The performance of gas turbines degrades over time due to deterioration mechanisms and single fault events. While deterioration mechanisms occur gradually, single fault events are characterized by occurring accidentally. In the case of single events, abrupt changes in the engine parameters are expected. Identifying these changes as soon as possible is referred to as detection. State-of-the-art detection algorithms are based on expert systems, neural networks, special filters, or fuzzy logic. This paper presents a novel detection technique, which is based on Bayesian forecasting and dynamic linear models (DLMs). Bayesian forecasting enables the calculation of conditional probabilities, whereas DLMs are a mathematical tool for time series analysis. The combination of the two methods can be used to calculate probability density functions prior to the next observation, or the so called forecast distributions. The change detection is carried out by comparing the current model with an alternative model, where the mean value is shifted by a prescribed offset. If the forecast distribution of the alternative model better fits the actual observation, a potential change is detected. To determine whether the respective observation is a single outlier or the first observation of a significant change, a special logic is developed. In addition to change detection, the proposed technique has the ability to perform a prognosis of measurement values. The developed method was run through an extensive test program. Detection rates have been achieved for changed heights, as small as 1.5 times the standard deviation of the observed signal (sigma). For changed heights greater than 2 sigma, the detection rates have proven to be 100%. It could also be shown that a high detection rate is gained by a high false detection rate . An optimum must be chosen between a high detection rate and a low false detection rate, by choosing an appropriate uncertainty limit for the detection. Increasing the uncertainty limit decreases both detection rate and false detection rate. In terms of prognostic abilities, the proposed technique not only estimates the point of time of a potential limit exceedance of respective parameters, but also calculates confidence bounds, as well as probability density and cumulative distribution functions for the prognosis. The conflictive requirements of a high degree of smoothing and a quick reaction to changes are fulfilled in parallel by combining two different detection conditions.
Skip Nav Destination
e-mail: lipowsky@ila.uni-stuttgart.de
e-mail: staudacher@ila.uni-stuttgart.de
e-mail: michael.bauer@mtu.de
e-mail: klaus-juergen.schmidt@mtu.de
Article navigation
March 2010
Research Papers
Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance
Holger Lipowsky,
Holger Lipowsky
Institute of Aircraft Propulsion Systems (ILA),
e-mail: lipowsky@ila.uni-stuttgart.de
University of Stuttgart
, Pfaffenwaldring 6, 70569 Stuttgart, Germany
Search for other works by this author on:
Stephan Staudacher,
Stephan Staudacher
Institute of Aircraft Propulsion Systems (ILA),
e-mail: staudacher@ila.uni-stuttgart.de
University of Stuttgart
, Pfaffenwaldring 6, 70569 Stuttgart, Germany
Search for other works by this author on:
Michael Bauer,
Michael Bauer
Department of Performance, TEAP,
e-mail: michael.bauer@mtu.de
MTU Aero Engines GmbH
, Dachauer Strasse 665, 80995 München, Germany
Search for other works by this author on:
Klaus-Juergen Schmidt
Klaus-Juergen Schmidt
Department of Performance, TEAP,
e-mail: klaus-juergen.schmidt@mtu.de
MTU Aero Engines GmbH
, Dachauer Strasse 665, 80995 München, Germany
Search for other works by this author on:
Holger Lipowsky
Institute of Aircraft Propulsion Systems (ILA),
University of Stuttgart
, Pfaffenwaldring 6, 70569 Stuttgart, Germanye-mail: lipowsky@ila.uni-stuttgart.de
Stephan Staudacher
Institute of Aircraft Propulsion Systems (ILA),
University of Stuttgart
, Pfaffenwaldring 6, 70569 Stuttgart, Germanye-mail: staudacher@ila.uni-stuttgart.de
Michael Bauer
Department of Performance, TEAP,
MTU Aero Engines GmbH
, Dachauer Strasse 665, 80995 München, Germanye-mail: michael.bauer@mtu.de
Klaus-Juergen Schmidt
Department of Performance, TEAP,
MTU Aero Engines GmbH
, Dachauer Strasse 665, 80995 München, Germanye-mail: klaus-juergen.schmidt@mtu.de
J. Eng. Gas Turbines Power. Mar 2010, 132(3): 031602 (8 pages)
Published Online: December 3, 2009
Article history
Received:
March 22, 2009
Revised:
March 23, 2009
Online:
December 3, 2009
Published:
December 3, 2009
Citation
Lipowsky, H., Staudacher, S., Bauer, M., and Schmidt, K. (December 3, 2009). "Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance." ASME. J. Eng. Gas Turbines Power. March 2010; 132(3): 031602. https://doi.org/10.1115/1.3159367
Download citation file:
Get Email Alerts
Shape Optimization of an Industrial Aeroengine Combustor to reduce Thermoacoustic Instability
J. Eng. Gas Turbines Power
Dynamic Response of A Pivot-Mounted Squeeze Film Damper: Measurements and Predictions
J. Eng. Gas Turbines Power
Review of The Impact Of Hydrogen-Containing Fuels On Gas Turbine Hot-Section Materials
J. Eng. Gas Turbines Power
Effects of Lattice Orientation Angle On Tpms-Based Transpiration Cooling
J. Eng. Gas Turbines Power
Related Articles
Application of Fuzzy Logic for Fault Isolation of Jet Engines
J. Eng. Gas Turbines Power (July,2003)
Data Visualization, Data Reduction and Classifier Fusion for Intelligent Fault Diagnosis in Gas Turbine Engines
J. Eng. Gas Turbines Power (July,2008)
HCCI Engine Combustion Phasing Prediction Using a Symbolic-Statistics Approach
J. Eng. Gas Turbines Power (August,2010)
An Overview of Artificial Intelligence-Based Methods for Building Energy Systems
J. Sol. Energy Eng (August,2003)
Related Proceedings Papers
Related Chapters
Prediction of Coal Mine Gas Concentration Based on Constructive Neural Network
International Conference on Information Technology and Computer Science, 3rd (ITCS 2011)
Research on Building Fault Detection Solution for IaaS Cloud Computing Based on Fuzzy Logic Algorithm
International Conference on Computer Research and Development, 5th (ICCRD 2013)
Interval Type-2 Fuzzy Logic for Improving Feature Extraction and Response Integration in Modular Neural Networks for Image Recognition
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17