Real-time control of laser materials processing using deep learning
Real-time control of laser materials processing using deep learning
The plasma that is generated during laser materials processing can prevent the direct observation of the target. However, the appearance of the generated plasma is correlated with the properties of the material being ablated. Here, we show that deep learning can enable the identification of the material in real-time directly from processing camera images of the plasma, and hence can be used to automatically prevent machining beyond material boundaries. This work could have applications across laser materials processing in cases where the laser induced plasma restricts direct observation of the sample.
11-14
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
November 2023
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
Grant-Jacob, James A., Mills, Ben and Zervas, Michael N.
(2023)
Real-time control of laser materials processing using deep learning.
Manufacturing Letters, 38, .
(doi:10.1016/j.mfglet.2023.08.145).
Abstract
The plasma that is generated during laser materials processing can prevent the direct observation of the target. However, the appearance of the generated plasma is correlated with the properties of the material being ablated. Here, we show that deep learning can enable the identification of the material in real-time directly from processing camera images of the plasma, and hence can be used to automatically prevent machining beyond material boundaries. This work could have applications across laser materials processing in cases where the laser induced plasma restricts direct observation of the sample.
Text
Manufacturing_Letters_Plasma_Corrected
- Accepted Manuscript
Text
1-s2.0-S2213846323002043-main
- Version of Record
More information
Accepted/In Press date: 20 August 2023
e-pub ahead of print date: 9 September 2023
Published date: November 2023
Additional Information:
Funding Information:
Funding. Engineering & Physical Sciences Research Council (EP/W028786/1, EP/T026197/1, EP/P027644/1).
Publisher Copyright:
© 2023 The Author(s)
Identifiers
Local EPrints ID: 482032
URI: http://eprints.soton.ac.uk/id/eprint/482032
ISSN: 2213-8463
PURE UUID: 9babf738-fe7e-4c45-9d48-8951f1c0678a
Catalogue record
Date deposited: 15 Sep 2023 17:08
Last modified: 18 Mar 2024 02:38
Export record
Altmetrics
Contributors
Author:
James A. Grant-Jacob
Author:
Ben Mills
Author:
Michael N. Zervas
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics