Abstract:

The lithium-ion battery is crucial for Electric Vehicles (EVs) due to its higher energy density, longer life cycle, and nominal voltage and capacity. The State of Charge (SOC) is a crucial parameter for EVs, and it plays a significant role in the Battery Management System (BMS). This research proposes an Equivalent Circuit Model (ECM) based on Kalman filtering method and a data-driven technique, Deep Feed-Forward Neural Network (DFNN), for accurate SOC estimation of the EVM. The model uses a second-order RC (2-RC) ECM to identify lithium-ion battery parameters, and then measures various operating conditions to minimize SOC estimation error and bound error. The UKF algorithm estimates a SOC bound error of 1.5% and an estimation error of 0.5%, proving its efficiency and reliability. The data-driven DFNN method is implemented for accuracy enhancement of SOC estimation with trained 20 iterations and epochs data, achieving a satisfactory SOC estimation accuracy of only 0.04% Root Mean Squared Error (RMSE). The validation results indicate that the model-based filtering method is an effective method for SOC estimation, while a novel data-driven approach improves SOC estimation accuracy by approximately 0.46%.