ABSTRACT The state of charge (SOC) of a battery is a core component of Battery Management Systems (BMS) and has become a key research focus due to its significant role in the development of clean energy. To address the limitations of traditional SOC estimation methods, this paper proposes a joint SOC estimation algorithm based on FFRLS‐AEKF‐LSTM. First, a second‐order RC equivalent circuit model of the battery is established, using data from Hybrid Pulse Power Characterization (HPPC) tests as input. The model parameters are initially identified using the Forgetting Factor Recursive Least Squares (FFRLS) method. Then, the Adaptive Extended Kalman Filter (AEKF) algorithm is employed to iteratively update and estimate the SOC. Finally, the parameters obtained from AEKF, together with voltage and current data under HPPC conditions, are used to train a Long Short‐Term Memory (LSTM) neural network to predict the SOC. Experimental results show that the proposed joint algorithm achieves a Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) both below 1%, demonstrating excellent performance.
Wei et al. (Mon,) studied this question.