journal article·2024-10-16Open access

General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models

Quentin Mayemba, Gabriel Ducret, An Li, Rémy Mingant, Pascal Venet

Batteries· Volume 10· Issue 10

Abstract

Today’s growing demand for lithium-ion batteries across various industrial sectors has introduced a new concern: battery aging. This issue necessitates the development of tools and models that can accurately predict battery aging. This study proposes a general framework for constructing battery aging models using machine learning techniques and compares these models with two existing empirical models, including a commercial one. To build the models, the databases produced by EVERLASTING and Bills et al. were utilized. The aim is to create universally applicable models that can address any battery-aging scenario. In this study, three types of models were developed: a vanilla neural network, a neural network inspired by extreme learning machines, and an encoder coupled with a neural network. The inputs for these models are derived from established knowledge in battery science, allowing the models to capture aging effects across different use cases. The models were trained on cells subjected to specific aging conditions and they were tested on other cells from the same database that experienced different aging conditions. The results obtained during the test for the vanilla neural network showed an RMSE of 1.3% on the Bills et al. test data and an RMSE of 2.7% on the EVERLASTING data, demonstrating similar or superior performance compared to the empirical models and proving the ability of the models to capture battery aging.
Source: crossref · 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.

Affiliations

Siemens Digital Industries Software, 19 Boulevard Jules Carteret, 69007 Lyon, France

IFP Energies Nouvelles, Rond-Point de L’échangeur de Solaize, 69360 Solaize, France

Université Claude Bernard Lyon 1, Ampère, UMR5005, INSA Lyon, Ecole Centrale de Lyon, CNRS, F-69100 Villeurbanne, France

IFP Energies Nouvelles, 1-4 Avenue du Bois Préau, 92500 Rueil-Malmaison, France

Funding

Siemens Industries Software

References (58)

Show source-provided references
1. Peng, J., Meng, J., Chen, D., Liu, H., Hao, S., Sui, X., and Du, X. (2022). A Review of Lithium-Ion Battery Capacity Estimation Methods for Onboard Battery Management Systems: Recent Progress and Perspectives. Batteries, 8.10.3390/batteries8110229 ↗
2. Aging datasets of commercial lithium-ion batteries: A review10.1016/j.est.2024.110560 ↗
3. (2024, April 10). University of Liverpool Lithium Cobalt Oxide–LiCoO2–Conduction Animation. Available online: https://www.chemtube3d.com/lib_lco-2/.
4. A study of lithium ion batteries cycle aging by thermodynamics techniques10.1016/j.jpowsour.2013.08.053 ↗
5. Calendar aging of silicon-containing batteries10.1038/s41560-021-00883-w ↗
6. Battery degradation and behaviour for electric vehicles: Review and numerical analyses of several models10.1016/j.trb.2017.01.020 ↗
7. Quantification of aging mechanisms and inhomogeneity in cycled lithium-ion cells by differential voltage analysis10.1016/j.est.2019.100813 ↗
8. Ahn, Y., Jo, Y.N., Cho, W., Yu, J.-S., and Kim, K.J. (2019). Mechanism of Capacity Fading in the LiNi0.8Co0.1Mn0.1O2 Cathode Material for Lithium-Ion Batteries. Energies, 12.10.3390/en12091638 ↗
9. An overview of degradation phenomena modeling in lithium-ion battery electrodes10.1016/j.coche.2016.08.008 ↗
10. Review and Performance Comparison of Mechanical-Chemical Degradation Models for Lithium-Ion Batteries10.1149/2.0281914jes ↗
11. A review of gas evolution in lithium ion batteries10.1016/j.egyr.2020.02.022 ↗
12. Degradation mechanisms in Li-ion batteries: A state-of-the-art review10.1002/er.3762 ↗
13. Enhanced Electrolyte Transport and Kinetics Mitigate Graphite Exfoliation and Li Plating in Fast-Charging Li-Ion Batteries10.1002/aenm.202202906 ↗
14. Before Li Ion Batteries10.1021/acs.chemrev.8b00422 ↗
15. Cathode-Electrolyte Interphase in Lithium Batteries Revealed by Cryogenic Electron Microscopy10.1016/j.matt.2020.10.021 ↗
16. Degradation in lithium ion battery current collectors10.1088/2515-7655/ac0c04 ↗
17. Ageing mechanisms in lithium-ion batteries10.1016/j.jpowsour.2005.01.006 ↗
18. One-to-One Comparison of Graphite-Blended Negative Electrodes Using Silicon Nanolayer-Embedded Graphite versus Commercial Benchmarking Materials for High-Energy Lithium-Ion Batteries10.1002/aenm.201700071 ↗
19. Aging Mechanisms of Electrode Materials in Lithium-Ion Batteries for Electric Vehicles10.1155/2015/104673 ↗
20. Aging of lithium-ion battery separators during battery cycling10.1016/j.est.2023.107107 ↗
21. Wheeler, W., Venet, P., Bultel, Y., Sari, A., and Riviere, E. (2024). Aging in First and Second Life of G/LFP 18650 Cells: Diagnosis and Evolution of the State of Health of the Cell and the Negative Electrode under Cycling. Batteries, 10.10.3390/batteries10040137 ↗
22. Combined experimental and modeling approaches of the thermal runaway of fresh and aged lithium-ion batteries10.1016/j.jpowsour.2018.07.094 ↗
23. Lithium-ion battery degradation: How to model it10.1039/D2CP00417H ↗
24. Lopetegi, I., Plett, G.L., Trimboli, M.S., Yeregui, J., Oca, L., Rojas, C., Miguel, E., and Iraola, U. (2023, January 24–27). Lithium-ion Battery Aging Prediction with Electrochemical Models: P2D vs. SPMe. Proceedings of the 2023 IEEE Vehicle Power and Propulsion Conference (VPPC), Milan, Italy.10.1109/VPPC60535.2023.10403316 ↗
25. Data-driven model development to predict the aging of a Li-ion battery pack in electric vehicles representative conditions10.1016/j.est.2021.102592 ↗
26. A Comprehensive Review on the Characteristics and Modeling of Lithium-Ion Battery Aging10.1109/TTE.2021.3138357 ↗
27. A review on methods for state of health forecasting of lithium-ion batteries applicable in real-world operational conditions10.1016/j.est.2022.105978 ↗
28. A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery10.1016/j.apenergy.2021.117346 ↗
29. Review of “grey box” lifetime modeling for lithium-ion battery: Combining physics and data-driven methods10.1016/j.est.2022.105992 ↗
30. Towards machine-learning driven prognostics and health management of Li-ion batteries. A comprehensive review10.1016/j.rser.2023.114224 ↗
31. Cao, L., Xu, R., and Bi, Y. (2022, January 15–17). Research on Life Prediction of Lithium-ion Battery based on WEMD-ARIMA Model. Proceedings of the 2022 34th Chinese Control and Decision Conference (CCDC), Hefei, China.10.1109/CCDC55256.2022.10033615 ↗
32. Time Series Feature extraction for Lithium-Ion batteries State-Of-Health prediction10.1016/j.est.2022.106436 ↗
33. Artificial Intelligence Applied to Battery Research: Hype or Reality?10.1021/acs.chemrev.1c00108 ↗
34. Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods10.1016/j.jpowsour.2012.11.146 ↗
35. Real-time state-of-health estimation for electric vehicle batteries: A data-driven approach10.1016/j.apenergy.2016.05.051 ↗
36. Battery health prediction under generalized conditions using a Gaussian process transition model10.1016/j.est.2019.03.022 ↗
37. Intelligent state of health estimation for lithium-ion battery pack based on big data analysis10.1016/j.est.2020.101836 ↗
38. Principal component analysis10.1038/s43586-022-00184-w ↗
39. State of health forecasting of Lithium-ion batteries applicable in real-world operational conditions10.1016/j.est.2021.103439 ↗
40. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
41. On hyperparameter optimization of machine learning algorithms: Theory and practice10.1016/j.neucom.2020.07.061 ↗
42. A machine learning-based framework for online prediction of battery ageing trajectory and lifetime using histogram data10.1016/j.jpowsour.2022.231110 ↗
43. Closed-loop optimization of fast-charging protocols for batteries with machine learning10.1038/s41586-020-1994-5 ↗
44. (2024, April 03). NASA. Available online: https://papers.phmsociety.org/index.php/phmconf/article/view/2490.
45. Piecewise-linear modelling with automated feature selection for Li-ion battery end-of-life prognosis10.1016/j.ymssp.2022.109612 ↗
46. Review—“Knees” in Lithium-Ion Battery Aging Trajectories10.1149/1945-7111/ac6d13 ↗
47. Trad, K., and Govindarajan, J. (2020). D2.3-Report Containing Aging Test Profiles and Test Results, EVERLASTING. Available online: https://everlasting-project.eu/wp-content/uploads/2020/03/EVERLASTING_D2.3_final_20200228.pdf.
48. Bills, A., Viswanathan, V., Sripad, S., Frank, E., Charles, D., and Fredericks, W.L. (2023). eVTOL Battery Dataset, Carnegie Mellon University.
49. Lithium-ion battery data and where to find it10.1016/j.egyai.2021.100081 ↗
50. Hassini, M., Redondo-Iglesias, E., and Venet, P. (2023). Lithium–Ion Battery Data: From Production to Prediction. Batteries, 9.10.3390/batteries9070385 ↗
51. Challenges and key requirements of batteries for electric vertical takeoff and landing aircraft10.1016/j.joule.2021.05.001 ↗
52. (2024, October 13). CC BY. Available online: https://creativecommons.org/licenses/by/4.0/.
53. Siemens Digital Industries Software (2023). Simcenter AMESim V2310 (Advanced Modeling Environment for Performing Simulations), Siemens Digital Industries Software.
54. Deterministic models of Li-ion battery aging: It is a matter of scale10.1016/j.est.2018.09.002 ↗
55. Extreme learning machine: Theory and applications10.1016/j.neucom.2005.12.126 ↗
56. A review on extreme learning machine10.1007/s11042-021-11007-7 ↗
57. Michelucci, U. (2022). An Introduction to Autoencoders. arXiv.10.1007/978-1-4842-8020-1_9 ↗
58. A comprehensive survey on design and application of autoencoder in deep learning10.1016/j.asoc.2023.110176 ↗