Hybrid Approach to Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack

Bostjan Dolenc, Pavle Boskoski, Antti Pohjoranta, Matti Noponen, Dani Juricic

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)2251-2264
Number of pages14
JournalECS Transactions
Volume78
Issue number1
DOIs
Publication statusPublished - 30 May 2017
MoE publication typeA1 Journal article-refereed
Event15th International Symposium on Solid Oxide Fuel Cells, SOFC XV - Hollywood, United States
Duration: 23 Jul 201728 Jul 2017

Fingerprint

Solid oxide fuel cells (SOFC)
Health
Control systems
Fabrication
Electric potential

Keywords

  • SOFC
  • diagnostics
  • estimation

Cite this

Dolenc, Bostjan ; Boskoski, Pavle ; Pohjoranta, Antti ; Noponen, Matti ; Juricic, Dani. / Hybrid Approach to Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack. In: ECS Transactions. 2017 ; Vol. 78, No. 1. pp. 2251-2264.
@article{41f4a1a3d8bb44a38dbdeccbd1e6a80b,
title = "Hybrid Approach to Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack",
abstract = "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.",
keywords = "SOFC, diagnostics, estimation",
author = "Bostjan Dolenc and Pavle Boskoski and Antti Pohjoranta and Matti Noponen and Dani Juricic",
note = "Project code: 101142",
year = "2017",
month = "5",
day = "30",
doi = "10.1149/07801.2251ecst",
language = "English",
volume = "78",
pages = "2251--2264",
journal = "ECS Transactions",
issn = "1938-5862",
publisher = "Electrochemical Society ECS",
number = "1",

}

Hybrid Approach to Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack. / Dolenc, Bostjan; Boskoski, Pavle; Pohjoranta, Antti; Noponen, Matti; Juricic, Dani.

In: ECS Transactions, Vol. 78, No. 1, 30.05.2017, p. 2251-2264.

Research output: Contribution to journalArticleScientificpeer-review

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 - Project code: 101142

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

ER -