Loading [MathJax]/extensions/MathMenu.js
Machine Learning Pattern Recognition Algorithm With Applications to Coherent Laser Combination | IEEE Journals & Magazine | IEEE Xplore

Machine Learning Pattern Recognition Algorithm With Applications to Coherent Laser Combination


Impact Statement:Coherent beam combination (CBC) is becoming more important for high power and ultrafast pulse lasers, for military, commercial and scientific applications. What makes thi...Show More

Abstract:

We analyze a new kind of machine learning algorithm designed to feedback stabilize coherently combined lasers. This algorithm learns differential, rather than absolute, v...Show More
Impact Statement:
Coherent beam combination (CBC) is becoming more important for high power and ultrafast pulse lasers, for military, commercial and scientific applications. What makes this possible is phase error sensing and feedback control. CBC systems can be controlled using machine learning (ML) to map observed interference patterns to corresponding phase errors. However, learning is difficult when the initially unstabilized phases drift. In this new paper, we present the most thoroughly analyzed and definitive reference on a novel ML algorithm that can recognize patterns and derive error information from an unstable system, with its intrinsic limits and unique solutions, accounting for stability and efficiency, scaling to higher numbers of beams, extension to other applications, as well as generalization of the basic concept with sufficient new results on simulations to validate the feasibility and scalability of the ML approach in both diffractive spatial combining and temporal stacking.

Abstract:

We analyze a new kind of machine learning algorithm designed to feedback stabilize coherently combined lasers. This algorithm learns differential, rather than absolute, values of action in phase space, in order to facilitate learning on initially unstable systems. Experiments have shown that this approach can control small-scale spatial beam combination with high stability. In this paper we analyze the algorithm’s performance and limitations in depth, showing that it can continuously learn during operation in order to track changes. Using simulation, we extend the application to temporal combination, and show that it scales to more complex instances by combining 81 beams.
Published in: IEEE Journal of Quantum Electronics ( Volume: 58, Issue: 6, December 2022)
Article Sequence Number: 6100309
Date of Publication: 05 September 2022

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.