Open AccessDesign and Experimental Verification of a Multirotor Aircraft with fuzzy neural network controller
Author(s) -
Di Li,
Shu Kun
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1939/1/012092
Subject(s) - multirotor , control theory (sociology) , thrust , controller (irrigation) , underactuation , rotor (electric) , flight dynamics , computer science , artificial neural network , fuzzy logic , tilt (camera) , engineering , control engineering , aerodynamics , aerospace engineering , control (management) , artificial intelligence , mechanical engineering , agronomy , biology
Conventional multirotor aircrafts are underactuated, while the translational and rotational motions are strongly coupled. These features severely limit the maneuverability of the aircraft. Therefore, a multi-rotor aircraft is designed, which can perform omnidirectional motion, vector thrust control flight and tilt-hovering. In addition, an fuzzy nerual network controller is designed. And the aircraft demonstrates a higher fault tolerance than the conventional ones. Finally, the experimental results show that the aircraft has a higher maneuverability than the conventional quadrotors.