State of Charge estimation is very important to deliver essential information about battery charge and aging level of Li-ion batteries in Electric Vehicles. This paper applies the Deep Leaning and Machine Learning approaches comparing decision tree and Long Short-Term Memory for estimating the State of Charge. The datasets for the training and the evaluation have been generated with a Digital Twin model applying driving cycles at different ambient temperature. The proposed Digital Twin model includes non-linear phenomena.

Keywords: {State of charge (SOC), Deep learning, Digital twin}