Self-learning controller for the compensation of periodic disturbances in continuous processing plants

In this paper, a new approach for the compensation of unknown periodic disturbances by means of a neural network is presented. The neural network learns an optimal compensation signal, such that the effect of the disturbance becomes zero. This signal supports the existing conventional controller; the neural network compensates the disturbance without redesigning existing control loops. Exemplified by the compensation of eccentricities of the unwinder of a continuous processing plant, the self-learning controller is explained and simulation results are shown. The main benefit of the presented method in industrial applications is the capability to augment the production speed and to improve the product quality.