Qiangqiang Lin;Jinzhu Zhou;Guozhuang Fan;Yongji Ma
{"title":"一种用于滤波器调谐的生成神经网络","authors":"Qiangqiang Lin;Jinzhu Zhou;Guozhuang Fan;Yongji Ma","doi":"10.1109/LMWT.2025.3557834","DOIUrl":null,"url":null,"abstract":"A generative neural network (GTNN) is presented for microwave filter tuning, consisting of two steps. The first step involves offline modeling, where the physics mechanism of the microwave filter is combined with a shared weight neural network. In the second step, online tuning is performed, and tuning values are generated using a gradient descent method. The experimental results of three different filters illustrate that the GTNN achieves better tuning results, and the tuning value is generated in less than 16 s.","PeriodicalId":73297,"journal":{"name":"IEEE microwave and wireless technology letters","volume":"35 7","pages":"945-948"},"PeriodicalIF":3.4000,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Generative Neural Network for Filter Tuning\",\"authors\":\"Qiangqiang Lin;Jinzhu Zhou;Guozhuang Fan;Yongji Ma\",\"doi\":\"10.1109/LMWT.2025.3557834\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A generative neural network (GTNN) is presented for microwave filter tuning, consisting of two steps. The first step involves offline modeling, where the physics mechanism of the microwave filter is combined with a shared weight neural network. In the second step, online tuning is performed, and tuning values are generated using a gradient descent method. The experimental results of three different filters illustrate that the GTNN achieves better tuning results, and the tuning value is generated in less than 16 s.\",\"PeriodicalId\":73297,\"journal\":{\"name\":\"IEEE microwave and wireless technology letters\",\"volume\":\"35 7\",\"pages\":\"945-948\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE microwave and wireless technology letters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10973239/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE microwave and wireless technology letters","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10973239/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
A generative neural network (GTNN) is presented for microwave filter tuning, consisting of two steps. The first step involves offline modeling, where the physics mechanism of the microwave filter is combined with a shared weight neural network. In the second step, online tuning is performed, and tuning values are generated using a gradient descent method. The experimental results of three different filters illustrate that the GTNN achieves better tuning results, and the tuning value is generated in less than 16 s.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
