Modification of sliding mode controller by neural network with application to a flexible-link

In this paper, the performance of a free chattering sliding mode controller has been modified by neural network in order to decrease the consumption of energy. In other word, the final goal is to decrease the switching part of the control signal to the lowest level such that under this condition the system states converge to the sliding surface. The designed controller is applied to a flexible-link to control the endpoint position. The flexible-link has one degree of freedom and rotates in horizontal plane. The dynamic model was obtained from an experimental setup. Simulation results reveal the effectiveness of the proposed approach.