Deep-learning-based phase control method for tiled aperture coherent beam combining systems

Tianyue Hou,Yanxing Ma,Qi Chang,Dong Zhi,Yi An,Jian Wu,Pu Zhou,Jun Li,Pengfei Ma,Rongtao Su,Liangjin Huang

doi:10.1017/hpl.2019.46

Abstract

We incorporate deep learning (DL) into tiled aperture coherent beam combining (CBC) systems for the first time, to the best of our knowledge. By using a well-trained convolutional neural network DL model, which has been constructed at a non-focal-plane to avoid the data collision problem, the relative phase of each beamlet could be accurately estimated, and then the phase error in the CBC system could be compensated directly by a servo phase control system. The feasibility and extensibility of the phase control method have been demonstrated by simulating the coherent combining of different hexagonal arrays. This DL-based phase control method offers a new way of eliminating dynamic phase noise in tiled aperture CBC systems, and it could provide a valuable reference on alleviating the long-standing problem that the phase control bandwidth decreases as the number of array elements increases.

Highlights

Coherent beam combining (CBC) of fiber lasers has great potential in breaking through the power limitation of a single laser beam while maintaining good beam quality – a topic that has been widely studied during the past decades[1,2,3,4,5,6,7,8]
The intensity profile of the combined beam collected by the CCD located at the non-focal-plane is sent to an FPGA controller carrying a well-trained convolutional neural network (CNN) to estimate the phase error of the CBC system
In order to demonstrate the feasibility and extensibility of the deep learning (DL)-based phase control method, we investigate the coherent combining of 7-element and 19-element hexagonal arrays as examples, and numerical simulations are performed in detail

Summary

Introduction

Coherent beam combining (CBC) of fiber lasers has great potential in breaking through the power limitation of a single laser beam while maintaining good beam quality – a topic that has been widely studied during the past decades[1,2,3,4,5,6,7,8]. As a result of their excellent real-time performance, machine learning and artificial intelligence algorithms may offer a route to further improve the phase control speed in CBC systems, which needs to be investigated carefully This new technique has been successfully applied to many optical research fields, such as mode-locked lasers, optical microscopy and laser mode decomposition[22,23,24,25]. The concept of extracting cost functions at the non-focal-plane has been proposed by our group[27] Drawing on this concept, the primary difficulty in incorporating the DL method into the tiled aperture CBC technique could expect to be solved. Our simulations are performed in detail to demonstrate the feasibility and extensibility of the proposed phase control technique, which has potential in improving the phase control bandwidth of CBC systems

Principle and method

Numerical simulation results and discussion

Conclusion