TY - JOUR
T1 - Hybrid Approach to Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack
AU - Dolenc, Bostjan
AU - Boskoski, Pavle
AU - Pohjoranta, Antti
AU - Noponen, Matti
AU - Juricic, Dani
N1 - Funding Information:
Projekti 101142
Work funded by the Spanish MCIU AGL2017-87373-C3-1R . Y.A. and LAAE acknowledge the Diputación General de Aragón for a predoctoral fellowship, as well as the European Social Fund.
Publisher Copyright:
© The Electrochemical Society.
PY - 2017/5/30
Y1 - 2017/5/30
N2 - Improvement in efficiency and reliability are essential for more intensive deployment and commercial exploitation of solid oxide fuel cell (SOFC) systems. Apart of advancement in fabrication of new materials and stack designs, there emerges a strong need for innovative control strategies capable of balancing maximal stack life and efficiency of power conversion in a trade-off manner. Reliable online estimation of stack health and prediction of the remaining useful life (RUL) play a key role in new generation of SOFC control systems. In most works until today, the authors utilize voltage as a health index and based on that predict the RUL. Unfortunately, such an approach becomes inappropriate when the SOFC is operating under varying load conditions and, in particular, when the SOFC ages. In this paper, we propose a novel hybrid approach to RUL prediction of SOFC systems, which overcomes the limitations of the known approaches and allows for reliable RUL prediction in non-stationary operating conditions. The approach consists of three main parts, executed continuously online: (i) estimation of area specific resistance (ASR) of the stack, (ii) prediction of its future progress based on collected data, and (iii) prediction of RUL. The methodology is evaluated on a 6 kW SOFC system.
AB - Improvement in efficiency and reliability are essential for more intensive deployment and commercial exploitation of solid oxide fuel cell (SOFC) systems. Apart of advancement in fabrication of new materials and stack designs, there emerges a strong need for innovative control strategies capable of balancing maximal stack life and efficiency of power conversion in a trade-off manner. Reliable online estimation of stack health and prediction of the remaining useful life (RUL) play a key role in new generation of SOFC control systems. In most works until today, the authors utilize voltage as a health index and based on that predict the RUL. Unfortunately, such an approach becomes inappropriate when the SOFC is operating under varying load conditions and, in particular, when the SOFC ages. In this paper, we propose a novel hybrid approach to RUL prediction of SOFC systems, which overcomes the limitations of the known approaches and allows for reliable RUL prediction in non-stationary operating conditions. The approach consists of three main parts, executed continuously online: (i) estimation of area specific resistance (ASR) of the stack, (ii) prediction of its future progress based on collected data, and (iii) prediction of RUL. The methodology is evaluated on a 6 kW SOFC system.
KW - SOFC
KW - diagnostics
KW - estimation
UR - http://www.scopus.com/inward/record.url?scp=85028468517&partnerID=8YFLogxK
U2 - 10.1149/07801.2251ecst
DO - 10.1149/07801.2251ecst
M3 - Article
VL - 78
SP - 2251
EP - 2264
JO - ECS Transactions
JF - ECS Transactions
SN - 1938-5862
IS - 1
T2 - 15th International Symposium on Solid Oxide Fuel Cells, SOFC XV
Y2 - 23 July 2017 through 28 July 2017
ER -