Accelerated battery life predictions through synergistic combination of physics-based models and machine learning
Source abstract
Abstract
There are tremendous economic and technical benefits to shortening battery test periods through robust predictive methods. Accurate long-term forecasting of battery life enables proactive planning of battery management (e.g., cell replacements) and preemptive actions to modify operating conditions to improve safety and life. The ever-evolving landscape of battery materials and applications ensure an abiding need for early capture of aging mechanisms. Herein we report on accelerated determination of battery aging mechanisms together with prediction of future capacity loss. Sigmoidal rate expressions (SREs) are used as diagnostic and predictive engines to evaluate aging mechanisms at play. We demonstrate three methods by which SRE parameters are early assessed. Overall results indicate that for cases dominated by loss of lithium inventory we can predict end-of-test capacity loss using less than three weeks of data. In many cases, predictions are within 5%–10% relative error and to within 1%–2% absolute error of observed performance.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Electric Vehicles and Infrastructure
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (24)
Show source-provided references
1. Fast-charging aging considerations: incorporation and alignment of cell design and material degradation pathways10.1021/acsaem.1c01398 ↗
2. Aging mechanisms of lithium cathode materials10.1016/j.jpowsour.2003.09.034 ↗
3. Nano Li4Ti5O12–LiMn2O4 batteries with high power capability and improved cycle-life10.1016/j.jpowsour.2008.10.018 ↗
4. A review on the key issues of the lithium ion battery degradation among the whole life cycle10.1016/j.etran.2019.100005 ↗
5. Model-instructed design of novel charging protocols for the extreme fast charging of lithium-ion batteries without lithium plating10.1149/1945-7111/ab8c84 ↗
6. 2020
7. Model-based lithium deposition detection method using differential voltage analysis10.1016/j.jpowsour.2021.230449 ↗
8. Li plating as unwanted side reaction in commercial Li-ion cells – a review10.1016/j.jpowsour.2018.02.063 ↗
9. Heterogeneous behavior of lithium plating during extreme fast charging10.1016/j.xcrp.2020.100114 ↗
10. Sensitivity and reliability of key electrochemical markers for detecting lithium plating during extreme fast charging10.1016/j.est.2021.103782 ↗
11. Novel method for evaluation and prediction of capacity loss metrics in Li-ion electrochemical cells10.1016/j.electacta.2017.01.052 ↗
12. Early battery performance prediction for mixed use charging profiles using hierarchal machine learning10.1002/batt.202100079 ↗
13. Impacts of lean electrolyte on cycle life for rechargeable Li metal batteries10.1016/j.jpowsour.2018.10.060 ↗
14. Rapid failure mode classification and quantification in batteries: a deep learning modeling framework10.1016/j.ensm.2021.07.016 ↗
15. A machine learning framework for early detection of lithium plating combining multiple physics-based electrochemical signatures10.1016/j.xcrp.2021.100352 ↗
16. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
17. Degradation diagnostics for lithium ion cells10.1016/j.jpowsour.2016.12.011 ↗
18. Challenging practices of algebraic battery life models through statistical validation and model identification via machine-learning10.1149/1945-7111/abdde1 ↗
19. SciPy 1.0: fundamental algorithms for scientific computing in Python10.1038/s41592-020-0772-5 ↗
20. Deep learning10.1038/nature14539 ↗
21. Pytorch: an imperative style, high-performance deep learning library
22. A method for stochastic optimization
23. Shumway · 2000 · 3
24. Random forests10.1023/A:1010933404324 ↗