Friction compensation of gantry crane model based on the B-spline neural compensator (CROSBI ID 567349)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Matuško, Jadranko ; Kolonić, Fetah ; Ileš, Šandor ; Slutej, Alojz
engleski
Friction compensation of gantry crane model based on the B-spline neural compensator
Fast and accurate positioning and swing min- imization of the containers and other loads in crane ma- nipulation are demanding and in the same time conflict- ing tasks. For accurate positioning, the main problem is nonlinear friction compensation, especially in the low speed region. In this paper authors propose position controller realized as hybrid controller. It consists of the conventional linear state feedback controller with additional friction self- learning neural compensator in the feedforwad loop. Self- learning compensator is based on the B- spline artificial neural network which consists of the one hidden layer of the B-spline second order functions. The experimental results show that friction compensator is able to remove position error in steady state.
Single Pendulum Gantry; Neural Network; Friction Compensation; B-spline network; on-line network learning.
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
180-186.
2010.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of 14th International Power Electronics and Motion Control Conference, EPE-PEMC 2010, 6-8 September 2010, Ohrid, Republic of Macedonia
Skopje: Faculty of Electrical Engineering and Information Technologies, Skopje
978-1-4244-7854-5
Podaci o skupu
14th International Power Electronics and Motion Control Conference, EPE-PEMC 2010
poster
06.09.2010-08.09.2010
Skopje, Sjeverna Makedonija