Hostname: page-component-cd9895bd7-mkpzs Total loading time: 0 Render date: 2024-12-22T10:11:31.812Z Has data issue: false hasContentIssue false
  • English
  • Français

Estimation of lateral-directional parameters using neural networks based modified delta method

Published online by Cambridge University Press:  03 February 2016

S. Singh  and
A. K. Ghosh
S. Singh
Affiliation:
Indian Institute of Technology, Kanpur, India
A. K. Ghosh
Affiliation:
Indian Institute of Technology, Kanpur, India
Get access Rights & Permissions [Opens in a new window]

Abstract

The aim of the study described herein was to develop and verify an efficient neural network based method for extracting aircraft stability and control derivatives from real flight data using feed-forward neural networks. The proposed method (Modified Delta method) draws its inspiration from feed forward neural network based the Delta method for estimating stability and control derivatives. The neural network is trained using differential variation of aircraft motion/control variables and coefficients as the network inputs and outputs respectively. For the purpose of parameter estimation, the trained neural network is presented with a suitably modified input file and the corresponding predicted output file of aerodynamic coefficients is obtained. An appropriate interpretation and manipulation of such input-output files yields the estimates of the parameter. The method is validated first on the simulated flight data using various combinations and types of real-flight control inputs and then on real flight data. A new technique is also proposed for validating the estimated parameters using feed-forward neural networks.

Type
Research Article
Information
The Aeronautical Journal , Volume 111 , Issue 1124 , October 2007 , pp. 659 - 667
Copyright
Copyright © Royal Aeronautical Society 2007 

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. Hess, R.A., On the use of back propagation with feed forward neural networks for the aerodynamic estimation problem, August 1993, AIAA Paper 93-3639.Google Scholar
2. Basappa, and Jategaonkar, R.V.. Aspects of feed forward neural network modeling and its application to lateral-directional flight-data, September 1995, DLR IB-111-95/30.Google Scholar
3. Linse, D.J. and Stengel, R.F.. Identification of aerodynamic coefficients using computational neural networks, J Guid Cont and Dynam, November – December 1993, 16, (6), pp 1018–1025.Google Scholar
4. Youseff, H.M. and Juang, J.C., Estimation of aerodynamic coefficients using neural networks, August 1993, AIAA Paper 93-3639.Google Scholar
5. Hornk, K., Stinchcombe, M. and White, H.. Multi layer feed forward neural networks are universal approximator, Neural Networks, 1989, 2, (5), pp 359–366.Google Scholar
6. Raol, J.R. and Jategaonkar, R.V., Aircraft parameter estimation using recurrent neural networks — a critical appraisal, August 1995, AIAA Paper 95-3004.Google Scholar
7. Raisinghani, S.C., Ghosh, A.K. and Kalra, P.K.. Two new techniques for aircraft parameter estimation using neural networks, Aeronaut J, January 1998, 102, (1011), pp 25–29.Google Scholar
8. Ghosh, A.K., Raisinghani, S.C. and Khubchandani, S.. Estimation of aircraft lateral-directional parameters using neural networks, J Aircr, November-December 1998, 35, (6), pp 876–881.Google Scholar
9. Gauche, E., Coelho, J. and Teive, R.C.G.. A mixed back-propa-gation/Marquardt-Levenberg algorithm for optimizing the distribution electrical systems operation, IEEE, 1999, pp 753–758.Google Scholar
10. Hagan, M.T. and Menhaj, M.B.. Training feed forward networks with the Marquardt algorithm, IEEE Transaction on Neural Networks, 1994, 5, (6), pp 989–993.Google Scholar
11. Jategaonkar, R.V., Flight vehicle system identification — a time domain methodology, 2006, AIAA, Reston, VA.Google Scholar
12. Scalero, R.S. and Tepedelenlioglu, N.. A fast new algorithm for training feed forward neural networks, IEEE Transactions on Signal Processing, January 1992, 40, (1), pp 202–210.Google Scholar
13. Lee, C.C, Chung, P.C., Tsai, J.R. and Chang, C.I.. Robust radial basis function neural networks, IEEE Transactions on System, Man, and Cybernetics-Part B, December 1999, 29, (6), pp 674–685.Google Scholar
14. Saha, A., Wu, C.L. and Tang, D.S.. Approximation, dimension reduction and nonconvex optimization using linear superposition of Gaussians, IEEE Transactions on Computers, 1993, 42, pp 1222–1233.Google Scholar
15. Yingwei, L., Sundararajan, N. and Saratchandran, P.. A sequential learning scheme for function approximation using minimal radial basic function neural networks, Neural Computation, 1997, 9, pp 461–478.Google Scholar
16. Yingwei, L., Sundararajan, N. and Saratchandran, P.. Performance evaluation of a sequential minimal radial basic function (RBF) neural network learning algorithm, IEEE Transaction on Neural Networks, 1998, 9, (2), pp 308–318.Google Scholar
17. Peng, H., Ozaki, T., Haggan, V. and Toyoda, Y.. A parameter optimization method for radial basis function type models, IEEE Transaction on Neural Networks, March 2003, 14, (2), pp 432–438.Google Scholar
18. Ozaki, T., Sosa, P.V. and Haggan-Ozaki, V.. Reconstructing the nonlinear dynamics of epilepsy data using nonlinear time series analysis, J Signal Processing, 1999, 3, (3), pp 153–162.Google Scholar
19. Hamel, P.G and Jategaonkar, R.V., The evolution of flight vehicle system identification AGARD, 8-10 May 1995, DLR Germany.Google Scholar
20. Ghosh, A.K.. Aircraft Parameter Estimation from Flight Data using Feed Forward Neural Networks, 1998, Ph.D dissertation, Aerospace Department, Indian Institute of Technology, Kanpur, India.Google Scholar
21. Singh, S. and Ghosh, A.K.. Parameter estimation from flight data of a missile using maximum likelihood and neural network method, August 2006, AIAA Atmospheric Flight Mechanics Conference and Exhibition, Keystone, CO.Google Scholar
22. Jategaonkar, R.V., Identification of the aerodynamic model of the DLR research aircraft ATTAS from flight test data DLR, September 1990, DLR-FB 90-40, Braunschweig, Germany.Google Scholar