机器学习预测多折射率层有源光纤的模场特性  

Machine Learning Predicting Mode Properties for Multi-Layer Active Fibers

作　　者：安毅 蒋敏 陈潇 李俊 粟荣涛 黄良金 潘志勇 冷进勇 姜宗福[1,3,4] 周朴[1] An Yi;Jiang Min;Chen Xiao;Li Jun;Su Rongtao;Huang Liangjin;Pan Zhiyong;Leng Jinyong;Jiang Zongfu;Zhou Pu(College of Advanced Interdisciplinary Studies,National University of Defense Technology,Changsha 410073,Hunan,China;Test Center,National University of Defense Technology,Xi an 710106,Shaanxi,China;Nanhu Laser Laboratory,National University of Defense Technology,Changsha 410073,Hunan,China;Hunan Provincial Key Laboratory of High Energy Laser Technology,National University of Defense Technology,Changsha 410073,Hunan,China)

机构地区：[1]国防科技大学前沿交叉学科学院,湖南长沙410073 [2]国防科技大学试验训练基地,陕西西安710106 [3]国防科技大学南湖之光实验室,湖南长沙410073 [4]国防科技大学高能激光技术湖南省重点实验室,湖南长沙410073

出　　处：《中国激光》2023年第11期187-194,共8页Chinese Journal of Lasers

基　　金：国家自然科学基金(61805280);国防科技大学学校科研计划(ZK19-07);脉冲功率激光技术国家重点实验室主任基金(SKL2020ZR07);湖南省研究生科研创新项目资助(CX20210018)。

摘　　要：高功率光纤激光是当前我国激光科学技术领域的前沿热点,而稀土掺杂的有源光纤是高功率光纤激光器的核心器件。与常规有源光纤不同,多折射率层有源光纤的纤芯和包层之间增加了一个或多个辅助折射率层,展现出了特殊的模场特性,有望进一步提升高功率光纤激光的输出功率。利用传统方法分析不同结构参数下多折射率层有源光纤的模场特性时,通常需要耗费较长的时间求解麦克斯韦方程组。笔者首次引入机器学习算法来预测多折射率层有源光纤的模场特性。该方法仅需要数据空间中0.1%的样本,就可以学习多折射率层有源光纤结构参数与其模场特性之间的复杂映射关系,进而实现无须求解麦克斯韦方程组的快速精准预测。该方法的平均预测误差小于0.6%,预测速度相比传统方法提升了约7000倍,为多折射率层有源光纤的模场特性分析提供了新思路。Objective Recently,high-power fiber lasers(HPFLs)have become a popular topic in laser science and technology.Rare earthdoped active fibers are key components of HPFL.In contrast to common active fibers,one or more auxiliary refractive index layers are added between the core and cladding of multi-layer active fibers.These types of fibers exhibit special mode properties;therefore,they are expected to further enhance the output power of HPFLs.Evaluating the mode properties of multilayer active fibers under different fiber structural parameters is important because the corresponding results reveal the relationship between the structural parameters and fiber properties,indicate which structural parameter has the best performance,and provide guidance for fiber design.Traditional methods,such as finite difference,finite element,and transfer matrix methods,have been adopted to evaluate the mode properties of such fibers.However,these traditional approaches typically require a long time to repeatedly solve Maxwell s equations under different structural parameters.Doubtlessly,a faster approach to evaluating multilayer active fibers would be vital.In this study,we used machine learning to predict the mode properties of multilayer active fibers for the first time.This new approach can achieve fast and accurate predictions without solving Maxwell s equations.Methods We introduce a shallow neural network(NN)to learn the mapping from input structural parameters to output mode properties.The structural parameters include the refractive index difference between the core and cladding,thickness of the auxiliary layers,and working wavelength.The mode properties included the effective index,mode field area,and power-filling factor of the fundamental mode(FM)and higher-order mode(HOM).The NN approach can be divided into three steps:data generation,network training,and rapid evaluation(Fig.2).In the data generation step,0.1%of the training samples in the defined data space(Table 1)were generated using the transfer matrix method.An NN w

关 键 词：光纤光学 人工智能 机器学习 光纤激光 有源光纤 多折射率层光纤 模场特性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]