development of next-generation batteries with high areal and volumetric energy density requires the use of high active material mass loading electrodes. This typically reduces the power density, but the push for rapid charging has propelled innovation in microstructure design for improved transport and electrochemical conversion efficiency. This requires accurate effective electrode property estimation, such as tortuosity, electronic conductivity, and interfacial area. Obtaining this information solely from experiments and 3D mesoscale simulations is time-consuming while empirical relations are limited to simplified microstructure geometry. In this work, we propose an alternate route for rapid characterization of electrode microstructural effective properties using machine learning (ML). Using the Li-ion battery graphite anode electrode as an exemplar system, we generate a comprehensive data set of ∼17 000 electrode microstructures. These consist of various shapes, sizes, orientations, and chemical compositions, and characterize their effective properties using 3D mesoscale simulations. A low dimensional representation of each microstructure is achieved by calculating a set of comprehensive physical descriptors and eliminating redundant features. The mesoscale ML analytics based on porous electrode microstructural characteristics achieves prediction accuracy of more than 90% for effective property estimation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical Engineering, Purdue University, West Lafayette, Indiana 47907, United States
Department of Materials Science and Engineering, North Carolina State University, Raleigh, North Carolina 27695, United States
Funding
National Science Foundation
References (71)
Show source-provided references
1. 10.1021/acsenergylett.8b0219510.1021/acsenergylett.8b02195 ↗
2. 10.1016/j.joule.2021.05.00110.1016/j.joule.2021.05.001 ↗
3. 10.1021/jz100553m10.1021/jz100553m ↗
4. 10.1039/c2ee21892e10.1039/c2ee21892e ↗
5. 10.1016/j.cplett.2019.13662210.1016/j.cplett.2019.136622 ↗
6. 10.3390/cryst901005410.3390/cryst9010054 ↗
7. 10.1038/s41597-020-00602-210.1038/s41597-020-00602-2 ↗
8. 10.1002/aenm.20120059310.1002/aenm.201200593 ↗
9. 10.1021/cr020731c10.1021/cr020731c ↗
10. 10.1021/cm902696j10.1021/cm902696j ↗
11. 10.1038/s41560-019-0405-310.1038/s41560-019-0405-3 ↗
12. 10.1038/natrevmats.2016.1310.1038/natrevmats.2016.13 ↗
13. 10.1021/acsami.7b1777110.1021/acsami.7b17771 ↗
14. 10.1149/2.053207jes10.1149/2.053207jes ↗
15. 10.1016/j.jpowsour.2015.02.08610.1016/j.jpowsour.2015.02.086 ↗
16. 10.1016/j.jpowsour.2013.08.14710.1016/j.jpowsour.2013.08.147 ↗
17. 10.1149/2.046210jes10.1149/2.046210jes ↗
18. 10.1149/1.242526910.1149/1.2425269 ↗
19. 10.1149/1.222159710.1149/1.2221597 ↗
20. 10.1149/2.0731814jes10.1149/2.0731814jes ↗
21. 10.1002/aenm.20130127810.1002/aenm.201301278 ↗
22. 10.1149/2.0311802jes10.1149/2.0311802jes ↗
23. 10.1021/acsami.8b2275810.1021/acsami.8b22758 ↗
24. 10.1149/1945-7111/ab8fd710.1149/1945-7111/ab8fd7 ↗
25. 10.1016/j.ensm.2020.11.02910.1016/j.ensm.2020.11.029 ↗
26. 10.1149/1945-7111/ab7fb910.1149/1945-7111/ab7fb9 ↗
27. 10.1021/acsami.0c1514410.1021/acsami.0c15144 ↗
28. 10.1038/nenergy.2016.9710.1038/nenergy.2016.97 ↗
29. 10.1038/nenergy.2016.9910.1038/nenergy.2016.99 ↗
30. 10.1016/j.electacta.2020.13603410.1016/j.electacta.2020.136034 ↗
31. 10.1016/j.electacta.2020.13601310.1016/j.electacta.2020.136013 ↗
32. 10.1002/adma.20120405510.1002/adma.201204055 ↗
33. 10.1149/2.0151508jes10.1149/2.0151508jes ↗
34. Torquato S. · 200210.1007/978-1-4757-6355-3 ↗
35. 10.1149/2.1141607jes10.1149/2.1141607jes ↗
36. 10.1149/2.0231803jes10.1149/2.0231803jes ↗
37. 10.1149/2.0331711jes10.1149/2.0331711jes ↗
38. 10.1016/j.jelechem.2005.03.03010.1016/j.jelechem.2005.03.030 ↗
39. 10.1149/1.297603110.1149/1.2976031 ↗
40. 10.1016/j.electacta.2012.03.16110.1016/j.electacta.2012.03.161 ↗
41. 10.1149/2.1181913jes10.1149/2.1181913jes ↗
42. 10.1016/j.jpowsour.2015.12.13410.1016/j.jpowsour.2015.12.134 ↗
43. 10.1002/aenm.20140161210.1002/aenm.201401612 ↗
44. 10.1016/j.jpowsour.2017.04.10210.1016/j.jpowsour.2017.04.102 ↗
45. 10.1038/s41467-018-03401-x10.1038/s41467-018-03401-x ↗
46. 10.1149/2.0981813jes10.1149/2.0981813jes ↗
47. 10.1109/MLDS42202.201710.1109/MLDS42202.2017 ↗
48. Kotsiantis S. B. · Informatica · 2007 · 31 · 249
49. 10.1038/s41467-020-15235-710.1038/s41467-020-15235-7 ↗
50. 10.1016/j.energy.2021.12011610.1016/j.energy.2021.120116 ↗
51. 10.1115/1.405129610.1115/1.4051296 ↗
52. 10.1149/1945-7111/ab975c10.1149/1945-7111/ab975c ↗
53. 10.1016/j.energy.2021.12126910.1016/j.energy.2021.121269 ↗
54. 10.1016/j.egyai.2020.10000610.1016/j.egyai.2020.100006 ↗
55. 10.1016/j.apenergy.2015.08.11910.1016/j.apenergy.2015.08.119 ↗
56. Berecibar M. · Life · 2019
57. 10.1038/s41560-019-0356-810.1038/s41560-019-0356-8 ↗
58. 10.1038/s41598-020-78415-x10.1038/s41598-020-78415-x ↗
59. Jung J. · 201910.1016/j.commatsci.2018.09.034 ↗
60. Vasilyeva, M.; Tyrylgin, A. Machine Learning for Accelerating Effective Property Prediction for Poroelasticity Problem in Stochastic Media. 2018.
61. 10.1002/aenm.20200390810.1002/aenm.202003908 ↗
62. GeoDict The Digital Material Laboratory - Fraunhofer ITWM. https://www.itwm.fraunhofer.de/en/departments/sms/products-services/geodict-digital-material-laboratory.html (accessed 2021–09–17).
63. 10.1016/j.carbon.2016.10.06010.1016/j.carbon.2016.10.060 ↗
64. 10.1111/j.1551-2916.2008.02736.x10.1111/j.1551-2916.2008.02736.x ↗
65. 10.1038/nmeth.201910.1038/nmeth.2019 ↗
66. Beitrag zur Schotteranalyse - Research Collection. https://www.research-collection.ethz.ch/handle/20.500.11850/135183 (accessed 09–17–2021).
67. 10.1002/andp.1935416070510.1002/andp.19354160705 ↗
68. 10.1149/2.jes11322410.1149/2.jes113224 ↗
69. 10.1088/0965-0393/21/7/07400910.1088/0965-0393/21/7/074009 ↗
70. 10.1115/1.402976810.1115/1.4029768 ↗
71. 1. Supervised learning─scikit-learn 0.24.2 documentation. https://scikit-learn.org/stable/supervised_learning.html (accessed 09–17–2021).