Abstract: The present invention relates to a roller device for treating sheet-form material, in particular for smoothing films (F*) or sheets, comprising a first roller unit 1 and a second roller unit 2, wherein each roller unit (1, 2) comprises: at least one drive motor with a motor moment of inertia JM, a roller (10, 20) with a roller moment of inertia JW, and at least one gear for the kinematic coupling of the roller (10, 20) to the at least one drive motor with a transmission ratio iMW between the at least one drive motor and the roller (10, 20), wherein the roller (20) of the second roller unit (2) is rotatable in the opposite direction to the roller (10) of the first roller unit (1), and wherein there is formed between the roller (10) of the first roller unit (1) and the roller (20) of the second roller unit (2) a first roller gap (40) through which the sheet-form material (F) is guided.

Abstract: The present invention relates to a roller device for treating sheet-form material, in particular for smoothing films (F*) or sheets, comprising a first roller unit 1 and a second roller unit 2, wherein each roller unit (1, 2) comprises: at least one drive motor with a motor moment of inertia JM, a roller (10, 20) with a roller moment of inertia JW, and at least one gear for the kinematic coupling of the roller (10, 20) to the at least one drive motor with a transmission ratio iMW between the at least one drive motor and the roller (10, 20), wherein the roller (20) of the second roller unit (2) is rotatable in the opposite direction to the roller (10) of the first roller unit (1), and wherein there is formed between the roller (1 0) of the first roller unit (1) and the roller (20) of the second roller unit (2) a first roller gap (40) through which the sheet-form material (F) is guided.

Abstract: A method of determining properties relating to the manufacture of an injection-molded article is described. The method makes use of a hybrid model which includes at least one neural network and at least one rigorous model. In order to forecast (or predict) properties relating to the manufacture of a plastic molded part, a hybrid model is used which includes: one or more neural networks NN1, NN2, NN3, NN4, . . . , NNk; and one or more rigorous models R1, R2, R3, R4, . . . , which are connected to one another. The rigorous models are used to map model elements which can be described in mathematical formulae. The neural model elements are used to map processes whose relationship is present only in the form of data, as it is typically impossible to model such processes rigorously. As a result, a forecast (or prediction) relating to properties including, for example, the mechanical, thermal and rheological processing properties and relating to the cycle time of a plastic molded part can be made.