Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration

Machine learning has already shown promising potential in tiled-aperture coherent beam combining (CBC) to achieve versatile advanced applications. By sampling the spatially separated laser array before the combiner and detuning the optical path delays, deep learning techniques are incorporated into...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongbing Zhou, Rumao Tao, Xi Feng, Haoyu Zhang, Min Li, Xiong Xin, Yuyang Peng, Honghuan Lin, Jianjun Wang, Lixin Yan, Feng Jing
Format: Article
Language:English
Published: Cambridge University Press 2025-01-01
Series:High Power Laser Science and Engineering
Subjects:
Online Access:https://www.cambridge.org/core/product/identifier/S2095471925000246/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329064667512832
author Hongbing Zhou
Rumao Tao
Xi Feng
Haoyu Zhang
Min Li
Xiong Xin
Yuyang Peng
Honghuan Lin
Jianjun Wang
Lixin Yan
Feng Jing
author_facet Hongbing Zhou
Rumao Tao
Xi Feng
Haoyu Zhang
Min Li
Xiong Xin
Yuyang Peng
Honghuan Lin
Jianjun Wang
Lixin Yan
Feng Jing
author_sort Hongbing Zhou
collection DOAJ
description Machine learning has already shown promising potential in tiled-aperture coherent beam combining (CBC) to achieve versatile advanced applications. By sampling the spatially separated laser array before the combiner and detuning the optical path delays, deep learning techniques are incorporated into filled-aperture CBC to achieve single-step phase control. The neural network is trained with far-field diffractive patterns at the defocus plane to establish one-to-one phase-intensity mapping, and the phase prediction accuracy is significantly enhanced thanks to the strategies of sin-cos loss function and two-layer output of the phase vector that are adopted to resolve the phase discontinuity issue. The results indicate that the trained network can predict phases with improved accuracy, and phase-locking of nine-channel filled-aperture CBC has been numerically demonstrated in a single step with a residual phase of λ/70. To the best of our knowledge, this is the first time that machine learning has been made feasible in filled-aperture CBC laser systems.
format Article
id doaj-art-012fbc5c92b14a69b9820679100545dc
institution Kabale University
issn 2095-4719
2052-3289
language English
publishDate 2025-01-01
publisher Cambridge University Press
record_format Article
series High Power Laser Science and Engineering
spelling doaj-art-012fbc5c92b14a69b9820679100545dc2025-08-20T03:47:23ZengCambridge University PressHigh Power Laser Science and Engineering2095-47192052-32892025-01-011310.1017/hpl.2025.24Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstrationHongbing Zhou0https://orcid.org/0009-0000-3825-3124Rumao Tao1https://orcid.org/0000-0001-9880-811XXi Feng2Haoyu Zhang3Min Li4Xiong Xin5Yuyang Peng6Honghuan Lin7Jianjun Wang8Lixin Yan9https://orcid.org/0000-0002-6572-4400Feng Jing10Laser Fusion Research Center, China Academy of Engineering Physics, Mianyang, China Department of Engineering Physics, Tsinghua University, Beijing, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaDepartment of Engineering Physics, Tsinghua University, Beijing, ChinaLaser Fusion Research Center, China Academy of Engineering Physics, Mianyang, ChinaMachine learning has already shown promising potential in tiled-aperture coherent beam combining (CBC) to achieve versatile advanced applications. By sampling the spatially separated laser array before the combiner and detuning the optical path delays, deep learning techniques are incorporated into filled-aperture CBC to achieve single-step phase control. The neural network is trained with far-field diffractive patterns at the defocus plane to establish one-to-one phase-intensity mapping, and the phase prediction accuracy is significantly enhanced thanks to the strategies of sin-cos loss function and two-layer output of the phase vector that are adopted to resolve the phase discontinuity issue. The results indicate that the trained network can predict phases with improved accuracy, and phase-locking of nine-channel filled-aperture CBC has been numerically demonstrated in a single step with a residual phase of λ/70. To the best of our knowledge, this is the first time that machine learning has been made feasible in filled-aperture CBC laser systems.https://www.cambridge.org/core/product/identifier/S2095471925000246/type/journal_articlecoherent beam combiningmachine learningphase control
spellingShingle Hongbing Zhou
Rumao Tao
Xi Feng
Haoyu Zhang
Min Li
Xiong Xin
Yuyang Peng
Honghuan Lin
Jianjun Wang
Lixin Yan
Feng Jing
Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
High Power Laser Science and Engineering
coherent beam combining
machine learning
phase control
title Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
title_full Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
title_fullStr Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
title_full_unstemmed Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
title_short Machine learning phase control of filled-aperture coherent beam combining: principle and numerical demonstration
title_sort machine learning phase control of filled aperture coherent beam combining principle and numerical demonstration
topic coherent beam combining
machine learning
phase control
url https://www.cambridge.org/core/product/identifier/S2095471925000246/type/journal_article
work_keys_str_mv AT hongbingzhou machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT rumaotao machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT xifeng machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT haoyuzhang machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT minli machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT xiongxin machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT yuyangpeng machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT honghuanlin machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT jianjunwang machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT lixinyan machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration
AT fengjing machinelearningphasecontroloffilledaperturecoherentbeamcombiningprincipleandnumericaldemonstration