Remaining Charging Time Accuracy Improvement through Preconditioning Prediction in Electric Vehicles

Remaining Charging Time (RCT) is an essential metric that is displayed to the customer/driver while charging the vehicle. It tells the driver how much time is remaining for the vehicle to be charged to 100% Display State of Charge (SOC) or the target SOC set by the driver. This metric helps drivers plan their time and decide when to unplug their device. For large battery systems like electric vehicles, the understanding of how much longer the battery needs to charge can help optimize energy use and avoid overcharging. The avoidance of un-necessary prolonged charging affects the long-term health of the battery. The RCT is calculated using a basic formula as the ratio of total energy needed to charge the battery to target SOC and the power pushed into the battery for charging. In this RCT formula numerator for a battery to be charged to a specific target SOC is fixed, but the denominator depends on lot of factors during charging and Battery Preconditioning is one of those factors that affect the denominator and hence the calculation of RCT. Battery Preconditioning (heating or cooling the battery before charging ) can help improve charging efficiency and speed, but during battery preconditioning the RCT shown to the driver is quite high since a large sum of charger power is used in Preconditioning the battery, and once the Preconditioning ends there is a huge jump in the RCT shown, since now most of the charger power is used in charging the battery. So, to avoid these jumps without compromising with the accuracy of the RCT, preconditioning needs to be predicted and considered in the calculation of the RCT from the beginning of the charging. This paper demonstrates the prediction of Preconditioning of the battery while charging with some known measurable quantities like battery temperatures, coolant temperature, ambient temperature with help of a function derived from neural network trained on vehicle data, and with the help of this function the calculation of RCT is improved with high accuracy and without considerable jumps due to preconditioning.