@article{16feb3b61e4b4c6eb9447b9f26138183,
title = "Battery aging mode identification across NMC compositions and designs using machine learning",
abstract = "A comprehensive understanding of lithium-ion battery (LiB) lifespan is the key to designing durable batteries and optimizing use protocols. Although battery lifetime prediction methods are flourishing, diagnosis of the root causes of aging and degradation have not yet been well developed nor studied for a broad mixture of designs and use cases. Here, we create a machine-learning (ML)-based framework that distinguishes aging modes using multiple electrochemical signatures recorded cycle-by-cycle. The predominant aging behaviors include a combination of loss of active materials in cathode (LAMPE) and a loss of Li inventory (LLI) in Li plating or solid electrolyte interphase (SEI) formation, manifested from 44 batteries representing two cathode chemistries, two electrode loadings, and five charging rates. The aging mode classification accuracy is 86\% using features within the first 50 cycles and increases to 88\% beyond 225 cycles. The same features can quantify the percentage of end-of-life LAMPE with only 4.3\% of error.",
keywords = "Li-ion battery, battery aging, degradation diagnostics, machine learning",
author = "Chen, \{Bor Rong\} and Walker, \{Cody M.\} and Sangwook Kim and Kunz, \{M. Ross\} and Tanim, \{Tanvir R.\} and Dufek, \{Eric J.\}",
note = "Funding Information: Funding was provided from the U.S. Department of Energy (DOE), Office of Energy Efficiency and Renewable Energy (EERE), and Vehicle Technologies Office (VTO). The authors thank Simon Thompson and Samuel Gillard from DOE for supporting this project under the Advanced Battery Cell Research Program . The cells were provided by the Extreme Fast Charge Cell Evaluation of Lithium-Ion Batteries (XCEL) under the Advanced Battery Cell Research Program. This manuscript has been written by Battelle Energy Alliance under contract DE-AC07-05ID14517 for Idaho National Laboratory (INL). The authors also acknowledge Zhenzhen Yang (Argonne National Laboratory) for providing anode images; the CAMP Facility at Argonne National Laboratory for providing cells; and Paramesware R. Chinnam, Michael Evans, and Ryan Jackman for data collection efforts at INL. The authors also thank Sangwook Kim, Zonggen Yi, and Kevin L. Gering at INL for participating in discussions related to this work. Funding Information: Funding was provided from the U.S. Department of Energy (DOE), Office of Energy Efficiency and Renewable Energy (EERE), and Vehicle Technologies Office (VTO). The authors thank Simon Thompson and Samuel Gillard from DOE for supporting this project under the Advanced Battery Cell Research Program. The cells were provided by the Extreme Fast Charge Cell Evaluation of Lithium-Ion Batteries (XCEL) under the Advanced Battery Cell Research Program. This manuscript has been written by Battelle Energy Alliance under contract DE-AC07-05ID14517 for Idaho National Laboratory (INL). The authors also acknowledge Zhenzhen Yang (Argonne National Laboratory) for providing anode images; the CAMP Facility at Argonne National Laboratory for providing cells; and Paramesware R. Chinnam, Michael Evans, and Ryan Jackman for data collection efforts at INL. The authors also thank Sangwook Kim, Zonggen Yi, and Kevin L. Gering at INL for participating in discussions related to this work. B.-R.C. C.M.W. M.R.K. T.R.T. and E.J.D. originated the research. B.-R.C. C.M.W. S.K. and T.R.T. analyzed the aging data, and C.M.W. established the ML classification framework. The manuscript was primarily written by B.-R.C. T.R.T. and C.M.W. All authors contributed to discussions of data and manuscript review. The authors declare no competing interests. Publisher Copyright: {\textcopyright} 2022 Elsevier Inc.",
year = "2022",
month = dec,
day = "21",
doi = "10.1016/j.joule.2022.10.016",
language = "English",
volume = "6",
pages = "2776--2793",
journal = "Joule",
issn = "2542-4351",
publisher = "Cell Press",
number = "12",
}