Engineering insight

Uncertainty-aware and explainable machine learning for early prediction of battery degradation trajectoryDigital Discovery (2023) · Laura Rieger, Erik Frank, Oleksandr V. Wodyński, Alpha A. Lee, Tejs Vegge, Anja B. BizerayDOI: https://doi.org/10.1039/d2dd00067aHTML 본문: https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00067a Uncertainty-aware and explainable machine learning for early pred..

Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learningNature Communications (2020) · Yunwei Zhang, Qiaochu Tang, Yao Zhang, Jiabin Wang, Ulrich Stimming, Alpha A. Lee원문: https://www.nature.com/articles/s41467-020-15235-7DOI: https://doi.org/10.1038/s41467-020-15235-7 한 줄 핵심이 논문은 배터리 EIS 전체 스펙트럼을 그대로 machine learning에 넣어 capacity와 RUL을 추정하면서, ..

A highly efficient polysulfide mediator for lithium–sulfur batteriesNature Communications (2015)저자: Xiao Liang, Connor Hart, Quan Pang, Arnd Garsuch, Thomas Weiss, Linda F. Nazar원문: https://www.nature.com/articles/ncomms6682DOI: https://doi.org/10.1038/ncomms6682 한 줄 핵심이 논문은 Li–S 배터리의 최대 병목인 polysulfide shuttle 문제를 단순 물리적 confinement가 아니라 MnO2 표면의 redox mediator chemistry로 제어해, 고황함량(75 wt%)과 장수명..

Multi-modal framework for battery state of health evaluation using open-source electric vehicle dataNature Communications (2025) · Hongao Liu et al. · DOI: 10.1038/s41467-025-56485-7원문: https://www.nature.com/articles/s41467-025-56485-7 · PMC: https://pmc.ncbi.nlm.nih.gov/articles/PMC11779878/한 줄 평가이 논문은 실차 EV SOH 추정에서 “모델”보다 “입력 표현(representation)”이 더 중요할 수 있다는 점을 설득력 있게 보여준 연구입니다. 가장 큰 기여는 딥러닝..

논문 전문 : https://www.sciencedirect.com/science/article/pii/S2666248521000093[출처] Evelina Wikner, Erik Björklund, Johan Fridner, Daniel Brandell, Torbjörn Thiringer, How the utilised SOC window in commercial Li-ion pouch cells influence battery ageing, Journal of Power Sources Advances, Volume 8, 2021, 100054, ISSN 2666-2485, https://doi.org/10.1016/j.powera.2021.100054. ※ The picture and content ..