Single step phase optimisation for coherent beam combination using deep learning

Coherent beam combination of multiple fibres can be used to overcome limitations such as the power handling capability of single fibre configurations. In such a scheme, the focal intensity profile is critically dependent upon the relative phase of each fibre and so precise control over the phase of each fibre channel is essential. Determining the required phase compensations from the focal intensity profile alone (as measured via a camera) is extremely challenging with a large number of fibres as the phase information is obfuscated. Whilst iterative methods exist for phase retrieval, in practice, due to phase noise within a fibre laser amplification system, a single step process with computational time on the scale of milliseconds is needed. Here, we show how a neural network can be used to identify the phases of each fibre from the focal intensity profile, in a single step of ~ 10 milliseconds, for a simulated 3-ring hexagonal close packed arrangement, containing 19 separate fibres and subsequently how this enables bespoke beam shaping. In addition, we show that deep learning can be used to determine whether a desired intensity profile is physically possible within the simulation. This, coupled with the demonstrated resilience against simulated experimental noise, indicates a strong potential for the application of deep learning for coherent beam

[1]  M. Tateda,et al.  Suppression of stimulated Brillouin scattering in a fibre by changing the core radius , 1995 .

[2]  A. Chraplyvy,et al.  Performance degradation due to stimulated Raman scattering in wavelength-division-multiplexed optical-fibre systems , 1983 .

[3]  Joseph L. Levy,et al.  Coherent array of 900 semiconductor laser amplifiers , 1995, Photonics West.

[4]  Tomoyoshi Shimobaba,et al.  Band-limited angular spectrum method for numerical simulation of free-space propagation in far and near fields. , 2009, Optics express.

[5]  T F Morse,et al.  All-fiber coherent beam combining of fiber lasers. , 1999, Optics letters.

[6]  Chuanfei Yao,et al.  Coherent beam combination based on Q-learning algorithm , 2021, Optics Communications.

[7]  Benjamin Mills,et al.  Lasers that learn: The interface of laser machining and machine learning , 2021, IET Optoelectronics.

[8]  A. J. Rogers,et al.  Temperature dependence of the Kerr effect in a silica optical fibre , 1983 .

[9]  Chunte A. Lu,et al.  First experimental demonstration of self-synchronous phase locking of an optical array. , 2006, Optics express.

[10]  J R Fienup,et al.  Phase retrieval algorithms: a comparison. , 1982, Applied optics.

[11]  Pu Zhou,et al.  Coherent Beam Combining of Fiber Amplifiers Using Stochastic Parallel Gradient Descent Algorithm and Its Application , 2009, IEEE Journal of Selected Topics in Quantum Electronics.

[12]  Ben Mills,et al.  Predictive capabilities for laser machining via a neural network. , 2018, Optics express.

[13]  Henrik Tünnermann,et al.  Deep reinforcement learning for tiled aperture beam combining in a simulated environment , 2020 .

[14]  John Canning,et al.  Fibre lasers and related technologies , 2006 .

[15]  Cyril Billet,et al.  Machine learning analysis of extreme events in optical fibre modulation instability , 2018, Nature Communications.

[16]  W. Clarkson.  High power fibre lasers , 2002 .

[17]  James A. Grant-Jacob,et al.  Machine learning for 3D simulated visualization of laser machining , 2018, Optics Express.

[18]  P. Zhou,et al.  First experimental demonstration of coherent beam combining of more than 100 beams , 2020, Photonics Research.

[19]  Shuai Li,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[20]  Mikhail A. Vorontsov,et al.  Stochastic parallel-gradient-descent technique for high-resolution wave-front phase-distortion correction , 1998 .

[21]  Q. Du,et al.  Stabilization of the 81-channel coherent beam combination using machine learning. , 2021, Optics express.

[22]  T. Shay,et al.  Theory of electronically phased coherent beam combination without a reference beam. , 2006, Optics express.

[23]  M. Zervas,et al.  High Power Fiber Lasers: A Review , 2014, IEEE Journal of Selected Topics in Quantum Electronics.

[24]  Jun Zhou,et al.  7.1 kW coherent beam combining system based on a seven-channel fiber amplifier array , 2021 .

[25]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Bing He,et al.  High power coherent beam combination from two fiber lasers. , 2006, Optics express.

[27]  Tianyue Hou,et al.  Deep-learning-assisted, two-stage phase control method for high-power mode-programmable orbital angular momentum beam generation , 2020 .

[28]  Matthew Praeger,et al.  Lensless imaging of pollen grains at three-wavelengths using deep learning , 2020, Environmental Research Communications.