基于深度物理启发神经网络的微波波导器件逆设计方法  

Inverse design of microwave waveguide devices based on deep physics-informed neural networks

作　　者：刘金品 王秉中[1] 陈传升 王任[1] Liu Jin-Pin;Wang Bing-Zhong;Chen Chuan-Sheng;Wang Ren(Institute of Applied Physics,University of Electronic Science and Technology of China,Chengdu 611731,China)

机构地区：[1]电子科技大学应用物理研究所,成都611731

出　　处：《物理学报》2023年第8期57-66,共10页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:62171081,61901086);四川省自然科学基金(批准号:2022NSFSC0039);四川省科技计划项目(批准号:2021YJ0100)资助的课题。

摘　　要：使用物理启发的神经网络方法求解物理逆问题正成为一种趋势,但仅通过损失函数引入物理信息的方案难以求解.为解决电磁器件逆设计中物理启发神经网络模型不易收敛的问题,本文引出了深度物理启发神经网络.深度物理启发神经网络使用偏微分方程的基本解构成的网络替代传统的前馈神经网络,将数学物理模型嵌入网络结构.这一特点使深度物理启发网络的训练参数具有实际物理意义,相较传统物理启发神经网络拥有更简洁的损失函数,计算效率和稳定性也有明显提升.以二端口波导的散射参数设计为例,数值实验结果表明该方案在保证与设计目标相关性系数大于0.99的同时,最快可在25 s实现器件逆设计,且能够获得多样化的结构设计结果.本文提出的方法为逆物理问题求解构建及神经网络的物理信息嵌入探索提供了新思路.Using physics-informed neural networks to solve physical inverse problems is becoming a trend.However,it is difficult to solve the scheme that only introduces physical knowledge through the loss function.Constructing a reasonable loss function to make the results converge becomes a challenge.To address the challenge of physics-informed neural network models for inverse design of electromagnetic devices,a deep physics-informed neural network is introduced by using the mode matching method.The physical equations have been integrated into the network structure when the network is constructed.This feature makes the deep physics-informed neural network have a more concise loss function and higher computational efficiency when solving physical inverse problems.In addition,the training parameters of deep physics-informed neural networks are physically meaningful compared with those of traditional physics-informed neural networks.Users can control the network by parameters more easily.Taking the scattering parameter design of a two-port waveguide for example,we present a new metal topology inverse design scheme and give a detailed explanation.In numerical experiments,we target a set of physically realizable scattering parameters and inversely design the metallic septum by using a deep physics-informed neural network.The results show that the method can not only achieve the design target but also obtain solutions with different topologies.The establishment of multiple solutions is extremely valuable in implementing the inverse design.It can allow the designer to determine the size and location of the design area more freely while achieving the performance requirements.This scheme is expected to promote the application and development of the inverse design of electromagnetic devices.

关 键 词：逆问题 逆设计 物理启发神经网络 拓扑优化 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN12[自动化与计算机技术—控制科学与工程]