Predicting battery lifetime under varying usage conditions from early aging data
Source abstract
Abstract
Accurate battery lifetime prediction is important for maintenance, warranties, and cell design. However, manufacturing variability and usage-dependent degradation make life prediction challenging. Here, we investigate new features derived from capacity-voltage data in early life to predict the lifetime of cells cycled under varying charge rates, discharge rates, and depths of discharge. The early-life features capture a cell's state of health and the change rate of component-level degradation modes. Using a newly generated dataset from 225 nickel-manganese-cobalt/graphite lithium-ion cells aged under a wide range of conditions, we demonstrate a lifetime prediction of in-distribution cells with 15.1% mean absolute percentage error (MAPE). A hierarchical Bayesian model shows improved performance on extrapolation, achieving 21.8% MAPE for out-of-distribution cells. Our approach highlights the importance of using domain knowledge of battery degradation to inform feature engineering and model construction. Further, a new publicly available battery lifelong aging dataset is provided.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Reliability and Maintenance Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (54)
Show source-provided references
1. Degradation diagnostics for lithium ion cells10.1016/j.jpowsour.2016.12.011 ↗
2. The challenge and opportunity of battery lifetime prediction from field data10.1016/j.joule.2021.06.005 ↗
3. Integrating physics-based modeling and machine learning for degradation diagnostics of lithium-ion batteries10.1016/j.ensm.2022.05.047 ↗
4. Early battery performance prediction for mixed use charging profiles using hierarchal machine learning10.1002/batt.202100079 ↗
5. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
6. Closed-loop optimization of fast-charging protocols for batteries with machine learning10.1038/s41586-020-1994-5 ↗
7. Autonomous discovery of battery electrolytes with robotic experimentation and machine learning10.1016/j.xcrp.2020.100264 ↗
8. Precision measurements of the coulombic efficiency of lithium-ion batteries and of electrode materials for lithium-ion batteries10.1149/1.3268129 ↗
9. Evaluation of effects of additives in wound Li-ion cells through high precision coulometry
10. Predicting and extending the lifetime of Li-ion batteries10.1149/2.060309jes ↗
11. Production caused variation in capacity aging trend and correlation to initial cell performance10.1016/j.jpowsour.2013.08.108 ↗
12. Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells10.1016/j.jpowsour.2016.12.083 ↗
13. Automated feature extraction and selection for data-driven models of rapid battery capacity fade and end of life10.1109/TII.2021.3106593 ↗
14. Prognostics of battery cycle life in the early-cycle stage based on hybrid model10.1016/j.energy.2021.119901 ↗
15. Lifespan prediction of lithium-ion batteries based on various extracted features and gradient boosting regression tree model10.1016/j.jpowsour.2020.228654 ↗
16. Predicting the impact of formation protocols on battery lifetime immediately after manufacturing10.1016/j.joule.2021.09.015 ↗
17. A convolutional neural network model for battery capacity fade curve prediction using early life data10.1016/j.jpowsour.2022.231736 ↗
18. BEEP: A python library for battery evaluation and early prediction10.1016/j.softx.2020.100506 ↗
19. Early prediction of battery lifetime via a machine learning based framework10.1016/j.energy.2021.120205 ↗
20. Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells10.1016/j.egyai.2020.100006 ↗
21. One-shot battery degradation trajectory prediction with deep learning10.1016/j.jpowsour.2021.230024 ↗
22. Feature engineering for machine learning enabled early prediction of battery lifetime10.1016/j.jpowsour.2022.231127 ↗
23. “Knees” in lithium-ion battery aging trajectories10.1149/1945-7111/ac6d13 ↗
24. Li plating as unwanted side reaction in commercial Li-ion cells–A review10.1016/j.jpowsour.2018.02.063 ↗
25. A review on the key issues of the lithium ion battery degradation among the whole life cycle10.1016/j.etran.2019.100005 ↗
26. Lithium-ion battery data and where to find it10.1016/j.egyai.2021.100081 ↗
27. Adaptation of an electrochemistry-based li-ion battery model to account for deterioration observed under randomized use
28. Prognostics methods for battery health monitoring using a Bayesian framework10.1109/TIM.2008.2005965 ↗
29. Prognostics of lithium-ion batteries based on Dempster–Shafer theory and the Bayesian Monte Carlo method10.1016/j.jpowsour.2011.08.040 ↗
30. An ensemble model for predicting the remaining useful performance of lithium-ion batteries10.1016/j.microrel.2012.12.003 ↗
31. Degradation of commercial lithium-ion cells as a function of chemistry and cycling conditions10.1149/1945-7111/abae37 ↗
32. Estimation of Li-Ion Degradation Test Sample Sizes Required to Understand Cell-to-Cell Variability10.1002/batt.202100148 ↗
33. A comparison between electrochemical impedance spectroscopy and incremental capacity-differential voltage as Li-ion diagnostic techniques to identify and quantify the effects of degradation modes within battery management systems10.1016/j.jpowsour.2017.03.042 ↗
34. Degradation mechanism detection for NMC batteries based on Incremental Capacity curves10.3390/wevj8020350 ↗
35. “Degradation mechanisms detection for HP and HE NMC cells based on incremental capacity curves”
36. Lithium-Ion Battery Life Model with Electrode Cracking and Early-Life Break-in Processes10.1149/1945-7111/ac2ebd ↗
37. Review and performance comparison of mechanical-chemical degradation models for lithium-ion batteries10.1149/2.0281914jes ↗
38. Solid-state diffusion limitations on pulse operation of a lithium ion cell for hybrid electric vehicles10.1016/j.jpowsour.2006.03.050 ↗
39. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance10.1111/j.1600-0587.2012.07348.x ↗
40. Feature selection in machine learning: A new perspective10.1016/j.neucom.2017.11.077 ↗
41. Hastie · 2013
42. Machine-Learning Assisted Identification of Accurate Battery Lifetime Models with Uncertainty10.1149/1945-7111/ac86a8 ↗
43. Bayesian learning for rapid prediction of lithium-ion battery-cycling protocols10.1016/j.joule.2021.10.010 ↗
44. Li · 2023
45. Gaussian Process Regression for In Situ Capacity Estimation of Lithium-Ion Batteries10.1109/TII.2018.2794997 ↗
46. “Comparison of Li-ion battery chemistries under grid duty cycles”. en10.1016/j.jpowsour.2022.231949 ↗
47. Best practices for incremental capacity analysis10.3389/fenrg.2022.1023555 ↗
48. Human-level concept learning through probabilistic program induction10.1126/science.aab3050 ↗
49. Hierarchical generalized additive models in ecology: an introduction with mgcv10.7717/peerj.6876 ↗
50. Hierarchical Bayesian model for probabilistic analysis of electric vehicle battery degradation10.1109/TTE.2019.2956350 ↗
51. Bayesian hierarchical model-based prognostics for lithium-ion batteries10.1016/j.ress.2017.11.020 ↗
52. Faster algorithms for the constrained k-means problem10.1007/s00224-017-9820-7 ↗
53. Bayesian hierarchical modelling for battery lifetime early prediction10.1016/j.ifacol.2023.10.708 ↗
54. Error Metrics and Performance Fitness Indicators for Artificial Intelligence and Machine Learning in Engineering and Sciences10.1007/s44150-021-00015-8 ↗