基于深度学习神经网络计算波导虹膜滤波器传输特性  

Calculation of transmission characteristics of waveguide iris filter based on deep learning neural network

作　　者：刘丽娟 陈宇 罗涛 唐闻锴 贾金果 LIU Lijuan;CHEN Yu;LUO Tao;TANG Wenkai;JIA Jinguo(Taiyuan Institute of Technology,Taiyuan 030008,China)

机构地区：[1]太原工业学院,太原030008

出　　处：《计算机应用文摘》2023年第12期301-302,304,共3页Chinese Journal of Computer Application

基　　金：基于深度学习逆向设计光学滤波器(20221182)。

摘　　要：全连接神经网络模型可以拟合复杂函数输入输出关系。文章基于深度学习神经网络方法,利用COMSOL数值模拟计算得到的数据集对神经网络进行训练,训练好的神经网络能够预测出响应未知的虹膜带通滤波器的透射谱。利用深度学习来解决波导滤波器传输特性的计算,可以避开传统的数理方法和麦克斯韦电磁方程的复杂求解,实现波导带通滤波器的快速预测。The fully connected neural network model can fit the input-output relationship of complex functions.Based on the deep learning neural network method,the neural network is trained using the data set calculated by COMSOI numerical simulation.The trained neural network can predict the transmission spectrum of the iris bandpass filter with unknown response.Using deep learning to solve the calculation of transmission characteristics of waveguide filter can avoid the complex solution of traditional mathematical methods and Maxwell's electromagnetic equation,and realize the fast prediction of waveguide bandpass filter.

关 键 词：深度学习 波导滤波器 虹膜 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]