Fault diagnosis in fuel cell systems using quantitative models and support vector machines

Author

Pellaco, L. ; Costamagna, P. ; De Giorgi, Andrea ; Greco, Alberto ; Magistri, L. ; Moser, Gabriele ; Trucco, Andrea

Author_Institution

Polytech. Sch., Univ. of Genoa, Genoa, Italy

Volume

50

Issue

11

fYear

2014

fDate

May 22 2014

Firstpage

824

Lastpage

826

Abstract

Fault detection and identification are new and challenging tasks for electrical generation plants that are based on solid oxide fuel cells. The use of a quantitative model of the plant together with a support vector machine to design and operate a supervised classification system is proposed. This type of system, which uses a few easy-to-measure features selected through the maximisation of a classification error bound, proved to be effective in revealing a faulty condition and identifying it among the four considered fault classes.

Keywords

fault diagnosis; fuel cell power plants; power engineering computing; solid oxide fuel cells; support vector machines; classification error bound maximisation; easy-to-measure features; electrical generation plants; fault class; fault detection; fault diagnosis; fault identification; faulty condition; fuel cell systems; quantitative model; solid oxide fuel cells; supervised classification system; support vector machines;

fLanguage

English

Journal_Title

Electronics Letters

Publisher

iet

ISSN

0013-5194

Type

jour

DOI

10.1049/el.2014.0565

Filename

6824376