TY - JOUR
T1 - Fault detection and isolation of high temperature proton exchange membrane fuel cell stack under the influence of degradation
AU - Jeppesen, Christian
AU - Araya, Samuel Simon
AU - Sahlin, Simon Lennart
AU - Thomas, Sobi
AU - Andreasen, Søren Juhl
AU - Kær, Søren Knudsen
PY - 2017/8
Y1 - 2017/8
N2 - This study proposes a data-drive impedance-based methodology for fault detection and isolation of low and high cathode stoichiometry, high CO concentration in the anode gas, high methanol vapour concentrations in the anode gas and low anode stoichiometry, for high temperature PEM fuel cells. The fault detection and isolation algorithm is based on an artificial neural network classifier, which uses three extracted features as input. Two of the proposed features are based on angles in the impedance spectrum, and are therefore relative to specific points, and shown to be independent of degradation, contrary to other available feature extraction methods in the literature. The experimental data is based on a 35 day experiment, where 2010 unique electrochemical impedance spectroscopy measurements were recorded. The test of the algorithm resulted in a good detectability of the faults, except for high methanol vapour concentration in the anode gas fault, which was found to be difficult to distinguish from a normal operational data. The achieved accuracy for faults related to CO pollution, anode- and cathode stoichiometry is 100% success rate. Overall global accuracy on the test data is 94.6%.
AB - This study proposes a data-drive impedance-based methodology for fault detection and isolation of low and high cathode stoichiometry, high CO concentration in the anode gas, high methanol vapour concentrations in the anode gas and low anode stoichiometry, for high temperature PEM fuel cells. The fault detection and isolation algorithm is based on an artificial neural network classifier, which uses three extracted features as input. Two of the proposed features are based on angles in the impedance spectrum, and are therefore relative to specific points, and shown to be independent of degradation, contrary to other available feature extraction methods in the literature. The experimental data is based on a 35 day experiment, where 2010 unique electrochemical impedance spectroscopy measurements were recorded. The test of the algorithm resulted in a good detectability of the faults, except for high methanol vapour concentration in the anode gas fault, which was found to be difficult to distinguish from a normal operational data. The achieved accuracy for faults related to CO pollution, anode- and cathode stoichiometry is 100% success rate. Overall global accuracy on the test data is 94.6%.
KW - Classification
KW - Electrochemical impedance spectroscopy (EIS)
KW - Fault diagnosis
KW - Fuel cell
KW - Pattern recognition
KW - PEM
UR - http://www.scopus.com/inward/record.url?scp=85019879701&partnerID=8YFLogxK
U2 - 10.1016/j.jpowsour.2017.05.021
DO - 10.1016/j.jpowsour.2017.05.021
M3 - Journal article
AN - SCOPUS:85019879701
SN - 0378-7753
VL - 359
SP - 37
EP - 47
JO - Journal of Power Sources
JF - Journal of Power Sources
ER -