Page 88 - MSAM-3-4

Materials Science in

Additive Manufacturing

ORIGINAL RESEARCH ARTICLE
Melt pool super solution reconstruction based

on dual path deep learning for laser powder bed
fusion monitoring

Xin Lin 1,2 , Yangkun Mao 2,3 , Lei Wu 2,3 , and Kunpeng Zhu *
2,4
1 Precision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan, Hubei,
China
2 Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences,
Hefei, Anhui, China
3 Science Island Branch, Graduate School of USTC, Hefei, Anhui, China
4 School of Mechanical Engineering, Wuhan University of Science and Technology, Wuhan, Hubei,
China

Abstract
Melt pool monitoring in laser powder bed fusion (L-PBF) is an important foundation for
process control and melting dynamics research. However, due to hardware limitations
and the intense metallurgical phenomena during the melting process, the quality of
the melt pool monitoring images cannot be guaranteed. This paper proposes a deep
learning-based melt pool image super-resolution (SR) reconstruction method based
on the particularity of melt pool images. It is an innovative dual-path structure. The first
*Corresponding author:
Kunpeng Zhu branch utilizes residual-in-residual structures and the efficient channel attention-Net
(zhukp@iamt.ac.cn) attention mechanism to achieve the adaptive feature extraction of high-frequency
Citation: Lin X, Mao Y, Wu L, information, thereby capturing effective melt pool boundary information. The second
Zhu K. Melt pool super solution branch uses the U-Net structure to address the low utilization of overall characteristics
reconstruction based on dual path of the melt pool in the chain-based SR network. In addition to the universal peak signal-
deep learning for laser powder bed to-noise ratio and structural similarity index measure metrics, the reconstruction
fusion monitoring. Mater Sci Add
Manuf. 2024;3(4):5585. accuracy of melt pool contour features is used to measure model performance, which
doi: 10.36922/msam.5585 intuitively reflects the significance of this work for melt pool monitoring. The results
Received: October 27, 2024 demonstrate that the proposed SR reconstruction method enhances the resolution
and clarity of melt pool images. Furthermore, SR reconstruction of the melt pool
Revised: November 21, 2024
effectively reduces errors in extracting melt pool features. This method provides
Accepted: November 26, 2024 a network paradigm for high-precision L-PBF monitoring. It integrates important
Published Online: December 13, boundary information and overall morphology features of the melt pool through a
2024 dual path structure, thereby achieving reliable SR reconstruction. This research will
Copyright: © 2024 Author(s). contribute to low-cost in situ monitoring of L-PBF and subsequent process control.
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution Keywords: Melt pool monitoring; Super-resolution; Laser powder bed fusion; Melt pool
License, permitting distribution, features; Deep learning
and reproduction in any medium,
provided the original work is
properly cited.
Publisher’s Note: AccScience
Publishing remains neutral with 1. Introduction
regard to jurisdictional claims in
published maps and institutional Nowadays, laser powder bed fusion (L-PBF) is regarded as one of the most promising
1
affiliations. technologies in the precision manufacturing sector. It is a laser-based rapid prototyping

Volume 3 Issue 4 (2024) 1 doi: 10.36922/msam.5585