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 $>92%$ 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 $(∼2%)$. 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.

1.
Lipowsky
,
H.
, and
Staudacher
,
S.
, 2008, “
Method and Apparatus for Gas Turbine Monitoring
,” German Patent No. DPMA 10 2008 022 459.6.
2.
DePold
,
H. R.
, and
Gass
,
D. F.
, 1999, “
The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics
,”
ASME J. Eng. Gas Turbines Power
0742-4795,
121
, pp.
607
612
.
3.
Brotherton
,
T.
, and
Johnson
,
T.
, 2001, “
Anomaly Detection for Advance Military Aircraft Using Neural Networks
,”
Proceedings of the IEEE Aerospace Conference
.
4.
Ganguli
,
R.
, 2002, “
Data Rectification and Detection of Trend Shifts in Jet Engine Path Measurements Using Median Filters and Fuzzy Logic
,”
ASME J. Eng. Gas Turbines Power
0742-4795,
124
, pp.
809
816
.
5.
Ghoreyshi
,
M.
,
Pilidis
,
P.
, and
Ramsden
,
K. W.
, 2005,
Diagnostics of a Small Jet Engine-Neural Networks Approach
,” ASME Paper No. GT-2005-68511.
6.
Eustace
,
R. W.
, 2007, “
A Real-World Application of Fuzzy Logic and Influence Coefficients for Gas Turbine Performance Diagnostics
,” ASME Paper No. GT2007-27442.
7.
Ganguli
,
R.
, 2002, “
Fuzzy Logic Intelligent System for Gas Turbine Module and System Fault Isolation
,”
J. Propul. Power
0748-4658,
18
(
2
), pp.
440
447
.
8.
Kamboukos
,
P.
,
Mathioudakis
,
K.
, and
Stamatis
,
A.
, 2003, “
A Comparative Study of Optimization Methods for Jet Engine Condition Diagnosis
,”
16th International Symposium on Air-Breathing Engines
, Cleveland, OH, Aug. 31–Sept. 5.
9.
Mathioudakis
,
K.
,
Kamboukos
,
P.
, and
Stamatis
,
A.
, 2002, “
Turbofan Performance Deterioration Tracking Using Non-Linear Models and Optimization Techniques
,” ASME Paper No. GT-2002-30026.
10.
Gulati
,
A.
,
Taylor
,
D.
, and
Singh
,
R.
, 2001, “
Multiple Operating Point Analysis Using Genetic Algorithm Optimisation for Gas Turbine Diagnostics
,”
15th International Symposium on Air-Breathing Engines
, Bangalore, India, Sept. 3–7.
11.
Aretakis
,
N.
,
Mathioudakis
,
K.
, and
Stamatis
,
A.
, 2004, “
Identification of Sensor Faults on Turbofan Engines Using Pattern Recognition Techniques
,”
Journal of Control Engineering Practice
,
12
(
7
), pp.
827
836
.
12.
Loukis
,
E.
,
Mathioudakis
,
K.
, and
Papailiou
,
K.
, 1994, “
Optimizing Automated Gas Turbine Fault Detection Using Statistical Pattern Recognition
,”
ASME J. Eng. Gas Turbines Power
0742-4795,
116
(
1
), pp.
165
171
.
13.
Sampath
,
S.
, and
Singh
,
R.
, 2006, “
An Integrated Fault Diagnostics Model Using Genetic Algorithm and Neural Networks
,”
ASME J. Eng. Gas Turbines Power
0742-4795,
128
, pp.
49
56
.
14.
Kobayashi
,
T.
, and
Simon
,
D. L.
, 2001, “
A Hybrid Neural Network-Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics
,”
J. Propul. Power
0748-4658,
21
(
4
), pp.
751
758
.
15.
Lipowsky
,
H.
,
Staudacher
,
S.
,
Nagy
,
D.
, and
Bauer
,
M.
, 2008, “
Gas Turbine Fault Diagnostics Using a Fusion of Least Squares Estimations and Fuzzy Logic Rules
,” ASME Paper No. GT2008-50190.
16.
Bauer
,
M.
, and
Staudacher
,
S.
, 2006, “
Fully Automated Model Based Performance Analysis Procedure for Online and Offline Applications
,” ASME Paper No. GT2006-91050.
17.
Pole
,
A.
,
West
,
M.
, and
Harrison
,
J.
, 1994,
Applied Bayesian Forecasting and Time Series Analysis
,
Chapman and Hall
,
New York
.
18.
Provost
,
M. J.
, 2003, “
Kalman Filtering Applied to Time Series Analysis
,”
VKI Lecture Series, Gas Turbine Condition Monitoring and Fault Diagnosis
, Brussels, Belgium, Jan. 13–17, Paper No. LS-2003-01.
19.
West
,
M.
, and
Harrison
,
J.
, 1997,
Bayesian Forecasting and Dynamic Models
,
2nd ed.
,
Springer
,
New York
.
20.
Jeffreys
,
H.
, 1961,
Theory of Probability
,
Oxford University Press
,
London
.
21.
Roesnick
,
M.
, 1984, “
A System Theory Based Solution of the Failure Diagnosis Problem Applied to a Jet Engine
,” Doctoral thesis, Institute of Automation Engineering, University of the German Federal Armed Forces, Hamburg, Germany.
You do not currently have access to this content.