Fast intelligent battery charging: neural-fuzzy approach

Author

Ullah, Zafar ; Burford, Brian ; Dillip, S.

Author_Institution

Nat. Semicond. Corp., USA

Volume

11

Issue

6

fYear

1996

fDate

6/1/1996 12:00:00 AM

Firstpage

26

Lastpage

34

Abstract

This paper focuses on the design of a super fast battery charger based on National´s proprietary neural network based NeuFuz technology. In this application, we have used a NiCd battery pack as the test vehicle. However, this technology can be extended to other chemistries such as Ni-MH, Li-ion, etc. This technology allows the designer to accurately model the charge controller using a neural network, based on battery charge characteristics provided by the manufacturer. This approach continuously monitors the battery status, and modifies the charge current accordingly. It also eliminates the need for standard charge termination methods used in today´s conventional chargers. The result is super fast charging in 20 to 30 minutes, and increased battery life. A low cost embedded controller (COP8) performs all the fuel-gauging and charge control functions by processing data obtained from the battery circuitry

Keywords

battery chargers; cadmium; fuzzy control; intelligent control; neural nets; nickel; power supplies to apparatus; 20 to 30 min; Li-ion battery; NeuFuz technology; Ni-MH battery; NiCd; NiCd battery pack; battery circuitry; charge control functions; charge controller; design; fuel-gauging; intelligent battery charging; neural-fuzzy approach; standard charge termination; super fast battery charger; super fast charging; Algorithm design and analysis; Batteries; Control systems; Costs; Fuzzy systems; Intelligent networks; Mathematical model; Neural networks; Optimal control; Temperature;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems Magazine, IEEE

Publisher

ieee

ISSN

0885-8985

Type

jour

DOI

10.1109/62.500207

Filename

500207