July 2024 - 04-1
July 2024 - 04-1
RESEARCH ARTICLE
Abstract
OPEN ACCESS Using a cutting-edge net-shape manufacturing technique called Additive Layer Manufactur-
Citation: Jatti VS, Sawant DA, Khedkar NK, Jatti ing (ALM), highly complex components that are not achievable with conventional wrought
VS, Salunkhe S, Pagáč M, et al. (2024) Tensile and cast methods can be produced. As a result, the aerospace sector is paying closer atten-
strength analysis of additively manufactured CM
tion to using this technology to fabricate superalloys based on nickel to develop the holistic
247LC alloy specimen by employing machine
learning classifiers. PLoS ONE 19(7): e0305744. gas turbine. Because of this, there is an increasing need for the mechanical characterisation
https://doi.org/10.1371/journal.pone.0305744 of such material. Conventional mechanical testing is hampered by the limited availability of
Editor: Himadri Majumder, G H Raisoni College of material that has been processed, especially given the large number of process factors that
Engineering and Management, Pune, INDIA need to be assessed. Thus, the present study focuses on manufacturing CM247LC Ni-
Received: January 17, 2024 based superalloy with exceptional mechanical characteristics by laser powder bed fusion
(L-PBF). This study evaluates the effect of input process variables such as laser power,
Accepted: June 4, 2024
scan speed, hatch distance and volumetric energy density on the mechanical performance
Published: July 29, 2024
of the LPBF CM247LC superalloy. The maximum value of as-built tensile strength obtained
Copyright: © 2024 Jatti et al. This is an open in the study is 997.81 MPa. Plotting Pearson’s heatmap and the Feature importance (F-test)
access article distributed under the terms of the
was used in the data analysis to examine the impact of input parameters on tensile strength.
Creative Commons Attribution License, which
permits unrestricted use, distribution, and The accuracy of the tensile strength data classification by machine learning algorithms,
reproduction in any medium, provided the original such as k-nearest neighbours, Naïve Baiyes, Support vector machine, XGBoost, AdaBoost,
author and source are credited. Decision tree, Random forest, and logistic regression algorithms, was 92.5%, 83.75%, 83%,
Data Availability Statement: All data that support 85%, 87.5%, 90%, 91.25%, and 77.5%, respectively.
the findings of this study are included within this
article.