[en] A diagnostic method consisting of a combination of Kalman filters and Bayesian Belief Network (BBN) is presented. A soft-constrained Kalman filter uses a priori information derived by a BBN at each time step, to derive estimations of the unknown health parameters. The resulting algorithm hers improved identification capability in comparison to the stand-alone Kalman filter. The paper focuses on a way of combining the information produced by the BBN with the Kalman filter. An extensive set of fault cases is used to test the method on a typical civil turbofan layout. The effectiveness of the method is thus demonstrated, and its advantages over individual constituent methods are presented.
Disciplines :
Mechanical engineering
Author, co-author :
Dewallef, Pierre ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Systèmes de conversion d'énergie pour un dévelop.durable
Romessis, C.
Léonard, Olivier ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Turbomachines et propulsion aérospatiale
Mathioudakis, K.
Language :
English
Title :
Combining classification techniques with Kalman filters for aircraft engine diagnostics
Publication date :
April 2006
Journal title :
Journal of Engineering for Gas Turbines and Power
ISSN :
0742-4795
eISSN :
1528-8919
Publisher :
American Society of Mechanical Engineers, New York, United States - New York
Bishop, C. M. 1995, Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
Volponi, A., 2003, "Foundation of Gas Path Analysis (Part i and ii)," Von Karman Institute Lecture Series: Gas Turbine Condition Monitoring and Fault Diagnosis, (2003-01).
Provost, M. J., 2003, "Kalman Filtering Applied to Gas Turbine Analysis," Von Karman Institute Lecture Series: Gas Turbine Condition Monitoring and Fault Diagnosis, (2003-01).
Kobayashi, T., and Simon, D. L., 2003, "Application of a Bank of Kalman Filters for Aircraft Engine Fault Diagnostics," ASME Turbo Expo, ASME Paper No. GT2003-38550.
Aretakis, N., Mathioudakis, K., and Stamatis, A., 2002, "Non-linear Engine Component Fault Diagnosis From a Limited Number of Measurements Using a Combinatorial Approach," ASME Turbo Expo, ASME Paper No. GT2002-30031.
Simon, D., and Simon, D. L., 2003, "Aircraft Turbofan Engine Health Estimation Using Constrained Kalman Filtering," ASME Turbo Expo, ASME Paper No. GT2003-38584.
Grodent, M., and Navez, A., 2001, "Engine Physical Diagnosis Using a Robust Parameter Estimation Method," 37th AIAA/ASME/SAE/ASEE Joint Propulsion Conference.
Dewallef, P., Mathioudakis, K., and Léonard, O., 2004, "On-Line Aircraft Engine Diagnostic Using a Soft-Constrained Kalman Filter," ASME Turbo Expo, ASME Paper No. GT2004-53539.
Romessis, C., and Mathioudakis, K., 2004, "Bayesian Network Approach for Gas Path Fault Diagnosis," ASME Turbo Expo, ASME Paper No. GT2004-53801.
Mathioudakis, K., 2003, "Neural Networks in Gas Turbine Fault Diagnosis," Von Karman Institute Lecture Series: Gas Turbine Condition Monitoring and Fault Diagnosis, (2003-01).
Brotherton, T., Volponi, A., Luppold, R., and Simon, D. L., 2003, "Estorm: Enhanced Selft Tuning On-Board Real-Time Engine Model," 2003 IEEE Aerospace Conf.
Moody, J. E., 1992, "The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems," Advances in Neural Information Processing System 4, Morgan Kaufmann, San Mateo, CA.
MacKay, D. J. C., 1995, "Bayesian Methods for Neural Networks: Theory and Application," Tech. Report, Cavendish Laboratory, University of Cambridge, http://wol.ra.phy.cam.ac.uk
Stamatis, A., Mathioudakis, K., Ruiz, J., and Curnock, B., 2001, "Real-Time Engine Model Implementation for Adaptive Control and Performance Monitoring of Large Civil Turbofans," ASME Turbo Expo, ASME Paper No. GT2001-362.