Fault Detection Design for RUAV with an Adaptive Threshold Neural-Network Scheme

This paper describes recent research on system design of a small-scaled rotorcraft UAV (RUAV) system and a control scheme for model-scaled helicopter. The small-scaled UAV helicopter is to be designed as a test bed for the implementation of new nonlinear control theories. The full system has been tested successfully in the manual operation and obtained useful data, which is to be analyzed and used in identifying the RUAV model and design advanced control technologies. A control methodology for helicopter autopilot, which is based on nonlinear dynamic equations with a simplified thrust-torque generation model valid for hovering and non-aggressive flights, is presented.