Presentation 2022-11-17
[Invited Lecture] A Neural-Network Assisted Microwave Filter Design
Masataka Ohira, Zhewang Ma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A surrogate-based electromagnetic (EM) optimization method using neural networks (NNs) is presented for computationally efficient microwave bandpass filter (BPF) design. This paper first describes the forward problem (EM analysis) and the inverse problems (EM circuit design), and the two fundamental issues in BPF designs. To accelerate the BPF design, two surrogate models of forward and inverse models are introduced, which are built with NNs. As a result, the inverse model can instantaneously guess initial structural parameters with high accuracy by inputting synthesized coupling-matrix elements into the NN. Then, the forward model in conjunction with optimization algorithm enables designers to rapidly find optimal structural parameters. The effectiveness of the surrogate-based EM optimization is verified through structural designs of a fifth-order microstrip BPF.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) microwave filters / surrogate model / neural network / optimization design
Paper # EMT2022-46
Date of Issue 2022-11-10 (EMT)

Conference Information
Committee EMT / IEE-EMT
Conference Date 2022/11/17(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Kikai-Shinko-Kaikan Bldg.
Topics (in Japanese) (See Japanese page)
Topics (in English) Electromagnetic Theory, etc.
Chair Hiroyuki Deguchi(Doshisha Univ.) / Shinichi Furukawa(Nihon Univ.)
Vice Chair Hideki Kawaguchi(Muroran Inst. of Tech)
Secretary Hideki Kawaguchi(Mitsubishi Electric) / (Kyushu Sangyo Univ.)
Assistant Ryo Natsuaki(Univ. of Tokyo) / Kazuki Niino(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Electromagnetic Theory / Technical Meeting on Electromagnetic Theory
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Lecture] A Neural-Network Assisted Microwave Filter Design
Sub Title (in English)
Keyword(1) microwave filters
Keyword(2) surrogate model
Keyword(3) neural network
Keyword(4) optimization design
1st Author's Name Masataka Ohira
1st Author's Affiliation Saitama University(Saitama Univ.)
2nd Author's Name Zhewang Ma
2nd Author's Affiliation Saitama University(Saitama Univ.)
Date 2022-11-17
Paper # EMT2022-46
Volume (vol) vol.122
Number (no) EMT-256
Page pp.pp.12-17(EMT),
#Pages 6
Date of Issue 2022-11-10 (EMT)