Machine Learning-enabled Powder Spreading Process Maps for Metal Additive Manufacturing (AM)

Abstract

The metal powder-bed AM process involves two main steps: the spreading of powder layer and selective fusing or binding the spread layer. Most AM research is focused on powder fusion. Powder spreading is more rarely studied but is of significant importance for considering the quality of the final part and total build time. It is thus essential to understand how to modify the spread parameters such as spreader speed, to generate layers with desirable roughness and porosity. A computational modeling framework employing Discrete Element Method (DEM) is applied to simulate the spreading process, which is difficult to study experimentally, of Ti-6Al-4V powder onto smooth substrates. Since the DEM simulations are computationally expensive, machine learning was employed to interpolate between the highly non-linear results obtained by the running a few DEM simulations. Eventually, a spreading process map is generated to determine which spreader parameters can achieve the desired surface roughness and spread speed. This eventually saves the total time for printing and reduces the cost of build.

[Publisher’s version]

If it is useful in your research work, please consider citing this paper:

 @inproceedings{zhang2017machine,
  title={Machine learning enabled powder spreading process map for metal additive manufacturing (AM)},
  author={Zhang, Wentai and Mehta, Akash and Desai, Prathamesh S and Higgs, C. Fred},
  booktitle={the 28th Annual International Solid Freeform Fabrication Symposium},
  pages={1235--1249},
  year={2017},
 }