PI-LSTM cuts RMSE by 81.9% and MAE by 81.3% versus standard LSTM on 13 battery datasets by enforcing thermal diffusion constraints during training.
Early diagnosis of battery faults through an unsupervised health scoring method for real- world applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Physics-Enhanced Deep Learning for Proactive Thermal Runaway Forecasting in Li-Ion Batteries
PI-LSTM cuts RMSE by 81.9% and MAE by 81.3% versus standard LSTM on 13 battery datasets by enforcing thermal diffusion constraints during training.