A hybrid energy pack combines lithium-ion batteries and supercapacitors to meet high-energy and high-power demands simultaneously, providing various benefits such as improved energy efficiency and extended battery life, which is crucial in the field o...
A hybrid energy pack combines lithium-ion batteries and supercapacitors to meet high-energy and high-power demands simultaneously, providing various benefits such as improved energy efficiency and extended battery life, which is crucial in the field of energy storage and management. This study proposed a Long Short-Term Memory(LSTM)-based algorithm for State of Charge(SOC) estimation in hybrid energy packs. Data generated from FTP72, FTP75, UDDS, WLTP Class 1, WLTP Class 2, and WLTP Class 3 drive cycles, each discharged 100 times, were used to train and test the model. Compared to a GRU-based model that uses the Root Mean Square Error(RMSE) metric, our proposed model demonstrated a 50 % improvement in performance, showing superior SOC estimation accuracy.