A method enabling the automated diagnosis of gas turbine compressor blade faults, based on the principles of statistical pattern recognition, is initially presented. The decision making is based on the derivation of spectral patterns from dynamic measurement data and then the calculation of discriminants with respect to reference spectral patterns of the faults while it takes into account their statistical properties. A method of optimizing the selection of discriminants using dynamic measurement data is also presented. A few scalar discriminants are derived, in such a way that the maximum available discrimination potential is exploited. In this way the success rate of automated decision making is further improved, while the need for intuitive discriminant selection is eliminated. The effectiveness of the proposed methods is demonstrated by application to data coming from an industrial gas turbine while extension to other aspects of fault diagnosis is discussed.
Skip Nav Destination
Article navigation
January 1994
Research Papers
Optimizing Automated Gas Turbine Fault Detection Using Statistical Pattern Recognition
E. Loukis,
E. Loukis
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
Search for other works by this author on:
K. Mathioudakis,
K. Mathioudakis
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
Search for other works by this author on:
K. Papailiou
K. Papailiou
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
Search for other works by this author on:
E. Loukis
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
K. Mathioudakis
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
K. Papailiou
Laboratory of Thermal Turbomachines, National Technical University of Athens, Athens, Greece
J. Eng. Gas Turbines Power. Jan 1994, 116(1): 165-171 (7 pages)
Published Online: January 1, 1994
Article history
Received:
January 28, 1992
Online:
April 24, 2008
Citation
Loukis, E., Mathioudakis, K., and Papailiou, K. (January 1, 1994). "Optimizing Automated Gas Turbine Fault Detection Using Statistical Pattern Recognition." ASME. J. Eng. Gas Turbines Power. January 1994; 116(1): 165–171. https://doi.org/10.1115/1.2906787
Download citation file:
Get Email Alerts
Gas Turbine's Role in Energy Transition
J. Eng. Gas Turbines Power (October 2024)
Analysis of In-Cylinder Flow in a Small-Bore Spark-Ignition Engine Using Computational Fluid Dynamics Simulations and Zero-Dimensional-Based Modeling
J. Eng. Gas Turbines Power (October 2024)
A Multistage Nonlinear Method for Aeroengine Health Parameter Estimation Based on Adjacent Operating Points
J. Eng. Gas Turbines Power (October 2024)
The Effect of Swirl Number on Lean Blow Out Limits of Lean Direct Injection Combustors
J. Eng. Gas Turbines Power (October 2024)
Related Articles
A Fault Diagnosis Method for Industrial Gas Turbines Using Bayesian Data Analysis
J. Eng. Gas Turbines Power (April,2010)
Nonlinear Fault Diagnosis of Jet Engines by Using a Multiple Model-Based Approach
J. Eng. Gas Turbines Power (January,2012)
Fault Detection and Identification in an IM270 Gas Turbine Using Measurements for Engine Control
J. Eng. Gas Turbines Power (October,2004)
Erratum: “Influence of Blade Deterioration on Compressor and Turbine Performance” [ Journal of Engineering for Gas Turbines and Power, 2010, 132(3), p. 032401 ]
J. Eng. Gas Turbines Power (November,2010)
Related Proceedings Papers
Related Chapters
Control and Operational Performance
Closed-Cycle Gas Turbines: Operating Experience and Future Potential
Study of Fault Detection Device Based on DSP in Distribution Networks
International Conference on Advanced Computer Theory and Engineering (ICACTE 2009)
Combined Cycle Power Plant
Energy and Power Generation Handbook: Established and Emerging Technologies