In this paper, we focus on the transition control of a ducted fan vertical takeoff and landing (VTOL) unmanned aerial vehicle (UAV). To achieve a steady transition from hover to high-speed flight, a neural-networks-based controller is proposed to learn the system dynamics and compensate for the tracking error between the aircraft dynamics and the desired dynamic performance. In prior, we derive the nonlinear system model of the aircraft full-envelope dynamics. Then, we propose a novel neural-networks-based control scheme and apply it on the underactuated aircraft system. Key features of the proposed controller consist of projection operator, state predictor and dynamic-formed adaptive input. It is proved and guaranteed that the tracking errors of both state predictor and neural-networks weights are upper bounded during the whole neural-networks learning procedure. The very adaptive input is formed into a dynamic structure that helps achieve a reliable fast convergence performance of the proposed controller, especially in highfrequency disturbance conditions. Consequently, the closed-loop system of the aircraft is able to track a certain trajectory with desired dynamic performance. Satisfactory results are obtained from both simulations and practical flight test in accomplishing the designed flight course. INDEX TERMS Ducted fan, fast convergence, high-speed flight, neural networks, transition control, unmanned aerial vehicle (UAV).

No abstract

No abstract

The sea breeze is a low‐frequency disturbance that severely damages the stability of small unmanned helicopters operating over the sea, especially for the yaw control, which is highly sensitive to disturbance. General internal model control is an appropriate method for dealing with this kind of operation conditions, whereas conventional internal model control cannot eliminate the tracking errors between a nominal model and a real model. In coping with unknown dynamics and low‐frequency gust disturbances for small helicopters, this paper proposes a novel robust controller constructed with system identification and integrator‐based improved general internal model. As a refinement of the conventional frame, the proposed control scheme extends the applicable scope of a controlled plant from a priori known dynamic to an unknown dynamic. Furthermore, under the proposed controller, it is guaranteed that the tracking error between the actual model and the nominal model converges to zero asymptotically. Finally, the effectiveness and advantage of the proposed control scheme are verified through comparative practical flight tests.

No abstract