Sparse data machine learning for battery health estimation and optimal design incorporating material characteristics

Jianyu Zhang and Wei Lu

Applied Energy, 2022, vol. 307, issue C, No S0306261921014380

Abstract: State of health estimation and optimal electrode design are two critical challenges in battery research, yet few work addressed them together. In this work we demonstrate a machine learning approach for next generation high capacity batteries with black phosphorus anodes. Experimentally 90 coin cells with various material properties are fabricated and cycled at different conditions, generating so far the most comprehensive dataset. For the first time, material characteristics are incorporated for state of health estimation in a data-driven framework. A virtual sample generator is developed to address sparse data by generating virtual samples, which significantly improves state of health prediction. Incorporating easy-to-measure material properties, the model is able to accurately predict state of health after a given number of cycles using only the first 2 cycles. The approach provides quantitative insights of feature importance, resulting in a multi-objective optimization framework for battery electrode design, achieving long cycling life, high active material loading and fast kinetics at the same time.

Keywords: State of health; Sparse data; Battery; Design optimization; Virtual sample (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261921014380
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:307:y:2022:i:c:s0306261921014380

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2021.118165

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().