A double-fuzzy diagnostic methodology dedicated to online fault diagnosis of proton exchange membrane fuel cell stacks

To improve the performance and lifetime of the low temperature polymer electrolyte membrane fuel cell (PEMFC) stack, water management is an important issue. This paper aims at developing an online diagnostic methodology with the capability of discriminating different degrees of flooding/drying inside the fuel cell stack. Electrochemical impedance spectroscopy (EIS) is utilized as a basis tool and a double-fuzzy method consisting of fuzzy clustering and fuzzy logic is developed to mine diagnostic rules from the experimental data automatically. Through online experimental verification, a high interpretability and computational efficiency of the proposed methodology can be achieved.