| Summary: | 碩士 === 國立臺灣海洋大學 === 導航與通訊系 === 92 === In a flight, take-off and landing are the most difficult operations in regard to safety issues. Airplane pilots must not only be acquainted with the operation of instrument boards, but also need flight sensitivity to the ever-changing environment, especially in landing phase when turbulence is encountered. The Automatic Landing system (ALS) can help to alleviate the pilot’s work during landing process but with limited conditions. Conventional flight controllers usually utilize gain-scheduling techniques, if the landing environment is beyond predefined conditions the ALS must disable and the pilot has to operate the aircraft manually. To improve the controller of the ALS this research uses a neural network called RAN, which can grow the hidden units automatically, and uses a real-valued genetic algorithm to search the control gains of the pitch autopilot. The proposed intelligent controller can enable the airplane to adapt to more extensive turbulences and guide the airplane to a safe landing. In addition, the Simulink and VisSim softwares, which have the property of dynamical simulation, are used to construct the flight control system. Since these softwares have graphical user interface the control system can easily be expanded by adding new modules. Environmental influences to the airplane can be observed through the visual flight simulation model. This paper also utilizes the VisSim/ TI C2000 Rapid Prototyper to develop an embedded control system that uses a fixed-point DSP controller. Thus realization of on-line real-time control can be achieved.
|
|---|
