The paper aims at developing a signal-based diagnosis tool diagnosing a high temperature fuel cell named solid oxide fuel cell (SOFC). The wavelet transform (WT) has been used to decompose the SOFCs voltage signals and to find out the effective feature variables that are discriminative for distinguishing the normal and abnormal operating conditions of the system. The diagnosis method is used to detect and isolate SOFC system fault by using the fuel cell stack as a sensor. Considering this, on-line fault detection without any additional sensor is available.