A cycle-aware and physics-informed framework for battery remaining useful life prediction
Yixuan Chen, Yueran Wu, Conghui Li · 2025
Read A cycle-aware and physics-informed framework for battery remaining useful life prediction by Yixuan Chen, Yueran Wu, Conghui Li (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12756295.txt.
Description
Yixuan Chen and co-authors present Bat-T-GNN in a 2025 paper on predicting how much life a lithium battery has left. Good forecasts keep energy systems safe, but battery data are messy and uneven in time.
Many deep models cut charge cycles into plain chunks with no physical sense. Bat-T-GNN instead cuts data by true charge and discharge cycles, giving the model clean units. A physics-based loss also forces forecasts to follow a plausible wear curve. Tests on public data beat prior top methods, and part-by-part checks credit both new pieces. Battery teams get a model grounded in how cells really age.
Catalog record
| CREATOR | Yixuan Chen, Yueran Wu, Conghui Li |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 83 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |