A neural-network-based controller for a single-link flexible manipulator using the inverse dynamics approach

This paper presents an intelligent-based control strategy for tip position tracking control of a single-link flexible manipulator. Motivated by the we ll-known inverse dynamics control strategy for rigid-link manipulators, two feedforward neural networks (NNs) are proposed to learn the nonlinearities of the flexible arm associated with the inverse dynamics controller. The r edefined output approach is used by feeding back this output to guarantee t he minimum phase behavior of the resulting closed-loop system. No a priori knowledge about the nonlinearities of the system is needed and the payload mass is also assumed to be unknown. The network weights are adjusted using a modified online error backpropagation algorithm that is based on the prop agation of output tracking error, derivative of that error and the tip defl ection of the manipulator. The real-time controller is implemented on an ex perimental test bed. The results achieved by the proposed NN-based controll er are compared experimentally with conventional proportional-plus-derivati ve-type and standard inverse dynamics controls to substantiate and verify t he advantages of our proposed scheme and its promising potential in identif ication and control of nonlinear systems.