Method for obtaining information from X-ray computed tomography data for optimizing the injection molding process of short fiber reinforced plastic parts

摘要

The present invention relates to a method for obtaining information from short fiber reinforced plastic components manufactured in mass production with a learning phase and a subsequent application phase by means of an X-ray computed tomography method, wherein the learning phase comprises the steps of: generating CT records for a qualified sample manufactured by a manufacturing process plastic components; Extraction of at least one defect-free region of the plastic components; Determining the characteristics of at least one feature in the extracted regions and the relevance of individual features and regions that are characteristic of the type of plastic components and its manufacturing process and in their expression significant differences between good parts and bad parts over the time course of the production of plastic components have; Definition of this at least one feature and its expression as a trained classifier, wherein the application phase comprises the following steps: Creation of a CT data set of the plastic component to be tested Classification of the test part on the basis of the trained classifier Examination of the characteristic of the at least one feature for the presence of a Negative trends in this feature compared to the previously studied plastic components in the defect-free region; automatic change of the process parameters in a way that counteracts the negative trend or a warning that this negative trend is present.