Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
•Neural network based hybrid force/position control of constrained reconfigurable manipulators is proposed.•RBF neural network is used to deal with the uncertainties of the system.•An adaptive compensator is used to compensate the effects of disturbances and network reconstruction error.•The system is shown to be stable utilizing Lyapunov theory.•Simulation studies are performed to show the effectiveness in a comparative manner.
This manuscript addresses the neural network-based hybrid force/position control scheme for the force and position control problem of constrained reconfigurable manipulators. The uncertainties in the dynamical model of the system are inevitable; therefore the model-based control approach is inadequate to handle these systems. Motivated by this, the authors have proposed a new hybrid control scheme for constrained reconfigurable manipulators by utilizing the available partial information about system dynamics together with the model-free approach. The inefficiency of the model-based control scheme is enhanced by using the approximation capability of the neural network. Radial basis function neural network estimates the unknown dynamics of the system. To overcome the aftereffects of neural network reconstruction error as well as the effects of friction terms and external disturbances, an adaptive compensator is added to the part of the controller. The online adaptive laws for the neural network weights and the parameter vector are used in the Lyapunov function to guarantee the system to be stable. As a result, position and force tracking errors boundedness are achieved and tracking error of the joints in all the directions converge to zero asymptotically. Finally, numerical simulation results are produced over a 2-DOF constrained reconfigurable manipulator to show the supremacy and robustness of the proposed approach in a comparative manner.