Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller

URAN, Suzana ;ŠAFARIČ, Riko .
Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 58, n.2, p. 93-101, june 2018. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/>. Date accessed: 22 dec. 2024. 
doi:http://dx.doi.org/10.5545/sv-jme.2011.098.

Uran, S., & Šafarič, R.
(2012).
Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller.
Strojniški vestnik - Journal of Mechanical Engineering, 58(2), 93-101.
doi:http://dx.doi.org/10.5545/sv-jme.2011.098

@article{sv-jmesv-jme.2011.098,
	author = {Suzana  Uran and Riko  Šafarič},
	title = {Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {58},
	number = {2},
	year = {2012},
	keywords = {sliding-mode adaptive controller; neural-network; robot},
	abstract = {The Lyapunov based theoretical development of a neural-network sliding-mode based estimation of highly non-linear and variable robot plant for a direct-drive robot controller is shown in the paper. Derived adaptive control law was tested for four types of robot neuralnetwork sliding-mode controllers: centralized, simplified centralized, decentralized and simplified decentralized, which were verified on a real laboratory direct-drive 3 D.O.F. PUMA like mechanism. Centralized and decentralized control approaches estimate only a part of the variable robot dynamic model (torque model due to friction, Coriolis, centripetal and centrifugal forces) and use only the part of a dynamic plant model (the so called estimated inertia matrix M). Both simplified methods do not need any plant model parameter for an accurate estimation of the direct-drive robot plant, but need some more time to learn dynamic model parameters. All four types of the neural network continuous slidingmode controllers were successfully tested for algorithm’s adaptation capability for sudden changes in the manipulator dynamics (load).},
	issn = {0039-2480},	pages = {93-101},	doi = {10.5545/sv-jme.2011.098},
	url = {https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/}
}

Uran, S.,Šafarič, R.
2012 June 58. Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 58:2

%A Uran, Suzana 
%A Šafarič, Riko 
%D 2012
%T Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller
%B 2012
%9 sliding-mode adaptive controller; neural-network; robot
%! Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller
%K sliding-mode adaptive controller; neural-network; robot
%X The Lyapunov based theoretical development of a neural-network sliding-mode based estimation of highly non-linear and variable robot plant for a direct-drive robot controller is shown in the paper. Derived adaptive control law was tested for four types of robot neuralnetwork sliding-mode controllers: centralized, simplified centralized, decentralized and simplified decentralized, which were verified on a real laboratory direct-drive 3 D.O.F. PUMA like mechanism. Centralized and decentralized control approaches estimate only a part of the variable robot dynamic model (torque model due to friction, Coriolis, centripetal and centrifugal forces) and use only the part of a dynamic plant model (the so called estimated inertia matrix M). Both simplified methods do not need any plant model parameter for an accurate estimation of the direct-drive robot plant, but need some more time to learn dynamic model parameters. All four types of the neural network continuous slidingmode controllers were successfully tested for algorithm’s adaptation capability for sudden changes in the manipulator dynamics (load).
%U https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/
%0 Journal Article
%R 10.5545/sv-jme.2011.098
%& 93
%P 9
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 58
%N 2
%@ 0039-2480
%8 2018-06-28
%7 2018-06-28

Uran, Suzana, & Riko  Šafarič.
"Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller." Strojniški vestnik - Journal of Mechanical Engineering [Online], 58.2 (2012): 93-101. Web.  22 Dec. 2024

TY  - JOUR
AU  - Uran, Suzana 
AU  - Šafarič, Riko 
PY  - 2012
TI  - Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2011.098
KW  - sliding-mode adaptive controller; neural-network; robot
N2  - The Lyapunov based theoretical development of a neural-network sliding-mode based estimation of highly non-linear and variable robot plant for a direct-drive robot controller is shown in the paper. Derived adaptive control law was tested for four types of robot neuralnetwork sliding-mode controllers: centralized, simplified centralized, decentralized and simplified decentralized, which were verified on a real laboratory direct-drive 3 D.O.F. PUMA like mechanism. Centralized and decentralized control approaches estimate only a part of the variable robot dynamic model (torque model due to friction, Coriolis, centripetal and centrifugal forces) and use only the part of a dynamic plant model (the so called estimated inertia matrix M). Both simplified methods do not need any plant model parameter for an accurate estimation of the direct-drive robot plant, but need some more time to learn dynamic model parameters. All four types of the neural network continuous slidingmode controllers were successfully tested for algorithm’s adaptation capability for sudden changes in the manipulator dynamics (load).
UR  - https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/

@article{{sv-jme}{sv-jme.2011.098},
	author = {Uran, S., Šafarič, R.},
	title = {Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {58},
	number = {2},
	year = {2012},
	doi = {10.5545/sv-jme.2011.098},
	url = {https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/}
}

TY  - JOUR
AU  - Uran, Suzana 
AU  - Šafarič, Riko 
PY  - 2018/06/28
TI  - Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 58, No 2 (2012): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2011.098
KW  - sliding-mode adaptive controller, neural-network, robot
N2  - The Lyapunov based theoretical development of a neural-network sliding-mode based estimation of highly non-linear and variable robot plant for a direct-drive robot controller is shown in the paper. Derived adaptive control law was tested for four types of robot neuralnetwork sliding-mode controllers: centralized, simplified centralized, decentralized and simplified decentralized, which were verified on a real laboratory direct-drive 3 D.O.F. PUMA like mechanism. Centralized and decentralized control approaches estimate only a part of the variable robot dynamic model (torque model due to friction, Coriolis, centripetal and centrifugal forces) and use only the part of a dynamic plant model (the so called estimated inertia matrix M). Both simplified methods do not need any plant model parameter for an accurate estimation of the direct-drive robot plant, but need some more time to learn dynamic model parameters. All four types of the neural network continuous slidingmode controllers were successfully tested for algorithm’s adaptation capability for sudden changes in the manipulator dynamics (load).
UR  - https://www.sv-jme.eu/article/neural-network-estimation-of-the-variable-plant-for-adaptive-sliding-mode-controller/

Uran, Suzana, AND Šafarič, Riko.
"Neural-Network Estimation of the Variable Plant for Adaptive Sliding-Mode Controller" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 58 Number 2 (28 June 2018)