Convolution Neural Network-Based SOC Estimation of Li-ion Battery in EV Applications

The State of Charge (SOC) is the most important index in the Battery Management System (BMS). It tells us how much charge the battery is holding at a particular time. An accurate SOC estimation is essential for ensuring the safe and reliable operation of the battery. In this paper, a Neural Network approach known as Convolutional Neural Network (CNN) opted for SOC estimation. Dataset Corresponding to New York City Cycle (NYCC) driving cycle at temperatures 15 degrees C, 25 degrees C, and 45 degrees C is considered for evaluating our model. The NYCC dataset used for estimation purposes is a real dataset obtained from experimenting. In order to achieve the optimal result, we validated the model against a different number of hyperparameters by varying the number of filters in the convolutional layers. The proposed CNN provides a competitive estimation performance compared to other model-based methods for SOC estimation.