Hybrid neural networks architectures for SOC and voltage prediction of new generation batteries storage

Author

Capizzi, G. ; Bonanno, F. ; Napoli, C.

Author_Institution

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

fYear

2011

fDate

14-16 June 2011

Firstpage

341

Lastpage

344

Abstract

This paper presents some experiences and results obtained about the problem of the SOC and voltage prediction and simulation of new generation batteries. A complex pipelined recurrent neural network (PRNN) was designed for modeling of new generation batteries storage in order to predict the SOC and the terminal voltage. The simulation results are compared with experimental data obtained on commercial batteries.

Keywords

battery chargers; electric charge; electric potential; power engineering computing; recurrent neural nets; secondary cells; complex pipelined recurrent neural network; hybrid neural network architecture; new generation battery storage; state of charge observer; voltage prediction; Batteries; Biological neural networks; Ions; Lithium; Pipeline processing; Recurrent neural networks; System-on-a-chip; Lithium ions batteries; hybrid neural network architectures; pipelined recurrent neural network (PRNN); recurrent neural networks (RNNs); state-of-charge (SOC) observer;

fLanguage

English

Publisher

ieee

Conference_Titel

Clean Electrical Power (ICCEP), 2011 International Conference on

Conference_Location

Ischia

Print_ISBN

978-1-4244-8929-9

Electronic_ISBN

978-1-4244-8928-2

Type

conf

DOI

10.1109/ICCEP.2011.6036301

Filename

6036301