This paper presents a pattern-recognition-based diagnosis approach for fault-diagnosis of fuel cell stacks, using Electrochemical Impedance Spectroscopy (EIS). It aims at implementing a diagnosis tool able to detect fuel cell degradations from EIS measurements. It consists in different steps. First,measurable features are extracted. Then, in order to improve fault classification, a correlation-based feature selection is used to keep only relevant features. Finally, the classification is achieved to assign each observation to one of the predefined defect classes. The performances are evaluated on an experimental dataset extracted from a twenty-cell PEMFC stack to show the effectiveness of the proposed approach.