Electric Vehicle Battery Charging State Prediction Based on Neural Network

In order to explore an efficient and accurate method to achieve accurate prediction of electric vehicle battery state of charge (SOC). In this study, a neural network model for SOC prediction of electric vehicle battery is designed and trained by synthesizing the basic principle of BP neural network, combining detailed data acquisition and pre-processing steps and fine feature engineering. The model can make full use of the historical operation data of the battery, capture the complex dynamic characteristics of the battery during charging and discharging, and realize the high-precision real-time prediction of SOC. The experimental results show that the prediction errors of BP neural network for EV battery SOC are kept at a low level at different temperatures of 0℃, 25℃ and 45℃, indicating that the BP neural network model designed in this paper has high prediction accuracy at different temperatures, and can meet the needs of practical applications.