Ph.D. Dissertation Defense by
Monday, November 14, 2005
(Dr. Nader Sadegh, Chair)
"Neural Network Based Adaptive Control for Nonlinear Dynamic Regimes "
Adaptive control designs using neural networks (NNs) based on dynamic inversion are investigated for aerospace vehicles which are operated at highly nonlinear dynamic regimes. NNs play a key role as the principal element of adaptation to approximately cancel the effect of inversion error, which subsequently improves robustness to parametric uncertainty and unmodeled dynamics in nonlinear regimes.
An adaptive control scheme previously named 'composite model reference adaptive control' is further developed so that it can be applied to multi-input multi-output output feedback dynamic inversion. I can have adaptive elements in both the dynamic compensator (linear controller) part and/or the conventional adaptive controller part, utilizing also state estimation information for NN adaptation. This methodology has more flexibility and thus hopefully greater potential than conventional adaptive designs for adaptive flight control in highly nonlinear flight regiemes. The stability of the control system is proved through Lyapunov theorems, and validated with simulations.
The control designs in this thesis also include the use of 'pseudo control hedging' techniques which are introduced to prevent the NN adaptive element from attempting to adapt to various actuation nonlinearities such as actuator position and rate saturations. Control allocation is also introduced for the case of redundant control effectors including thrust vector nozzles. A thorough comparison study of conventional and NN-based adaptive designs for a system under a limit cycle at nonlinear dynamic regime is included in this research, and the NN based adaptive control designs demonstrate their adaptive performances for two highly maneuverable aerial vehicles, F-15 ACTIVE and FQM-117B UAV, operated under various nonlinearities and uncertainties at nonlinear dynamic regimes.