{"title":"基于人工智能的通用光纤波导光栅耦合器快速设计","authors":"Zhenjia Zeng, Qiangsheng Huang, Sailing He","doi":"10.2528/pierm23072703","DOIUrl":null,"url":null,"abstract":"|Utilizing deep learning to replace numerical simulation solvers for electromagnetic wave propagation is a promising approach for the rapid design of photonic devices. However, to realize the advantages of deep learning for rapid design, it is essential to apply it to a general device structure. In this study, we propose a method that employs deep learning to assist in fast design of a general grating coupler structure. We use a modi(cid:12)ed 1D-ResNet18(1D-MR18) to predict the coupling efficiency of various grating couplers at different wavelengths. After comparing and selecting the optimal combination of learning rate, activation functions, and batch normalization size, the 1D-MR18 demonstrates remarkable accuracy ( MSE : 2 : 18 (cid:2) 10 (cid:0) 5 , R 2 : 0 : 969, MAE : 0 : 003). By integrating the 1D-MR18 with the adaptive particle swarm algorithm, we can efficiently design periodic and nonuniform grating couplers that meet various functional requirements, including single-wavelength grating couplers, multi-wavelength grating couplers, and robust grating couplers. The time for designing a single device is no more than 2 minutes, and the shortest is only 17 seconds. This novel approach of employing deep learning for the fast and efficient design from standard photonic device structures offers valuable insights and guidance for photonic devices design.","PeriodicalId":39028,"journal":{"name":"Progress in Electromagnetics Research M","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AI-based Fast Design for General Fiber-to-waveguide Grating Couplers\",\"authors\":\"Zhenjia Zeng, Qiangsheng Huang, Sailing He\",\"doi\":\"10.2528/pierm23072703\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"|Utilizing deep learning to replace numerical simulation solvers for electromagnetic wave propagation is a promising approach for the rapid design of photonic devices. However, to realize the advantages of deep learning for rapid design, it is essential to apply it to a general device structure. In this study, we propose a method that employs deep learning to assist in fast design of a general grating coupler structure. We use a modi(cid:12)ed 1D-ResNet18(1D-MR18) to predict the coupling efficiency of various grating couplers at different wavelengths. After comparing and selecting the optimal combination of learning rate, activation functions, and batch normalization size, the 1D-MR18 demonstrates remarkable accuracy ( MSE : 2 : 18 (cid:2) 10 (cid:0) 5 , R 2 : 0 : 969, MAE : 0 : 003). By integrating the 1D-MR18 with the adaptive particle swarm algorithm, we can efficiently design periodic and nonuniform grating couplers that meet various functional requirements, including single-wavelength grating couplers, multi-wavelength grating couplers, and robust grating couplers. The time for designing a single device is no more than 2 minutes, and the shortest is only 17 seconds. This novel approach of employing deep learning for the fast and efficient design from standard photonic device structures offers valuable insights and guidance for photonic devices design.\",\"PeriodicalId\":39028,\"journal\":{\"name\":\"Progress in Electromagnetics Research M\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Progress in Electromagnetics Research M\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2528/pierm23072703\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Progress in Electromagnetics Research M","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2528/pierm23072703","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
AI-based Fast Design for General Fiber-to-waveguide Grating Couplers
|Utilizing deep learning to replace numerical simulation solvers for electromagnetic wave propagation is a promising approach for the rapid design of photonic devices. However, to realize the advantages of deep learning for rapid design, it is essential to apply it to a general device structure. In this study, we propose a method that employs deep learning to assist in fast design of a general grating coupler structure. We use a modi(cid:12)ed 1D-ResNet18(1D-MR18) to predict the coupling efficiency of various grating couplers at different wavelengths. After comparing and selecting the optimal combination of learning rate, activation functions, and batch normalization size, the 1D-MR18 demonstrates remarkable accuracy ( MSE : 2 : 18 (cid:2) 10 (cid:0) 5 , R 2 : 0 : 969, MAE : 0 : 003). By integrating the 1D-MR18 with the adaptive particle swarm algorithm, we can efficiently design periodic and nonuniform grating couplers that meet various functional requirements, including single-wavelength grating couplers, multi-wavelength grating couplers, and robust grating couplers. The time for designing a single device is no more than 2 minutes, and the shortest is only 17 seconds. This novel approach of employing deep learning for the fast and efficient design from standard photonic device structures offers valuable insights and guidance for photonic devices design.
期刊介绍:
Progress In Electromagnetics Research (PIER) M publishes peer-reviewed original and comprehensive articles on all aspects of electromagnetic theory and applications. Especially, PIER M publishes papers on method of electromagnetics, and other topics on electromagnetic theory. It is an open access, on-line journal in 2008, and freely accessible to all readers via the Internet. Manuscripts submitted to PIER M must not have been submitted simultaneously to other journals.