TY - GEN
T1 - ADRC Based on Artificial Neural Network for a Six-rotor UAV
AU - Xi, Lin
AU - Shao, Yunfeng
AU - Zou, Suli
AU - Ma, Zhongjing
N1 - Publisher Copyright:
© 2021 Technical Committee on Control Theory, Chinese Association of Automation.
PY - 2021/7/26
Y1 - 2021/7/26
N2 - An on-line intelligent optimization method based on an artificial neural network is proposed for the parameter adjustment of the active disturbance rejection controller. And a cascaded ADRC controller including the artificial neural network attitude ADRC is investigated for trajectory tracking of the six-rotor UAV. First, establish the kinematics and dynamics model of the six-rotor, and design a cascaded active disturbance rejection controller for the six-rotor to deal with the non-linear disturbance problem in flight. Secondly, an artificial neural network is designed to optimize the parameters of the attitude ADRC controller on-line, and the particle swarm algorithm is used to set the initial value of the artificial neural network. Finally, the simulation results demonstrated that ADRC based on the artificial neural network can effectively resist the disturbances and enhance the robustness of the attitude controller and the cascade ADRC controller based on the artificial neural network can track the reference trajectory quickly and accurately.
AB - An on-line intelligent optimization method based on an artificial neural network is proposed for the parameter adjustment of the active disturbance rejection controller. And a cascaded ADRC controller including the artificial neural network attitude ADRC is investigated for trajectory tracking of the six-rotor UAV. First, establish the kinematics and dynamics model of the six-rotor, and design a cascaded active disturbance rejection controller for the six-rotor to deal with the non-linear disturbance problem in flight. Secondly, an artificial neural network is designed to optimize the parameters of the attitude ADRC controller on-line, and the particle swarm algorithm is used to set the initial value of the artificial neural network. Finally, the simulation results demonstrated that ADRC based on the artificial neural network can effectively resist the disturbances and enhance the robustness of the attitude controller and the cascade ADRC controller based on the artificial neural network can track the reference trajectory quickly and accurately.
KW - active disturbance rejection control
KW - artificial neural network
KW - particle swarm optimization algorithm
UR - http://www.scopus.com/inward/record.url?scp=85117349183&partnerID=8YFLogxK
U2 - 10.23919/CCC52363.2021.9549308
DO - 10.23919/CCC52363.2021.9549308
M3 - Conference contribution
AN - SCOPUS:85117349183
T3 - Chinese Control Conference, CCC
SP - 7809
EP - 7815
BT - Proceedings of the 40th Chinese Control Conference, CCC 2021
A2 - Peng, Chen
A2 - Sun, Jian
PB - IEEE Computer Society
T2 - 40th Chinese Control Conference, CCC 2021
Y2 - 26 July 2021 through 28 July 2021
ER -