State of Charge Estimation of Lead-Acid Battery with Coulomb Counting and Feed-Forward Neural Network Method

This study aims to design and assess the simulation of the state of charge (SoC) estimation on lead-acid batteries using the Coulomb counting (CC) and feed-forward neural network (FFNN) method. Also, this study compared the effectiveness of each technique. CC and FFNN methods were designed and simulated in Simulink, and the results were analyzed. The two estimation results are compared to see the level of efficiency of each technique. The results of this study show that the feed-forward neural network method is better than the Coulomb counting method in load variation with a ratio of 5.56% on the first data input and 0.46% on the second data input, and 5.78% in temperature variation.