Online implementation of SVM based fault diagnosis strategy for PEMFC systems

被引：99

作者：

Li, Zhongliang ^{[1
,2
]}

Outbib, Rachid ^{[3
]}

Giurgea, Stefan ^{[1
,2
]}

Hissel, Daniel ^{[1
,2
]}

Jemei, Samir ^{[1
,2
]}

Giraud, Alain ^{[4
]}

Rosini, Sebastien ^{[5
]}

机构：

[1] CNRS, FR 3539, FCLAB Fuel Cell Lab Res Federat, Rue Thierry Mieg, F-90010 Belfort, France

[2] UFC UTBM ENSMM, Dept Energy, CNRS, FEMTO ST,UMR 6174, Paris, France

[3] Univ Aix Marseille, LSIS, Marseille, France

[4] CEA, LIST, F-91191 Gif Sur Yvette, France

[5] CEA Grenoble, LITEN, F-38054 Grenoble, France

来源：

APPLIED ENERGY | 2016年 / 164卷

关键词：

PEMFC system; Fault diagnosis; SVM classification; System in Package; Online implementation; FUEL-CELL; MODEL; STACK; METHODOLOGIES;

D O I：

10.1016/j.apenergy.2015.11.060

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

In this paper, the topic of online diagnosis for Polymer Electrolyte Membrane Fuel Cell (PEMFC) systems is addressed. In the diagnosis approach, individual cell voltages are used as the variables for diagnosis. The pattern classification tool Support Vector Machine (SVM) combined with designed diagnosis rule is used to achieve fault detection and isolation (FDI). A highly-compacted embedded system of the System in Package (SiP) type is designed and fabricated to monitor individual cell voltages and to perform the diagnosis algorithms. For validation, the diagnosis approach is implemented online on PEMFC experimental platform. Four concerned faults can be detected and isolated in real-time. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：284 / 293

页数：10

共 41 条

[1] Vibration Spectrum Imaging: A Novel Bearing Fault Classification Approach [J].

Amar, Muhammad ;

Gondal, Iqbal ;

Wilson, Campbell .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2015, 62 (01) :494-502

[2]

[Anonymous], 1998, TECH REP

[3] Fuel cell diagnosis method based on multifractal analysis of stack voltage signal [J].

Benouioua, D. ;

Candusso, D. ;

Harel, F. ;

Oukhellou, L. .

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2014, 39 (05) :2236-2245

[4] Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network [J].

Cai, Baoping ;

Liu, Yonghong ;

Fan, Qian ;

Zhang, Yunwei ;

Liu, Zengkai ;

Yu, Shilin ;

Ji, Renjie .

APPLIED ENERGY, 2014, 114 :1-9

[5] Fast exact leave-one-out cross-validation of sparse least-squares support vector machines [J].

Cawley, GC ;

Talbot, NLC .

NEURAL NETWORKS, 2004, 17 (10) :1467-1475

[6] A NOVEL POLYPHASE MULTIPOLE SQUARE-WAVE PERMANENT-MAGNET MOTOR DRIVE FOR ELECTRIC VEHICLES [J].

CHAN, CC ;

JIANG, JZ ;

CHEN, GH ;

WANG, XY ;

CHAU, KT .

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1994, 30 (05) :1258-1266

[7] Lifetime prediction and the economic lifetime of Proton Exchange Membrane fuel cells [J].

Chen, Huicui ;

Pei, Pucheng ;

Song, Mancun .

APPLIED ENERGY, 2015, 142 :154-163

[8] LPV observer design for PEM fuel cell system: Application to fault detection [J].

de Lira, S. ;

Puig, V. ;

Quevedo, J. ;

Husar, A. .

JOURNAL OF POWER SOURCES, 2011, 196 (09) :4298-4305

[9] Model-based fault diagnosis in PEM fuel cell systems [J].

Escobet, T. ;

Feroldi, D. ;

de Lira, S. ;

Puig, V. ;

Quevedo, J. ;

Riera, J. ;

Serra, M. .

JOURNAL OF POWER SOURCES, 2009, 192 (01) :216-223

[10] Experimental and modelling studies of CO poisoning in PEM fuel cells [J].

Farrell, C. G. ;

Gardner, C. L. ;

Ternan, M. .

JOURNAL OF POWER SOURCES, 2007, 171 (02) :282-293

← 1 2 3 4 5 →