Neural networks for fault diagnosis and identification of industrial processes. Simani, S. and Fantuzzi, C. In Proc. of the 10th European Symposium on Artificial Neural Networks: ESANN'02, Bruges, Belgium, April, 24–26, 2002. Invited Paper in the sesstion entitled: Neural Network Techniques in Fault Detection and Isolation.
abstract   bibtex   
In this work 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. Fault identification is therefore performed by means of different neural network architectures. In particular, neural networks are used as function approximators for estimating sensor fault sizes. The proposed fault diagnosis and identification tool is tested on a industrial gas turbine.
@InProceedings{Simani-Fantuzzi-ESANN:2002,
  author =   {Simani, S. and Fantuzzi, C.},
  title =   {Neural networks for fault diagnosis and identification of
industrial processes},
  booktitle =   {{P}roc. of the 10th {E}uropean {S}ymposium on
{A}rtificial {N}eural {N}etworks: {ESANN}'02},
  year =   2002,
  address =   {{B}ruges, {B}elgium},
  month =   {April, 24--26},
  id =           200204,
  ISBN = {2-930307-02-1},
  href =         {\hyperbibref{2002-04-ESANN-Bruges.pdf}},
  abstract = {In this work 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. Fault identification is
                  therefore performed by means of different neural
                  network architectures. In particular, neural
                  networks are used as function approximators for
                  estimating sensor fault sizes. The proposed fault
                  diagnosis and identification tool is tested on a
                  industrial gas turbine.},
  note =   {Invited Paper in the sesstion entitled: Neural Network Techniques in Fault Detection and Isolation.}
}
Downloads: 0