DocumentCode :
583621
Title :
Neural Network controller for two-degree-freedom helicopter control system
Author :
Rahman, Ribhan Zafira Abdul ; Shoumy, Nusrat Jahan
Author_Institution :
Dept. of Electr. Eng., Univ. Putra Malaysia, Serdang, Malaysia
fYear :
2012
fDate :
17-21 Oct. 2012
Firstpage :
101
Lastpage :
106
Abstract :
Now a day automatic flight control is a crucial issue especially for emergency services. One of the fittest candidates for such services is two-degree-freedom (2DOF) helicopter. Automatic control features of 2-DOF helicopter are usually approximated using the linear quadratic regulator (LQR), which can be further enhanced in-terms of Neural Network (NN). Hence, this paper presents the nonlinear flight control of 2DOF helicopter using NN. A back propagation, feed forward NN model is developer and employed to approximate the nonlinear control features of 2DOF helicopter using Matlab software. The effectiveness of the basic 2DOF helicopter NN controller is apparent (~ 2% pitch and 14% yaw improvement) compared to the conventional (LQR) methods.
Keywords :
aircraft control; backpropagation; control engineering computing; feedforward neural nets; helicopters; linear quadratic control; neurocontrollers; nonlinear control systems; 2DOF helicopter; LQR; Matlab software; automatic flight control; backpropagation; emergency services; feedforward NN model; linear quadratic regulator; neural network controller; nonlinear control feature; nonlinear flight control; two-degree-freedom helicopter control; Artificial neural networks; Control systems; Helicopters; MATLAB; Mathematical model; Nonlinear dynamical systems; 2-DOF; Neural Network;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control, Automation and Systems (ICCAS), 2012 12th International Conference on
Conference_Location :
JeJu Island
Print_ISBN :
978-1-4673-2247-8
Type :
conf
Filename :
6393412
Link To Document :
بازگشت