紀要論文 System Identification for Quad-rotor Parameters Using Neural Network

Dief, Tarek N.  ,  Yoshida, Shigeo

3 ( 1 )  , pp.6 - 11 , 2016-03 , Green Asia Education Center
ISSN:1884-6300
内容記述
This paper presents a new technique to identify the system parameters without using the system governing equations. This technique is the time series prediction using neural network. The theoretical model was applied using simulations, after that the experiments were done to get the suitable construction for the neural model. A comparison between neural network and placket’s model is discussed. The advantages and disadvantages of both models were explained. The main idea of neural network is based on back-propagation algorithm. The equations and steps for iteration are presented and the relation between changing the number of iteration with the system frequency. The controller used is pole placement controller based on the neural network results as a system model.
本文を読む

http://catalog.lib.kyushu-u.ac.jp/handle/2324/1657380/p006.pdf

このアイテムのアクセス数:  回

その他の情報