TY - GEN
T1 - Application of neural network dynamic inversion control arithmetic
AU - Guang-Lin, He
AU - Guo-Hui, Wu
AU - Li, Lao
AU - Jing, Chen
PY - 2009
Y1 - 2009
N2 - The MAV is very little, so it is easily disturbed by the environment and has week stability. Due to its low Reynolds number, it is easy to be affected by the unstable air (turbulence and gusts), and other outside interference. Recent work in dynamic inversion with neural network may be applied to control a MAV where the reference commands include position, velocity, attitude and angular rate. This control technology can provide the MAV with an admirably command follow and steady control capability. Neural networks are used directly as the controller as well as indirect designs that are based on a neural network process model. The emulator is compiled by using neural network toolbox in MATLAB. Then the main result of this simulation is presented. It indicates that the method has high precision and strong stability, which can serve the control of MAV. Thereafter, an amendment about controlling system with dynamic inversion of the MAV is described.
AB - The MAV is very little, so it is easily disturbed by the environment and has week stability. Due to its low Reynolds number, it is easy to be affected by the unstable air (turbulence and gusts), and other outside interference. Recent work in dynamic inversion with neural network may be applied to control a MAV where the reference commands include position, velocity, attitude and angular rate. This control technology can provide the MAV with an admirably command follow and steady control capability. Neural networks are used directly as the controller as well as indirect designs that are based on a neural network process model. The emulator is compiled by using neural network toolbox in MATLAB. Then the main result of this simulation is presented. It indicates that the method has high precision and strong stability, which can serve the control of MAV. Thereafter, an amendment about controlling system with dynamic inversion of the MAV is described.
KW - Dynamic inversion
KW - MATLAB
KW - MAV
KW - Neural network
UR - http://www.scopus.com/inward/record.url?scp=64549129592&partnerID=8YFLogxK
U2 - 10.1109/ICECT.2009.35
DO - 10.1109/ICECT.2009.35
M3 - Conference contribution
AN - SCOPUS:64549129592
SN - 9780769535593
T3 - Proceedings - 2009 International Conference on Electronic Computer Technology, ICECT 2009
SP - 507
EP - 510
BT - Proceedings - 2009 International Conference on Electronic Computer Technology, ICECT 2009
T2 - 2009 International Conference on Electronic Computer Technology, ICECT 2009
Y2 - 20 February 2009 through 22 February 2009
ER -