In this paper, we investigate four key issues associated with data-driven approaches for fault classification using the Pratt and Whitney commercial dual-spool turbofan engine data as a test case. The four issues considered here include the following. (1) Can we characterize, a priori, the difficulty of fault classification via self-organizing maps? (2) Do data reduction techniques improve fault classification performance and enable the implementation of data-driven classification techniques in memory-constrained digital electronic control units (DECUs)? (3) When does adaptive boosting, an incremental fusion method that successively combines moderately inaccurate classifiers into accurate ones, help improve classification performance? (4) How to synthesize classifier fusion architectures to improve the overall diagnostic accuracy? The classifiers studied in this paper are the support vector machine, probabilistic neural network, -nearest neighbor, principal component analysis, Gaussian mixture models, and a physics-based single fault isolator. As these algorithms operate on large volumes of data and are generally computationally expensive, we reduce the data set using the multiway partial least squares method. This has the added benefits of improved diagnostic accuracy and smaller memory requirements. The performance of the moderately inaccurate classifiers is improved using adaptive boosting. These results are compared to the results of the classifiers alone, as well as different fusion architectures. We show that fusion reduces the variability in diagnostic accuracy, and is most useful when combining moderately inaccurate classifiers.
Skip Nav Destination
Article navigation
July 2008
Research Papers
Data Visualization, Data Reduction and Classifier Fusion for Intelligent Fault Diagnosis in Gas Turbine Engines
William Donat,
William Donat
University of Connecticut
, Storrs, CT 06268
Search for other works by this author on:
Kihoon Choi,
Kihoon Choi
University of Connecticut
, Storrs, CT 06268
Search for other works by this author on:
Woosun An,
Woosun An
University of Connecticut
, Storrs, CT 06268
Search for other works by this author on:
Satnam Singh,
Satnam Singh
University of Connecticut
, Storrs, CT 06268
Search for other works by this author on:
Krishna Pattipati
Krishna Pattipati
Search for other works by this author on:
William Donat
University of Connecticut
, Storrs, CT 06268
Kihoon Choi
University of Connecticut
, Storrs, CT 06268
Woosun An
University of Connecticut
, Storrs, CT 06268
Satnam Singh
University of Connecticut
, Storrs, CT 06268
Krishna Pattipati
J. Eng. Gas Turbines Power. Jul 2008, 130(4): 041602 (8 pages)
Published Online: April 29, 2008
Article history
Received:
July 1, 2007
Revised:
September 5, 2007
Published:
April 29, 2008
Citation
Donat, W., Choi, K., An, W., Singh, S., and Pattipati, K. (April 29, 2008). "Data Visualization, Data Reduction and Classifier Fusion for Intelligent Fault Diagnosis in Gas Turbine Engines." ASME. J. Eng. Gas Turbines Power. July 2008; 130(4): 041602. https://doi.org/10.1115/1.2838993
Download citation file:
Get Email Alerts
Experimental Identification Of Blade Tip Rub Forces At Engine Relevant Temperatures And Speeds
J. Eng. Gas Turbines Power
Study Of Tandem Rotor Dual Wake Interaction With Downstream Stator Under Unsteady Numerical Approach
J. Eng. Gas Turbines Power
Experimental Design Validation of a Swirl-Stabilized Burner With Fluidically Variable Swirl Number
J. Eng. Gas Turbines Power (April 2025)
Experimental Characterization of a Bladeless Air Compressor
J. Eng. Gas Turbines Power (April 2025)
Related Articles
Nonlinear Fault Diagnosis of Jet Engines by Using a Multiple Model-Based Approach
J. Eng. Gas Turbines Power (January,2012)
Fault Diagnosis of Bearings Using Recurrences and Artificial Intelligence Techniques
ASME J Nondestructive Evaluation (August,2022)
Ensemble Learning Approach to the Prediction of Gas Turbine Trip
J. Eng. Gas Turbines Power (February,2023)
Enhanced Fault Localization Using Probabilistic Fusion With Gas Path Analysis Algorithms
J. Eng. Gas Turbines Power (September,2009)
Related Proceedings Papers
Related Chapters
Performance Validation Using Several Statistical Learning Theory Paradigms for Mammogram Screen Film and Clinical Data Features
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Application of Improved Wavelet Neural Network to Fault Diagnosis of Pumping Wells
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)
Fault Diagnosis of Power Transformers with Neural Network
International Conference on Software Technology and Engineering, 3rd (ICSTE 2011)