Characteristic extraction of soliton dynamics based on convolutional autoencoder neural network  

作　　者：刘聪聪 何江勇 王攀 邢登科 李晋 刘艳格 王志 Congcong Liu;Jiangyong He;Pan Wang;Dengke Xing;Jin Li;Yange Liu;Zhi Wang(Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology,Institute of Modern Optics,Nankai University,Tianjin 300350,China)

机构地区：[1]Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology,Institute of Modern Optics,Nankai University,Tianjin 300350,China

出　　处：《Chinese Optics Letters》2023年第3期108-112,共5页中国光学快报（英文版）

基　　金：supported by the National Natural Science Foundation of China(Nos.12274238 and 61835006);the National Key Research and Development Program of China(No.2018YFB1801802);the Beijing-Tianjin-Hebei Basic Research Cooperation Project(No.21JCZXJC00010);the Natural Science Foundation of Tianjin City(No.19JCZDJC31200);the Tianjin Research Innovation Project for Postgraduate Students(No.2021YJSB083)。

摘　　要：In this article,we use a convolutional autoencoder neural network to reduce data dimensioning and rebuild soliton dynamics in a passively mode-locked fiber laser.Based on the particle characteristic in double solitons and triple solitons interactions,we found that there is a strict correspondence between the number of minimum compression parameters and the number of independent parameters of soliton interaction.This shows that our network effectively coarsens the high-dimensional data in nonlinear systems.Our work not only introduces new prospects for the laser self-optimization algorithm,but also brings new insights into the modeling of nonlinear systems and description of soliton interactions.

关 键 词：fiber lasers optical solitons convolutional autoencoder neural network 

分 类 号：TN248[电子电信—物理电子学] TP183[自动化与计算机技术—控制理论与控制工程]