A Novel Adaptive Back Propagation Neural Network-Unscented Kalman Filtering Algorithm for Accurate Lithium-Ion Battery State of Charge Estimation

Accurate State of Charge (SOC) estimation for lithium-ion batteries has great significance with respect to the correct decision-making and safety control. In this research, an improved second-order-polarization equivalent circuit (SO-PEC) modelling method is proposed. process estimating SOC, a joint algorithm, Adaptive Back Propagation Neural Network Unscented Kalman Filtering algorithm (ABP-UKF), It combines advantages robust learning rate in (BP) neural network linearization error reduction (UKF) algorithm. BP part, self-adjustment factor accompanies whole process, improvement corrects shortcomings UKF verification model validated using segmented double-exponential fit. Using Ampere-hour integration as reference value, results (BP-UKF) are compared, accuracy proposed by 1.29% under Hybrid Pulse Power Characterization (HPPC) working conditions, 1.28% Beijing Bus Dynamic Stress Test (BBDST) 2.24% (DST) conditions. The ABP-UKF good SOC will play important role high-precision energy management process.