Capacity Estimation in Automotive Battery Management Systems with Intelligent Techniques

The urgency of addressing global warming has made electric vehicles and lithium-ion batteries key to sustainable transportation. Efficient battery management, notably through Battery Management Systems (BMS), is crucial for battery longevity. BMS calculates State of Charge (SOC) and State of Health (SOH), ensuring optimal battery performance and longevity, as they determine the remaining charge and health status, critical for preventing overcharging and extending battery life. For achieving accurate estimations, data-driven approaches have demonstrated notable efficacy. Among them, Neural Networks and Fuzzy Logic are frequently utilized techniques. This paper focuses on evaluating the capacity estimation methods for Li-ion batteries, employing both Neural Network and Fuzzy Logic methodologies, with the primary aim of ascertaining which approach proves more efficacious. The investigation encompasses both techniques to gain insights into their respective capabilities in estimating Battery Capacity. Our findings indicate that the Neural Network method stands out as the superior choice for battery capacity estimation. This conclusion is substantiated by the observation that the root mean square error associated with the ANN method is significantly lower when compared to the Fuzzy Logic method. Furthermore, we implemented these methodologies using the MATLAB tool.