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

A Generalized Fault Classification for Gas Turbine Diagnostics at Steady States and Transients

[+] Author and Article Information
Igor Loboda

School of Mechanical and Electrical Engineering, National Polytechnic Institute, Santa Ana Street, 1000, Mexico City, Federal District, Post Office 04430, Mexicoloboda@calmecac.esimecu.ipn.mx

Sergiy Yepifanov

 National Aerospace University, Chkalov Street, 17, Kharkov, Post Office 61070, Ukraineaedlab@ic.kharkov.ua

Yakov Feldshteyn

 Compressor Controls Corporation, 4725 121 Street, Des Moines, IA 50323yfeldshteyn@cccglobal.com

J. Eng. Gas Turbines Power 129(4), 977-985 (Jan 24, 2007) (9 pages) doi:10.1115/1.2719261 History: Received June 29, 2006; Revised January 24, 2007

Gas turbine diagnostic techniques are often based on the recognition methods using the deviations between actual and expected thermodynamic performances. The problem is that the deviations generally depend on current operational conditions. However, our studies show that such a dependency can be low. In this paper, we propose a generalized fault classification that is independent of the operational conditions. To prove this idea, the probabilities of true diagnosis were computed and compared for two cases: the proposed classification and the conventional one based on a fixed operating point. The probabilities were calculated through a stochastic modeling of the diagnostic process. In this process, a thermodynamic model generates deviations that are induced by the faults, and an artificial neural network recognizes these faults. The proposed classification principle has been implemented for both steady state and transient operation of the analyzed gas turbine. The results show that the adoption of the generalized classification hardly affects diagnosis trustworthiness and the classification can be proposed for practical realization.

Copyright © 2007 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Neural network structure

Grahic Jump Location
Figure 2

Time plots of the fuel consumption and the deviations of the compressor discharge pressure (CDP) dPc and the gas generator turbine exhaust gas temperature (EGT) dThpt. (The deviations are calculated according to expression (1).)

Grahic Jump Location
Figure 3

Transient trajectories of simulated faults in the space of monitored variables. (Normal behavior D0 and faults D1, D2, and D3 are simulated at transient 1 of Table 8. The faults correspond to maximal change of the first three correction factors listed in Table 7. The coordinates Y1, Y2, and Y3 are compressor discharge pressure, gas generator turbine exhaust gas temperature, and gas generator rotation speed.)

Grahic Jump Location
Figure 4

Fault presentation by the deviations for transient operation. (The monitored variables and the transient are the same as in Fig. 3. Faults D1–D8 correspond to maximal change of the corrections factors listed in Table 7. No measurement errors are applied.)

Grahic Jump Location
Figure 5

Fault presentation by the deviations for different transients. (The faults are simulated at the 16 transients of Table 8. Fault severity corresponds to maximal change of the corrections factors listed in Table 7. No measurement errors are applied.)




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.

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