Industrializing metal additive manufacturing for mass production requires a consistent manufacturing process that reliably produces high-quality end products. In order to meet these quality requirements, layer-wise in-situ monitoring data is captured to detect process deviations that potentially lead to product defects. However, this way of process monitoring is limited to a retrospective analysis, where defect development is usually unavoidable. Still, accurate forecasting of part fabrication within the same or subsequent layers would allow a timely corrective adjustment of the control strategy.
In our work, we formulate the forecasting of part fabrication as an image inpainting problem, where areas of the part that have not been printed yet, are treated as missing regions within layer-wise in-situ image data. We propose to train generative inpainting models to fill in these missing regions, thus predicting possible outcomes of the printing process. In our experiments, we train a generative neural architecture on layer-wise images of heat signatures that were captured with an optical tomography monitoring system during Laser Powder Bed Fusion (LPBF) processes. By varying machine parameter configurations and part geometry, we evaluate the prediction capabilities of the model. Our results reveal, that our model is capable of accurately predicting realistic outcomes of LPBF processes using in-situ monitoring data with a sufficient level of detail. From that we conclude, that generative models show promising results towards an online defect prediction system, that allows a timely intervention of the current control strategy. With our approach, we lay the foundation of a model-based control framework that may be able to prevent product defects from forming.

Recent process developments in Fused Filament Fabrication (FFF), such as the possibilities to use high end polymers (for example PEEK) or to manufacture metal parts and parts reinforced with continuous fibers, have increased industrial interest. Previously, this additive manufacturing (AM) technology was mostly popular among hobbyists thanks to its low investment cost. With the increased industrial interest comes higher demands on product strength and production efficiency.

The FFF process has many parameters that should be optimized to meet these tougher requirements. One of these parameters is the size of the nozzle through which the filament is extruded. Today a fairly wide range of sizes are available on the market, but most standard-sized printers come equipped with a 0.4 mm nozzle.

In this study, a wide range of nozzles of different sizes have been manufactured to investigate how the nozzle size affects both the printing process and the mechanical properties of the printed parts. Tensile bars have been manufactured in polylactic acid (PLA) using 7 different nozzle sizes. The samples were investigated by means of computer tomography (CT) and optical microscopy and subjected to tensile testing.

Additive Manufacturing (AM) technologies are considered to be essential production processes of the future, as they enable novel products due to the high geometric design freedom at almost constant production costs. In terms of industrialization, the efficient integration of AM systems into lean production lines is essential. Up to 80% of the total lead time and costs of additively manufactured components are currently generated before or after the actual AM printing process, specifically within pre- and post-process steps.

A common tool to reduce lead times and costs in production lines is the automation of manual process steps along the entire end-to-end process chain. Since the development of complex automation solutions is usually very cost-intensive, the application must be analyzed extensively before development. However, due to the high complexity and diversity of end-to-end AM process chains, the assessment of the automation potential for AM technologies is considered to be challenging.

The goal of this work is to develop a methodology to systematically analyze the automation potential along the end-to-end AM process chain and identify high potentials of automation. For this, the common end-to-end process chains of Laser-Powder Bed Fusion (L-PBF) and Laser Metal Deposition (LMD) were defined systematically. According to the end-to-end process chains, the mutual literature-based degree of automation was determined for each process step and its linkage. Finally, a value-benefit analysis of automation solutions was carried out for every process step, to highlight high and low automation potentials.