Recurrent Neural Network-Based Modeling and Simulation of Lead-Acid Batteries Charge–Discharge

Author

Capizzi, Giacomo ; Bonanno, Francesco ; Tina, Giuseppe M.

Author_Institution

Dept. of Electr. Electron. & Syst. Eng., Univ. of Catania, Catania, Italy

Volume

26

Issue

2

fYear

2011

fDate

6/1/2011 12:00:00 AM

Firstpage

435

Lastpage

443

Abstract

This paper presents the main experiences and results obtained about the problem of the lead-acid battery modeling and simulation. A nonlinear mathematical model is presented as well as results of neuroprocessing of the charge-discharge experimental and simulated data. Recurrent neural networks were used to provide a state-of-charge observer and model parameter estimation and tuning. The simulation results are compared with those obtained by extensive lab tests performed on different batteries used for electric vehicle and photovoltaic application.

Keywords

neural nets; parameter estimation; power engineering computing; secondary cells; Pb-PbO₂; electric vehicle; lead-acid battery charge-discharge; model parameter estimation; nonlinear mathematical model; photovoltaic application; recurrent neural network-based modeling; state-of-charge observer; Batteries; Discharges; Lead; Mathematical model; Neurons; Recurrent neural networks; System-on-a-chip; Lead-acid batteries; mathematical modeling; recurrent neural networks (RNNs); state-of-charge (SOC) observer;

fLanguage

English

Journal_Title

Energy Conversion, IEEE Transactions on

Publisher

ieee

ISSN

0885-8969

Type

jour

DOI

10.1109/TEC.2010.2095015

Filename

5688309