TECHNICAL PAPERS: Gas Turbines: Controls, Diagnostics, and Instrumentation

Setting Up of a Probabilistic Neural Network for Sensor Fault Detection Including Operation With Component Faults

[+] Author and Article Information
C. Romesis, K. Mathioudakis

Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens 15710, Greece

J. Eng. Gas Turbines Power 125(3), 634-641 (Aug 15, 2003) (8 pages) doi:10.1115/1.1582493 History: Received December 01, 2001; Revised March 01, 2002; Online August 15, 2003
Copyright © 2003 by ASME
Your Session has timed out. Please sign back in to continue.


Bettocchi, R., Spina, P. R., and Azzoni, P. M., 1996, “Fault Detection for Gas Turbine Sensors Using I/O Dynamic Linear Models—Methodology of Fault Code Generation,” ASME Paper 96-TA-2.
Kelly, R., 1996, “Application of Analytical Redundancy to Detection of Sensor Faults on a Turbofan Engine,” ASME Paper 96-GT-3.
Simani, S., Spina, P., Beghelli, S., Bettocchi, R., and Fantuzzi, C., 1998, “Fault Detection and Isolation Based on Dynamic Observers Applied to Gas Turbine Control Sensors,” ASME Paper 98-GT-158.
Bettocchi, R., and Spina, P. R., 1999, “A Method for the Diagnosis of Gas Turbine Sensor Faults in Presence of Measurement Noise,” ASME Paper 99-GT-303.
Caliskan,  F., and Hajiyev,  C., 2000, “Innovation Sequence Application to Aircraft Sensor Fault Detection: Comparison of Checking Covariance Matrix Algorithms,” ISA Trans., 39, pp. 47–56.
Healy, T., Kerr, L., and Larkin, L., 1997, “Model Based Fuzzy Logic Sensor Fault Accommodation,” ASME Paper 97-GT-222.
Eustace, R., and Merrington, G., 1995, “Fault Diagnosis of Fleet Engines Using Neural Networks,” ISABE Paper ISABE 95-7085.
Volponi, A. J., de Pold, H., Ganguli, Ranjan, and Daguang, Chen, 2000, “The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics: A Comparative Study,” ASME Paper 2000-GT-547.
Pong, J. L., Ming, C. Z., Tzu, C. H., and Jin, Z., 2000, “An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks,” ASME Paper 2000-GT-29.
Kanelopoulos, K., Stamatis, A., and Mathioudakis, K., 1997, “Incorporating Neural Networks Into Gas Turbine Performance Diagnostics,” ASME Paper 97-GT-35.
Mattern, D., Guo, T., Graham, R., and McCoy, W., 1998, “Using Neural Networks for Sensor Validation,” prepared for the 34th Joint Propulsion Conference Paper No. NASA/TM-1998-208483.
Doke, R., and Singh, R., 1999, “Neural Networks for the Detection of Gas Turbine Sensor Faults,” ISABE paper ISABE 99-7255.
Napolitano, M., An, Y., and Seanor, B., 2000, “A Fault Tolerant Flight Control System for Sensor and Actuator Failures Using Neural Networks,” Aircraft Design 3, Pergamon, New York, pp. 103–128.
Bose, N. K., and Liang, P., 1996, Neural Network Fundamentals With Graphs, Algorithms and Applications, McGraw-Hill, New York.
Bin, S., Jin, Z., and Shaoji, Z., 2000, “An Investigation of Artificial Neural Network (ANN) in Quantitative Fault Diagnosis for Turbofan Engine,” ASME Paper 2000-GT-32.
Romessis, C., Stamatis, A., and Mathioudakis, K., 2001, “A Parametric Investigation of the Diagnostic Ability of Probabilistic Neural Networks on Turbofan Engines,” ASME Paper 2001-GT-11.
Doel, D., 1992, “TEMPER—A Gas Path Analysis Tool for Commercial Jet Engines,” ASME Paper 92-GT-315.
Stamatis,  A., Mathioudakis,  K., and Papailiou,  K. D., 1990, “Adaptive Simulation of Gas Turbine Performance,” ASME J. Eng. Gas Turbines Power, 112, pp. 168–175.
Stamatis, A., Mathioudakis, K., Ruiz, J., and Curnock, B., 2001, “Real Time Engine Model Implementation for Adaptive Control & Performance Monitoring of Large Civil Turbofans,” ASME Paper 2001-GT-362.
Curnock, B., 2001, “OBIDICOTE Program Work Package 4 Steady-State Test Cases for Engine Deterioration,” Rolls Royce Report, Document Number DNS78608, May.
Mathioudakis, K., Kamboukos, Ph., and Stamatis, A., 2002, “Turbofan Performance Deterioration Tracking Using Non-Linear Models And Optimization Techniques,” ASME Paper GT-2002-30026.


Grahic Jump Location
Layout and station numbering of a turbofan engine
Grahic Jump Location
Probabilistic neural network architecture for turbofan sensor fault diagnosis
Grahic Jump Location
Patterns of deltas for different situations: (a) healthy engine and sensors, (b) faulty engine, healthy sensor, (c) healthy engine, faulty sensor (XNLP), (d) faulty engine and sensor (XNLP)
Grahic Jump Location
The procedure for generating the sets of patterns
Grahic Jump Location
The procedure for evaluating sensor fault cases
Grahic Jump Location
PNN performance matrix for sensor fault detection
Grahic Jump Location
PNN output for several levels of T3 sensor fault
Grahic Jump Location
Minimum detectable levels of sensor faults
Grahic Jump Location
Minimum detectable levels of sensor faults in terms of measurement standard deviations
Grahic Jump Location
Detection of a drift in sensor P13: (a) time variation of P13, (b) probabilities produced by the network
Grahic Jump Location
Procedure followed for multiple sensor fault detection
Grahic Jump Location
PNN success rate for cases of multiple sensor faults
Grahic Jump Location
Performance of the PNN on detection of sensor’s XNHP and WFE fault on a turbofan with single-component fault
Grahic Jump Location
Minimum detectable levels of XNHP sensor fault, for several levels of HP turbine fault (SW41 deviation)
Grahic Jump Location
Performance of the PNN on sensor fault detection on a turbofan with multiple component faults
Grahic Jump Location
Performance of the PNN on sensor fault detection on a drifting deteriorated turbofan



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In