Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Towards efficient melt pool tracking in Additive Manufacturing via semi-supervised Semantic Segmentation

Hrechuk, Andrii LU orcid ; Hassan, Mohamed Abubakr ; Lee, Chi Guhn ; Sadek, Ahmad and Hassan, Mahmoud (2026) 13th CIRP Global Web Conference, CIRPe 2025 In Procedia CIRP 139. p.262-267
Abstract

Monitoring and characterizing melt pool dynamics in additive manufacturing is essential for understanding complex thermal and material behaviors that govern layer formation. Melt pool characteristics, such as size, shape, and dynamics, directly influence microstructure evolution, mechanical properties, and dimensional accuracy of the printed part. Therefore, accurate and efficient methods for melt pool detection and tracking are vital for advancing process control and part quality. This work investigates the application of advanced image processing techniques based on Semantic Segmentation to extract melt pool regions from high-speed imaging data. A semi-supervised learning framework employing teacher-student architecture is proposed to... (More)

Monitoring and characterizing melt pool dynamics in additive manufacturing is essential for understanding complex thermal and material behaviors that govern layer formation. Melt pool characteristics, such as size, shape, and dynamics, directly influence microstructure evolution, mechanical properties, and dimensional accuracy of the printed part. Therefore, accurate and efficient methods for melt pool detection and tracking are vital for advancing process control and part quality. This work investigates the application of advanced image processing techniques based on Semantic Segmentation to extract melt pool regions from high-speed imaging data. A semi-supervised learning framework employing teacher-student architecture is proposed to reduce the need for extensive labelled datasets while preserving segmentation accuracy. Comparative analyses with conventional approaches are conducted under varying printing conditions to demonstrate the method’s effectiveness. Results show the efficiency of the proposed methods addressing accuracy and labor intensity. Finally, the study discusses the challenges and bottlenecks of the implemented methods and their usability in an industrial perspective.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Additive Manufacturing, Machine Learning, Process Monitoring, Semantic Segmentation
host publication
Procedia CIRP
series title
Procedia CIRP
volume
139
pages
6 pages
conference name
13th CIRP Global Web Conference, CIRPe 2025
conference dates
2025-10-16 - 2025-10-17
external identifiers
  • scopus:105032947364
ISSN
2212-8271
DOI
10.1016/j.procir.2025.09.042
language
English
LU publication?
yes
id
1f988e75-24cc-4304-8ab0-44a294c34248
date added to LUP
2026-04-29 10:07:59
date last changed
2026-04-29 10:09:10
@inproceedings{1f988e75-24cc-4304-8ab0-44a294c34248,
  abstract     = {{<p>Monitoring and characterizing melt pool dynamics in additive manufacturing is essential for understanding complex thermal and material behaviors that govern layer formation. Melt pool characteristics, such as size, shape, and dynamics, directly influence microstructure evolution, mechanical properties, and dimensional accuracy of the printed part. Therefore, accurate and efficient methods for melt pool detection and tracking are vital for advancing process control and part quality. This work investigates the application of advanced image processing techniques based on Semantic Segmentation to extract melt pool regions from high-speed imaging data. A semi-supervised learning framework employing teacher-student architecture is proposed to reduce the need for extensive labelled datasets while preserving segmentation accuracy. Comparative analyses with conventional approaches are conducted under varying printing conditions to demonstrate the method’s effectiveness. Results show the efficiency of the proposed methods addressing accuracy and labor intensity. Finally, the study discusses the challenges and bottlenecks of the implemented methods and their usability in an industrial perspective.</p>}},
  author       = {{Hrechuk, Andrii and Hassan, Mohamed Abubakr and Lee, Chi Guhn and Sadek, Ahmad and Hassan, Mahmoud}},
  booktitle    = {{Procedia CIRP}},
  issn         = {{2212-8271}},
  keywords     = {{Additive Manufacturing; Machine Learning; Process Monitoring; Semantic Segmentation}},
  language     = {{eng}},
  pages        = {{262--267}},
  series       = {{Procedia CIRP}},
  title        = {{Towards efficient melt pool tracking in Additive Manufacturing via semi-supervised Semantic Segmentation}},
  url          = {{http://dx.doi.org/10.1016/j.procir.2025.09.042}},
  doi          = {{10.1016/j.procir.2025.09.042}},
  volume       = {{139}},
  year         = {{2026}},
}