In recent years, aircraft accidents have especially increased on concorde aircrafts. Due to the aircrafts going out of control, many people have lost their lives. Neural network controllers can be accepted as an alternative to control this kind of plane. In this study, a neural network control system was employed to control the nose angle of supersonic concorde aircrafts. The designed model reference adaptive neural controller is a feedforward multilayered perceptron structure. Backpropagation algorithm was utilized to update weights of the neural controller. For comparison, standard proportional-integral-derivate control system was also used with empirically selected gain parameters. Consequently, between the two approaches, the neural networks have a superior performance in the control of such aircrafts.
Design of neural controller system for concorde aircrafts
Automatic Control and Computer Sciences ; 38 , 3 ; 45-54
2004
10 Seiten, 14 Quellen
Article (Journal)
English
European Patent Office | 2017
European Patent Office | 2016
|SLUB | 2009
|British Library Conference Proceedings | 2002
|Neural network-based dynamic inversion controller for fighter aircrafts
Tema Archive | 2009
|