Abstract: A method for modeling a paper winding device, particularly for modeling a tambour drum cutter. Influencing and control quantities are determined at a real paper winding device and are stored dependent on time. Said quantities are used to determine the web strength depending on the wound number of layers or, respectively, or a correlative quantity is used as a target quantity along with the other relevant control and influencing quantities to enable a neural network to be trained as a model for a nip (Ni) for this winding device. New data for training the network can be continually obtained during the operation of the arrangement, thereby improving the model. Optimal control parameters can be determined for various production requirements by means of an iterative process dependent on the winding quality, which can also be determined from the web strength.

Abstract: When winding a paper web, in order to achieve a constant reeling layer thickness, which represents a significant quality parameter in the production process of paper, the line force or the web tension of the paper is corrected as an influencing force. Using measurements, the relationship between force and layer thickness is determined and used to set a controller. In winding devices, winding from the parent reel generally takes place on a winding station, so that the invention makes use of the relationship between the winding and unwinding operation to the effect that the change in the layer thickness is measured and these measured values are used to train a predictor. In continuous operation, in order to regulate a paper winding device, a measured variable which can be registered is measured, and this measured variable is used to determine the layer thickness change or another correlated quality parameter.