High‐Speed 3D Printing Coupled with Machine Learning to Accelerate Alloy Development for Additive Manufacturing

Abstract Developing novel alloys for 3D printing of metals is a time‐ and resource‐intensive challenge. High‐throughput 3D printing and material characterization protocols are used in this work to rapidly screen a wide range of chemical compositions and processing conditions. In situ, alloying of hi...

Full description

Saved in:
Bibliographic Details
Main Authors: Avinash Hariharan, Marc Ackermann, Stephan Koss, Ali Khosravani, Johannes Henrich Schleifenbaum, Patrick Köhnen, Surya R. Kalidindi, Christian Haase
Format: Article
Language:English
Published: Wiley 2025-05-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202414880
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Developing novel alloys for 3D printing of metals is a time‐ and resource‐intensive challenge. High‐throughput 3D printing and material characterization protocols are used in this work to rapidly screen a wide range of chemical compositions and processing conditions. In situ, alloying of high‐strength steel with pure Al in the targeted range of 0–10 wt.% and flexible adjustment of the volumetric energy input is performed to derive 20 individual alloy combinations. These conditions are characterized using large‐area crystallographic analysis combined with chemistry and nanoindentation protocols. The significant influence of Al content and processing conditions on the constitutive material behavior of the metastable base alloy allowed for efficient exploration of the underlying process‐structure‐properties (PSP) relationships. The extracted PSP relations are discussed based on the dominant physical mechanisms observed in the samples. Furthermore, the microstructure‐property relationship based on limited experimental data is supported by an explainable machine‐learning approach.
ISSN:2198-3844