Machine Learning-Enabled Competitive Grain Growth Behavior Study in Directed Energy Deposition Fabricated Ti6Al4V

Directed energy deposition (DED) of titanium alloys is a rapidly developing technology because of its flexibility in freeform fabrication and remanufacturing. However, the uncertainties of a solidification microstructure during the deposition process are limiting its development. This article presents an artificial neural network (ANN) to investigate the relation between the grain boundary tilt angle and three causative factors, namely the thermal gradient, crystal orientation and Marangoni effect. A series of wire feedstock DED, optical microscope and electron backscatter diffraction experiments was carried out under the Taguchi experimental design to gather the training and testing data for the ANN. Compared with conventional microstructure simulation methods, the strategy and ANN model developed in this work were demonstrated to be a valid way to describe the competitive grain growth behavior in DED fabricated Ti6Al4V. They can be deployed to achieve a quantitative microstructure simulation and extended to other polycrystal material solidification processes.