Data-driven simultaneous fault diagnosis for solid oxide fuel cell system using multi-label pattern identification

被引:57
作者
Li, Shuanghong [1 ,2 ]
Cao, Hongliang [3 ,4 ]
Yang, Yupu [1 ,2 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Automat, 800 Dong Chuan Rd, Shanghai 200240, Peoples R China
[2] Minist Educ, Key Lab Syst Control & Informat Proc, Shanghai 200240, Peoples R China
[3] Huazhong Agr Univ, Coll Engn, 1 Shizishan St, Wuhan 430070, Hubei, Peoples R China
[4] Minist Agr, Key Lab Agr Equipment Midlower Yangtze River, Wuhan 430070, Hubei, Peoples R China
关键词
SOFC system; Data-driven; Multi-label; Pattern identification; Simultaneous faults; SUPPORT VECTOR MACHINE; NEURAL-NETWORKS; CLASSIFICATION; VALIDATION; SVM;
D O I
10.1016/j.jpowsour.2018.01.015
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Fault diagnosis is a key process for the reliability and safety of solid oxide fuel cell (SOFC) systems. However, it is difficult to rapidly and accurately identify faults for complicated SOFC systems, especially when simultaneous faults appear. In this research, a data-driven Multi-Label (ML) pattern identification approach is proposed to address the simultaneous fault diagnosis of SOFC systems. The framework of the simultaneous-fault diagnosis primarily includes two components: feature extraction and ML-SVM classifier. The simultaneous-fault diagnosis approach can be trained to diagnose simultaneous SOFC faults, such as fuel leakage, air leakage in different positions in the SOFC system, by just using simple training data sets consisting only single fault and not demanding simultaneous faults data. The experimental result shows the proposed framework can diagnose the simultaneous SOFC system faults with high accuracy requiring small number training data and low computational burden. In addition, Fault Inference Tree Analysis (FITA) is employed to identify the correlations among possible faults and their corresponding symptoms at the system component level.
引用
收藏
页码:646 / 659
页数:14
相关论文
共 52 条
[21]   Fault detection and diagnosis in process data using one-class support vector machines [J].
Mahadevan, Sankar ;
Shah, Sirish L. .
JOURNAL OF PROCESS CONTROL, 2009, 19 (10) :1627-1639
[22]   A semi-supervised approach to fault diagnosis for chemical processes [J].
Monroy, Isaac ;
Benitez, Raul ;
Escudero, Gerard ;
Graells, Moises .
COMPUTERS & CHEMICAL ENGINEERING, 2010, 34 (05) :631-642
[23]   Novel solid oxide fuel cell system controller for rapid load following [J].
Mueller, Fabian ;
Jabbari, Faryar ;
Gaynor, Robert ;
Brouwer, Jacob .
JOURNAL OF POWER SOURCES, 2007, 172 (01) :308-323
[24]   Monitoring of solid oxide fuel cell systems [J].
Murshed, A. K. M. M. ;
Huang, B. ;
Nandakumar, K. .
ASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING, 2011, 6 (02) :204-219
[25]   An Adaptive Approach Based on KPCA and SVM for Real-Time Fault Diagnosis of HVCBs [J].
Ni, Jianjun ;
Zhang, Chuanbiao ;
Yang, Simon X. .
IEEE TRANSACTIONS ON POWER DELIVERY, 2011, 26 (03) :1960-1971
[26]   Model-based development of a fault signature matrix to improve solid oxide fuel cell systems on-site diagnosis [J].
Polverino, Pierpaolo ;
Pianese, Cesare ;
Sorrentino, Marco ;
Marra, Dario .
JOURNAL OF POWER SOURCES, 2015, 280 :320-338
[27]   Simultaneous Fault Diagnosis using multi class support vector machine in a Dew Point process [J].
Pooyan, Navid ;
Shahbazian, Mehdi ;
Salahshoor, Karim ;
Hadian, Mohsen .
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2015, 23 :373-379
[28]  
Singhal S.C., 2003, HIGH TEMPERATURE SOL
[29]   FDI oriented modeling of an experimental SOFC system, model validation and simulation of faulty states [J].
Sorce, A. ;
Greco, A. ;
Magistri, L. ;
Costamagna, P. .
APPLIED ENERGY, 2014, 136 :894-908
[30]   On the Use of Neural Networks and Statistical Tools for Nonlinear Modeling and On-Field Diagnosis of Solid Oxide Fuel Cell Stacks [J].
Sorrentino, M. ;
Marra, D. ;
Pianese, C. ;
Guida, M. ;
Postiglione, F. ;
Wang, K. ;
Pohjoranta, A. .
ATI 2013 - 68TH CONFERENCE OF THE ITALIAN THERMAL MACHINES ENGINEERING ASSOCIATION, 2014, 45 :298-307