A statistical signal processing technique was proposed and verified as independent component analysis (ICA) for fault detection and diagnosis of industrial systems without exact and detailed model. Actually, the aim is to utilize system as a black box. The system studied is condenser system of one of MAPNA’s power plants. At first, principal component analysis (PCA) approach was applied to reduce the dimensionality of the real acquired data set and to identify the essential and useful ones. Then, the fault sources were diagnosed by ICA technique. The results show that ICA approach is valid and effective for faults detection and diagnosis even in noisy states, and it can distinguish main factors of abnormality among many diverse parts of a power plant’s condenser system. This selectivity problem is left unsolved in many plants, because the main factors often become unnoticed by fault expansion through other parts of the plants.