Studying the topography of laser cut aluminium using latent space produced by deep learning
Studying the topography of laser cut aluminium using latent space produced by deep learning
Modelling topography resulting from laser cutting is challenging due to the highly non-linear light-matter interactions that occur during cutting. We show that unsupervised deep learning offers a data-driven capability for modelling the changes in the topography of 3mm thick, laser cut, aluminium, under different cutting conditions. This was achieved by analysing the parameter space encoded by the neural network, to interpolate between output topographies for different laser cutting parameter settings. This method enabled the use of neural network parameters to determine relationships between input laser cutting parameters, such as cutting speed or focus position, and output laser cutting parameters, such as verticality or dross formation. These relationships can then be used to optimise the laser cutting process.
Courtier, Alexander
0a50732a-ef3f-4042-82f4-9b573c8c9ee8
Praeger, Matthew
84575f28-4530-4f89-9355-9c5b6acc6cac
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Codemard, Christophe
3aa50483-b61c-4e7e-b178-c9a88bb47bef
Harrison, Paul
992a7c06-5d61-4591-8455-f6530d5faa6c
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
16 February 2023
Courtier, Alexander
0a50732a-ef3f-4042-82f4-9b573c8c9ee8
Praeger, Matthew
84575f28-4530-4f89-9355-9c5b6acc6cac
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Codemard, Christophe
3aa50483-b61c-4e7e-b178-c9a88bb47bef
Harrison, Paul
992a7c06-5d61-4591-8455-f6530d5faa6c
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
Courtier, Alexander, Praeger, Matthew, Grant-Jacob, James, Codemard, Christophe, Harrison, Paul, Mills, Benjamin and Zervas, Michael N.
(2023)
Studying the topography of laser cut aluminium using latent space produced by deep learning.
PHOTOPTICS 2023 – 11th International Conference on Photonics, Optics and Laser Technology, , Lisbon, Portugal.
16 - 18 Feb 2023.
4 pp
.
Record type:
Conference or Workshop Item
(Other)
Abstract
Modelling topography resulting from laser cutting is challenging due to the highly non-linear light-matter interactions that occur during cutting. We show that unsupervised deep learning offers a data-driven capability for modelling the changes in the topography of 3mm thick, laser cut, aluminium, under different cutting conditions. This was achieved by analysing the parameter space encoded by the neural network, to interpolate between output topographies for different laser cutting parameter settings. This method enabled the use of neural network parameters to determine relationships between input laser cutting parameters, such as cutting speed or focus position, and output laser cutting parameters, such as verticality or dross formation. These relationships can then be used to optimise the laser cutting process.
Text
Unsupervised_learning_2_page_summary_formatted Final
- Author's Original
More information
Published date: 16 February 2023
Venue - Dates:
PHOTOPTICS 2023 – 11th International Conference on Photonics, Optics and Laser Technology, , Lisbon, Portugal, 2023-02-16 - 2023-02-18
Identifiers
Local EPrints ID: 482807
URI: http://eprints.soton.ac.uk/id/eprint/482807
PURE UUID: 39496f0b-6ff7-409c-991a-692eaa5d2562
Catalogue record
Date deposited: 12 Oct 2023 16:48
Last modified: 17 Mar 2024 03:59
Export record
Contributors
Author:
Alexander 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