Parametric Modeling of Fifth-Order Waveguide Filter using Combined Hybrid Transfer Functions with Neural networks - 文章详情页

作者：

收录：

EI Scopus

摘要：

Neuro-transfer　function　(neuro-TF)　approaches　are　diffusely　applied　in　the　field　of　parametric　modeling　technology,　the　coefficient　of　the　rational　transfer　function　become　more　responsive　to　dealing　with　higher　order　problems;　The　sensitivity　of　the　pole-residue　transfer　function　keeps　at　a　low　level,　but　the　problems　of　noncontinuity　and　non-smooth　of　the　poles/residues　will　appear　when　the　geometric　dimension　changes　greatly.　This　paper　applies　a　hybrid　neuro-TF　to　parameterized　model　of　a　fifth-order　waveguide　filter　to　address　the　above　problem.　From　the　results,　this　method　of　hybrid　neuro-TF　can　obtain　better　improvement　in　accuracy　than　other　methods.　©　2023　IEEE.

关键词：

Circular waveguides Poles Transfer functions Waveguide filters Rational functions

作者机构：

[ 1 ] [Liu, Jinyi]Tianjin University, School of Microelectronics, Tianjin, China
[ 2 ] [Feng, Feng]Tianjin University, School of Microelectronics, Tianjin, China
[ 3 ] [Na, Weicong]Beijing University of Technology, School of Information and Technology, Beijing, China
[ 4 ] [Liu, Wenyuan]Shaanxi University of Science and Technology, College of Electrical and Information Engineering, Xian, China
[ 5 ] [Lin, Zhu]Tianjin Chengjian University, School of Control and Mechanical Engineering, Tianjin, China
[ 6 ] [Ma, Kaixue]Tianjin University, School of Microelectronics, Tianjin, China
[ 7 ] [Zhang, Qi-Jun]Carleton University, Department of Electronics, Ottawa; ON; K1S5B6, Canada

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至