Synergistic use of soft computing technologies for fault detection in gas turbine engines

SMCia 2003 - Proceedings of the 2003 IEEE International Workshop on Soft Computing in Industrial Applications

Volumn , Issue , 2003, Pages 115-120

  Uluyol, O ^a   Kim, Kyusung ^a   Menon, S ^a   Nwadiogbu, E O ^a  

^a HONEYWELL   (United States)

Author keywords

Computers; Engines; Fault detection; Fault diagnosis; Principal component analysis; Sensor phenomena and characterization; Signal processing; Statistics; Steady state; Turbines

Indexed keywords

COMPUTERS; ENGINES; FAILURE ANALYSIS; GAS TURBINES; NEURAL NETWORKS; PRINCIPAL COMPONENT ANALYSIS; SIGNAL DETECTION; SIGNAL PROCESSING; SOFT COMPUTING; STATISTICAL METHODS; STATISTICS; TURBINES;

FAULT DETECTION AND DIAGNOSIS; FAULT DETECTION AND DIAGNOSIS METHODS; NEURAL NETWORK TRAINING; OBJECTIVE EVALUATION; SOFTCOMPUTING TECHNIQUES; START-UP CHARACTERISTICS; STEADY STATE; STEADY-STATE CONDITION;

FAULT DETECTION;

EID: 84943606469     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SMCIA.2003.1231355     Document Type: Conference Paper

References (4)

1. Christopher Bishop, Neural Networks for Pattern Recognition. New York: Oxford University Press, 1995.
2. I. T. Jolliffe, Principal Component Analysis, Springer-Verlag, 1986.
3. Michael R. Chernick, Bootstrap Methods. Wiley, 1999.
4. S. Menon, O. Uluyol, K. Kim, and E. Nwadiogbu, "Improved Incipient Fault Detection And Diagnosis In Turbine Engines Using Hidden Markov Models," ASME Turbo Expo 2003, June 16-19, 2003 (submitted).