0
Research Papers: Gas Turbines: Oil and Gas Applications

Application of Forecasting Methodologies to Predict Gas Turbine Behavior Over Time

[+] Author and Article Information
Andrea Cavarzere

 Dipartimento di Ingegneria, Università degli Studi di Ferrara, Via G. Saragat, 1, 44122 Ferrara, Italy

Mauro Venturini

 Dipartimento di Ingegneria, Università degli Studi di Ferrara, Via G. Saragat, 1, 44122 Ferrara, Italymauro.venturini@unife.it

J. Eng. Gas Turbines Power 134(1), 012401 (Oct 28, 2011) (8 pages) doi:10.1115/1.4004184 History: Received April 27, 2011; Revised April 27, 2011; Published October 28, 2011; Online October 28, 2011

The growing need to increase the competitiveness of industrial systems continuously requires a reduction of maintenance costs, without compromising safe plant operation. Therefore, forecasting the future behavior of a system allows planning maintenance actions and saving costs, because unexpected stops can be avoided. In this paper, four different methodologies are applied to predict gas turbine behavior over time: Linear and Nonlinear Regression, One Parameter Double Exponential Smoothing, Kalman Filter and Bayesian Forecasting Method. The four methodologies are used to provide a prediction of the time when a threshold value will be exceeded in the future, as a function of the current trend of the considered parameter. The application considers different scenarios which may be representative of the trend over time of some significant parameters for gas turbines. Moreover, the Bayesian Forecasting Method, which allows the detection of discontinuities in time series, is also tested for predicting system behavior after two consecutive trends. The results presented in this paper aim to select the most suitable methodology that allows both trending and forecasting as a function of data trend over time, in order to predict time evolution of gas turbine characteristic parameters and to provide an estimate of the occurrence of a failure.

FIGURES IN THIS ARTICLE
<>
Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Data trend for scenario #1 and extrapolating lines (linear interpolation lines of YT values or line passing through the last two YT values)

Grahic Jump Location
Figure 2

YT linear trend and Ymeth values obtained through SLRM for scenario #1

Grahic Jump Location
Figure 3

YT quadratic trend and Ymeth values obtained through BFM for scenario #1 (uncertainty limits obtained according to Eq. 4)

Grahic Jump Location
Figure 4

RMSE values for scenarios #1 and #3 (σu 2  = 1.0%)

Grahic Jump Location
Figure 5

Prediction errors by means of linear interpolation line of YT values for scenarios #1, #2, and #3 (YT linear trend)

Grahic Jump Location
Figure 6

Prediction errors by means of the line passing through the last two YT values for scenarios #1, #2, and #3 (YT linear trend)

Grahic Jump Location
Figure 7

Prediction errors by means of linear interpolation line of YT values obtained through SLRM for scenarios #1, #2, and #3

Grahic Jump Location
Figure 8

RMSE values for scenarios #1 and #3 (σu 2  = 0.5%)

Grahic Jump Location
Figure 9

Prediction errors by means of linear interpolation line of YT values for scenarios #1 and #3 (YT linear trend; σu 2  = 0.5%)

Grahic Jump Location
Figure 10

Ymeth values and uncertainty limits obtained through BFM for scenario #4a

Grahic Jump Location
Figure 11

Ymeth values and uncertainty limits obtained through BFM for scenario #5a

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