State of charge estimation of lithium-ion battery based on multi-input extreme learning machine using online model parameter identification

Abstract

The state of charge (SOC) is important for ensuring both battery safety and life. Furthermore, the SOC is required to estimate other battery states such as state of power (SOP) and state of health (SOH). Because the SOC is determined by estimation rather than observation, it is important to establish a proper estimation method. In this paper, an equivalent circuit model (ECM) was first constructed through online parameter extraction. Online parameter identification was based on a recursive least squares (RLS) method to input the various internal information regarding the battery into the extreme learning machine to achieve accurate SOC estimation. Second, to deliver a highly accurate SOC estimation of lithium-ion batteries (LiBs), the multi-input extreme learning machine (MI-ELM) method based on an online model parameter identification technique was applied to the SOC estimation of LiBs. Finally, experiments were conducted under various operating conditions to assess the performance of the proposed method. Compared with other estimation methods such as the extended Kalman filter (EKF), the ordinary extreme learning machine (ELM), the adaptive square root extended Kalman filter (ASREKF), the autoencoder neural network with long short-term memory neural network (AUTOENCOD-LSTM), the artificial neural network and unscented Kalman filter (NN&UKF), and the gravitational search algorithm-based ELM (ELM-GSA) in terms of the mean absolute error (MAE) and the root mean square error (RMSE), the proposed MI-ELM method achieved 60.00 %, 88.83 %, 52.50 %, 80.00 %, 84.55 %, and 79.64 % of the maximum performance improvement, respectively.