Wire arc additive manufacturing (WAAM) by gas metal arc welding (GMAW) is a suitable option for the production of large volume metal parts. The main challenge is the high and periodic heat input of the arc on the generated layers, which directly affects geometrical features of the layers such as height and width as well as metallurgical properties such as grain size, solidification or material hardness. Therefore, processing with reduced energy input is necessary. This can be implemented with short arc welding regimes and respectively energy reduced welding processes. A highly efficient strategy for further energy reduction is the adjustment of contact tube to work piece distance (CTWD) during the welding process. Based on the current controlled GMAW process an increase of CTWD leads to a reduction of the welding current due to increased resistivity in the extended electrode and constant voltage of the power source. This study shows the results of systematically adjusted CTWD during WAAM of low-alloyed steel. Thereby, an energy reduction of up to 40% could be implemented leading to an adaptation of geometrical and microstructural features of additively manufactured work pieces.

Today, the quality of welded seams is often examined off-line with either destructive or non-destructive testing. These test procedures are time-consuming and therefore costly. This is especially true if the welds are not welded accurately due to process anomalies. In manual welding, experienced welders are able to detect process anomalies by listening to the sound of the welding process. In this paper, an approach to transfer the “hearing” of an experienced welder into an automated testing process is presented. An acoustic measuring device for recording audible sound is installed for this purpose on a fully automated welding fixture. The processing of the sound information by means of machine learning methods enables in-line process control. Existing research results until now show that the arc is the main sound source. However, both the outflow of the shielding gas and the wire feed emit sound information. Other investigations describe welding irregularities by evaluating and assessing existing sound recordings. Descriptive analysis was performed to find a connection between certain sound patterns and welding irregularities. Recent contributions have used machine learning to identify the degree of welding penetration. The basic assumption of the presented investigations is that process anomalies are the cause of welding irregularities. The focus was on detecting deviating shielding gas flow rates based on audio recordings, processed by a convolutional neural network (CNN). After adjusting the hyperparameters of the CNN it was capable of distinguishing between different flow rates of shielding gas.

As part of a feasibility study, an alternative production process for titanium aluminides was investigated. This process is based on in situ alloying by means of a multi-wire technique in the layer-wise additive manufacturing process. Thereby, gas metal arc welding (GMAW) was combined with additional hot-wire feeding. By using two separate wires made of titanium and aluminum, it is possible to implement the alloy formation of titanium aluminides directly in the weld bead of the welding process. In this study, wall structures were built layer-by-layer with alloy compositions between 10 at% and 55 at% aluminum by changing the feeding rates. During this investigation, the macroscopic characteristics, microstructural formation, and the change of the microhardness values were analyzed. A close examination of the influence of welding speed and post-process heat treatment on the Ti–47Al alloy was performed; this being particularly relevant due to its economically wide spread applications.

This research presents a hybrid approach to generate sample data for future machine learning applications for the prediction of mechanical properties in directed energy deposition-arc (DED-Arc) using the GMAW process. DED-Arc is an additive manufacturing process which offers a cost-effective way to generate 3D metal parts, due to its high deposition rate of up to 8 kg/h. The mechanical properties additively manufactured wall structures made of the filler material G4Si1 (ER70 S-6) are shown in dependency of the t_8/5 cooling time. The numerical simulation is used to link the process parameters and geometrical features to a specific t_8/5 cooling time. With an input of average welding power, welding speed and geometrical features such as wall thickness, layer height and heat source size a specific temperature field can be calculated for each iteration in the simulated welding process. This novel approach allows to generate large, artificial data sets as training data for machine learning methods by combining experimental results to generate a regression equation based on the experimentally measured t_8/5 cooling time. Therefore, using the regression equations in combination with numerically calculated t_8/5 cooling times an accurate prediction of the mechanical properties was possible in this research with an error of only 2.6%. Thus, a small set of experimentally generated data set allows to achieve regression equations which enable a precise prediction of mechanical properties. Moreover, the validated numerical welding simulation model was suitable to achieve an accurate calculation of the t_8/5 cooling time, with an error of only 0.3%.

In previous works we discovered that rule-based systems severely suffer in performance when increasing the number of rules. In order to increase the amount of possible boolean relations while keeping the number of rules fixed, we employ ideas from well known Spatial Transformer Systems and Self-Attention Networks: here, our learned rules are not static but are dynamically adjusted to fit the input data by training a separate rule-prediction system, which is predicting parameter matrices used in Neural Logic Rule Layers. We show, that these networks, termed Adaptive Neural Logic Rule Layers, outperform their static counterpart both in terms of final performance, as well as training stability and excitability during early stages of training.