Authors:
Khedoudja Kherraz
1
;
Mustapha Hamerlain
2
and
Nouara Achour
1
Affiliations:
1
University of Sciences and Technology U.S.T.H.B, Algeria
;
2
Center of Development of Advanced Technologies (CDTA, Algeria
Keyword(s):
Robot Manipulator, Flexible Link, Sliding Mode, Neuro Fuzzy, Vibration Control, Chattering, Trajectory Control, Hybrid Control, Super Twisting Algorithm.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Fuzzy Control
;
Fuzzy Systems
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Neural Networks Based Control Systems
;
Soft Computing
Abstract:
In most robotic applications, trajectory tracking control and vibration suppression in flexible link manipulator is a recurring problem, due to the unknown nonlinearities and strong coupling often caused by the presence of flexibility in the links. In order to solve this problem, a new sliding mode controller using neural networks and fuzzy logic is presented in this paper. The stability of the proposed controller is proved with the Lyapunov function method. The neural network is used to compensate the highly nonlinear system uncertainties. The fuzzy logic is used to eliminate the chattering effect caused by the robust conventional sliding mode control. The effectiveness of this control system will be compared to the performance obtained with a second order sliding mode control which is the super twisting algorithm. Comparative simulations show the superiority of the proposed controller regarding the second order sliding mode controller and confirm its robustness with bounded disturb
ance and its ability to suppress the flexible link manipulator vibrations.
(More)