<p>Establishment of precise state-of-health (SOH) consists of a vital step to guarantee reliable, secure, and preventive maintenance of electric vehicle (EV) fleets and grid-associated energy storage systems based on lithium-ion batteries. Nevertheless, existing SOH estimation approaches primarily consider situations where complete sensor profiles or full charge/discharge conditions are available, which is not often the case due to sensor degradation, communication losses, or economic factors. This work introduces a novel Physics-Informed Neural Network (PINN) framework to enable robust SOH estimation under partial observability, leveraging minimal sensor data and physics-constrained learning to ensure both accuracy and interpretability. The model relies on an approximation of the PINN architecture that is able to embed the fundamental degradation mechanisms, such as solid electrolyte interphase (SEI) layer growth and capacity fading, as information that the training process can utilize through physical regularization. While PINN is semantically mixed with traditional purely data-driven models, it uses a composite loss function that leverages data consistency with underlying electrochemical laws. This enables accurate predictions even when no further capacity measurements or complete voltage profiles are available. The framework is tested in the case of publicly available lithium-ion battery data sets, which show superior generalization and the capacity to withstand situations where missing inputs or sensor noise are introduced under simulated sensor sparsity scenarios. The results of the experiments demonstrate the quality of the model, which enhances the precision of SOH estimation in conditions of partial observability and also increases the model’s interpretability and applicability in real-time in various operational settings. Statistical results show that the proposed method achieves a mean absolute error (MAE) of 0.008, root mean square error (RMSE) of 0.011, and a coefficient of determination (R²) of 0.96, outperforming baseline models such as CNN–LSTM and hybrid SE-NN by 25–40% in sparse data regimes. Furthermore, the framework exhibits high generalization capability across different chemistries and retains robustness with as little as 50% of the input features. These results underscore the practical potential of the proposed PINN approach for real-time, physically consistent battery health diagnostics in embedded battery management systems.</p>