SOC and SOH Identification Method of Li-Ion Battery Based on SWPSO-DRNN

Abstract

To realize accurate estimation of state of charge (SOC) and state of health (SOH), Li-ion battery's operating characteristic is analyzed in this article while fully considering temperature, degree of aging, and other practical factors that could impact their operating status. On the basis of the nonlinear autoregressive with exogenous input (NARX) architecture, an improved dynamic recurrent neural network (DRNN) with the ability of dynamic mapping is established, which is more suitable than the static network for estimating the batteries' state with strongly nonlinear and dynamic behaviors. Meanwhile, a self-adaptive weight particle swarm optimization (SWPSO) algorithm is introduced for training the network. Compared with the gradient descent algorithm, the SWPSO algorithm could improve the error convergence speed and avoid falling into local optimum. The validation results highlight that the presented method is able to improve the estimation accuracy of the SOC and SOH under different conditions including temperature, current, and degree of aging and has strong robustness and ability of generalization.