The objective of this paper is to present results from the evaluation of a direct adaptive tracking controller. The control architecture employs both pre-trained and an on-line neural networks to represent the non-linear aircraft dynamics in the model inversion portion of the controller. The aircraft model used for this evaluation is representative of the F-15 Advanced Control Technology for Integrated Vehicles (ACTIVE) aircraft. The controller was evaluated for three cases: (1) nominal conditions; (2) loss of control power; and (3) loss of control power in the presence of atmospheric turbulence. The results were compared with the existing F-15 ACTIVE conventional mode controller in all cases. The results indicate extremely desirable airframe stabilization characteristics for case (1) that do not degrade significantly for case (2) or (3) as does the conventional mode controller. It was concluded that this controller exhibits both stable and robust adaptive characteristics when subjected to mild and extreme loss of control power conditions. Integration of this neural adaptive flight controller into the full non-linear six degree-of-freedom F-15 ACTIVE simulation is recommended for evaluation in a real-time high fidelity piloted simulation environment.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Evaluation of a Neural Adaptive Flight Controller


    Contributors:

    Conference:

    AIAA Guidance, Navigation and Control Conference ; 1997 ; New Orleans, LA, United States


    Publication date :

    1997-01-01


    Type of media :

    Conference paper


    Type of material :

    No indication


    Language :

    English




    Simulation Evaluation of a Neural-Based Flight Controller

    Totah, J. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 1996


    Direct Adaptive Neural Flight Controller for F-8 Fighter Aircraft

    S Suresh / S N Omkar / V Mani et al. | AIAA | 2006