Bayesian network supervision on fault tolerant fuel cells

Luis A.M. Riascos; Fábio G. Cozman; Paulo E. Miyagi; Marcelo G. Simões

doi:10.1109/IAS.2006.256655

Bayesian network supervision on fault tolerant fuel cells

Luis A.M. Riascos, Fábio G. Cozman, Paulo E. Miyagi, Marcelo G. Simões

Research output: Contribution to conference › Conference Paper

18 Scopus citations

Abstract

In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell (PEMFC), is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause-effect relationship among the variables of the process. The fault diagnosis is based on the online monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The fault effects are based on experiments on a fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment. © 2006 IEEE.

Original language	American English
Pages	1059-1066
Number of pages	8
DOIs	https://doi.org/10.1109/IAS.2006.256655
State	Published - 1 Dec 2006
Externally published	Yes
Event	Conference Record - IAS Annual Meeting (IEEE Industry Applications Society) - Duration: 1 Dec 2006 → …

Conference

Conference	Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)
Period	1/12/06 → …

Access to Document

10.1109/IAS.2006.256655

Fingerprint Dive into the research topics of 'Bayesian network supervision on fault tolerant fuel cells'. Together they form a unique fingerprint.

Cite this

@conference{386878b012fd43a89d745886c9dcbfb3,

title = "Bayesian network supervision on fault tolerant fuel cells",

abstract = "In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell (PEMFC), is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause-effect relationship among the variables of the process. The fault diagnosis is based on the online monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The fault effects are based on experiments on a fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment. {\textcopyright} 2006 IEEE.",

author = "Riascos, {Luis A.M.} and Cozman, {F{\'a}bio G.} and Miyagi, {Paulo E.} and Sim{\~o}es, {Marcelo G.}",

year = "2006",

month = dec,

day = "1",

doi = "10.1109/IAS.2006.256655",

language = "American English",

pages = "1059--1066",

note = "Conference Record - IAS Annual Meeting (IEEE Industry Applications Society) ; Conference date: 01-12-2006",

}

TY - CONF

T1 - Bayesian network supervision on fault tolerant fuel cells

AU - Riascos, Luis A.M.

AU - Cozman, Fábio G.

AU - Miyagi, Paulo E.

AU - Simões, Marcelo G.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell (PEMFC), is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause-effect relationship among the variables of the process. The fault diagnosis is based on the online monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The fault effects are based on experiments on a fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment. © 2006 IEEE.

AB - In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell (PEMFC), is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause-effect relationship among the variables of the process. The fault diagnosis is based on the online monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The fault effects are based on experiments on a fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment. © 2006 IEEE.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=34948842907&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=34948842907&origin=inward

U2 - 10.1109/IAS.2006.256655

DO - 10.1109/IAS.2006.256655

M3 - Conference Paper

SP - 1059

EP - 1066

T2 - Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

Y2 - 1 December 2006

ER -