MiCLAD as a platform for real-time monitoring and machine learning in laser metal deposition

Julien Ertveldt; Patrick Guillaume; Jan Helsen

doi:10.1016/j.procir.2020.09.164

MiCLAD as a platform for real-time monitoring and machine learning in laser metal deposition

Julien Ertveldt, Patrick Guillaume, Jan Helsen

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

13 Citations (Scopus)

Abstract

The MiCLAD machine designed at the VUB, Belgium, allows for closed-loop controlled laser metal deposition including various in-situ optical based measurement systems. These integrated sensors collect information on deposition geometry and temperature during the building process. Hence, each cubic millimeter of material that is either added or removed is mapped to its digital twin with a millisecond temporal resolution in the machines database. This paper introduces the platform and its capabilities by focusing on the procedure of obtaining the necessary training data for the future application of machine learning algorithms, with the goal of controlling the geometry and temperature history during additive manufacturing.

Original language	English
Title of host publication	11th CIRP Conference on Photonic Technologies [LANE 2020]
Place of Publication	Erlangen
Publisher	Elsevier
Pages	456-461
Number of pages	6
Volume	94
DOIs	https://doi.org/10.1016/j.procir.2020.09.164
Publication status	Published - 16 Sep 2020
Event	LANE 2020: 11th CIRP Conference on Photonic Technologies - Virtual edition, Erlangen, Germany Duration: 7 Sep 2020 → 10 Oct 2020 https://www.lane-conference.org/

Publication series

Name	Procedia CIRP
Publisher	Elsevier
ISSN (Print)	2212-8271

Conference

Conference	LANE 2020
Country	Germany
City	Erlangen
Period	7/09/20 → 10/10/20
Internet address	https://www.lane-conference.org/

Bibliographical note

Funding Information:
The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FO)W through project HiPAS and the Department of Economics, Innovation and Science (EIW ) of the Flanders government, Belgium, through the project HyLaFORM.

Funding Information:
The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FWO) through project HiPAS and the Department of Economics, Innovation and Science (EWI) of the Flanders government, Belgium, through the project HyLaFORM.

Publisher Copyright:
© 2020 The Authors. Published by Elsevier B.V.

Copyright:
Copyright 2022 Elsevier B.V., All rights reserved.

Keywords

Laser Metal Deposition
Feed-back control
Real-time monitoring
Machine learning

Access to Document

10.1016/j.procir.2020.09.164

Cite this

@inproceedings{f066c95a48ea4e2abf7d601db21ae2ef,

title = "MiCLAD as a platform for real-time monitoring and machine learning in laser metal deposition",

abstract = "The MiCLAD machine designed at the VUB, Belgium, allows for closed-loop controlled laser metal deposition including various in-situ optical based measurement systems. These integrated sensors collect information on deposition geometry and temperature during the building process. Hence, each cubic millimeter of material that is either added or removed is mapped to its digital twin with a millisecond temporal resolution in the machines database. This paper introduces the platform and its capabilities by focusing on the procedure of obtaining the necessary training data for the future application of machine learning algorithms, with the goal of controlling the geometry and temperature history during additive manufacturing.",

keywords = "Laser Metal Deposition, Feed-back control, Real-time monitoring, Machine learning",

author = "Julien Ertveldt and Patrick Guillaume and Jan Helsen",

note = "Funding Information: The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FO)W through project HiPAS and the Department of Economics, Innovation and Science (EIW ) of the Flanders government, Belgium, through the project HyLaFORM. Funding Information: The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FWO) through project HiPAS and the Department of Economics, Innovation and Science (EWI) of the Flanders government, Belgium, through the project HyLaFORM. Publisher Copyright: {\textcopyright} 2020 The Authors. Published by Elsevier B.V. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.; LANE 2020 : 11th CIRP Conference on Photonic Technologies ; Conference date: 07-09-2020 Through 10-10-2020",

year = "2020",

month = sep,

day = "16",

doi = "10.1016/j.procir.2020.09.164",

language = "English",

volume = "94",

series = "Procedia CIRP",

publisher = "Elsevier",

pages = "456--461",

booktitle = "11th CIRP Conference on Photonic Technologies [LANE 2020]",

url = "https://www.lane-conference.org/",

}

TY - GEN

T1 - MiCLAD as a platform for real-time monitoring and machine learning in laser metal deposition

AU - Ertveldt, Julien

AU - Guillaume, Patrick

AU - Helsen, Jan

N1 - Funding Information: The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FO)W through project HiPAS and the Department of Economics, Innovation and Science (EIW ) of the Flanders government, Belgium, through the project HyLaFORM. Funding Information: The authors would like to acknowledge Mr. Wim Devesse and Mr. Jorge Sanchez Medina for their contributions in setting up the camera integration in the machine. As well as Mr. Jona Gladines from the University of Antwerp for delivery of the CAD geometry of the test plate. This work was financed by the Research Foundation Flanders (FWO) through project HiPAS and the Department of Economics, Innovation and Science (EWI) of the Flanders government, Belgium, through the project HyLaFORM. Publisher Copyright: © 2020 The Authors. Published by Elsevier B.V. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.

PY - 2020/9/16

Y1 - 2020/9/16

N2 - The MiCLAD machine designed at the VUB, Belgium, allows for closed-loop controlled laser metal deposition including various in-situ optical based measurement systems. These integrated sensors collect information on deposition geometry and temperature during the building process. Hence, each cubic millimeter of material that is either added or removed is mapped to its digital twin with a millisecond temporal resolution in the machines database. This paper introduces the platform and its capabilities by focusing on the procedure of obtaining the necessary training data for the future application of machine learning algorithms, with the goal of controlling the geometry and temperature history during additive manufacturing.

AB - The MiCLAD machine designed at the VUB, Belgium, allows for closed-loop controlled laser metal deposition including various in-situ optical based measurement systems. These integrated sensors collect information on deposition geometry and temperature during the building process. Hence, each cubic millimeter of material that is either added or removed is mapped to its digital twin with a millisecond temporal resolution in the machines database. This paper introduces the platform and its capabilities by focusing on the procedure of obtaining the necessary training data for the future application of machine learning algorithms, with the goal of controlling the geometry and temperature history during additive manufacturing.

KW - Laser Metal Deposition

KW - Feed-back control

KW - Real-time monitoring

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85093365863&partnerID=8YFLogxK

U2 - 10.1016/j.procir.2020.09.164

DO - 10.1016/j.procir.2020.09.164

M3 - Conference paper

VL - 94

T3 - Procedia CIRP

SP - 456

EP - 461

BT - 11th CIRP Conference on Photonic Technologies [LANE 2020]

PB - Elsevier

CY - Erlangen

T2 - LANE 2020

Y2 - 7 September 2020 through 10 October 2020

ER -

MiCLAD as a platform for real-time monitoring and machine learning in laser metal deposition

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this