Hostname: page-component-586b7cd67f-tf8b9 Total loading time: 0 Render date: 2024-11-26T11:15:28.187Z Has data issue: false hasContentIssue false
  • English
  • Français

GPR-based novel approach for non-linear aerodynamic modelling from flight data

Published online by Cambridge University Press:  17 October 2018

A. Kumar  and
A. K. Ghosh
A. Kumar*
Affiliation:
Department of Aerospace EngineeringIndian Institute of Technology of KanpurKanpurUttar PradeshIndia
A. K. Ghosh*
Affiliation:
Department of Aerospace EngineeringIndian Institute of Technology of KanpurKanpurUttar PradeshIndia
*
[email protected]
[email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

In this paper, a Gaussian process regression (GPR)-based novel method is proposed for non-linear aerodynamic modelling of the aircraft using flight data. This data-driven regression approach uses the kernel-based probabilistic model to predict the non-linearity. The efficacy of this method is examined and validated by estimating force and moment coefficients using research aircraft flight data. Estimated coefficients of aerodynamic force and moment using GPR method are compared with the estimated coefficients using maximum-likelihood estimation (MLE) method. Estimated coefficients from the GPR method are statistically analysed and found to be at par with estimated coefficients from MLE, which is popularly used as a conventional method. GPR approach does not require to solve the complex equations of motion. GPR further can be directed for the generalised applications in the area of aeroelasticity, load estimation, and optimisation.

Keywords

Gaussian process regressionNon-linear aerodynamic modellingFlight data
Type
Research Article
Information
The Aeronautical Journal , Volume 123 , Issue 1259 , January 2019 , pp. 79 - 92
Copyright
© Royal Aeronautical Society 2018 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1. Grauer, J.A. and Morelli, E.A. A generic nonlinear aerodynamic model for aircraft. In AIAA Atmospheric Flight Mechanics Conference 2014, p 0542.Google Scholar
2. Jategaonkar, R.V. Flight Vehicle System Identification: A Time Domain Methodology, AIAA Education Series, AIAA, Reston, VA, 2006.Google Scholar
3. Klein, V. and Morelli, E.A. Aircraft System Identification: Theory and Practice. American Institute of Aeronautics and Astronautics, Reston, VA, 2006, pp 351–382.Google Scholar
4. Mehra, R.K., Stepner, D.E. and Tyler, J.S. Maximum likelihood identification of aircraft stability and control derivatives, J Aircr, 1974, 11, (2), 81–89.Google Scholar
5. Morelli Eugene, A. Real-time aerodynamic parameter estimation without air flow angle measurements, J Aircraft, 2012, 49, (4), 1064–1074.Google Scholar
6. Morelli, E. Efficient global aerodynamic modeling from flight data, 50th Aerospace Sciences Meeting, AIAA, January 2012, pp 1–26.Google Scholar
7. Goman, M.G. and Khrabrov, A.N. State-space representation of aerodynamic characteristics of an aircraft at high, J Aircr, 1994, 31, (5), pp 1109–1115.Google Scholar
8. Nelson, R.C. and Pelletier, A. The unsteady aerodynamics of slender wings and aircraft undergoing large amplitude maneuvers, Progress in Aerospace Sciences, 2003, 39, (2–3), pp 185–248.Google Scholar
9. Fischenberg, D. and Jategaonkar, R.V. Identification of aircraft stall behavior from flight test data. RTO MP-11 Paper No. 17, 1999.Google Scholar
10. Ghoreyshi, M. and Cummings, R.M. Unsteady aerodynamics modeling for aircraft maneuvers: a new approach using time-dependent surrogate modeling, Aerospace Science and Technology, 2014, 39, pp 222–242.Google Scholar
11. Peyada, N.K. and Ghosh, A.K. Aircraft parameter estimation using a new filtering technique based upon a neural network and Gauss–Newton method, Aeronautical J, 2009, 113, (1142), pp 243–252.Google Scholar
12. Kumar, R. and Ghosh, A.K. Nonlinear modeling of cascade fin aerodynamics using Kirchhoff’s steady-stall model, J Aircr, 2012, 49, (1), pp 315–319.Google Scholar
13. Kumar, R. and Ghosh, A.K. Nonlinear aerodynamic modeling of Hansa-3 aircraft using neural Gauss–Newton method, J Aerospace Science and Technology, 2011, 63, (3), pp 194–204.Google Scholar
14. Faller, W.E. and Schreck, S.J. Unsteady fluid mechanics applications of neural networks, J Aircr, 1997, 34, (1), pp 48–55.Google Scholar
15. Marques, F.D. and Anderson, J. Identification and prediction of unsteady transonic aerodynamic loads by multi-layer functionals, J Fluids and Structures, 2001, 15, (1), pp 83–106.Google Scholar
16. Voitcu, O. and Wong, Y.S. Neural network approach for nonlinear aeroelastic analysis, J Guidance, Control, and Dynamics, 2003, 26, (1), pp 99–105.Google Scholar
17. Zhang, W., et al. Efficient method for limit cycle flutter analysis based on nonlinear aerodynamic reduced-order models, AIAA J, 2012, 50, (5), pp 1019–1028.Google Scholar
18. Winter, M. and Breitsamter, C. Reduced-order Modeling of Unsteady Aerodynamic Loads Using Radial Basis Function Neural Networks. Deutsche Gesellschaft für Luft-und Raumfahrt-Lilienthal-Oberth eV, 2014.Google Scholar
19. Lindhorst, K., Haupt, M.C. and Horst, P. Efficient surrogate modelling of nonlinear aerodynamics in aerostructural coupling schemes, AIAA J, 2014, 52, (9), pp 1952–1966.Google Scholar
20. Winter, M. and Breitsamter, C. Unsteady Aerodynamic Modeling Using Neuro-Fuzzy Approaches Combined with POD. Deutsche Gesellschaft für Luft-und Raumfahrt-Lilienthal-Oberth eV, 2015.Google Scholar
21. Babuska, R. Neuro-fuzzy methods for modeling and identification, Recent Advances in Intelligent Paradigms and Applications, Springer-Verlag, Heidelberg, 2002, pp 161–186.Google Scholar
22. Oliver Nelles. Nonlinear System Identification from Classical approaches to Neural Networks and Fuzzy Models. Springer-Verlag, Baden-Württemberg, Germany, 2001.Google Scholar
23. Ignatyev, D., Khrabrov, A. and Alexander, N. Neural network modeling of unsteady aerodynamic characteristics at high angles of attack, Aerospace Science and Technology, 2015, 41, pp 106–115.Google Scholar
24. Leishman, J.G. and Nguyen, K.Q. State-space representation of unsteady airfoil behavior, AIAA J, 1990, 28, (5), pp 836–844.Google Scholar
25. De JesusMota, S. and Botez, R.M. New helicopter model identification method based on a neural network optimization algorithm and on flight test data, Aeronautical J, 2011, 115, (1167), pp 295–314.Google Scholar
26. Boely, N., Botez, R.M. and Kouba, G. Identification of a nonlinear F/A-18 model by use of fuzzy logic and neural network methods, Proceedings of the Institution of Mechanical Engineers, Part G, J Aerospace Engineering, 2011, 225, (5), pp 559–574.Google Scholar
27. Boely, N. and Botez, R.M. New approach for the identification and validation of a nonlinear F/A-18 model by use of neural networks, IEEE Transactions on Neural Networks, 2010, 21, (11), pp 1759–1765.Google Scholar
28. Chati, Y.S. and Balakrishnan, H. A Gaussian process regression approach to model aircraft engine fuel flow rate. In 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems (ICCPS) IEEE, April 2017, pp 131–140.Google Scholar
29. Lee, K. and Johnson, E.N. State estimation using Gaussian process regression for colored noise systems. In Aerospace Conference, 2017 IEEE, March 2017, IEEE, pp. 1–8.Google Scholar
30. Rasmussen, C.E. and Williams, C.K.I. Gaussian Processes for Machine Learning. The MIT Press, New York, US, 2006. Google Scholar
31. Vanhatalo, J., Riihim¨aki, J., Hartikainen, J., Jyl¨anki, P., Tolvanen, V. and Vehtari, A. GP stuff: Bayesian modeling with Gaussian processes, J Machine Learning Research, 2013, 14, (2013), pp 1175–1179.Google Scholar
32. Saderla, S., Dhayalan, R. and Ghosh, A.K. Non-linear aerodynamic modelling of unmanned cropped delta configuration from experimental data, Aeronautical J, 2017, 121, (1237), pp 320–340.Google Scholar
33. The Mathworks, MATLAB User Manual. The MathWorks, Inc., Natick, MA.Google Scholar