Predictive visualization of fiber laser cutting topography via deep learning with image inpainting
Predictive visualization of fiber laser cutting topography via deep learning with image inpainting
Laser cutting is a fast, precise, and noncontact processing technique widely applied throughout industry. However, parameter specific defects can be formed while cutting, negatively impacting the cut quality. While light-matter interactions are highly nonlinear and are, therefore, challenging to model analytically, deep learning offers the capability of modeling these interactions directly from data. Here, we show that deep learning can be used to scale up visual predictions for parameter specific defects produced in cutting as well as for predicting defects for parameters not measured experimentally. Furthermore, visual predictions can be used to model the relationship between laser cutting defects and laser cutting parameters.
CNN, deep learning, fiber laser, GAN, image inpainting, laser cutting, laser processing
Courtier, Alexander F.
0a50732a-ef3f-4042-82f4-9b573c8c9ee8
Praeger, Matthew
84575f28-4530-4f89-9355-9c5b6acc6cac
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Codemard, Christophe
3aa50483-b61c-4e7e-b178-c9a88bb47bef
Harrison, Paul
691ee6c1-6616-4995-8a71-841889e1812d
Zervas, Michalis
1840a474-dd50-4a55-ab74-6f086aa3f701
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
August 2023
Courtier, Alexander F.
0a50732a-ef3f-4042-82f4-9b573c8c9ee8
Praeger, Matthew
84575f28-4530-4f89-9355-9c5b6acc6cac
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Codemard, Christophe
3aa50483-b61c-4e7e-b178-c9a88bb47bef
Harrison, Paul
691ee6c1-6616-4995-8a71-841889e1812d
Zervas, Michalis
1840a474-dd50-4a55-ab74-6f086aa3f701
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Courtier, Alexander F., Praeger, Matthew, Grant-Jacob, James A., Codemard, Christophe, Harrison, Paul, Zervas, Michalis and Mills, Ben
(2023)
Predictive visualization of fiber laser cutting topography via deep learning with image inpainting.
Journal of Laser Applications, 35 (3), [032007].
(doi:10.2351/7.0000957).
Abstract
Laser cutting is a fast, precise, and noncontact processing technique widely applied throughout industry. However, parameter specific defects can be formed while cutting, negatively impacting the cut quality. While light-matter interactions are highly nonlinear and are, therefore, challenging to model analytically, deep learning offers the capability of modeling these interactions directly from data. Here, we show that deep learning can be used to scale up visual predictions for parameter specific defects produced in cutting as well as for predicting defects for parameters not measured experimentally. Furthermore, visual predictions can be used to model the relationship between laser cutting defects and laser cutting parameters.
Text
032007_1_7.0000957
- Version of Record
More information
Submitted date: 21 December 2022
Accepted/In Press date: 31 May 2023
e-pub ahead of print date: 29 June 2023
Published date: August 2023
Additional Information:
Funding Information: we gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research. For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. This study was funded by Engineering and Physical Sciences Research Council (Nos. EP/N03368X/1 and EP/T026197/1).
Keywords:
CNN, deep learning, fiber laser, GAN, image inpainting, laser cutting, laser processing
Identifiers
Local EPrints ID: 485556
URI: http://eprints.soton.ac.uk/id/eprint/485556
ISSN: 1042-346X
PURE UUID: 64013b53-3106-4566-ba3f-87bc0d614ead
Catalogue record
Date deposited: 11 Dec 2023 17:32
Last modified: 18 Mar 2024 03:55
Export record
Altmetrics
Contributors
Author:
Alexander F. Courtier
Author:
Paul Harrison
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