G. Guglielmi et al., KEYNOTE PAPER - FAULT-DIAGNOSIS AND NEURAL NETWORKS - A POWER-PLANT APPLICATION, Control engineering practice, 3(5), 1995, pp. 601-620
Citations number
35
Categorie Soggetti
Controlo Theory & Cybernetics","Robotics & Automatic Control
Correct and timely fault detection is of major importance in the field
of system engineering, and constitutes a primary problem in a broad s
pectrum of cases, from industrial processes to high-performance system
s and to mass-produced consumer equipment. A large number of methods c
an be found in the literature, and the recent use of neural networks f
or solving fault-diagnosis problems in real industrial situations seem
s to be particularly promising. This paper describes a neural approach
to solving approximately some very difficult fault-diagnosis problems
. A real system (the four heaters of a feedwater high-pressure line of
a 320 MW power plant) has been chosen to test the neural methodology.
Simulation results obtained by a very accurate and validated model of
the plant show the effectiveness of using multilayer feedforward and
Radial Basis Functions neural networks to solve real fault-detection a
nd diagnosis problems.