Optimisation of coherent beam combination using deep learning (Invited Paper)
Optimisation of coherent beam combination using deep learning (Invited Paper)
Coherent beam combination can be used to overcome limitations associated with the power handling capability of a single fibre laser. However, due to interference effects, the spatial intensity profile of the combined beam is directly affected by the phase of each fibre. Therefore, monitoring and control of the fibre phases is required for practical application. Here, we show that a neural network can extract this phase information from a far-field intensity profile, in a single step, hence unlocking the potential for real-time beam shaping. Further investigation shows that the neural network encoded fundamental rules associated with interference theory.
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
31 January 2023
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Zervas, Michael N.
1840a474-dd50-4a55-ab74-6f086aa3f701
Mills, Benjamin, Grant-Jacob, James and Zervas, Michael N.
(2023)
Optimisation of coherent beam combination using deep learning (Invited Paper).
SPIE Photonics West 2023, The Moscone Center, San Francisco, United States.
28 Jan - 02 Feb 2023.
Record type:
Conference or Workshop Item
(Other)
Abstract
Coherent beam combination can be used to overcome limitations associated with the power handling capability of a single fibre laser. However, due to interference effects, the spatial intensity profile of the combined beam is directly affected by the phase of each fibre. Therefore, monitoring and control of the fibre phases is required for practical application. Here, we show that a neural network can extract this phase information from a far-field intensity profile, in a single step, hence unlocking the potential for real-time beam shaping. Further investigation shows that the neural network encoded fundamental rules associated with interference theory.
Text
PW23 manuscript v1
- Accepted Manuscript
More information
Accepted/In Press date: 28 January 2023
e-pub ahead of print date: 31 January 2023
Published date: 31 January 2023
Venue - Dates:
SPIE Photonics West 2023, The Moscone Center, San Francisco, United States, 2023-01-28 - 2023-02-02
Identifiers
Local EPrints ID: 474770
URI: http://eprints.soton.ac.uk/id/eprint/474770
PURE UUID: c28b905f-8688-401c-ae04-f1f7b56b82ab
Catalogue record
Date deposited: 02 Mar 2023 17:46
Last modified: 17 Mar 2024 03:22
Export record
Contributors
Author:
Benjamin Mills
Author:
James Grant-Jacob
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