The escalating demand for efficient thermal management in lithium-ion batteries necessitates precise characterization of their thermal behavior under diverse operating conditions. This study develops a three-dimensional (3D) electrochemical–thermal coupling model grounded in porous electrode theory and energy conservation principles. The model solves multi-physics equations such as Fick’s law, Ohm’s law, and the Butler–Volmer equation, to resolve coupled electrochemical and thermal dynamics, with temperature-dependent parameters calibrated via the Arrhenius equation. Simulations under varying discharge rates reveal that high-rate discharges exacerbate internal heat accumulation. Low ambient temperatures amplify polarization effects. Forced convection cooling reduces surface temperatures but exacerbates core-to-surface thermal gradients. Structural optimization strategies demonstrate that enhancing through-thickness thermal conductivity reduces temperature differences. These findings underscore the necessity of balancing energy density and thermal management in lithium-ion battery design, proposing actionable insights such as preheating protocols for low-temperature operation, optimized cooling systems for high-rate scenarios, and material-level enhancements for improved thermal uniformity.

Thermal runaway (TR) remains a critical bottleneck for the safe application of lithium-ion battery (LIB) in large-scale energy storage systems, arising from the instability of battery materials under high temperatures. This review systematically summarizes materials design strategies to suppress TR, focusing on modifications of cathodes, anodes, separators, and electrolytes. For cathodes, surface coating and bulk doping enhance the structural stability and thermal decomposition temperature of high-Ni materials, while nanoscale engineering and carbon networks improve the electronic conductivity and interfacial stability of LiFePO₄ (LFP). For anodes, surface modification of graphite suppresses solid-electrolyte interphase degradation, and nanostructured silicon-based composites mitigate thermal failure caused by volume expansion. Separator functionalization, including ceramic coating, inorganic separators, and thermal shutdown separators, enhances thermo-mechanical stability and enables thermally triggered ion blocking. Flame-retardant electrolytes incorporate phosphorus-based, organosilicon, and halogenated additives that act through combined gas- and condensed-phase mechanisms. The review further discusses challenges in interfacial compatibility, system integration, and trade-offs among multiple performance metrics. Future efforts should focus on integrating intrinsic thermal stability with smart safety functions to achieve both high energy density and inherent safety. This review provides a systematic reference for the design and industrialization of high-safety materials for LIBs.

Accurate State-of-Health (SOH) prediction for lithium-ion batteries is essential for the safe and stable operation of Battery Management Systems (BMSs). However, achieving high-precision estimation remains challenging due to the complex interplay of non-stationary degradation characteristics, observation noise, and bidirectional temporal dependencies. This study proposes a robust hybrid temporal prediction framework integrating Variational Mode Decomposition (VMD), Bidirectional Long Short-Term Memory (BiLSTM) networks, an Attention mechanism, and the Grey Wolf Optimizer (GWO). First, VMD is employed to decompose the raw SOH time-series signals, isolating observation noise and mitigating temporal non-stationarity. A BiLSTM network is then utilized to extract bidirectional temporal correlations throughout the aging process, while an attention mechanism adaptively allocates weights to focus on critical degradation features. Furthermore, GWO automatically searches for optimal network hyperparameters, eliminating the subjective bias of manual tuning and enhancing cross-condition generalization. The proposed framework is rigorously validated using full-lifecycle datasets of four lithium-ion batteries (CS2_35 to CS2_38) from the CALCE laboratory. Standard temporal networks (LSTM, GRU, and Transformer) serve as comparative baselines, alongside an intra-battery ablation study to quantify the performance gain of each module. Experimental results demonstrate that the proposed VMD–GWO–BiLSTM–Attention framework achieves enhanced prediction accuracy compared to standard baseline temporal models (LSTM, GRU, and Transformer) across all evaluated degradation profiles. For the CS2_35 battery with a smooth aging trend, the root mean square error (RMSE) and mean absolute percentage error (MAPE) are minimized to 0.008 and 1.442%, respectively. Even under the severe capacity fluctuations of the CS2_38 battery, the model successfully controls the RMSE at 0.012 and the MAPE at 2.541%, exhibiting a significant error reduction compared to all baselines. These findings confirm that the synergistic integration of these four modules effectively addresses complex, nonlinear battery aging scenarios, offering a viable methodological baseline for deep-learning-based SOH prediction.

Accurate short-term load forecasting for EV public charging stations is essential for grid and station operations. However, predictions are challenging because charging loads are non-stationary, spatially heterogeneous, and closely coupled with external factors such as weather and pricing. In this study, we forecast hourly regional charging energy using the open UrbanEV benchmark dataset, which includes hourly charging records from 1362 public charging stations across 275 traffic-analysis zones in Shenzhen from September 2022 to February 2023. We propose ST-Attention, a lightweight and modular forecasting model. It integrates temporal self-attention, spatial self-attention, an adjacency-matrix bias, and a residual prediction head. We compare ST-Attention with five baselines using a leakage-free rolling time-series evaluation protocol. For the 3 h horizon, ST-Attention achieves an MAE of 62.44 kWh, an RMSE of 291.8 kWh, and an MAPE of 5.91%, reducing the MAE by approximately 41% compared with the last-observation baseline. The model also maintains superior MAE performance at the 6 h and 9 h horizons. A modular ablation study shows that temporal attention and the residual head are the most stable sources of improvement, whereas dense spatial attention does not automatically provide benefits at hourly granularity with limited samples; removing it further reduces the 3 h MAE to 59.58 kWh. We present this as a cautionary finding: local temporal inertia dominates dense spatial coupling in hourly forecasting, and spatial model complexity must align with data granularity.