INTEGRATED GAS TURBINE HEALTH MONITORING SYSTEM

Daniel Nagy and Stephan Staudacher

References

  1. [1] H.R. DePold and D.F. Gass, The application of expert systemsand neural networks to gas turbine prognostics and diagnostics,Journal of Engineering for Gas Turbines and Power, 121,October, 1999, 607–612.
  2. [2] T. Brotherton and T. Johnson, Anomaly detection for advancemilitary aircraft using neural networks, Proceedings of theIEEE Aerospace Conference, 6, Big Sky, MT, USA, 2001,3113–3123.
  3. [3] R. Ganguli, Data rectification and detection of trend shifts injet engine path measurements using median filters and fuzzylogic, Journal of Engineering for Gas Turbines and Power,124, October, 2002, 809–816.
  4. [4] H. Lipowsky, S. Staudacher, D. Nagy, and M. Bauer, Prob-abilistic gas turbine fault diagnostics using a fusion of leastsquares estimations and fuzzy logic rules, ASME GT2008-50190, Berlin, Germany, June 9–13, 2008.
  5. [5] A. Volponi, Method for performing gas turbine performancediagnostics, Patent No. US 6,909,960 B2, June 21, 2005.
  6. [6] S. Sampath and R. Singh, Evolution strategy for engine andsensor fault diagnosis, 16th International Symposium on Air-breathing Engines, ISABE-2003-1207, Cleveland, 31 August–05 September 2003.
  7. [7] A. Stamatis, K. Mathioudakis and K. Papailiou, Optimal mea-surement and health index selection for gas turbine perfor-mance status and fault diagnosis, Journal for Engineering forGas Turbines and Power, 114, 1992, 209–216.
  8. [8] L.A. Urban, Parameter selection for multiple fault diagnosticsof gas turbine engines, ASME, 74-GT-62, Z¨urich, 1974.
  9. [9] M. Roesnick, Eine systemtheoretische L¨osung des Fehlerdiag-noseproblems am Beispiel eines Flugtriebwerkes, Ph.D. disser-tation, Institute of Automation Engineering, University of theGerman Federal Armed Forces, Hamburg, 1984.
  10. [10] N. Aretakis, K. Mathioudakis, and A. Stamatis, Non-linearengine component fault diagnosis from a limited number ofmeasurements using a combinatorial approach, ASME GT2002-30031, Amsterdam, The Netherlands, June 3–6, 2002.
  11. [11] C. Romesis, Ph. Kamboukos and K. Mathioudakis, The useof probabilistic reasoning to improve least squares based gaspath diagnostics, ASME GT2006-90619, Barcelona, Spain,May 8–11, 2006.
  12. [12] A. Kyriazis and K. Mathioudakis, Enhanced fault localizationusing probabilistic fusion with gas path analysis algorithms,ASME GT2008-51079, Berlin, Germany, June 9–13, 2008.
  13. [13] G. Welsh and G. Bishop, An introduction to the kalman filter,University of North Carolina at Chapel Hill, Department ofComputer Science TR-95-041, NC, USA, July 2006.
  14. [14] M.J. Provost, Kalman filtering applied to gas turbine analysis,VKI Lecture Series: Gas Turbine Condition Monitoring andFault Diagnosis, LS 2003-01, 2003.
  15. [15] K. Mathioudakis, P. Kamboukos, and A. Stamatis, Turbofanperformance deterioration tracking using non-linear models and230optimization techniques, Journal of Turbomachinary, 124(4),2002, 580–588.
  16. [16] N. Aretakis and K. Mathioudakis, Classification of radialcompressor faults using pattern-recognition techniques, ControlEngineering Practice 6, 1998.
  17. [17] K. Mathioudakis, and C. Romesis, Probabilistic neural net-works for validation of on-board jet engine data, Proceedingsof the Institution of Mechanical Engineers, Part G: Journal ofAerospace Engineering, 218, 2004, 59–72.
  18. [18] C. Romesis, and K. Mathioudakis, Implementation of stochasticmethods for industrial gas turbine fault diagnosis, ASME,GT2005-68739, Reno-Tahoe, NV, June 6–9, 2005.
  19. [19] C. Romesis, A. Stamatis, and K. Mathioudakis, Parametricinvestigation of the diagnostic ability of probabilistic neuralnetworks on turbofan engines, ASME, 2001-GT-0011, NewOrleans, LA, June 4–7, 2001.
  20. [20] H. Lipowsky, Entwicklung und Demonstration einer integri-erten Systems zur Zustands¨uberwachung von Gasturbinen,Ph.D. dissertation, Institute of Aircraft Propulsion Systems,Stuttgart, 2010.
  21. [21] H. Lipowsky, M. Bauer, K.J. Schmidt, and S. Staudacher,Application of bayesian forecasting to change detection andprognosis of gas turbine performance, ASME, GT2009-59447,Orlando, FL, June 8–12, 2009.
  22. [22] D. Nagy, S. Staudacher, and M. Bauer, Optimale Auswahlder Serieninstrumentierung moderner Gasturbinen, DGLR,DGLR-81200, Darmstadt, Germany, September 23–25, 2008.
  23. [23] D. Nagy, S. Staudacher, and K.J. Schmidt, An enchancedfusion approach for fault allocation based on a limited numberof measurements, DGLR, DGLR-121373, Aachen, Germany,September 8–10, 2009.
  24. [24] D. Nagy, D. Erweiterung eines Zustands¨uberwachungssystemsf¨ur Fluggasturbinen unter besonderer Ber¨ucksichtigung derBeobachtbarkeit, Ph.D. dissertation, Institute of AircraftPropulsion Systems, Stuttgart, DRAFT.
  25. [25] H. Lipowsky, and D. Nagy, HealthGT User’s Guide, UserGuide. (Stuttgart: Institute of Aircraft Propulsion Systems,2010).

Important Links:

Go Back