Page 27 - IJAMD-1-2

International Journal of AI for
Materials and Design

REVIEW ARTICLE
Machine learning techniques for quality

assurance in additive manufacturing processes

Surajit Mondal and Shankha Shubhra Goswami*
Department of Mechanical Engineering, Abacus Institute of Engineering and Management, Hooghly,
West Bengal, India

Abstract
Additive manufacturing (AM) processes have revolutionized manufacturing
industries by enabling the production of complex geometries with reduced material
waste and lead times. However, ensuring the quality of AM parts remains a significant
challenge due to the complexity of the process and inherent variability in material
properties. This review investigates the use of artificial intelligence (AI) to enhance
quality assurance in AM processes, focusing on specific machine learning techniques
such as convolutional neural networks for defect detection, support vector machines
for classification of material properties, and reinforcement learning for real-time
process optimization. The AI-driven methodologies are applied to predict defects,
optimize process parameters, and monitor real-time production quality, utilizing
large datasets generated from sensors and in-situ monitoring systems. The study
demonstrates significant improvements in the accuracy of defect detection,
the reliability of material property classification, and the efficiency of process
optimization. In addition, it addresses challenges such as data pre-processing, model
interpretability, and integration with existing AM systems. The findings highlight
the potential of AI to transform quality assurance in AM and outline future research
*Corresponding author:
Shankha Shubhra Goswami directions for further integration and enhancement of AI techniques in AM.
(ssg.mech.official@gmail.com)
Citation: Mondal S, Goswami SS. Keywords: Additive manufacturing; Artificial intelligence; Quality assurance; Reliability;
Machine learning techniques Challenges; Future directions
for quality assurance in additive
manufacturing processes. Int J AI
Mater Design. 2024;1(2):3455.
doi: 10.36922/ijamd.3455
Received: April 19, 2024 1. Introduction
Accepted: May 31, 2024
Published Online: July 25, 2024 Additive manufacturing (AM), often referred to as 3D printing, has emerged as a
transformative technology with the potential to revolutionize traditional manufacturing
Copyright: © 2024 Author(s).
This is an Open-Access article processes. Unlike subtractive manufacturing methods that involve cutting away material
distributed under the terms of the from a solid block, AM builds objects layer by layer from digital designs, offering
Creative Commons Attribution 1
License, permitting distribution, unparalleled flexibility and freedom in design complexity. This capability has opened
and reproduction in any medium, up new horizons across various industries, including aerospace, automotive, healthcare,
provided the original work is and consumer goods, by enabling the production of highly customized, lightweight, and
properly cited.
intricately detailed components.
Publisher’s Note: AccScience
Publishing remains neutral with The fundamental principle of AM involves the deposition or binding of material, layer
regard to jurisdictional claims in on layer, guided by a digital model or computer-aided design (CAD) file. This layer-by-
published maps and institutional
affiliations. layer approach allows for the creation of complex geometries that are often impossible

Volume 1 Issue 2 (2024) 21 doi: 10.36922/ijamd.3455