The objective of this work is to present a method to monitor the health of Auxiliary Power Units (APU) using a Dynamic Computational Model, Gas Path Analysis and Classification and Regression Trees (CART). The main data used to train the CART consists of measurements of the exhaust gas temperature, the bleed pressure and the fuel flow. The proposed method was tested using actual APU data collected from a prototype aircraft. The method succeeded in classifying several relevant fault conditions. The few misclassification errors were found to be due to the insufficiency of the information content of the measurement data.
How to Cite
fault isolation, APU, Classification and Regression Trees
Jones S. M. (2007). An Introduction to Thermodynamic Performance Analysis of Aircraft Gas Turbine Engine Cycles Using the Numerical Propulsion System Simulation Code. NASA Glenn Research Center, Cleveland, Ohio NASA/TM—2007-214690.
Li Y. G. (2003) A gas Turbine Approach with Transient Measurements in Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, Volume 217, Number 2, pp. 169-177
Sabyasachi B., Farner S., Schimert J. and Wineland (2008) A Data Driven Method for Predicting Engine Wear from Exhaust Gas Temperature in Proceedings of International Conference on Prognostics and Health Management .
SAE. (2006). E-32 AIR5317 - A guide to APU Health Management
Saravanamuttoo H.I.H. and Maclsaac B.D. (1982). Thermodynamic Models for Pipeline Gas Turbine Diagnostics, Journal of Engineering for Power, Vol. 105, pp.875-884, October 1982
Timofeev R. (2004), Classification and Regression Trees (CART) Theory and Applications, Master Thesis - CASE - Center of Applied Statistics and Economics Humboldt University, Berlin.
Urban L. A.(1967). Gas Turbine Engine Parameter Interrelationship, HSD UTC, Windsor Locks, Ct., 1st edition.
Vieira, F. M. and Bizarria C. O. (2009).Health Monitoring using Support Vector Classification on an Auxiliary Power Unit, in Proceedings of IEEE Aerospace Conference, Big Sky, MO.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.