Abstract: The invention relates to an injection moulding process for producing thick-walled precision components, of transparent thermoplastic polymers using a mould comprising at least two mould halves, characterised in that the molten polymer is injected into the cavity of the mould and then, after the cavity of the mould has been filled, a hydraulic holding follow-up pressure of at least 1000 bar (100 MPa) is applied and the action of such a high pressure is maintained during the cooling of the melt.

Abstract: A method for controlling the quality of thermoplastic molding compositions in granular form is disclosed. The method entails obtaining a sample from a batch of granules, producing at least one transparent plastics article from the sample, examining the article for visible defects and determining, on the basis of the examination whether said article meets at least one predetermined quality acceptance criterion. Also disclosed is a device for carrying out the inventive method.

Abstract: A stress/strain curve is established by means of neural networks 1 to N and 4. To that end, parameters are input into the input 50, from which the neural networks 1 to N respectively establish the principal components of characteristic points. The curve type is selected on the basis of the output of the neural network 4. The principal components of the characteristic points of the corresponding curve type are then inverse-transformed. The stress/strain curve is then calculated by the generator 59 on the basis of the inverse transformation.

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.

Abstract: A method of predicting the properties (e.g., mechanical and/or processing properties) of an injection-molded article is disclosed. The method makes use of a hybrid model which includes at least one neural network. In order to forecast (or predict) properties with respect to the manufacture of a plastic molded article, a hybrid model is used in the present invention, which includes: one or more neural networks NN1, NN2, NN3, NN4, . . . , NNk; and optionally 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 networks are used to map processes whose relationship is present only in the form of data, as it is in effect impossible to model such processes rigorously. As a result, a forecast relating to properties including the mechanical, thermal and rheological processing properties and relating to the process time of a plastic molded article is obtained.

Abstract: A device for determining a coefficient of friction is disclosed. The device entails means for applying a normal force to a test piece via a die, means for subjecting the test piece to a torque and means for measuring the torque transmitted to the die via the test piece. Also disclosed is a multi-steps process for determining the coefficient of friction.

Abstract: The invention relates to methods and a computer system for marketing goods. In a first method, a client selects an appropriate product by means of a consulting software. In a second method, a client determines the properties, processing parameters, design parameters, or performance characteristics of a certain product by means of a consulting software. In each method, the utilization of that consulting software is quantified and the quantity is stored. Furthermore a rebate is credited to the client depending on that quantity. The software on which both methods are based is installed on a computer system. The client can connect to the computer system via a digital network.

Abstract: A method of predicting the properties (e.g., mechanical and/or processing properties) of an injection-molded article is disclosed. The method makes use of a hybrid model which includes at least one neural network. In order to forecast (or predict) properties with respect to the manufacture of a plastic molded article, a hybrid model is used in the present invention, which includes: one or more neural networks NN1, NN2, NN3, NN4, . . . , NNk; and optionally 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 networks are used to map processes whose relationship is present only in the form of data, as it is in effect impossible to model such processes rigorously. As a result, a forecast relating to properties including the mechanical, thermal and Theological processing properties and relating to the process time of a plastic molded article is obtained.

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.

Abstract: A stress/strain curve is established by means of neural networks 1 to N and 4. To that end, parameters are input into the input 50, from which the neural networks 1 to N respectively establish the principal components of characteristic points. The curve type is selected on the basis of the output of the neural network 4. The principal components of the characteristic points of the corresponding curve type are then inverse-transformed. The stress/strain curve is then calculated by the generator 59 on the basis of the inverse transformation.