Abstract
Defects in the hot-gas path of aero engines have been shown to leave typical signatures in the density distribution of the exhaust jet. These signatures are superposed when several defects are present. For improved maintenance and monitoring applications, it is important to not only detect that there are defects present but to also identify the individual classes of defects. This diagnostic approach benefits both, the analysis of prototype or acceptance test and the preparation of Maintenance, Repair, and Overhaul. Recent advances in the analysis of tomographic Background-Oriented Schlieren (BOS) data have enabled the technique to be automated such that typical defects in the hot-gas path of gas turbines can be detected and distinguished automatically. This automation is achieved by using Support Vector Machine (SVM) algorithms. Choosing suitable identification parameters is critical and can enable SVM algorithms to distinguish between different defect types. The results show that the SVM can be trained such that almost no defects are missed and that false attributions of defect classes can be minimized.
Highlights
The solving of engineering problems often relies on a combination of deductive logic and the engineer’s intuition
It is shown that the Support Vector Machine (SVM) can even detect and distinguish combined defects in the highpressure turbine of an aero engine
The reconstructed density fields obtained from the background-oriented Schlieren method (BOS) measurements form the basis for training and validating the defect detection using an SVM
Summary
The solving of engineering problems often relies on a combination of deductive logic and the engineer’s intuition. Motivated by the economic potential and the potential to provide accurate and reliable engine diagnosis, this paper investigates the automated detection of hot-gas path defects using an SVM algorithm to evaluate exhaust density fields of an aircraft engine. These density fields can be captured experimentally using the BackgroundOriented Schlieren (BOS) method (see Goldhahn and Seume, 2007; Raffel, 2015) which yields a cross-sectional density distribution based on the local variation in the refraction index. Is the automated defect detection capable of distinguishing between individual defect mechanisms without creating false positives?
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of the Global Power and Propulsion Society
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
