Fault diagnosis in a power plant using artificial neural networks: analysis and comparison

In this paper a model-based procedure exploiting analytical redundancy via state estimation techniques for the diagnosis of faults regarding sensors of a dynamic system is presented. Fault detection is based on Kalman filters designed in stochastic environment. Such a design is enhanced by processing the noisy data according to the Frisch Scheme identification method. Fault diagnosis is performed by means of different neural network architectures. In particular, neural networks are used as function approximators to estimate single sensor fault size. The proposed fault diagnosis tool is tested on a power plant. Results from simulation are compared with the ones obtained in some related works.