Developing accurate models for batteries, capturing ageing effects and nonlinear behaviors, is critical for the development of efficient and effective performance. Due to the inherent difficulties in developing physics-based models, data-driven techniques have been gaining popularity. However, most machine learning methods are black boxes, lacking interpretability and requiring large amounts of labeled data. In this paper, we propose a physics-informed encoder–decoder model that learns from unlabeled data to separate slow-changing battery states, such as state of charge (SOC) and state of health (SOH), from fast transient responses, thereby increasing interpretability compared to conventional methods. By integrating physics-informed loss functions and modified architectures, we map the encoder output to quantifiable battery states, without needing explicit SOC and SOH labels. Our proposed approach is validated on a lithium-ion battery ageing dataset capturing dynamic discharge profiles that aim to mimic electric vehicle driving profiles. The model is trained and validated on sparse intermittent cycles (6 %–7 % of all cycles), accurately estimating SOC and SOH while providing accurate multistep ahead voltage predictions across single and multiple-cell based training scenarios.

For reliable and safe battery operations, accurate and robust State of Charge (SOC) and model parameters estimation is vital. However, the nonlinear dependency of the model parameters on battery states makes the problem challenging. We propose a Moving-Horizon Estimation (MHE)-based robust approach for joint state and parameters estimation. Dut to all the time scales involved in the model dynamics, a multi-rate MHE is designed to improve the estimation performance. Moreover, a parallelized structure for the observer is exploited to reduce the computational burden, combining both multi-rate and a reduced-order MHEs. Results show that the battery SOC and parameters can be effectively estimated. The proposed MHE observers are verified on a Simulink-based battery equivalent circuit model.

Accurate prediction of battery performance under various ageing conditions is necessary for reliable and stable battery operations. Due to complex battery degradation mecha-nisms, estimating the accurate ageing level and ageing-dependent battery dynamics is difficult. This work presents a health-aware battery model that is capable of separating fast dynamics from slowly varying states of degradation and state of charge (SOC). The method is based on a sequence to sequence learning-based encoder-decoder model, where the encoder infers the slowly varying states as the latent space variables in an unsupervised way, and the decoder provides health-aware multi-step ahead prediction conditioned on slowly varying states from the encoder. The proposed approach is verified on a Lithium-ion battery ageing dataset based on real driving profiles of electric vehicles.