Now showing 1 - 4 of 4
  • Publication
    Transferability of ANN-generated parameter sets from welding tracks to 3D-geometries in Directed Energy Deposition
    ( 2022-11-04)
    Marko, Angelina
    ;
    Bähring, Stefan
    ;
    Raute, Maximilian Julius
    ;
    ;
    Directed energy deposition (DED) has been in industrial use as a coating process for many years. Modern applications include the repair of existing components and additive manufacturing. The main advantages of DED are high deposition rates and low energy input. However, the process is influenced by a variety of parameters affecting the component quality. Artificial neural networks (ANNs) offer the possibility of mapping complex processes such as DED. They can serve as a tool for predicting optimal process parameters and quality characteristics. Previous research only refers to weld beads: a transferability to additively manufactured three-dimensional components has not been investigated. In the context of this work, an ANN is generated based on 86 weld beads. Quality categories (poor, medium, and good) are chosen as target variables to combine several quality features. The applicability of this categorization compared to conventional characteristics is discussed in detail. The ANN predicts the quality category of weld beads with an average accuracy of 81.5%. Two randomly generated parameter sets predicted as “good” by the network are then used to build tracks, coatings, walls, and cubes. It is shown that ANN trained with weld beads are suitable for complex parameter predictions in a limited way.
  • Publication
    Prognose von Qualitätsmerkmalen durch Anwendung von KI-Methoden beim "Directed Energy Deposition"
    ( 2022-10)
    Marko, Angelina
    ;
    Bähring, Stefan
    ;
    Raute, Maximilian Julius
    ;
    ;
    Dieser Beitrag enthält die Ergebnisse eines im Rahmen der DVS Forschung entwickelten Ansatzes zur Qualitätssicherung im Directed Energy Deposition. Es basiert auf der Verarbeitung verschiedener während des Prozesses gesammelter Sensordaten unter Anwendung Künstlicher Neuronale Netze (KNN). So ließen sich die Qualitätsmerkmale Härte und Dichte auf der Datenbasis von 50 additiv gefertigten Probenwürfel mit einer Abweichung < 2 % vorhersagen. Des Weiteren wurde die Übertragbarkeit des KNN auf eine Schaufelgeometrie untersucht. Auch hier ließen sich Härte und Dichte hervorragend prognostizieren (Abweichung < 1,5 %), sodass der Ansatz als validiert betrachtet werden kann.
  • Publication
    Influence of electron beam welding parameters on the weld seam geometry of Inconel 718 at low feed rates
    ( 2020)
    Raute, Julius
    ;
    Jokisch, Torsten
    ;
    Marko, Angelina
    ;
    ;
    Ni-based superalloys are well established in various industrial applications, because of their excellent mechanical properties and corrosion resistance at high temperatures. Despite the high development stage and a common industrial use of these alloys, hot cracking remains a major challenge limiting the weldability of the materials. As commonly known, the hot cracking susceptibility during welding increases with the amount of precipitation phases. Hence, a large amount of highstrength Ni-Alloys is rated as non-weldable. A new approach based on electron beam welding at low feed rates shows great potential for reducing the hot cracking tendency of precipitation-hardened alloys. However, geometry and properties of the weld seam differ significantly in comparison to the common process range for practical uses. The aim of this study is to investigate the influence of welding parameters on the seam geometry at low feed rates between 1 mm/s and 10 mm/s. For this purpose, 25 bead on plate welds on a 12 mm thick sheet made of Inconel 718 are carried out. First, the relevant parameters are identified by performing a screening. Then the effects discovered are further studied by using a central composite design. The results show a significant difference between the analyzed weld seam geometry in comparison to the well-known appearance of electron beam welded seams.
  • Publication
    Finite element analysis of in-situ distortion and bulging for an arbitrarily curved additive manufacturing directed energy deposition geometry
    ( 2018) ;
    Marko, Angelina
    ;
    Graf, Benjamin
    ;
    With the recent rise in the demand for additive manufacturing (AM), the need for reliable simulation tools to support experimental efforts grows steadily. Computational welding mechanics approaches can simulate the AM processes but are generally not validated for AM-specific effects originating from multiple heating and cooling cycles. To increase confidence in the outcomes and to use numerical simulation reliably, the result quality needs to be validated against experiments for in-situ and post process cases. In this article, a validation is demonstrated for a structural thermomechanical simulation model on an arbitrarily curved Directed Energy Deposition (DED) part: at first, the validity of the heat input is ensured and subsequently, the model's predictive quality for in-situ deformation and the bulging behaviour is investigated. For the in-situ deformations, 3D-Digital Image Correlation measurements are conducted that quantify periodic expansion and shrinkage as they occur. The results show a strong dependency of the local stiffness of the surrounding geometry. The numerical simulation model is set up in accordance with the experiment and can reproduce the measured 3 dimensional in-situ displacements. Furthermore, the deformations due to removal from the substrate are quantified via 3D scanning, exhibiting considerable distortions due to stress relaxation. Finally, the prediction of the deformed shape is discussed in regards to bulging simulation: to improve the accuracy of the calculated final shape, a novel extension of the model relying on the modified stiffness of inactive upper layers is proposed and the experimentally observed bulging could be reproduced in the finite element model.