ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Fuzzy logic intelligent system for gas turbine module and system fault isolation

Ganguli, R (2002) Fuzzy logic intelligent system for gas turbine module and system fault isolation. In: Journal of Propulsion and Power, 18 (2). pp. 440-447.

Full text not available from this repository. (Request a copy)
Official URL: http://cat.inist.fr/?aModele=afficheN&cpsidt=13555...

Abstract

A fuzzy logic intelligent system is developed for gas-turbine fault isolation. The gas path measurements used for fault isolation are exhaust gas temperature, low and high rotor speed, and fuel flow. These four measurements are also called the cockpit parameters and are typically found in almost all older and newer jet engines. The fuzzy logic system uses rules developed from a model of performance influence coefficients to isolate engine faults while accounting for uncertainty in gas path measurements. It automates the reasoning process of an experienced powerplant engineer. Tests with simulated data show that the fuzzy system isolates faults with an accuracy of 89% with only the four cockpit measurements. However, if additional pressure and temperature probes between the compressors and before the burner, which are often found in newer jet engines, are considered, the fault isolation accuracy rises to as high as 98%. In addition, the additional sensors are useful in keeping the fault isolation system robust as quality of the measured data deteriorates.

Item Type: Journal Article
Publication: Journal of Propulsion and Power
Publisher: American Institute of Aeronautics and Astronautics
Additional Information: Copyright of this article belongs to American Institute of Aeronautics and Astronautics.
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 19 Jul 2011 05:57
Last Modified: 19 Jul 2011 05:57
URI: http://eprints.iisc.ac.in/id/eprint/39217

Actions (login required)

View Item View Item