Bayer Aktiengesellschaft

Bayer Technology Services Gmbh

Covestro Deutschland Ag

Underwriters Laboratories, Inc.

Thomas Mrziglod

Michael Bierdel

Bahman Sarabi

Martin Wanders

Roland Loosen

Klaus Salewski

Georg Mogk

Jürgen Flecke

Rolf Burghaus

Peter Hübl

Linus GÖRLITZ

The invention relates to a system and a method for training a number of neural networks, by determining a first training data record, wherein the training data have a particular accuracy, generating a number of second data training records by perturbing the first training data record with a random variable, and training each of the neural networks with one of the training data records. A prognosis and an estimation of the prognosis error can be carried out by means of such a system.

Method for training neural networks

The invention relates to a method for the automatic design of experiments, having the following steps:

Method and system for the automatic design of experiments

A stress/strain curve is established by means of neural networksto N andTo that end, parameters are input into the inputfrom which the neural networksto N respectively establish the principal components of characteristic points. The curve type is selected on the basis of the output of the neural networkThe principal components of the characteristic points of the corresponding curve type are then inverse-transformed. The stress/strain curve is then calculated by the generatoron the basis of the inverse transformation.

Method for establishing stress/strain curves by means of spline interpolation on the basis of characteristic points and with the use of neural networks

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 NN, NN, NN, NN, . . . , NN; and one or more rigorous models R, R, R, R, . . . , 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.

Hybrid model and method for determining manufacturing properties of an injection-molded part

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 NN, NN, NN, NN, . . . , NN; and optionally one or more rigorous models R, R, R, R, . . . , 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.

Hybrid model and method for determining mechanical properties and processing properties of an injection-molded part

Growing community of inventors

Bergisch Gladbach, Germany

Thomas Mrziglod