Physics-Informed Transfer Learning for Cross-Condition State of Health Prediction of Lithium-Ion Batteries
TL;DR
This study proposes a physics-informed transfer learning (PITL) framework that combines a common health descriptor space, parameter function decomposition, and PINN–DeepHPM regularization, and partial freezing can lower adaptation cost, but its accuracy benefit is target dependent.
Abstract
Estimating lithium-ion battery state of health (SOH) across operating conditions is challenging because operating profiles, measurement characteristics, and degradation trajectories differ among domains. This study proposes a physics-informed transfer learning (PITL) framework that combines a common health descriptor space, parameter function decomposition, and PINN–DeepHPM regularization. Open-circuit voltage reconstruction is used before feature extraction for dynamic profiles, whereas constant-current data are processed directly in the same descriptor space. During target-domain adaptation, selected shared-representation layers are frozen and the predictor and dynamic constraint parameters remain trainable. In the predefined Cell_1# tests, the resulting feature transfer configuration reduced RMSE relative to full fine-tuning by 23.53% for 21700_Dynamics and 61.78% for CEPREI. In leave-one-cell-out validation, PITL and full fine-tuning had comparable mean RMSEs on 21700_Dynamics, whereas full fine-tuning was more accurate on CEPREI. Freezing approximately 48% of the parameters reduced adaptation time and peak GPU memory. Thus, partial freezing can lower adaptation cost, but its accuracy benefit is target dependent.