A Novel Back Propagation Neural Network-square Root Cubature Kalman Filtering Strategy Based on Fusion Dual Factor Parameter Identification for State-of-Charge Estimation of Lithium-ion Batteries

Accurate real-time estimation of the state-of-charge (SOC) of the battery is of great significance for promoting the development of electric vehicles. In this research, a novel back propagation neural network-square root cubature Kalman filtering (BPNN-SRCKF) strategy based on fusion dual factor parameter identification for SOC estimation of lithium-ion batteries is proposed. First of all, with the organic integration of the forgetting factor and memory length, a dual factor parameter identification algorithm is designed. Secondly, the square root filtering is incorporated into the CKF algorithm to speed up the operation and avoid filter divergence. Finally, a BPNN is introduced to improve the fault tolerance of the model. The results show that the mean absolute error and root mean square error range from 1.13%~1.28% under complex working conditions, which proves that the proposed strategy has high precision and good robustness.