Simulated flight control using a hybrid neural network/genetic algorithm architecture

Author

Langley, A.M. ; Barton, S.A. ; Markov, A.B.

Author_Institution

Atlantis Aerosp. Corp., Brampton, Ont., Canada

fYear

1995

fDate

23-25 May 1995

Firstpage

150

Lastpage

154

Abstract

A controller for an agile, high-subsonic autonomous flight vehicle, incorporating neural network and genetic algorithm techniques, is presented. Simulated flight results for nominal and off-nominal vehicle configurations are reported. The results show that an inverse dynamic model neural network can offer better tracking performance and greater robustness than a conventional linear controller. However, the genetic algorithm technique employed here was found to offer no significant improvement in controller performance

Keywords

aerospace control; aerospace simulation; genetic algorithms; neural net architecture; neural nets; autonomous flight vehicle; controller; hybrid neural network; hybrid neural network/genetic algorithm architecture; inverse dynamic model neural network; linear controller; robustness; simulated flight; simulated flight control; vehicle configurations; Adaptive control; Aerospace control; Aerospace simulation; Control systems; Genetic algorithms; Medical simulation; Mobile robots; Neural networks; Programmable control; Remotely operated vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronic Technology Directions to the Year 2000, 1995. Proceedings.

Conference_Location

Adelaide, SA

Print_ISBN

0-8186-7085-1

Type

conf

DOI

10.1109/ETD.1995.403478

Filename

403478