Data-driven optimization for more resource-efficient 3D-printing processes

Research area

Additive manufacturing (AM) is a relatively new technology, and there is still not an in-depth understanding of the correlation between process parameters and the resulting microstructure for many materials. The aim of this project is to enhance our understanding of these process-structure relationships by developing and applying machine learning models to data gathered for light-weight, Mg-based alloys.

Sustainability aspects

Learning about the relationship between processing and material microstructure will allow us to train models that can speed up the AM material development processes, hence requiring less material, energy and other resources. This will in particular be applied to light-weight alloys, to, in the future, improve their properties and expand their use for fuel- and emission-saving purposes. There is hence a dual sustainability aspect.