The State of Charge Estimation Based on GRU for Lithium-ion Batteries

Monitoring the state of charge (SOC) of the battery can prevent overcharge and over-discharge for improving battery life. This study considers the effect of battery aging on the SOC and uses a model based on a gated recurrent unit (GRU) network to predict the state of health (SOH). Furthermore, the predicted SOH with voltage, current, and temperature is adopted as the input of another GRU-based model to predict SOC. The results show that the proposed method has a higher prediction accuracy than other methods.