Journal Information
Research Areas
Publication Ethics and Malpractice Statement
To Scholarlink Resource Center
Guidelines for Authors
For Authors
Instructions to Authors
Copyright forms
Submit Manuscript
Call for papers
Guidelines for Reviewers
For Reviewers
Review Forms
Contacts and Support
Support and Contact
List of Issues


Journal of Emerging Trends in Engineering and Applied Sciences (JETEAS)


Article Title: Health Monitoring of Gas Turbine Engine using Principal Component Analysis Approach
by Jerry E. Eyoh, Imoh Jerry Eyoh, Uduak A. Umoh Edward N. Udoh

Monitoring health condition of Gas Turbine Engines (GTE), using data-based method requires a large amount of systems' parameter variables (data). These data are nonlinear and of high dimension. To analyse these data, dimensionality reduction techniques are required to transform the high-dimensional data to a lower dimensional space. This study adopts Principal Component Analysis (PCA) technique to analyse the GTE data to extract features from the data which are then compared with feature from the normal operating condition of the GTE for change detection. GTE generates a huge amount from the numerous measured variables. We consider twelve measured variables and seven operating conditions from three-hundred gas turbines. Nearest-neighbour classification of the training data is explored for GTE fault diagnosis. We achieve visualization of the low-dimensional data in two-dimension using scatter plot. M-fold cross-validation is employed to test the performance of our model. The model is implemented in Matlab and C++ programming tool. This model serves as predictive maintenance strategy with efficiency and cost effective. It also helps to minimize the downtime of gas turbine engines, improves safety plant operations. Thus enhances system reliability and availability.
Keywords: health monitoring, principal component analysis, fault diagnosis, nearest-neighbour classification, m-fold cross-validation, efficiency
Download full paper

ISSN: 2141-7016

Editor in Chief.

Prof. Gui Yun Tian
Professor of Sensor Technologies
School of Electrical, Electronic and Computer Engineering
University of Newcastle
United Kingdom



Copyright © Journal of Emerging Trends in Engineering and Applied Sciences 2010