SOFC modelling based on discrete Bayesian network for system diagnosis use

K. Wang; M.C. Pera; D. Hissel; N. Yousfi Steiner; Antti Pohjoranta; S. Pofahl

doi:10.3182/20120902-4-FR-2032.00118

SOFC modelling based on discrete Bayesian network for system diagnosis use

K. Wang
, M.C. Pera
, D. Hissel
, N. Yousfi Steiner
, Antti Pohjoranta
, S. Pofahl

University of Franche-Comté
EIFER- European Institute for Energy Research by EDF and KIT
HTceramix S.A.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

4 Citations (Scopus)

Abstract

We propose in this paper a diagnosis method that is aimed to detect and isolate SOFC system fault by using the FC stack as a sensor. A discrete Bayesian network (BN) was established to illustrate the input-output causal relations of the stack. In order to examine the generalizability of the network structure, the BN was parameterized to fit the experimental data from two different SOFC systems. The models showed reasonable accuracy of state estimation for 6 operating variables. Finally, the BN model was experimented for diagnosing a specified system fault.

Original language	English
Title of host publication	8th Power Plant and Power System Control Symposium
Editors	Maurice Fadel, Stéphane Caux
Publisher	Elsevier
Pages	675-680
ISBN (Print)	978-3-902823-24-3
DOIs	https://doi.org/10.3182/20120902-4-FR-2032.00118
Publication status	Published - 2012
MoE publication type	A4 Article in a conference publication
Event	8th Power Plant and Power System Control Symposium, PPPSC 2012 - Toulouse, France Duration: 2 Sept 2012 → 5 Sept 2012

Publication series

Series	IFAC Proceedings Volumes
Number	21
Volume	45
ISSN	1474-6670

Conference

Conference	8th Power Plant and Power System Control Symposium, PPPSC 2012
Abbreviated title	PPPSC 2012
Country/Territory	France
City	Toulouse
Period	2/09/12 → 5/09/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Bayesian network
conditional probability
fault diagnosis
maximum likelihood
SOFC

Access to Document

10.3182/20120902-4-FR-2032.00118

Cite this

@inproceedings{a24f6fa448454120863e9207ecbd0f23,

title = "SOFC modelling based on discrete Bayesian network for system diagnosis use",

abstract = "We propose in this paper a diagnosis method that is aimed to detect and isolate SOFC system fault by using the FC stack as a sensor. A discrete Bayesian network (BN) was established to illustrate the input-output causal relations of the stack. In order to examine the generalizability of the network structure, the BN was parameterized to fit the experimental data from two different SOFC systems. The models showed reasonable accuracy of state estimation for 6 operating variables. Finally, the BN model was experimented for diagnosing a specified system fault.",

keywords = "Bayesian network, conditional probability, fault diagnosis, maximum likelihood, SOFC",

author = "K. Wang and M.C. Pera and D. Hissel and \{Yousfi Steiner\}, N. and Antti Pohjoranta and S. Pofahl",

year = "2012",

doi = "10.3182/20120902-4-FR-2032.00118",

language = "English",

isbn = "978-3-902823-24-3",

series = "IFAC Proceedings Volumes",

publisher = "Elsevier",

number = "21",

pages = "675--680",

editor = "Maurice Fadel and St{\'e}phane Caux",

booktitle = "8th Power Plant and Power System Control Symposium",

address = "Netherlands",

note = "8th Power Plant and Power System Control Symposium, PPPSC 2012, PPPSC 2012 ; Conference date: 02-09-2012 Through 05-09-2012",

}

Wang, K, Pera, MC, Hissel, D, Yousfi Steiner, N, Pohjoranta, A & Pofahl, S 2012, SOFC modelling based on discrete Bayesian network for system diagnosis use. in M Fadel & S Caux (eds), 8th Power Plant and Power System Control Symposium. Elsevier, IFAC Proceedings Volumes, no. 21, vol. 45, pp. 675-680, 8th Power Plant and Power System Control Symposium, PPPSC 2012, Toulouse, France, 2/09/12. https://doi.org/10.3182/20120902-4-FR-2032.00118

SOFC modelling based on discrete Bayesian network for system diagnosis use. / Wang, K.; Pera, M.C.; Hissel, D. et al.
8th Power Plant and Power System Control Symposium. ed. / Maurice Fadel; Stéphane Caux. Elsevier, 2012. p. 675-680 (IFAC Proceedings Volumes; No. 21, Vol. 45).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - SOFC modelling based on discrete Bayesian network for system diagnosis use

AU - Wang, K.

AU - Pera, M.C.

AU - Hissel, D.

AU - Yousfi Steiner, N.

AU - Pohjoranta, Antti

AU - Pofahl, S.

PY - 2012

Y1 - 2012

N2 - We propose in this paper a diagnosis method that is aimed to detect and isolate SOFC system fault by using the FC stack as a sensor. A discrete Bayesian network (BN) was established to illustrate the input-output causal relations of the stack. In order to examine the generalizability of the network structure, the BN was parameterized to fit the experimental data from two different SOFC systems. The models showed reasonable accuracy of state estimation for 6 operating variables. Finally, the BN model was experimented for diagnosing a specified system fault.

AB - We propose in this paper a diagnosis method that is aimed to detect and isolate SOFC system fault by using the FC stack as a sensor. A discrete Bayesian network (BN) was established to illustrate the input-output causal relations of the stack. In order to examine the generalizability of the network structure, the BN was parameterized to fit the experimental data from two different SOFC systems. The models showed reasonable accuracy of state estimation for 6 operating variables. Finally, the BN model was experimented for diagnosing a specified system fault.

KW - Bayesian network

KW - conditional probability

KW - fault diagnosis

KW - maximum likelihood

KW - SOFC

U2 - 10.3182/20120902-4-FR-2032.00118

DO - 10.3182/20120902-4-FR-2032.00118

M3 - Conference article in proceedings

SN - 978-3-902823-24-3

T3 - IFAC Proceedings Volumes

SP - 675

EP - 680

BT - 8th Power Plant and Power System Control Symposium

A2 - Fadel, Maurice

A2 - Caux, Stéphane

PB - Elsevier

T2 - 8th Power Plant and Power System Control Symposium, PPPSC 2012

Y2 - 2 September 2012 through 5 September 2012

ER -

SOFC modelling based on discrete Bayesian network for system diagnosis use

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this