Combining Thermal–Electrochemical Modeling and Deep Learning: A Physics-Constrained GRU for State-of-Health Estimation of Li-Ion Cells

Battery health monitoring is essential for ensuring the safety, longevity, and efficiency of energy storage systems, particularly in critical applications where reliability is important. Traditional methods for assessing battery degradation, such as Electrochemical Impedance Spectroscopy (EIS), are effective but impractical for large-scale deployment due to their time-intensive nature. This study introduces a novel model-based approach for estimating a critical indicator of battery aging, the internal resistance. Using the NASA battery dataset, specifically focusing on battery numbers 5 and 7 with NCA chemistry, a comprehensive framework that integrates advanced predictive models, i.e., the Random Forest Regressor (RF), the XGBoost Regressor (XGBR), the Gated Recurrent Unit (GRU), and the Long Short-Term Memory (LSTM) networks, was developed. The models were evaluated using common regression metrics, while hyperparameter tuning was performed to optimize performance. The results demonstrated that recurrent neural networks, particularly GRU and LSTM, effectively capture the temporal dependencies inherent in battery aging, offering more accurate state-of-health (SOH) predictions. This approach significantly improves computational efficiency and prediction accuracy, paving the way for practical applications in Battery Management Systems (BMSs).