Combined State of Charge and State of Energy Estimation for Echelon-Use Lithium-Ion Battery Based on Adaptive Extended Kalman Filter

To ensure the safety and reliability of an echelon-use lithium-ion battery (EULIB), performance a EULIB is accurately reflected. This paper presents method estimating combined state energy (SOE) charge (SOC). First, aiming to improve accuracy SOE SOC estimation, third-order resistor-capacitance equivalent model (TRCEM) established. Second, long short-term memory (LSTM) introduced optimize Ohmic internal resistance (OIR), actual (AE), capacity (AC) parameters in real time model. Third, process observation noise equation are updated iteratively make adaptive corrections enhance ability. Finally, estimation based on LSTM optimization extended Kalman filter (AEKF) In simulation experiments, when decays 90%, 60% 30% rated capacity, regardless whether initial value consistent with value, values can track strong ability, estimated error less than 1.19%, indicating that algorithm has high level accuracy. The presented this provides new perspective for EULIB.