Analysis of a Li-ion battery state of charge by artificial neural network

Abstract

The state of charge (SOC) is a battery residual capacity crucial assessment metric. The need for a precise SOC estimate is very important to ensure the safe functioning of a Li-ion battery and to prevent overload and over-depletion. However, the renewable energy-based standalone application has become a key problem to determine the exact capacity of SOC of the Li-ion battery. To estimate the capacity over time, the battery management system calculates the SOC of a Li-ion battery. This allows for the implementation of intelligent control systems. This paper presents an enhanced radial basis function (RBF) of the SOC battery estimate following the limits and weaknesses of the back propagation (BP) neural network (NN) in estimating battery SOC, such as sluggish convergence speed, poor generalization and can increase the accuracy of the network but it takes time to iterate. Train the enhanced RBF with experimental data in real-time. The trained NN of SOC is compared to actual values and the MATLAB is used to simulate the method to evaluate its accuracy.