Data-driven Terminal Voltage Prediction of Li-ion Batteries Under Dynamic Loads

Extensive investigation and prediction of the effects of dynamic battery loading is key to on-board Battery Management Systems (BMS) of Electric Vehicles (EVs) in order to ensure reliable operation and efficient energy management. In this paper, measurements of WLTP discharge tests at different temperatures are conducted on a Lithium Nickel Manganese Cobalt Oxide (LiNiMnCoO2) cell. Terminal voltage, discharge rate and temperatures at four points are taken into consideration. After, historical measurement data is used to build ensemble of boosted tree models and then predict cell voltage outcome sequence into the future. The efficiency of the performance is compared in case of various measurement sets. The results support the efficiency and applicability of direct multi-step-ahead forecasting strategy with standard Machine Learning techniques in battery SoC prediction.