Sage Journals: Discover world-class research

Abstract

The aim of this article is to determine the mathematical model between control deflections and structural deflections in an F/A-18 modified aircraft in the active aeroelastic wing programme. One future application would be the design of a flutter suppression model based on flight flutter tests. Five excited sources were provided by NASA Dryden Flight Research Center from flight flutter tests. These excitations, given by aircraft control surfaces, are: differential and collective ailerons, collective and differential stabilizers, and rudders. The neural network and fuzzy logic algorithms were chosen in order to identify the multi-input multi-output system for the F/A-18 aircraft. One main contribution of this article is the mapping of fuzzy logic algorithm results into neural network data. Then, these methods were applied for the F/A-18 model identification and validation for sixteen flight conditions expressed in terms of Mach numbers variations between 0.85 and 1.30 and altitudes varying between 5000 and 25 000 ft. Accurate results were obtained, expressed in terms of fit coefficients between estimated and measured signals greater than 99 per cent, which allows one to conclude that these new methodologies are very efficient for an aircraft identification and validation.

Keywords

fuzzy logic neural network model identification flight tests

Get full access to this article

View all access options for this article.

References

Ahmed-Zaid

Ioannou

P. A.

Polycarpou

M. M.

Youssef

H. M.

Identification and control of aircraft dynamics using radial basis function networks. In Proceedings of the IEEE International Conference on Control applications. Vancouver, Canada, 1993, 2. 567–572.

De Weerdt

Chu

Q. P.

Mulder

J. A.

Neural networks aerodynamic model identification for aerospace reconfiguration. In Proceedings of the AIAA Guidance, Navigation and Control Conference. San Francisco, California, USA, 2005, 8. 5962–5991.

Suresh

Kannan

Omkar

S. N.

Mani

Time bounded neural network command 2004-773 control design for unstable aircraft. In Proceedings of the 42nd AIAA Aerospace Sciences Meeting and Exhibit. Reno, Nevada, USA, 2004, 8884–8889.

Mehiel

E. A.

On direct model reference adaptative controller design for flexible space structure, 2003, PhD, University of Colorado (Boulder, 217–217.

Castravete

S. C.

Nonlinear flutter of a cantilever wing including the influence of structure uncertainties, 2007, PhD, Wayne State University, 318–318.

Gujjula

Suppresion of limit cycle oscillations in an aeroelastic system using robust and adaptative control, 2004, PhD, University of Nevada (Las Vegas, 94–94.

Zink

P. S.

A methodology for robust structural design with application to active aeroelastic wing, 2001, PhD, Georgia Institute of Technology, 282–282.

Artificial intelligence methodologies for aerospace and other control systems, 1993, DSc, Washington University, 165–165.

Intelligent systems for active vibration control in flexible engineering structures, 2008, MSc, Lake head University (Canada, 135–135.

10.

De Jesus Mota

Nadeau-Beaulieu

Botez

Brenner

Modeling of structural deflections on a F/A-18 aircraft following flight flutter tests by use of subspace identification method. Proc. IMechE, Part G: J. Aerospace Engineering, 2007, 221(G5), DOI: 10.1243/09544100JAER0219, 719–731.

11.

Hagan

M. T.

Demuth

H. B.

Neural networks for control, invited tutorial. In Proceedings of the 1999 American Control Conference. San Diego, 1999, 1642–1656.

12.

Hagan

M. T.

Menhaj

Training feed-forward networks with the Marquardt algorithm. IEEE Trans. Neural Netw., 1994, 5(6), 989–989.

13.

Yang

Z. J.

Hidden-layer size reducing for multilayer neural methods using the orthogonal least-squares method. Trans. Soc. Instrum. Control Engr, 1997, 33(3), 216–223.

14.

Tagaki

Sugeno

Fuzzy identification of system and its application of modeling and control. IEEE Trans. Syst. Man Cybern., 1985, 15. 116–132.

15.

Chiu

Liu

2005, Matlab, version R2008a, MathWorks.

16.

Chiu

S. L.

A cluster estimation method with extension to fuzzy model identification. In Proceedings of the IEEE International Conference on Fuzzy system. San Diego, California, 1994.

Identification of a non-linear F/A-18 model by the use of fuzzy logic and neural network methods

Abstract

Keywords

Get full access to this article

References