Pregled bibliografske jedinice broj: 120879
Neural Network Based Sliding Mode Controller for a Class of Linear Systems with Unmatched Uncertainties
Neural Network Based Sliding Mode Controller for a Class of Linear Systems with Unmatched Uncertainties // CD-ROM Proceedings of IEEE 41st Conference on Decision and Control, CDC'02.
Las Vegas (NV), 2002. str. 967-972 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 120879 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Neural Network Based Sliding Mode Controller for a Class of Linear Systems with Unmatched Uncertainties
Autori
Barić, Miroslav ; Petrović, Ivan ; Perić, Nedjeljko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
CD-ROM Proceedings of IEEE 41st Conference on Decision and Control, CDC'02.
/ - Las Vegas (NV), 2002, 967-972
Skup
IEEE 41st Conference on Decision and Control, CDC'02.
Mjesto i datum
Las Vegas (NV), Sjedinjene Američke Države, 10.12.2002. - 13.12.2002
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Sliding mode control; neural network; unmatched uncertainities; backstepping
Sažetak
This paper considers the application of a neural network for the performance improvement of the sliding mode controller for a class of linear systems with unmatched uncertainties/disturbances. Neural network is employed for the on-line estimation of the uncertainties using simple gradient descent learning algorithm. The combination of the sliding mode and backstepping like recursive control design is used to achieve the desired tracking performance. The algorithm is verified through computer simulations.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
