Page 73 - MSAM-1-1

Materials Science in Additive Manufacturing

ORIGINAL RESEARCH ARTICLE
Additive manufacturing: A machine learning

model of process-structure-property linkages for
machining behavior of Ti-6Al-4V

1
3
2
Xi Gong , Dongrui Zeng , Willem Groeneveld-Meijer , Guha Manogharan *
1
1 Pennsylvania State University, Department of Mechanical Engineering, University Park,
PA 16801, USA
2 Pennsylvania State University, Department of Computer Science and Engineering, University Park,
PA 16801, USA
3 Pennsylvania State University, Department of Materials Science and Engineering, University Park,
PA 16801, USA

Abstract

Prior studies in metal additive manufacturing (AM) of parts have shown that
various AM methods and post-AM heat treatment result in distinctly different
microstructure and machining behavior when compared with conventionally
manufactured parts. There is a crucial knowledge gap in understanding this
process-structure-property (PSP) linkage and its relationship to material behavior.
In this study, the machinability of metallic Ti-6Al-4V AM parts was investigated to
better understand this unique PSP linkage through a novel data science-based
approach, specifically by developing and validating a new machine learning (ML)
*Corresponding author:
Guha Manogharan model for material characterization and material property, that is, machining
(gum53@psu.edu) behavior. Heterogeneous material structures of Ti-6Al-4V AM samples fabricated
Citation: Gong X, Zeng D, through laser powder bed fusion and electron beam powder bed fusion in two
Groeneveld-Meijer W, et al., 2022, different build orientations and post-AM heat treatments were quantitatively
Additive manufacturing: A machine
learning model of process-structure- characterized using scanning electron microscopy, electron backscattered
property linkages for machining diffraction, and residual stress measured through X-ray diffraction. The reduced
behavior of Ti-6Al-4V. Mater Sci dimensional representation of material characterization data through chord
Add Manuf, 1(1): 6.
https://doi.org/10.18063/msam.v1i1.6 length distribution (CLD) functions, 2-point correlation functions, and principal
component analysis was found to be accurate in quantifying the complexities of
Received: February 23, 2022
Ti-6Al-4V AM structures. Specific cutting energy was the response variable for the
Accepted: March 10, 2022 Taguchi-based experimentation using force dynamometer. A low-dimensional S-P
Published Online: March 30, 2022 linkage model was established to correlate material structures of metallic AM and
Copyright: © 2022 Author(s). machining properties through this novel ML model. It was found that the prediction
This is an Open-Access article accuracy of this new PSP linkage is extremely high (>99%, statistically significant
distributed under the terms of the at 95% confidence interval). Findings from this study can be seamlessly integrated
Creative Commons Attribution
License, permitting distribution, with P-S models to identify AM processing conditions that will lead to desired
and reproduction in any medium, material behaviors, such as machining behavior (this study), fatigue behavior, and
provided the original work is
properly cited. corrosion resistance.
Publisher’s Note: Whioce
Publishing remains neutral with Keywords: Additive manufacturing; Machine learning; Structure-property relationship;
regard to jurisdictional claims in
published maps and institutional Microstructure; Ti-6-Al-4V; Machining behavior
affiliations.

Volume 1 Issue 1 (2022) 1 https://doi.org/10.18063/msam.v1i1.6