Abstract
This paper presents a Neuro-Based Adaptive Control (NBAC) for torque control of a flexible beam with structural uncertainties. In the NBAC scheme, a neural network is connected in parallel with a linearized plant model, so that the neural network can be expected to identify the uncertainties included in the controlled plant. At the same time, the neural network works as an adaptive controller that can compensate effects of the unknown part of the plant. In this paper, the NBAC is applied to a torque control of a flexible beam that includes linear and nonlinear structural uncertainties caused by a contact force, a frictional force, shape and material of the beam, and so on. The comparison of the experimental results under the NBAC and other control methods illustrates the effectiveness and applicability of the NBAC.
