Page 36 - MSAM-1-4

Materials Science in Additive Manufacturing Process optimization of SEBM IN718 via ML

(ii) SVR and GPR models were trained to predict the
relative density, and GPR model presents superior
predictability. The SEBM processing window for
Inconel 718 was obtained by combining GPR relative
density contour map with processing parameter
window of surface morphology. Machine learning
model allows the high-density area to be predicted
from a data set which contains a few samples, and the
parameter space is larger than before.
(iii) Inconel 718 samples with high relative density
(>99.5%) were fabricated by SEBM. Mechanical
properties and plasticity are different while at the
same energy density. Although the unmelted powder
particles did not reduce the relative density of the
sample, the smooth surface and the Laves phase inside,
which are perpendicular to the tensile direction of the
powder, aggravate the properties.
Figure 16. Summary of the tensile strength and elongation of as-built (iv) Sample P2 with few defects and finer columnar
Inconel 718 by selective electron-beam melting from other work [48,54-57] and grains was prepared using the optimized parameters,
Wrought Inconel 718, compared to the as-built Inconel 718 sample in and further, mechanical test indicated its excellent
[56]
this work.
combination of strength and ductility.
also beneficial to the energy absorption of the powder. The Acknowledgment
above results suggest that energy density is not good enough
to represent the energy absorbed by the powder. None.
In this study, the mechanical properties were measured Funding
in the as-built state. As shown in Figure 16, compared with
SEBM and wrought Inconel 718 in other reports, P2 had This work is supported by National Science and Technology
considerable strength and elongation, because the sample Major Project (J2019-IV-0003-0070), National Natural
with no defects and finer columnar grains was fabricated Science Foundation of China (91860105, 52074366,
in processing window. Laves phase and δ phase (Figure 9B) 52001334), China Postdoctoral Science Foundation
were rich in strengthening elements such as Nb and Mo (2019M662799), Natural Science Foundation of Hunan
which reduced the effect of solid solution strengthening Province of China (2021JJ40757), Science and Technology
and inhibited the precipitation of γ′ and γ′′ strengthening Innovation Program of Hunan Province (2021RC3131),
phase . The bulk Laves phase is also the initiation region and Project Supported by State Key Laboratory of Powder
[17]
of the crack. Under normal conditions, solution treatment Metallurgy, Central South University, Changsha, China.
can make Laves phase dissolve into the matrix, and aging
treatment can make strengthening phase precipitate Conflict of interest
uniformly. Therefore, heat treatment is suggested to further The authors declared no potential conflicts of interest with
improve mechanical property of Inconel 718. respect to the research, authorship, and/or publication of
this article.
5. Conclusions
In this study, SEBM processing window was established Author contributions
for Inconel 718 using machine learning model to obtain Conceptualization: Heng Dong, Feng Liu, Liming Tan
high relative density. The relationship between the SEBM Formal analysis: Heng Dong
processing parameters, surface morphology, defects, Funding acquisition: Yong Liu, Li wang
microstructure, and mechanical properties has been Investigation: Heng Dong, Lin Ye, Xiaoqiong Ouyang
investigated. The main conclusions are as follows: Methodology: Heng Dong, Lin Ye, Xiaoqiong Ouyang

(i) Excessive energy input leads to uneven surfaces or Resources: Qiangbing Wang
unshaped samples. Insufficient energy input results in Supervision: Liming Tan, Lan Huang
porous surface with lack-of-fusion defects, which is Validation: Heng Dong, Feng Liu
the main reason for low density. Writing – original draft: Heng Dong, Feng Liu

Volume 1 Issue 4 (2022) 13 https://doi.org/10.18063/msam.v1i4.23