The Comparison of RBF NN and BPNN for SOC Estimation of LiFePO4 Battery

State of Charge (SOC) defined as the percentage of remaining capacity relative to the maximum capacity of the battery. In Battery Management Systems (BMS), SOC is an important variable. In this paper will describe comparison between Backpropagation Neural Networks (BPNN) and Radial Basis Function Neural Network (RBF NN) method for SOC estimation of LiFePO4 battery. BPNN and RBF NN have good characteristics to solve the nonlinear problem. We used discharge and Urban Dynamometer Driving Schedule (UDDS) as training data and testing data. In this research, architecture of BPNN are input layer, one hidden layer with 8 neurons and one output layer. Then architecture of RBF NN are input layer, one hidden layer with 2 neurons and output layer. The experiment used LiFePO4 battery with capacity 2200 mAh, with nominal voltage 4.2 volt. The actual SOC used coloumb counting which are 0 and 1. In this study shows that BPNN and RBF NN can be applied for SOC estimation in LiFePO4 of battery. Both of method have different charcteristics to give output in the network. Applying BPNN can make network more accurate but need more time for iteration. Then implementation RBF NN to estimate SOC is more efficiency in time. It means that network not needs more time for iteration.