Page 33 - IJAMD-2-2

International Journal of AI for
Materials and Design

REVIEW ARTICLE
Advancing intelligent additive

manufacturing: Machine learning approaches
for process optimization and quality control

Hayeol Kim 1 , Kyung-Hwan Kim 1 , Jiyun Jeong 1 , Hongryung Jeon 1 , and
1,2
Im Doo Jung *
1 Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, Ulsan,
Republic of Korea
2 Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology, Ulsan,
Republic of Korea
(This article belongs to the Special Issue: Artificial Intelligence Applications in Additive Manufacturing
and 3D Printing)

Abstract
Additive manufacturing (AM) has revolutionized modern fabrication by enabling
complex geometries, material efficiency, and customized production. However,
process variability, material inconsistencies, and defect formation remain critical
*Corresponding author: challenges, limiting scalability and industrial adoption. Machine learning (ML) has
Im Doo Jung emerged as a powerful tool to address these limitations by enabling data-driven
(idjung@unist.ac.kr) optimization, defect detection, material property prediction, and real-time process
Citation: Kim H, Kim K, Jeong J, control. This review provides a comprehensive analysis of ML applications in AM,
Jeon H, Jung ID. Advancing spanning polymers, metals, ceramics, and carbon-based materials, with a focus on
intelligent additive manufacturing:
Machine learning approaches for process optimization, quality assurance, and predictive modeling. Specifically, this
process optimization and quality review examines real-time defect detection through vision-based ML techniques,
control. Int J AI Mater Design. printing parameter optimization using supervised and reinforcement learning,
2025;2(2):27-55.
doi: 10.36922/IJAMD025130010 and predictive modeling of material properties–laying the groundwork for deeper
exploration of key methodologies such as deep learning and physics-informed
Received: March 24, 2025 models. Key ML methodologies, including deep learning, reinforcement learning,
Revised: May 20, 2025 and hybrid physics-informed models, are explored in the context of enhancing print
Accepted: May 23, 2025 precision, mechanical performance, and functional properties. Despite significant
advancements, challenges such as data scarcity, model generalization, and real-
Published online: June 11, 2025 time integration into AM workflows persist. Emerging trends, including multimodal
Copyright: © 2025 Author(s). sensor fusion, in situ monitoring, and cloud-based predictive analytics, are discussed
This is an Open-Access article as potential pathways toward fully autonomous and intelligent manufacturing.
distributed under the terms of the
Creative Commons Attribution By consolidating recent developments and outlining future directions, this review
License, permitting distribution, provides essential insights for researchers, engineers, and industry professionals
and reproduction in any medium, looking to harness ML in AM, facilitating advancements in process efficiency, quality
provided the original work is
properly cited. control, and overall manufacturing reliability.
Publisher’s Note: AccScience
Publishing remains neutral with Keywords: Additive manufacturing; Machine learning; Process optimization; Defect detection;
regard to jurisdictional claims in
published maps and institutional Quality assurance; Material property; Real-time monitoring; Data-driven manufacturing
affiliations.

Volume 2 Issue 2 (2025) 27 doi: 10.36922/IJAMD025130010