Fault diagnosis in a steam generator applying fuzzy clustering techniques

Abstract

In this chapter the design of a fault diagnosis system using fuzzy clustering techniques for a BKZ-340-140 29M steam generator in a thermoelectric power station is presented. The application aims to study the advantages of these techniques in the development of a fault diagnosis method with the characteristic to be robust to external disturbances and sensitive to small magnitude faults. The wavelet transform (WT) is used for isolating noise present in measurements. The fault diagnosis system was designed for the water-steam circuit of the steam generator by its great incidence in the correct operation of the generation blocks. The obtained results indicate the feasibility of the proposal.