Application of a Neural Network in Gas Turbine Control Sensor Fault Detection. Simani, S., Fantuzzi, C., & Spina, P. In Proceedings of IEEE Conference on Control Applications, pages 182-186, Trieste (Italy), September~1–4,, 1998.
abstract   bibtex   
In this paper an application of a procedure using a neural network for the detection and isolation of faults modeled by step functions in input-output control sensors of a single shaft industrial gas turbine is presented. The real process is modeled as a linear dynamical system corrupted by stochastic additive noise. The diagnosis system involves dynamic observers and utilizes the neural network in order to classify observer residuals into fault classes.
@InProceedings{Simani-et-al:Trieste:1998,
  author = 	 {Simani, S. and  Fantuzzi, C.  and Spina, P.R.},
  title = 	 {Application of a Neural Network in Gas Turbine Control
  Sensor Fault Detection},
  booktitle = 	 {Proceedings of IEEE Conference on Control Applications},
  address =	 {Trieste (Italy)},
  month =	 sep # "~1--4,",
  ID =           199809,
  year =	 1998,
  href = {\hyperbibref{cca98.pdf}},
  pages = {182-186},
  abstract = {In this paper an application of a procedure using a neural network
  for the detection and isolation of faults modeled by step functions
  in input-output control sensors of a single shaft industrial gas
  turbine is presented. The real process is modeled as a linear
  dynamical system corrupted by stochastic additive noise.  The
  diagnosis system involves dynamic observers and utilizes the neural
  network in order to classify observer residuals into fault classes.
}
}

Downloads: 0