Xuan Meng

Accurate state-of-charge (SOC) estimation is essential for range prediction, power allocation, and operational safety in electric vehicles. Low-temperature operation introduces coupled effects of capacity degradation and polarization dynamics, which challenge conventional fixed-capacity models and single-timescale estimation methods. This paper proposes a hierarchical multi-timescale SOC estimation framework that combines data-driven capacity prediction, online parameter identification, and nonlinear state estimation. At the upper layer, a temperature-aware temporal self-attention long short-term memory network (TS-LSTM) estimates the available battery capacity. At the lower layer, forgetting-factor recursive least squares (FFRLS) and a gain-scheduled unscented Kalman filter (UKF) jointly track impedance variations and recursively estimate SOC. The framework is validated on public lithium-ion battery datasets at 4, 24, and 43 °C under pulse and sparse high-current conditions. Under the challenging 4 °C scenario with a 10% initial SOC bias, the method achieves an SOC root mean square error (RMSE) of 1.35%. Additional perturbation tests yield SOC RMSEs of 1.35–2.40% under −5% to +10% initial-SOC offsets, 1 mV voltage noise, a +2 °C temperature bias, and a +20% impedance-prior error. Furthermore, the computational overhead remains substantially lower than the data sampling interval, indicating promising potential for online estimation in battery management systems.

Efficient thermal management is critical for proton exchange membrane fuel cells (PEMFCs). This study develops a bio-inspired active liquid cooling architecture to overcome the limitations of conventional flow channels, where convective heat transfer augmentation significantly increases pressure drop. The proposed configuration adheres to constructal theory and Murray’s law. A three-dimensional conjugate heat transfer model was formulated to evaluate the thermo-hydrodynamic performance against parallel and serpentine flow channels. Under identical conditions, the proposed configuration exhibits superior thermal uniformity and hydrodynamic behavior, alongside minimized parasitic pumping power. At an inlet Reynolds number (Re) of 400, this configuration stabilizes the average bipolar plate temperature at 349.63 K. It reduces the index of uniform temperature (IUT) to 1.49 K, representing a 52.8% thermal uniformity improvement over the parallel flow channel. Furthermore, at an inlet Re of 600, the overall pressure drop is restricted to 68.44 Pa, reducing the single-plate parasitic pumping power to 1.27 × 10⁻⁴ W, which represents reductions of 93.5% and 12.5% relative to the serpentine and parallel flow channels, respectively. This study provides an alternative architectural scheme for the design of active liquid cooling flow channels in PEMFCs.

Precise prediction of voltage degradation is critical for the prognostics and health management of proton exchange membrane fuel cells (PEMFCs). The performance degradation of PEMFCs is governed by a complex coupling of multiple physicochemical mechanisms, including catalyst layer and proton exchange membrane degradation. Crucially, these internal degradation processes evolve across highly heterogeneous time scales, ranging from transient high-frequency fluctuations to low-frequency and long-term irreversible performance fade. Conventional predictive models, which typically rely on single-scale architectures or fixed receptive fields, are inherently ill-equipped to simultaneously decouple and capture these cross-scale temporal dynamics. To tackle this challenge, this paper innovatively proposes a multi-scale deep learning framework that integrates a multi-scale degradation trend perception module, a long short-term memory (LSTM)-based encoder–decoder architecture, and a multi-head attention mechanism. One-dimensional convolutional layers with different kernel sizes are employed to simultaneously extract local temporal features at multiple granularities, followed by the LSTM encoder–decoder to model long-range temporal dependencies, while the cross-attention mechanism dynamically allocates attention across the encoded context at each autoregressive decoding step. Experimental outcomes indicate that the proposed model realizes excellent predictive accuracy across five evaluation indices in comparison with standard baselines. In particular, the mean absolute percentage error (MAPE) reaches 1.6696%, and the maximum absolute percentage error (Max-APE) is strictly bounded within 5%, substantiating the reliability of the proposed framework for high precision and long-horizon health prognostics for PEMFCs.

As a type of electrochemical energy storage, the vanadium redox flow battery system (VRFB) is currently one of the most promising large-scale energy storage methods. Nevertheless, the ability to accurately estimate the state of charge (SOC) is one of the critical factors restricting the commercialization of VRFBs. This review summarizes the estimation methods for the SOCs of VRFBs used by scholars in the past 10 years, comprehensively discusses the main factors affecting the accuracy of SOC estimation, and discusses the direct measurement methods, combined with modeling filter estimation methods and data-driven SOC estimation approaches currently investigated by mainstream scholars. Although several recent literature reviews describe the current modeling and estimation methods for VRFBs, there has been relatively little attention paid to the more common equivalent circuit modeling methods and parameter identification approaches. This review mainly focuses on common equivalent circuit model (ECM) modeling methods and filter estimation algorithms using modeling, and it summarizes their advantages and disadvantages. Finally, a description of potential research directions for VRFB modeling and SOC estimation in the future is presented.