0
Research Papers: Gas Turbines: Aircraft Engine

Regression-Based Modeling of a Fleet of Gas Turbine Engines for Performance Trending

[+] Author and Article Information
S. Borguet

Turbomachinery Group,
University of Liège,
Campus du Sart-Tilman, B52/3,
Liège 4000, Belgium
e-mail: s.borguet@ulg.ac.be

O. Léonard

Turbomachinery Group,
University of Liège,
Campus du Sart-Tilman, B52/3,
Liège 4000, Belgium
e-mail: o.leonard@ulg.ac.be

P. Dewallef

Laboratory of Thermodynamics,
University of Liège,
Campus du Sart-Tilman, B49,
Liège 4000, Belgium
e-mail: p.dewallef@ulg.ac.be

Contributed by the Aircraft Engine Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received July 13, 2015; final manuscript received July 19, 2015; published online September 1, 2015. Editor: David Wisler.

J. Eng. Gas Turbines Power 138(2), 021201 (Sep 01, 2015) (9 pages) Paper No: GTP-15-1273; doi: 10.1115/1.4031253 History: Received July 13, 2015

Module performance analysis is a well-established framework to assess changes in the health condition of the components of the engine gas-path. The primary material of the technique is the so-called vector of residuals, which are built as the difference between actual measurement taken in the gas-path and the values predicted by means of an engine model. Obviously, the quality of the assessment of the engine condition depends strongly on the accuracy of the engine model. The present paper proposes a new approach for data-driven modeling of a fleet of engines of a given type. Such black-box models can be designed by operators, such as airlines and third-party companies. The fleet-wide modeling process is formulated as a regression problem that provides a dedicated model for each engine in the fleet, while recognizing that all engines are of the same type. The methodology is applied to a virtual fleet of engines generated within the Propulsion Diagnostic Methodology Evaluation Strategy (ProDiMES) environment. The set of models is assessed quantitatively through the coefficient of determination and is further used to perform anomaly detection.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Topics: Sensors , Modeling , Flight , Engines
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 2

Sketch of a high bypass ratio turbofan

Grahic Jump Location
Fig. 1

Graphical interpretation of the coefficient of determination

Grahic Jump Location
Fig. 7

WSSR for engine 221: dashed line—no detrending of gradual deterioration and solid line—detrending of gradual deterioration

Grahic Jump Location
Fig. 8

WSSR for engine 250: dashed line—no detrending of gradual deterioration and solid line—detrending of gradual deterioration

Grahic Jump Location
Fig. 3

Distribution of the coefficient of determination for Wf over the fleet for the testing set: solid line—model 1 and dashed line—model 2

Grahic Jump Location
Fig. 4

Distribution of the coefficient of determination for T24 over the fleet on the testing set: solid line—model 1 and dashed line—model 2

Grahic Jump Location
Fig. 5

Distribution of the coefficient of determination for Wf over the fleet with model 1: solid line—training set and dashed line—testing set

Grahic Jump Location
Fig. 6

Distribution of the coefficient of determination for Wf over the fleet with model 2: solid line—training set and dashed line—testing set

Grahic Jump Location
Fig. 9

Partial ROC curves for configuration 2 of the proposed anomaly detector

Tables

Errata

Discussions

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