Methods for Rapid Pore Classification in Metal Additive Manufacturing

Abstract

The additive manufacturing of metals requires optimisation to find the melting conditions that give the desired material properties. A key aspect of the optimisation is minimising the porosity that forms during the melting process. A corresponding analysis of pores of different types (e.g. lack of fusion or keyholes) is therefore desirable. Knowing that pores form under different thermal conditions allows greater insight into the optimisation process. In this work, two pore classification methods were trialled: unsupervised machine learning and defined limits. These methods were applied to 3D pore data from X-ray computed tomography and 2D pore data from micrographs. Data were collected from multiple alloys (Ti-6Al-4V, Inconel 718, Ti-5553 and Haynes 282). Machine learning was found to be the most useful for 3D pore data and defined limits for the 2D pore data; the latter worked by optimising the limits using energy densities.

Comparative Quality Control of Titanium Alloy Ti–6Al–4V, 17–4 PH Stainless Steel, and Aluminum Alloy 4047 Either Manufactured or Repaired by Laser Engineered Net Shaping (LENS)

“…There is no clear definition of the correlation between sphericity value and defect type. Yet, Snell et al [ 55 ] recently showed, based on clustered results, that sphericity factors lower than 0.6, higher than 0.7, and higher than 0.92 represent an irregular shape that may be associated with lack of fusion, keyholes (usually, the result of high energy causing localized vaporization), and gas porosity, respectively. Irregular pores may also be attributed to partially melted powder particles resulting from insufficient laser energy [ 56 ].…”

A Novel Classification Method for Pores in Laser Powder Bed Fusion

“…Another approach is to use machine learning for pore classification. Snell et al [15] classified pores using unsupervised machine learning methods, such as K-means clustering. Unsupervised learning is a very interesting approach to classify pores without prior knowledge about the used data set.…”

Relationship between internal defect size and fatigue limit in selective laser melted Inconel 718

“…Fatigue fracture in SLM parts originates from their internal defects. (Rao et al, 2019) (Günther et al, 2017) (Beevers et al, 2018) Therefore, as the mechanical properties of SLM parts are significantly affected by the internal defects present in them, computed tomography (CT) has been used to detect the presence of the defects in SLM parts (Snell et al, 2020) (Sangid et al, 2020) (Wits et al, 2016) (Kasperovich et al, 2016). However, from the viewpoint of strength design, it is necessary to determine the internal defect size and investigate its effect on the fatigue characteristics of SLM parts before production.…”