PROJECT TITLE :

Robust GRBF Static Neurocontroller With Switch Logic for Control of Robot Manipulators

ABSTRACT:

A new Gaussian radial basis operate static neurocontroller is presented for stable adaptive tracking control. This can be a two-stage controller acting during a supervisory fashion by means of a switch logic and allowing arbitration between a neural network (NN) and a robust proportional-derivative controller. The structure is meant to cut back the results of the curse of dimensionality in multidimensional systems by fully exploiting the mechanical properties of the robot manipulator. A new factorization of the Coriolis/centripetal matrix is used, resulting in an NN model that's a lot of smaller than the dynamic ones. By resorting to the extended multivariate Shannon theorem and the computation of the effective bandwidth of the revolute robot manipulators, the network parameters are tuned. Stability and convergence properties are analyzed. This provides the assurance of reliability and effectiveness to create such controller viable. A robot manipulator with 2 degrees of freedom is used to check the adaptive options of the neural control algorithm. Finally, the effectiveness of the proposed method is compared to the nonadaptive case.