Startseite Technik Machine learning augmented multi-sensor data fusion to detect aero engine fan rotor blade flutter
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

Machine learning augmented multi-sensor data fusion to detect aero engine fan rotor blade flutter

  • A. N. Viswanatha Rao ORCID logo EMAIL logo , T. N. Satish ORCID logo , V. P. S. Naidu ORCID logo und Soumendu Jana ORCID logo
Veröffentlicht/Copyright: 30. November 2022
Veröffentlichen auch Sie bei De Gruyter Brill

Abstract

Flutter-induced fatigue failure investigation of the fan blades of aero-engines necessitates extensive testing. During engine ground testing, strain gauges on rotor fan blades and casing vibration sensors were employed to investigate structural dynamic aspects. The correlation between strain sensor signals and fan casing vibration signals allowed the diagnosis of fluttering fan blades. For automated flutter detection during engine development testing, a machine learning-augmented information fusion methodology was developed. The method analyses casing vibration signals by extracting time-domain statistical features, intrinsic mode function characteristics through empirical mode decomposition, and recurrence quantification features. Feature vectors obtained from a relatively large set of engine tests were subjected to dimension reduction by applying machine learning techniques to rank them. Reduced feature vector space was labelled as “flutter” or “normal” based on the correlation of rotor strain gauge signals. In addition, the labelled feature vectors were employed to train classifier models using supervised learning-based algorithms such as Support Vector Machines, Linear Discriminant Analysis, K-means Clustering, and Artificial Neural Networks. Using only vibration signals from the casing, the trained and validated classifiers were able to detect flutter in fan baldes with a 99% probability during subsequent testing.


Corresponding author: A. N. Viswanatha Rao, Academy of Scientific and Innovative Research (AcSIR), Ghaziabad 201 002, India; and DRDO – Gas Turbine Research Establishment, Bengaluru 560 093, India, E-mail:

Acknowledgements

The authors would like to thank the Directors of the Gas Turbine Research Establishment (GTRE) and the National Aerospace Laboratories (NAL) in Bangalore, India for allowing them to conduct this research. They would also like to thank Mr. Vikas and Mr. Saurabh, scientists in the GTRE instrumentation and control engineering group, for their assistance with the various data analysis efforts.

  1. Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.

  2. Research funding: None declared.

  3. Conflict of interest statement: The authors declare no conflicts of interest regarding this article.

References

1. Srinivasan, AV. Flutter and resonant vibration characteristics of engine blades. ASME J Eng Gas Turbines Power 1997;119:742–75. https://doi.org/10.1115/1.2817053.Suche in Google Scholar

2. Vishwanatha Rao, AN, Satish, TN, Anagha, S, Soumendu, J, Naidu, VPS, Uma, G, et al.. Challenges in engine health monitoring instrumentation during developmental testing of gas turbine engines. In: Mistry, C, Kumar, S, Raghunandan, B, Sivaramakrishna, G, editors. Proceedings of the national aerospace propulsion conference. Lecture notes in mechanical engineering. Singapore: Springer; 2021.10.1007/978-981-15-5039-3_16Suche in Google Scholar

3. Guo, C. Study on the recognition of aero-engine blade-casing rubbing fault based on the casing vibration acceleration. Measurement 2015;65:71–80. https://doi.org/10.1016/j.measurement.2014.12.038.Suche in Google Scholar

4. Hörl, F, Richter, K. Monitoring the EJ200 engine. In: Proceedings of the 18th symposium “aircraft integrated monitoring systems”. Stuttgart, Germany; 1995:20 p. [Online]. Available from: https://enginemonitoring.org/publications/aims95.pdf [Accessed 18 Aug 2022].Suche in Google Scholar

5. Barragin, DJM, Strasse, D. Engine vibration monitoring and diagnosis based on On-Board Captured Data. 15 p. Defence Technical Information Centre Compilation Part Notice ADP014124. [Online]. Available from: https://apps.dtic.mil/sti/pdfs/ADP014124.pdf [Accessed 18 Aug 2022].Suche in Google Scholar

6. Purushothaman, K, Jeyaraman, SK, Pratap, A, Prasad Deshkulkarni, K. Aeroelastic flutter investigation and stability enhancement of a transonic axial compressor rotor using casing treatment. In: Proceedings of the ASME 2017 gas turbine India conference. Volume 1: compressors, fans and pumps; turbines; heat transfer; combustion, fuels and emissions. Bangalore, India. December 7–8, 2017. V001T01A015. ASME.10.1115/GTINDIA2017-4767Suche in Google Scholar

7. Sarkar, S, Jin, X, Ray, A. Data-driven fault detection in aircraft engines with noisy sensor measurements. J Eng Gas Turbines Power 2020;133:81602. https://doi.org/10.1115/1.4002877.Suche in Google Scholar

8. Varanis, M, Silva, AL, Balthazar, JM, Pederiva, R. A tutorial review on time-frequency analysis of non-stationary vibration signals with nonlinear dynamics applications. Braz J Phys 2021;51:859–77. https://doi.org/10.1007/s13538-020-00842-y.Suche in Google Scholar

9. Bouchain, A, Picheral, J, Lahalle, E, Vercoutter, A, Burgardt, B, Talon, A. New possibilities for analyzing complex asynchronous blade vibrations from tip-timing data using a sparse spectral analysis method. In: Proceedings of the ASME turbo expo 2019: turbomachinery technical conference and exposition. Volume 7B: structures and dynamics. Phoenix, Arizona, USA. June 17–21, 2019. V07BT35A022. ASME.10.1115/GT2019-91573Suche in Google Scholar

10. Viswanatha Rao, AN, Satish, TN, Naidu, VPS, Jana, Soumendu. Exploration of an unconventional validation tool to investigate aero engine transonic fan flutter signature. Int J Turbo Jet Engines 2022;Ahead of print. https://doi.org/10.1515/tjj-2022-0005.Suche in Google Scholar

11. Roffo, G, Melzi, S, Cristani, M. Infinite feature selection. IEEE Int Conf Comput Vis 2015;ICCV:4202–10. https://doi.org/10.1109/ICCV.2015.478.Suche in Google Scholar

12. Setti, S, Srinivas, M, Naidu, VPS. Vibration analysis of gearbox fault diagnosis using DWT and statistical features. J Eng Res 2021;10:156–65. https://doi.org/10.36909/jer.10465.Suche in Google Scholar

13. Hayton, P, Utete, S, King, D, King, S, Anuzis, P, Tarassenko, L. Static and dynamic novelty detection methods for jet engine health monitoring. Phil Trans Math Phys Eng Sci 2007;365:493–514. https://doi.org/10.1098/rsta.2006.1931.Suche in Google Scholar PubMed

14. Viswanatha Rao, AN, Naidu, VPS, Jana, S. Gas turbine engine fan blade flutter detection using casing vibration signals by application of recurrence plots and recurrence quantification analysis. In: Rao, JS, Arun Kumar, V, Jana, S, editors. Proceedings of the 6th national symposium on rotor dynamics. Lecture notes in mechanical engineering. Singapore: Springer; 2021.10.1007/978-981-15-5701-9_31Suche in Google Scholar

15. Sanjay Barad, G, Ramaiah, PV, Giridhar, RK, Krishnaiah, G. Neural network approach for a combined performance and mechanical health monitoring of a gas turbine engine. Mech Syst Signal Process 2012;27:729–42. https://doi.org/10.1016/j.ymssp.2011.09.011.Suche in Google Scholar

16. Purushothaman, K, Naveen Kumar, NR, Jeyaraman, SK, Pratap, A. Aeroelastic instability evaluation of transonic compressor at design and off-design conditions. In: Mistry, C, Kumar, S, Raghunandan, B, Sivaramakrishna, G, editors. Proceedings of the national aerospace propulsion conference. Lecture notes in mechanical engineering. Singapore: Springer; 2021.10.1007/978-981-15-5039-3_3Suche in Google Scholar

17. Prosig-DATS-Software-Datasheet-1.00.pdf. [Online]. Available from: https://prosigdotcom.b-cdn.net/wp-content/uploads/2020/11/Prosig-DATS-Software-Datasheet-1.00.pdf [Accessed 18 Aug 2022].Suche in Google Scholar

18. CA134 piezoelectric accelerometer – vibro-meter catalogue. https://catalogue.meggittsensing.com/shop/sensors-and-signal-conditioners/high-temperature-vibration-sensors/ca134-piezoelectric-accelerometer/ [Accessed 13 Aug 2022].Suche in Google Scholar

19. slip-rings.pdf. [Online]. Available from: https://www.aerodyn-global.com/downloads/slip-rings.pdf [Accessed 09 Aug 2022].Suche in Google Scholar

20. TT351 strain gauge load cell input four-wire trans.pdf. [Online]. Available from: https://www.acromag.com/wp-content/uploads/2019/10/TT351-StrainGauge-Input-Four-wire-Transmitter.pdf [Accessed 13 Aug 2022].Suche in Google Scholar

21. System signal conditioning amplifier. Available from: http://www.vishaypg.com/docs/11255/syst2300.pdf [accessed on 11 Nov 2022].Suche in Google Scholar

22. de Jesus Romero-Troncoso, R. Multirate signal processing to improve FFT-based analysis for detecting faults in induction motors. IEEE Trans Ind Inf 2017;13:1291–300. https://doi.org/10.1109/TII.2016.2603968.Suche in Google Scholar

23. Marwan, N, Romano, MC, Thiel, M, Kurths, J. Recurrence plots for the analysis of complex systems. Phys Rep 2007;438: 237–329. https://doi.org/10.1016/j.physrep.2006.11.001.Suche in Google Scholar

24. Marwan, N, Webber, CL. Mathematical and computational foundations of recurrence quantifications. In: Webber, Jr. C, Marwan, N, editors. Recurrence quantification analysis. Understanding complex systems. Cham: Springer; 2015.10.1007/978-3-319-07155-8Suche in Google Scholar

25. Huang, NE, Shen, Z, Long, SR, Wu, M, Shih, HH, Zheng, Q, et al.. The empirical mode decomposition and Hilbert spectrum for nonlinear and nonstationary time series analysis. Proc R Soc London, A 1998;454:903–98. https://doi.org/10.1098/rspa.1998.0193.Suche in Google Scholar

26. Zeiler, A, Faltermeier, R, Keck, IR, Tomé, AM, Puntonet, CG, Lang, EW. Empirical mode decomposition – an introduction. In: The 2010 international joint conference on neural networks (IJCNN); 2010:1–8 pp.10.1109/IJCNN.2010.5596829Suche in Google Scholar

27. Venkatesh, B, Anuradha, J. A review of feature selection and its methods. Cybern Inf Technol 2019;19:3–26. https://doi.org/10.2478/cait-2019-0001.Suche in Google Scholar

28. Yang, W, Wang, K, Zuo, W. Neighborhood component feature selection for high-dimensional data. J Comput 2012;7:161–8. https://doi.org/10.4304/jcp.7.1.161-168.Suche in Google Scholar

29. Bottou, L. Stochastic gradient descent tricks. In: Montavon, G, Orr, GB, Müller, KR, editors. Neural networks: tricks of the trade. Lecture notes in computer science. Berlin, Heidelberg: Springer; 2012, vol 7700.10.1007/978-3-642-35289-8_25Suche in Google Scholar

30. Choudhary, R, Gianey, HK. Comprehensive review on supervised machine learning algorithms. Int Conf Machine Learn Data Sci (MLDS) 2017;2017:37–43. https://doi.org/10.1109/MLDS.2017.11.Suche in Google Scholar

Received: 2022-10-17
Accepted: 2022-11-04
Published Online: 2022-11-30

© 2022 Walter de Gruyter GmbH, Berlin/Boston

Artikel in diesem Heft

  1. Frontmatter
  2. The International Journal of Turbo and Jet Engines
  3. The aerothermodynamic cycle optimal design of a turbofan engine
  4. Multi-condition design optimization of groove flow control technique in an axial-flow pump
  5. Analysis on impulse characteristics of pulse detonation engine with nozzles
  6. Numerical investigation on implication of innovative hydrogen strut injector on performance and combustion characteristics in a scramjet combustor
  7. Optimization of Kiel geometry for better recovery factor in high temperature measurement in aero gas turbine engine
  8. Applicability of correlational data-mining to small-scale turbojet performance map generation
  9. Effect of multi-zone effusion cooling on an adiabatic flat plate for gas turbine application
  10. Flow quality improvement of the wind tunnel testing for a highly-loaded compressor cascade at high incidence
  11. Modeling and analysis of 3D radiative heat transfer in combustor
  12. A creep-fatigue life prediction model considering multi-factor coupling effect
  13. Optimization-based transient control of turbofan engines: a sequential quadratic programming approach
  14. Investigations on the interaction between the front and aft purge flow and the downstream vane of 1.5-stage turbine
  15. A study on design optimization for compressor blisks
  16. Exploration of an unconventional validation tool to investigate aero engine transonic fan flutter signature
  17. Evaluation of non-uniform water film behavior on the performance of an axial aeroengine compressor
  18. Predicting remaining useful life of turbofan engines using degradation signal based echo state network
  19. Effect of G-type integral squeeze film damper on the dynamic characteristics in rotor system
  20. Development of a one-dimensional code for the initial design of a micro gas turbine mixed flow compressor stage
  21. Numerical and experimental investigations of tip clearance effects in a high-flow-coefficient centrifugal compressor
  22. Experimental and numerical investigation on the effect of turboprop engine exhaust gas impingement on pusher aircraft
  23. Heat transfer distribution of single oblique jet impingement in crossflow under different inlet conditions
  24. Performance enhancement and flow separation control in an S-duct by air injection
  25. Gas dynamic analysis of the modern single shaft gas turbine engine flow path
  26. Aero engine health monitoring, diagnostics and prognostics for condition-based maintenance: an overview
  27. Influence of leading edge point on aerodynamic performance of asymmetric leading edge compressor airfoils
  28. The aerothermal performance of turbine blade squealer tip at various Reynolds numbers and Mach numbers with moving endwall
  29. Numerical investigation of a variable stator vane with nonuniform partial radial gaps in an annular compressor cascade
  30. Effect of self-recirculating casing treatment on the unsteady flow and stability of counter-rotating axial-flow compressor
  31. Research on temperature rise characteristics of end V-groove ring seal
  32. Research on the influence of honeycomb cell blockage on the seal leakage characteristics
  33. Vortex structure control based bleed in axial compressor cascade with tip clearance using large eddy simulation
  34. Development and application of a profile loss model considering the low-Re effect in low-pressure turbine
  35. Optimization of ACE mode transition control schedule considering geometric adjustment speed
  36. Numerical investigation of flow control in low-pressure turbine cascade using Gurney Flaps
  37. The design method of the V-shaped groove piston ring
  38. Control of subsonic jets using vanes as vortex generators
  39. Impact investigation of inlet environmental changes on the rated condition performance of a high-pressure compressor
  40. Research on new integral squeeze film damper vibration control of micro turbojet engine at high speed
  41. Effect of the distribution of the upstream probe support on performance of compressor cascade
  42. Effect of bypass ratio on sonic underexpanded co-flow jets with finite lip thickness
  43. Machine learning augmented multi-sensor data fusion to detect aero engine fan rotor blade flutter
  44. CFD analysis of flow control in compressor cascade using MVGs
  45. Quantitative investigation of the evaporation and resistance characteristics of inlet jet precooling
  46. Study on laser de-weight and dynamic balance technology of rotating machines
  47. Integrated design and analysis of inlet and missile with two side layout
  48. Research on turboprop engine control method based on linear parameter varying model
  49. Modeling and validation of the volume effect on the axial fan transient performance
  50. Ground effects on the aerodynamics of a wing with slot type distributed propulsion system for VTOL applications
  51. Multidisciplinary sensitivity analysis for turbine blade considering thickness uncertainties
  52. Accurate measurement and evaluation method of axial compressor efficiency under the influence of multiple factors
  53. Control mechanism of secondary flow in a turbine cascade with non-axisymmetric endwall profiling under Co-rotating incoming vortex
  54. Infrared simulation of aircraft rear fuselage based on a coupled CFD method
  55. Effect of multi-hole trench cooling on an adiabatic flat plate for gas turbine application
  56. Numerical study of transition process in different zones of a compressor cascade channel
Heruntergeladen am 19.1.2026 von https://www.degruyterbrill.com/document/doi/10.1515/tjj-2022-0066/pdf
Button zum nach oben scrollen