High-precision state of charge estimation of lithium-ion batteries based on improved particle swarm optimization-backpropagation neural network-dual extended Kalman filtering.

Chen, Lu; Wang, Shunli; Chen, Lei; Qiao, Jialu; Fernandez, Carlos

Abstract

High precision state of Charge (SOC) estimation is essential for battery management systems (BMS). In this paper, a new SOC estimation method is proposed. The dual Kalman filter algorithm is combined with the backpropagation neural network (PSO-BPNN-DEKF) which optimizes the initial weights and thresholds by particle swarm optimization algorithm to estimate and correct the SOC of lithium-ion batteries. Based on the second-order RC equivalent circuit model, parameter identification is carried out using the adaptive forgetting factor least squares method (AFFRLS). Implement online parameter updates and SOC estimation through the DEKF algorithm. Then, the trained PSO-BPNN is used to predict the SOC estimation error in real time, and the SOC estimation value is corrected by adding prediction errors. The SOC estimates before and after correction under Beijing Dynamic Stress Test (BBDST), dynamic Stress Test (DST), and Hybrid Pulse Power Characterization(HPPC) were compared. Under BBDST, DST, and HPPC tests, the maximum errors of the corrected SOC estimates are 0.0107, 0.0090, and 0.0147, respectively. The root mean square error (RMSE) of the corrected SOC estimates decreased by 94.02%, 83.18%, and 88.03% respectively compared with the EKF. The MAE of the corrected SOC estimates remained around 0.1% for all the BBDST dynamic operating conditions at different temperatures. The experimental results demonstrate the accuracy, effectiveness, and temperature adaptability of the proposed algorithm for SOC estimation under complex conditions of lithium-ion batteries.

Citation

CHEN, L., WANG, S., CHEN, L., QIAO, J. and FERNANDEZ, C. 2024. High-precision state of charge estimation of lithium-ion batteries based on improved particle swarm optimization-backpropagation neural network-dual extended Kalman filtering. International journal of circuit theory and application [online], 52(3), pages 1192-1209. Available from: https://doi.org/10.1002/cta.3788

• Journal Article Type: Article
• Acceptance Date: Aug 15, 2023
• Online Publication Date: Sep 16, 2023
• Publication Date: Mar 31, 2024
• Deposit Date: Aug 15, 2023
• Publicly Available Date: Sep 17, 2024
• Journal: International journal of circuit theory and applications
• Print ISSN: 0098-9886
• Electronic ISSN: 1097-007X
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 52
• Issue: 3
• Pages: 1192-1209
• DOI: https://doi.org/10.1002/cta.3788
• Keywords: Double extended Kalman filter; Backpropagation neural network; Particle swarm optimization algorithm; Estimation of state of charge; Ternary lithium battery
• Public URL: https://rgu-repository.worktribe.com/output/2043536