Robert Tempke, Liam A Thomas, Christina Wildfire, D. Shekhawat, T. Musho
{"title":"将散射参数转换为复介电常数的机器学习方法","authors":"Robert Tempke, Liam A Thomas, Christina Wildfire, D. Shekhawat, T. Musho","doi":"10.1080/08327823.2021.1993046","DOIUrl":null,"url":null,"abstract":"Abstract This study investigates the application of artificial neural networks to determine the complex dielectric material properties derived from experimental VNA scattering parameter measurements. The study utilizes a finite element approach to synthetically generate data to train the neural network. The neural network was trained using a supervised learning approach and validated using experimental measurement data. The frequency range of interest was between 0.1 and 13.5 GHz with the real part of the dielectric constants ranging from 1 − 100 and the imaginary part ranging from 0 − 0.2. This modelling approach decreases the uncertainty when compared to existing inverse approaches. This approach demonstrates a general framework that can be used for converting experimental or computational derived scattering parameters to complex permittivities.","PeriodicalId":16556,"journal":{"name":"Journal of Microwave Power and Electromagnetic Energy","volume":"64 1","pages":"287 - 302"},"PeriodicalIF":0.9000,"publicationDate":"2021-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Machine learning approach to transform scattering parameters to complex permittivities\",\"authors\":\"Robert Tempke, Liam A Thomas, Christina Wildfire, D. Shekhawat, T. Musho\",\"doi\":\"10.1080/08327823.2021.1993046\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract This study investigates the application of artificial neural networks to determine the complex dielectric material properties derived from experimental VNA scattering parameter measurements. The study utilizes a finite element approach to synthetically generate data to train the neural network. The neural network was trained using a supervised learning approach and validated using experimental measurement data. The frequency range of interest was between 0.1 and 13.5 GHz with the real part of the dielectric constants ranging from 1 − 100 and the imaginary part ranging from 0 − 0.2. This modelling approach decreases the uncertainty when compared to existing inverse approaches. This approach demonstrates a general framework that can be used for converting experimental or computational derived scattering parameters to complex permittivities.\",\"PeriodicalId\":16556,\"journal\":{\"name\":\"Journal of Microwave Power and Electromagnetic Energy\",\"volume\":\"64 1\",\"pages\":\"287 - 302\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2021-10-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Microwave Power and Electromagnetic Energy\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1080/08327823.2021.1993046\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Microwave Power and Electromagnetic Energy","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/08327823.2021.1993046","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
Machine learning approach to transform scattering parameters to complex permittivities
Abstract This study investigates the application of artificial neural networks to determine the complex dielectric material properties derived from experimental VNA scattering parameter measurements. The study utilizes a finite element approach to synthetically generate data to train the neural network. The neural network was trained using a supervised learning approach and validated using experimental measurement data. The frequency range of interest was between 0.1 and 13.5 GHz with the real part of the dielectric constants ranging from 1 − 100 and the imaginary part ranging from 0 − 0.2. This modelling approach decreases the uncertainty when compared to existing inverse approaches. This approach demonstrates a general framework that can be used for converting experimental or computational derived scattering parameters to complex permittivities.
期刊介绍:
The Journal of the Microwave Power Energy (JMPEE) is a quarterly publication of the International Microwave Power Institute (IMPI), aimed to be one of the primary sources of the most reliable information in the arts and sciences of microwave and RF technology. JMPEE provides space to engineers and researchers for presenting papers about non-communication applications of microwave and RF, mostly industrial, scientific, medical and instrumentation. Topics include, but are not limited to: applications in materials science and nanotechnology, characterization of biological tissues, food industry applications, green chemistry, health and therapeutic applications, microwave chemistry, microwave processing of materials, soil remediation, and waste processing.