Konrad Wegener

TL;DR: A machine learning approach using convolutional neural networks for in-process fault identification based on automatic image processing is presented to provide the SLM system with cognition, decision making and self-learning capabilities inspired by human intelligence and cognitive skills.

TL;DR: In this paper, an algorithm is proposed that creates a digital twin of the part from a given NC code, analyses the massiveness of the parts by calculating a local geometric factor, and alters the laser power accordingly: the heat flux in a thin wall is limited compared to a massive plate due to its smaller cross section and requires therefore less laser power to generate a comparable melt pool, especially if waiting times shall be avoided.

TL;DR: This is a presentation of an alternative way for simulating the thermo-mechanical behavior of machine tools that combines the advantages of the finite difference method (FDM) and the finite element analysis (FEA).

TL;DR: A software tool which allows the evaluation of the performance and conformance to requirements of machine structure variants at an early stage, in contrast to computer-aided manufacturing (CAM) tools which process numerical control code to predict the tool trajectory.

TL;DR: The linear friction models can be used together with linear models of the control for an efficient frequency domain analysis of the dynamic behavior, while preserving high accuracy.