LSTM with AhI-Model Based Kalman Filter for Lithium-ion Battery State of Charge Estimation

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the Center for Advanced Life Cycle Engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively.