Pregled bibliografske jedinice broj: 518904
Tensor Product Based Control of the Single Pendulum Gantry Process with Stable Neural Network Based Friction Compensation
Tensor Product Based Control of the Single Pendulum Gantry Process with Stable Neural Network Based Friction Compensation // Proceedings of the 2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
Budimpešta, 2011. str. 1010-1015 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 518904 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Tensor Product Based Control of the Single Pendulum Gantry Process with Stable Neural Network Based Friction Compensation
Autori
Matuško, Jadranko ; Lešić, Vinko ; Kolonić, Fetah ; Ileš, Šandor
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
/ - Budimpešta, 2011, 1010-1015
ISBN
978-1-4577-0837-4
Skup
2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM2011)
Mjesto i datum
Budimpešta, Mađarska, 03.07.2011. - 07.07.2011
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Single Pendulum Gantry; Neural Network; Friction
(Single Pendulum Gantry; Neural Network; Friction Compensation; RBFnetwork; on-line network learning)
Sažetak
Fast and accurate positioning and swing miminimization of the containers and other loads in crane manipulation are demanding and in the same time conflicting tasks. For accurate positioning, the main problem is nonlinear friction effect, especially in the low speed region. In this paper authors propose position controller realized as hybrid controller. It consists of the tensor product based nonlinear feedback controller with additional friction self- learning neural compensator. The experimental results show that friction compensator is able to remove position error in steady state.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Strojarstvo, Tehnologija prometa i transport
POVEZANOST RADA
Projekti:
036-0363078-1629 - Upravljanje složenim elektromehaničkim sustavima za manipulacije u transportu (Kolonić, Fetah, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb