본문 바로가기

Early calendar life and health prediction of silicon batteries via machine learning with uncertainty quantification

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
피인용
Web of Science 5Scopus 5
FWCI (Scopus)
5.11
JCR IF
JCR 2024 7.3
ISSN
2666-3864

저자

  1. Prakash, Nina제1저자교신저자Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  2. Verma, AnkitNatl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  3. Weddle, Peter J.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  4. Colclasure, Andrew M.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  5. Schulze, Maxwell C.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  6. Carroll, Gerard M.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  7. McBrayer, Josefine D.Sandia Natl Labs, 1515 Eubank Blvd SE, Albuquerque, NM 87123 USA
  8. Rodrigues, Marco-Tulio F.Argonne Natl Lab, 9700 S Cass Ave, Lemont, IL 60439 USA
  9. 김재호Pusan Natl Univ, Busan 46241, South Korea
  10. Pach, Gregory F.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  11. Gasper, PaulNatl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  12. Meyer, LydiaNatl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  13. Musgrove, AmandaOak Ridge Natl Lab, 1 Bethel Valley Rd, Oak Ridge, TN 37830 USA
  14. Neale, Nathan R.Natl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA
  15. Veith, Gabriel M.Oak Ridge Natl Lab, 1 Bethel Valley Rd, Oak Ridge, TN 37830 USA
  16. Burrell, AnthonyNatl Lab Rockies, 15015 Denver W Pkwy, Golden, CO 80401 USA

초록

Lithium-ion batteries with silicon anodes promise high energy density but are limited by calendar lifetime. Reducing the long iteration time to obtain experimental results requires predicting calendar lifetime early in a cell’s life. In this study, we demonstrate that lightweight machine learning models with feature engineering can provide calendar lifetime estimates from early electrochemical signals. After 1 month of electrochemical aging, the best models achieve 10% error in calendar-life prediction and can separate “bad” from “good” lifetime cells with a mean F1 score of 0.857. As battery systems exhibit inherent variability, four methods for uncertainty quantification are compared, and confidence intervals are demonstrated with an uncertainty of ±3.6 months in lifetime prediction. A feature importance analysis indicates that early patterns in voltage decay are the strongest indicators of calendar lifetime. Finally, this modeling approach has high error when generalizing to new electrode chemistries or testing conditions but with appropriately low confidence.

키워드

calendar lifetimefeature engineeringlifetime estimationlithium-ion batterymachine learningsilicon batteryuncertainty quantification

식별자

Scopus EID
2-s2.0-105035655885
WoS UID
001747088100001