SOC Prediction of power lithium battery using BP neural network theory based on keras

Abstract

The estimation of state of charge(SOC) is among the key technologies in battery management system. Compared with many estimation methods, neural network has obvious advantages in the estimation accuracy. But requiring great amount of data is its main limitation. In order to solve the above problems, a method for SOC estimation based on the cross validation of artificial neural network and k-fold was proposed. An 18650 power lithium-ion battery is used as the experimental object, and the data are obtained by collecting the battery voltage, current and temperature data. High SOC estimation accuracy on different verification sets is pursued under circumstance of low data amount. The BP artificial neural network model is established based on the Keras platform with tensorflow, and K-fold cross validation method is added to the network. After training, the model is used to predict the experimental data. The estimation of SOC is realized by function fitting. Compared with the traditional BP neural network prediction, the prediction accuracy is 99%. Finally, it is proved that the method combining BP neural network and K-flow cross validation is effective and the validity of the neural network model for SOC estimation is verified.