Research Papers: Gas Turbines: Combustion, Fuels, and Emissions

Automatic Detection of Defects in a Swirl Burner Array Through an Exhaust Jet Pattern Analysis

[+] Author and Article Information
Ulrich Hartmann

Institute of Turbomachinery and Fluid Dynamics,
Leibniz Universität Hannover,
Hannover 30167, Lower Saxony, Germany
e-mail: hartmann@tfd.uni-hannover.de

Christoph Hennecke, Friedrich Dinkelacker

Institute of Technical Combustion,
Leibniz Universität Hannover,
Hannover 30167, Lower Saxony, Germany

Joerg R. Seume

Institute of Turbomachinery and Fluid Dynamics,
Leibniz Universität Hannover,
Hannover 30167, Lower Saxony, Germany

1Corresponding author.

Contributed by the Combustion and Fuels Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received June 28, 2016; final manuscript received July 12, 2016; published online September 27, 2016. Editor: David Wisler.

J. Eng. Gas Turbines Power 139(3), 031504 (Sep 27, 2016) (8 pages) Paper No: GTP-16-1283; doi: 10.1115/1.4034449 History: Received June 28, 2016; Revised July 12, 2016

A significant challenge in improving the regeneration process of jet engines is the reduction of engine down-time during inspection. As such, early defect detection without engine disassembly will speed up the regeneration process. Defects in the engines hot-gas path (HGP) influence the density distribution of the flow and lead to irregularities in the density distribution of the exhaust jet which can be detected with the optical background-oriented Schlieren (BOS) method in a tomographic setup. The present paper proposes a combination of tomographic BOS measurements and supervised learning algorithms to develop a methodology for an automatic defect detection system. In the first step, the methodology is tested by analyzing the exhaust jet of a swirl burner array with a nonuniform fuel-supply of single burners with tomographic BOS measurements. The measurements are used to implement a support vector machine (SVM) pattern recognition algorithm. It is shown that the reconstruction quality of tomographic BOS measurements is high enough to be combined with pattern recognition algorithms. The results strengthen the hypothesis that it is possible to automatically detect defects in jet engines with tomographic BOS measurements and pattern recognition algorithms.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.


Adamczuk, R. R. , Buske, C. , Roehle, I. , Hennecke, C. , Dinkelacker, F. , and Seume, J. R. , 2013, “ Impact of Defects and Damage in Aircraft Engines on the Exhaust Jet,” ASME Paper No. GT2013-95079.
Richard, H. , Raffel, M. , Rein, M. , Kompenhans, J. , and Meier, G. E. A. , 2000, “ Demonstration of the Applicability of a Background Oriented Schlieren (BOS) Method,” 10th International Symposium on Applications of Laser Techniques to Fluid Mechanics, Lisbon, Portugal, July 10–13, pp. 145–156.
Politz, C. , Over, B. , and Kirmse, T. , 2013, “ The Application of Background Oriented Schlieren Method to Aircraft Wake Vortex Investigations,” Advanced In-Flight Measurement Techniques, Springer, Berlin, pp. 321–329.
Schröder, A. , Geisler, R. , Schanz, D. , Agocs, J. , Pallek, D. , Schroll, M. , Klinner, J. , Beversdorff, M. , Voges, M. , and Willert, C. , 2014, “ Application of Image Based Measurement Techniques for the Investigation of Aeroengine Performance on a Commercial Aircraft in Ground Operation,” 17th International Symposium on Applications of Laser Techniques to Mechanics, Lisbon, Portugal, July 7–10.
Adamczuk, R. R. , Hartmann, U. , and Seume, J. , 2013, “ Experimental Demonstration of Analyzing an Engine's Exhaust Jet With the Background-Oriented Schlieren Method,” AIAA Paper No. AIAA 2013-2488.
Raffel, M. , 2015, “ Background-Oriented Schlieren (BOS) Techniques,” Exp. Fluids, 56(3), pp. 1–17.
Bathel, B. F. , Borg, S. E. , Walker, E. , and Mizukaki, T. , 2015, “ Development of Background-Oriented Schlieren for NASA Langley Research Center Ground Test Facilities (Invited),” 53rd AIAA Aerospace Sciences Meeting, American Institute of Aeronautics and Astronautics, AIAA Paper No. 2015-1691.
Mizukaki, T. , Bathel, B. F. , Borg, S. E. , Danehy, P. M. , Murman, S. M. , Matsumura, T. , Wakabayashi, K. , and Nakayama, Y. , 2015. “ Background-Oriented Schlieren for Large-Scale and High-Speed Aerodynamic Phenomena (Invited),” AIAA Paper No. 2015-1692.
Hennecke, C. , Hartmann, U. , Dinkelacker, F. , and Seume, J. , 2015, “ Correlation of Defects in an Annular Swirl-Burner-Array by Optical Measuring Exhaust Gases and Numerical Analysis,” Deutscher Luft- und Raumfahrtkongress, Rostock, Germany, Sept. 22–24.
von der Haar, H. , Hartmann, U. , Hennecke, C. , Dinkelacker, F. , and Seume, J. R. , 2016, “ Defect Detection in an Annular Swirl-Burner-Array by Optical Measuring Exhaust Gases,” ASME Paper No. GT2016-57847.
Goldhahn, E. , and Seume, J. , 2007, “ The Background Oriented Schlieren Technique: Sensitivity, Accuracy, Resolution and Application to a Three-Dimensional Density Field,” Exp. Fluids, 43(2–3), pp. 241–249. [CrossRef]
Hartmann, U. , and Seume, J. , 2015, “ Application of an Algebraic Reconstruction Algorithm to Tomographic BOS Measurements,” International Gas Turbine Congress, Tokyo, Japan, Nov. 15–20, pp. 1214–1221.
Herbst, F. , Peters, M. , and Seume, J. R. , 2011, “ To the Limits of the Application of the Bos-Method,” 11th International Conference on Fluid Control, Measurements, and Visualization (FLUCOME 2011), Keelung, Taiwan, Dec. 5–9.
Goldhahn, E. , Alhaj, O. , Herbst, F. , and Seume, J. , 2009, “ Quantitative Measurements of Three-Dimensional Density Fields Using the Background Oriented Schlieren Technique,” Imaging Measurement Methods for Flow Analysis (Notes on Numerical Fluid Mechanics and Multidisciplinary Design, Vol. 106), W. Nitsche , and C. Dobriloff , eds., Springer, Berlin, pp. 135–144.
Widodo, A. , and Yang, B.-S. , 2007, “ Support Vector Machine in Machine Condition Monitoring and Fault Diagnosis,” Mech. Syst. Signal Process., 21(6), pp. 2560–2574. [CrossRef]
Wang, Z. , Zarader, J. L. , and Argentieri, S. , 2012, “ A Novel Aircraft Engine Fault Diagnostic and Prognostic System Based on SVM,” IEEE International Conference on Condition Monitoring and Diagnosis (CMD 2012), Bali, Indonesia, Sept. 23–27, pp. 723–728.
Heng, H. , Zhang, J. , and Xin, C. , 2012, “ Research on Aircraft Engine Fault Detection Based on Support Vector Machines,” Consumer Electronics, Communications and Networks (CECNet), Yichang, China, Apr. 21–23, pp. 496–499.
Hayton, P. , Schölkopf, B. , Tarassenko, L. , and Anuzis, P. , 2001, “ Support Vector Novelty Detection Applied to Jet Engine Vibration Spectra,” Advances in Neural Information Processing Systems 13, T. K. Leen , T. G. Dietterich , and V. Tresp , eds., MIT Press, Cambridge, MA, pp. 946–952.
Hayton, P. , Utete, S. , King, D. , King, S. , Anuzis, P. , and Tarassenko, L. , 2007, “ Static and Dynamic Novelty Detection Methods for Jet Engine Health Monitoring,” Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci., 365(1851), pp. 493–514. [CrossRef]
Kim, Y. , Jang, J. , Kim, W. , Roh, T. S. , and Choi, D. W. , 2012, “ Multiple Defect Diagnostics of Gas Turbine Engine Using SVM and RCGA-Based ANN Algorithms,” J. Mech. Sci. Technol., 26(5), pp. 1623–1632. [CrossRef]
Xu, Q.-h. , and Shi, J. , 2006, “ Fault Diagnosis for Aero-Engine Applying a New Multi-Class Support Vector Algorithm,” Chin. J. Aeronaut., 19(3), pp. 175–182. [CrossRef]
Stein, M. , 1987, “ Large Sample Properties of Simulations Using Latin Hypercube Sampling,” Technometrics, 29(2), pp. 143–151. [CrossRef]
Florian, A. , 1992, “ An Efficient Sampling Scheme: Updated Latin Hypercube Sampling,” Probab. Eng. Mech., 7(2), pp. 123–130. [CrossRef]
Platt, J. C. , 2000, “ Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods,” Advances in Large Margin Classifiers, Vol. 10, A. Smola , P. Bartlett , B. Schoelkopf , and D. Schuurmans , eds., MIT Press, Cambridge, MA, pp. 61–74.


Grahic Jump Location
Fig. 1

Swirl burner array

Grahic Jump Location
Fig. 2

Principle of the BOS method modeled after [12]

Grahic Jump Location
Fig. 3

Tomographic BOS setup at the burner test rig

Grahic Jump Location
Fig. 4

Density distribution in the burners exhaust jet measured with BOS for different output powers of the single burner: (a) PSingle = 10 kW, (b) PSingle = 5 kW, and (c) PSingle = 0 kW

Grahic Jump Location
Fig. 5

Principle of SVM classification

Grahic Jump Location
Fig. 6

Generation of the synthetic training data out of tomographic BOS measurements: (a) parameters obtained from BOS measurements, (b) generation of the training data using a LHS algorithm, and (c) separating hyperplane

Grahic Jump Location
Fig. 7

SVM classification of tomographic BOS measurements



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In