Estimating a battery state of charge using neural networks

Author

Enache, Bogdan-Adrian ; Diaconescu, Eugen

Author_Institution

Electron., Comput. & Electr. Eng. Dept., Univ. of Pitesti, Arges, Romania

fYear

2014

Firstpage

1

Lastpage

6

Abstract

This paper presents the means for estimating a battery State of Charge (SoC) using neural networks. Several neural networks such as: radial basis function (RBF), feed forward (FF) and nonlinear autoregressive with exogenous (external) input (NARX) are used for curve fitting and predicting features values. The conclusions are drawn after comparing the values obtained from the models and the data obtained from discharging a LiFePO₄ (LFP) battery.

Keywords

autoregressive processes; battery charge measurement; curve fitting; iron compounds; lithium compounds; phosphorus compounds; power engineering computing; radial basis function networks; secondary cells; LFP battery; LiFePO4 battery; LiFePO₄; NARX; RBF; battery SoC estimation; battery state of charge estimation; curve fitting; features values prediction; feed forward; neural networks; nonlinear autoregressive with exogenous input; nonlinear autoregressive with external input; radial basis function; Approximation methods; Batteries; Discharges (electric); Neurons; Radial basis function networks; System-on-chip; LFP battery; NARX network; State of Charge; battery modelling; neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Fundamentals of Electrical Engineering (ISFEE), 2014 International Symposium on

Print_ISBN

978-1-4799-6820-6

Type

conf

DOI

10.1109/ISFEE.2014.7050636

Filename

7050636