This research aims at proposing an intelligent flight control system which makes unmanned aerial vehicles tolerant of actuator faults. The proposed system can detect, identify and accommodate the faults automatically. To make the unmanned system downsizing and low-cost, this study focuses on keeping the redundancy by software approach. The purpose of this study is to establish the systematic learning-based design method of control system with the evaluation function based on control purpose. The proposed technique adds to normal flight control system (Navigation, Guidance, and Control) with detection, identification, and accommodation mechanisms. Each mechanism consists of neural network. In this study, the availability of the proposed system is verified by sixdegree-of-freedom nonlinear simulation. In the simulation, it was assumed that an unmanned aerial vehicle is in steady flight and the elevon fault (lock-in-place) is happened. Under various conditions, the proposed technique can evaluate the flight condition and decouple the broken actuator and generate a new flight path. Then, it can achieve the stable flight in spite of the actuator fault.
|ジャーナル||Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C|
|号||756 PART C|
|出版ステータス||Published - 2009|
ASJC Scopus subject areas