Data-Driven Health Prognostics of NMC Lithium-Ion Batteries via Impedance Spectroscopy Using a Hybrid CNN-BiLSTM Model

(NMC811) pouch cells. A hybrid Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture is developed to estimate state of health (SoH) and predict remaining useful life (RUL) from EIS spectra. Trained on an in-house dataset comprising over 13,000 impedance spectra from 22 cells (8 NMC111 and 14 NMC811), the model achieves robust performance, with average coefficients of determination (R2) exceeding 0.92 for SoH estimation and 0.90 for RUL prediction across various batteries and cycling protocols. Salient feature analysis further reveals chemistry- and protocol-dependent frequency regimes associated with degradation. These results demonstrate that impedance spectra constitute physically informative descriptors for data-driven battery prognostics and provide a scalable and interpretable pathway for deploying EIS-AI frameworks in real-world battery management systems (BMSs).