A melt pool geometry-based approach is developed to predict surface roughness in metal additively manufactured parts for a range of processing parameters. It is shown that surface roughness on a particular facet can be estimated by stacking melt pools along the facet, extracting their outer contour and applying the necessary transformations. To be able to predict surface quality of various processing parameters in a reasonable time frame, a machine learning framework is developed. This framework is trained over melt pool data generated by high-fidelity FE simulations.
EXTENDED ABSTRACT

Fatigue crack is a major concern to all industries for safety reasons. Fatigue life predictions for structural components such as railways or turbine disks are based on fracture mechanics analysis. Such components are inevitably submitted to underloads or overloads. The aim of this paper is to provide a DIC-BASED experimental analysis of overload 2D fatigue cracks using higher order terms in the Williams’ series expansion.
The prediction of the fatigue life of these components is often based on crack propagation calculations. However, overloads and underloads perturb steady state fatigue crack growth conditions and affect the growth rates by retarding or accelerating growth. The application of overloads generates complex effects on the crack behavior which induce delays that are difficult to predict. The mechanisms that have been proposed to explain retardation after tensile overload include, e.g. residual stress, crack closure and plasticity ahead of the crack tip.
In this work, based on DIC we use full-field measurements to obtain LEFM crack tip features (Stress Intensity Factor and T-stress). Therefore, with these crack tip features, we propose to analyze the T-stress effect on the crack growth propagation.
EXTENDED ABSTRACT