Accurate assessment of battery State of Health (SOH) is crucial for the safe and efficient operation of electric vehicles (EVs), which play a significant role in reducing reliance on non-renewable energy sources. This study introduces a novel SOH estimation method combining Kolmogorov–Arnold Networks (KAN) and Long Short-Term Memory (LSTM) networks. The method is based on fully charged battery characteristics, extracting key parameters such as voltage, temperature, and charging data collected during cycles. Validation was conducted under a temperature range of 10 °C to 30 °C and different charge–discharge current rates. Notably, temperature variations were primarily caused by seasonal changes, enabling the experiments to more realistically simulate the battery’s performance in real-world applications. By enhancing dynamic modeling capabilities and capturing long-term temporal associations, experimental results demonstrate that the method achieves highly accurate SOH estimation under various charging conditions, with low mean absolute error (MAE) and root mean square error (RMSE) values and a coefficient of determination ($R^2$) exceeding 97%, significantly improving prediction accuracy and efficiency.

Accurately estimating the remaining useful life (RUL) of lithium-ion batteries in energy storage systems is critical for ensuring both the safety and reliability of the power grid. To address the complex nonlinear degradation behavior associated with battery aging, this study proposes a novel RUL prediction framework that integrates ensemble empirical mode decomposition (EEMD) with an ensemble learning algorithm. The approach first applies EEMD to decompose aging data into a residual component and several intrinsic mode functions (IMFs). The residual component is then modeled using a long short-term memory (LSTM) network, while the Kolmogorov–Arnold network (KAN) focuses on learning from the IMF components. These individual predictions are subsequently combined to reconstruct the overall capacity degradation trajectory. Experimental validation on real lithium-ion battery aging datasets demonstrates that the proposed method provides highly accurate RUL predictions, exhibits strong robustness, and effectively captures nonlinear characteristics under varying operating conditions. Specifically, the method achieves R² above 0.96 with absolute RUL errors within 2–3 cycles on NASA datasets, and maintains R² values above 0.91 with errors within 7–15 cycles on CALCE datasets. Furthermore, the optimal KAN hyperparameters for different IMF components are identified, offering valuable insights for multi-scale modeling and future model optimization.

Manganese oxide (MnO_x)-based nanozymes have attracted growing interest due to their low cost, high catalytic robustness, and adjustable oxidation states that influence enzyme-mimicking performance. In this study, we report a systematic approach to synthesize MnO_x nanocomposites with tunable Mn valence states via a two-step pyrolysis of Mn-BTC precursors, enabling us to explore their valence-dependent peroxidase-like activities. Among the synthesized forms, Mn₃O₄ exhibited the highest catalytic efficiency by facilitating the decomposition of H₂O₂ to generate hydroxyl radicals (•OH), which oxidize tetramethylbenzidine (TMB) to produce a blue-colored product. The catalytic mechanism was supported by UV–vis spectroscopy and fluorescence assays. Kinetic studies revealed low Km values, indicating high substrate affinity. Leveraging these properties, we further developed a disposable paper-based colorimetric bioassay using Mn₃O₄, which demonstrated excellent selectivity, sensitivity, and a low detection limit (0.25 μM in solution and 6.77 μM on paper). This work not only elucidates the correlation between Mn valence state and catalytic behavior but also provides a promising strategy for designing efficient nanozymes for low-cost, portable biosensing platforms.

Nanozymes as a promising alternative to natural enzymes are attracting enormous attention in past decades, yet their catalytic activities remain inferior to natural enzymes owing to the difficulties in performance improvement and precise control over composition, which greatly limits their practical application. Herein, by using metal organic frameworks as the sacrificial templates, we arbitrarily synthesize cobaltosic oxide (Co3O4) nanostructures with tunable valence states of Co sites via a one-step pyrolysis facilitated by a post-thermal treatment. It is found that through balancing the content between Co3+ and Co2+, partially reduced Co3O4 (R-Co3O4) exhibits the optimal peroxidase-like activity similar to natural horseradish peroxidase with Co2+ catalytically decomposing H2O2 while Co3+ adsorbs 3,30,5,50-tetramethylbenzidine. In addition, R-Co3O4 shows good stability in wide pH (2.58–10.04) and temperature (25.5–64.5 °C) ranges. Based on R-Co3O4 nanozymes, disposable paper-based bioassays are subsequently designed, exhibiting a good sensitivity to dopamine with a paper-based detection limit estimated to be 1.4 μM.