Lithium-Ion batteries modeling and state of charge estimation using Artificial Neural Network

Younes Boujoudar (Sidi Mohamed Ben Abdellah University)
Hassan Elmoussaoui (Sidi Mohamed Ben Abdellah University)
Tijani Lamhamdi (Sidi Mohamed Ben Abdellah University)

International Journal of Electrical and Computer Engineering
Vol 9, No 5: October 2019

In This paper, we propose an effective and online technique for modeling nd State of Charge (SoC) estimation of Lithium-Ion (Li-Ion) batteries using Feed Forward Neural Networks(FFNN) and Nonlinear Auto Regressive model with eXogenous input(NARX). The both Artificial Neural Network (ANN) are rained using the data collected from the batterycharging and discharging pro ess. The NARX network finds the needed battery model, where the input ariables are the battery terminal voltage, SoC at the previous sample, and the urrent, temperature at the present sample. The proposed method is imple mented on a Li-Ion battery cell to estimate online SoC. Simulation results show good estimation of theSoC.