Estimation of power battery SOC based on PSO-Elman neural network

Estimation of the state-of-charge (SOC) of a battery for an electric vehicle is one of the key technologies for battery management technology (BMS). For the problem of low SOC estimation accuracy, this paper proposes an improved PSO-Elman neural network prediction model. In this model, the current and voltage of the battery are the input of the model, and the SOC of the battery is the output of the model. In the modeling process, the PSO algorithm is improved by combining the nonlinear weight reduction of inertia weights with the stochastic inertia weights. The improved PSO algorithm is used to optimize the weights and thresholds of Elman neural network. The data set is used to train and verify the improved PSO-Elman neural network with data sets in the MATLAB. The results show that the improved PSO-Elman neural network has higher accuracy and faster prediction speed than the basic PSO-Elman neural network.