Optical orbital angular momentum machine learning recognition method based on turbulence effect

Abstract

The invention discloses an optical orbital angular momentum machine learning recognition method based on a turbulence effect, and solves the problems that a huge training sample is needed when an existing machine learning method is used for recognizing an orbital angular momentum mode, and synchronous recognition of various turbulence environments is difficult to realize. The method comprises thesteps of obtaining a training sample under a numerical simulation condition; training a support vector machine multi-classification model with more optimized parameters by using a genetic algorithm and the feature vectors; performing orbital angular momentum recognition by using the trained support vector machine multi-classification model; and grouping joint identification is carried out on the images with a large identification range. According to the invention, a physical mechanism and machine learning are combined for optical orbital angular momentum identification. According to the method, the orbital angular momentum mode number of the vortex beam in various atmospheric turbulence environments can be effectively recognized, the accuracy is far higher than that of a traditional optical detection method, compared with a machine learning method based on an image algorithm, training samples can be effectively reduced, and the learning difficulty is lower. The optical orbital angularmomentum machine learning recognition method is used for free space optical communication.

Description

technical field [0001] The invention belongs to the technical field of optical communication, and mainly relates to efficient identification of optical orbital angular momentum, in particular to a turbulent effect-based optical orbital angular momentum machine learning identification method for free-space optical communication based on optical orbital angular momentum. Background technique [0002] With the rapid development of optical information technology, information exchange methods continue to increase, the scope of information continues to expand, people's demand for information transmission, information security and confidentiality continues to increase, which leads to the transmission channel of optical information by optical fiber with limited space The medium extends to the atmosphere and water medium with infinite or semi-infinite space, and the carrier of optical information also adds a new degree of freedom of orbital angular momentum to the traditional degrees ...

AI Technical Summary

Problems solved by technology

Although the algorithm seems simple, it is difficult to apply a model to a variety of turbulent environments. Directly using images for orbital angular momentum pattern recognition not only requires a large number of training samples but also is difficult to learn. When the number of orbital angular momentum patterns is large, the accuracy rate will decrease. The calculation time is significantly reduced, and the calculation time is more lengthy, and there are still some problems in the actual optical communication system

[0005] In summary, the problems existing in the existing technology are that the recognition accuracy is not high when large-scale orbital angular momentum and strong turbulence are transmitted over long distances. The recognition method based on machine learning has a large sample size, high training difficulty, and low computational efficiency.

Images