Title :
State of charge estimation for a lead-acid battery using backpropagation neural network method
Author :
Husnayain, F. ; Utomo, A.R. ; Priambodo, P.S.
Author_Institution :
Dept. of Electr. Eng., Univ. Indonesia, Depok, Indonesia
Abstract :
An accurate battery State of Charge (SOC) method are essential for having optimum utilization of a battery. The SOC estimation in this research propose Back propagation Neural Network method, then the result compare with Open Circuit Voltage (OCV) prediction and coulometric counting method. Experiment results show that the SOC estimation shows accurate measurements with maximum average percentage error no more than 0.893%.
Keywords :
backpropagation; battery charge measurement; lead acid batteries; neural nets; power engineering computing; OCV prediction; SOC estimation; back propagation neural network method; battery SOC method; battery state of charge method; coulometric counting method; lead-acid battery; open circuit voltage prediction; Batteries; Biological neural networks; Estimation; Lead; Mathematical model; System-on-chip; coulometric counting; lead-acid batteries; neural network; open circuit voltage; state-of-charge estimation;
Conference_Titel :
Electrical Engineering and Computer Science (ICEECS), 2014 International Conference on
Print_ISBN :
978-1-4799-8477-0
DOI :
10.1109/ICEECS.2014.7045261
