Abstract

This thesis presents an intelligent strategy for controlling the tip position of a flexible-link manipulator. Motivated by the well-known inverse dynamics control approach for rigid-link manipulators, two multi-layer feedforward neural networks are developed to learn the nonlinearities of the system dynamics. The re-defined output scheme is used by feeding back this output to guarantee the minimum phase behavior of the resulting closed-loop system. No a priori knowledge about the nonlinearities of the system is needed where the payload mass is also assumed to be unknown. The weights of the networks are adjusted using a modified on-line error backpropagation algorithm that is based on the propagation of the redefined output error, derivative of this error and the tip deflection of the manipulator. Numerical simulations as well as real-time controller implementation on an experimental setup are carried out. The results achieved by the proposed neural network-based controller are compared in simulations and experimentally with conventional PD-type and inverse dynamics controls to substantiate and demonstrate the advantages and the promising potentials of this scheme.