Ingenieurwissenschaften und zugeordnete Tätigkeiten
Filtern
Erscheinungsjahr
- 2020 (2) (entfernen)
Dokumenttyp
Sprache
- Englisch (2)
Referierte Publikation
- ja (2) (entfernen)
Schlagworte
- Additive manufacturing (1)
- Artificial neural network (1)
- Clustering (1)
- Computer vision (1)
- DED (1)
- Deep learning (1)
- Dimensional accuracy (1)
- High strength steels (1)
- Instumented indentation test (1)
- LMD (1)
Organisationseinheit der BAM
Components distort during directed energy deposition (DED) additive manufacturing (AM) due to the repeated localised heating. Changing the geometry in such a way that distortion causes it to assume the desired shape – a technique called distortion-compensation – is a promising method to reach geometrically accurate parts. Transient numerical simulation can be used to generate the compensated geometries and severely reduce the amount of necessary experimental trials. This publication demonstrates the simulation-based generation of a distortioncompensated DED build for an industrial-scale component. A transient thermo-mechanical approach is extended for large parts and the accuracy is demonstrated against 3d-scans. The calculated distortions are inverted to derive the compensated geometry and the distortions after a single compensation iteration are reduced by over 65%.
This paper demonstrates that the instrumented indentation test (IIT), together with a trained artificial neural network (ANN), has the capability to characterize the mechanical properties of the local parts of a welded steel structure such as a weld nugget or heat affected zone.
Aside from force-indentation depth curves generated from the IIT, the profile of the indented surface deformed after the indentation test also has a strong correlation with the materials’ plastic behavior. The profile of the indented surface was used as the training dataset to design an ANN to determine the material parameters of the welded zones. The deformation of the indented surface in three dimensions shown in images were analyzed with the computer vision algorithms and the obtained data were employed to train the ANN for the characterization of the mechanical properties. Moreover, this method was applied to the images taken with a simple light microscope from the surface of a specimen. Therefore, it is possible to quantify the mechanical properties of the automotive steels with the four independent methods: (1) force-indentation depth curve; (2) profile of the indented surface; (3) analyzing of the 3D-measurement image; and (4) evaluation of the images taken by a simple light microscope. The results show that there is a very good Agreement between the material parameters obtained from the trained ANN and the experimental uniaxial tensile test. The results present that the mechanical properties of an unknown steel can be determined by only analyzing the images taken from its surface after pushing a simple indenter into its surface.