首页|结合ANN的VO2/GST光子结构的多级动态光谱选择性调控

结合ANN的VO2/GST光子结构的多级动态光谱选择性调控

VO2/GST Photonic Structure Combined with ANN for Multi-level Dynamic Spectral Selectivity

扫码查看
光谱选择性吸收/发射的微纳光子结构广泛应用在诸多领域.本文提出了结合两种相变材料的简单多层光子结构的设计.首先采用FEM对该结构的光谱反射进行计算,建立数据集并训练了快速计算的ANN模型.最后展示了结合相变材料VO2和GST的光子结构的多级动态光谱选择性调控.结果显示光子结构参数为d1=0.1 μm、d2=0.3μm时,ANN模型计算时间为1.5 s,节省了计算耗时;此光子结构的四种模态表现不同的光谱选择性吸收.为光谱选择性调控提供了多级动态调控的新设计思路.
Photonic structure with selective absorption performance and emission control ability are widely applied in many fields.In this work,a design of multilayer photonic structure including two phase-changing materials is presented.Firstly,the spectral reflectivity of the structure is calculated by FEM method,and a dataset is established to train a ANN model.Finally,the multi-level dynamic spectral selectivity of the photonic structure combined with phase-changing material VO2 and GST is demonstrated.The results show that when the structural parameters are d1=0.1 μm and d2=0.3μm,the calculation time of the ANN model is 1.5 s,which saves the calculation time.The four modes of this photonic structure exhibit different spectral selective absorption.This work provides an idea of multi-level dynamic control for spectral selectivity.

photonic structurespectral selective tuningmulti-level dynamic tuningartificial neural network

宋奎龙、谢鸣、艾青

展开 >

哈尔滨工业大学能源科学与工程学院,哈尔滨 150001

光子结构 光谱选择性调控 多级动态调控 人工神经网络

国家自然科学基金国家重大科研仪器研制项目国家重点研发计划引力波探测重点专项

522278132022YFC2204300

2024

工程热物理学报
中国工程热物理学会 中国科学院工程热物理研究所

工程热物理学报

CSTPCD北大核心
影响因子:0.4
ISSN:0253-231X
年,卷(期):2024.45(9)