Filtern
Erscheinungsjahr
- 2021 (2) (entfernen)
Dokumenttyp
Sprache
- Englisch (2)
Schlagworte
- Directed energy deposition (2) (entfernen)
Organisationseinheit der BAM
Additive manufacturing, and therefore directed energy deposition, is
gaining more and more interest from industrial users. However, quality assurance for the components produced is still a challenge. Machine learning, especially using artificial neuronal networks, is a potential method for ensuring a high-quality standard. Based on process Parameters and monitoring data, part quality can be predicted. A further advantage is the ability to constantly learn and adopt to slight process changes.
First tests using artificial neural networks focus on the prediction of track geometry. The results show that even a small data set is enough to provide high accuracy in the predictions. In this work, an artificial neural network for the predictive analysis of relative density in laser powder cladding has been developed. A central composite experimental design is used to generate 19 data sets. Input variables are laser power, feed rate and powder mass flow. Cubes are built up where density is considered as a target value. Several neural networks are trained and evaluated with these data sets. Different topologies and initial weights are considered. The best network reaches a confidence level of around 90 % for the prediction of relative density based on the process parameters. Finally, the optimization of the generalization performance is investigated. To this purpose, methods of variation in error limit as well as cross-validation are applied. In this way, density is predictable by an artificial neural network with an accuracy of about 95 %.
The combination of laser powder bed fusion (LPBF), known for its geometrical freedom and accuracy, and the nozzle-based laser metal deposition process (LMD), known for its high build-up rates, has great potential to reduce the additive manufacturing times for large metallic parts. For the industrial application of the LPBF-LMD hybrid process chain, it is necessary to investigate the infuence of the LMD process on the LPBF substrate. In addition, the build plate material also has a signifcant impact on the occurrence of distortion along the additive manufacturing process chain. In the literature, steel build plates are often used in laser-based additive manufacturing processes of Inconel 718, since a good metallurgical Bonding can be assured whilst reducing costs in the production and restoration of the build plates. This paper examines the distortion caused by LMD material deposition and the infuence of the build plate material along the hybrid additive manufacturing process chain. Twin cantilevers are manufactured by LPBF and an additional layer is subsequently deposited with LMD. The distortion is measured in the as-built condition as well as after heat treatment. The efect of diferent LMD hatch strategies on the distortion is determined. The experiments are conducted using the nickel-base alloy Inconel 718. The results show a signifcant infuence of LMD path strategies on distortion, with shorter tool paths leading to less distortion. The remaining distortion after heat treatment is considerably dependent on the material of the build plate.