With the rapid expansion of electric vehicles (EVs) and energy storage systems (ESS), ensuring the operational safety of lithium-ion batteries has become a critical technical challenge. Conventional battery management systems (BMS) primarily rely on threshold-based rule logic, which is limited in detecting coupled anomalies and early-stage degradation patterns. In this study, a deep learning-based framework for multivariate anomaly detection is proposed using BMS sensor data, including voltage, current, temperature, state of charge (SOC), and state of health (SOH). Five representative fault scenarios were defined, including thermal runaway precursors, cell voltage imbalance, SOC inconsistency, internal resistance increase, and communication delay. The proposed CNN-LSTM model was compared with conventional Rule-based methods and machine learning models, including Isolation Forest, Autoencoder, and LSTM. Experimental results show that the proposed model achieved the highest performance, with an F1-score of 0.885, an AUC of 0.94, and a detection delay of 8.1 s. In contrast, the Rule-based method exhibited a significantly higher false negative rate of 42.0%, indicating limitations in detecting complex anomaly patterns. These results demonstrate that the proposed spatiotemporal deep learning approach can significantly improve the accuracy and responsiveness of battery anomaly detection. Furthermore, the proposed method is expected to contribute to enhancing safety, reliability, and predictive diagnostics in next-generation intelligent BMS platforms.

Lithium-ion batteries are utilized as an energy source for electric vehicles because of their advantages such as excellent cyclability, high energy density, high capacity, high efficiency, and low price. However, lithium-ion batteries use combustible electrolytes, which have also reported problems related to fire safety. Therefore, research on the fire safety of lithium-ion batteries is actively being conducted. In this study, detection criteria for the fire safety of lithium-ion batteries were proposed through incremental capacity analysis (ICA) and frequency analysis. The experimental results showed that the battery micro internal short circuit (MISC) indicator could be identified through changes in specific frequency bands and fluctuations in the ICA curve.

Recently, active research has been conducted to enhance the power characteristics and thermal stability of lithiumion batteries (LiBs) by modifying separators using a ceramic coating method. However, since the thermal properties and surface features of the separator vary depending on the characteristics of the ceramic powders applied to the separator, it is crucial to manufacture ceramic powders optimized for the separator’s performance. In this study, we evaluated the characteristics of three types of α-alumina (A-1, A-2, and A-3) produced with varying dispersant contents and milling times, in addition to commercial α-alumina (AES-11). Subsequently, the optimized powders (A-3) were coated onto the separator using an aqueous binder for comparison with the characteristics of an AES-11 coated separator and an uncoated PE separator. The A-3 coated separator improved electrolyte wettability with a low contact angle (44.69°) and increased puncture strength (538 gf). Furthermore, it exhibited excellent thermal stability, with a shrinkage value of 5.64% when exposed to 140℃ for 1 hour, compared to the AES- 11 coated separator (6.09%) and the bare PE separator (69.64%).

Lithium-ion batteries (LIBs) have become a main energy storage device in various applications, such as portable appliances, renewable energy facilities, and electric vehicles. However, the poor thermal stability of LIBs may cause explosion or fire. The thermal runaway is the result of a failure of the separator inside LIB. Damages like tearing, piercing, and collapsing of the separator were simulated in a mechanical, an electrical, and a thermal way, and small discharge pulses of a few mV were detected at the time of separator damages. From the experimental results, this paper provided a method that can identify the separator failure before thermal runaway in the aspect of a potential explosion and fire prevention measures.

All-solid-state thin-film lithium-ion batteries are important in the development of next-generation energy storage devices with high energy density. However, thin-film batteries have many challenges in their manufacturing procedure. This is because there are many factors, such as substrate selection, to consider when producing the thin film multilayer structure. In this study, we compare the fabrication and performance of all-solid-state thin-film lithium-ion batteries with a LiNi_0.5Mn_1.5O₄ cathode/LiPON solid electrolyte/ Li₄Ti₅O₁₂ anode structure using stainless steel and Si substrates with different surface roughness. We demonstrate that the smoother the surface of the substrate, the thinner the thickness of the all-solid-state thin-film lithium-ion battery that can be made, and as a result, the corresponding electrochemical characteristics can be improved.

Black phosphorus (BP) is a potential candidate for an anode in lithium ion batteries due to its high theoretical capacity and the large interlayer spacing in the monolayered phosphorene form, allowing for lithium intercalation/ deintercalation. In this study, large-scale exfoliation of bulk BP was accomplished using a solution of NaOH and N-methyl-2-pyrrolidone (NMP), yielding phosphorene, which can be assembled into nanoflakes using electrophoretic deposition (EPD). Through the systematic addition of NaOH and subsequent sonication, BP nanoflakes were obtained in high yields by EPD, allowing for the integration of these nanoflakes into an anode in the film state. Anodes with a charge/discharge capacity of 172 mAh/g at a rate of 200 mA/g were obtained, which are promising for battery applications through various post-film treatments.

Transition metal oxide materials have attracted widespread attention as Li-ion battery electrode materials owing to their high theoretical capacity and good Li storage capability, in addition to various nanostructured materials. Here, we fabricated a CoO Li-ion battery in which Co nanoparticles (NPs) are deposited into a current collector through electrophoretic deposition (EPD) without binding and conductive agents, enabling us to focus on the intrinsic electrochemical properties of CoO during the conversion reaction. Through optimized Co NP synthesis and electrophoretic deposition (EPD), CoO Li-ion battery with 630 mAh/g was fabricated with high cycle stability, which can potentially be used as a test platform for a fundamental understanding of conversion reaction.