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.

This study proposes an optimization strategy for the over-current protection (OCP) parameters of a lithium iron phosphate (LiFePO₄, LFP) battery system used in electric golf carts operating under high motor-load conditions. Real-world hillclimbing tests were conducted under four clearly defined payload/passenger conditions to analyze the transient discharge-current pro-file, voltage sag, and cell-temperature response. The maximum discharge current reached -238.2 A under the 200 kg cargopayload and one-passenger condition, and the current interval exceeding 150 A lasted up to 27 s. The maximum instantaneous power was 11.05 kW. Thermal analysis showed that the cell-temperature rise was within 2°C and the maximum measured cell temperature was 22.3°C. Linear regression of voltage and current yielded R² = 0.9368 and dV/dI = 0.0126 Ω, which was used as the DC internalresistance estimate. Based on these quantitative results and the cell specification limit of 300 A continuous discharge, the OCP threshold was reviewed from 250 A to 280 A to improve driving continuity while remaining below the allowable continuous-discharge current. EIS-based SOH estimation and the AI-BMS variable protection logic are presented as an extension framework for reflecting temperature and aging effects in future OCP-setting decisions.