utation of the Equivalent ontrol in Sliding Made For Ro Trajectory Control Applications

In the application of Sliding Mode Controllers, the main problem which is encountered is that a whole knowledge of the system dynamics (or inverse dynamics) and the system parameters is required to be able to compute the equivalent control. This is actually vely rare in practice. In this paper, a feed-forward neural network is proposed to compute the equivalent control. The weights of the net are updated such that the additional control term of the sliding mode goes to zero. Experimental studies carried out on a direct drive arm indicate that the proposed approach is a good candidate for trajectory control applications.