• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Feng, Feng (Feng, Feng.) | Guo, Qianyi (Guo, Qianyi.) | Chen, Jing (Chen, Jing.) | Liu, Wei (Liu, Wei.) | Zhang, Wei (Zhang, Wei.) | Zhang, Jianan (Zhang, Jianan.) | Na, Weicong (Na, Weicong.) | Ma, Kaixue (Ma, Kaixue.) | Zhang, Qi-Jun (Zhang, Qi-Jun.)

收录:

EI Scopus SCIE

摘要:

Gradient-based surrogate optimization usually has a fast convergence capability. However, it can be easily stuck in local minima, especially when the electromagnetic (EM) response of the starting point is far away from the design specification. This article proposes a novel feature and EM sensitivity coassisted neuro-transfer function (TF) surrogate optimization for microwave filter design. The proposed technique introduces EM sensitivity information into the pole-zero-based neuro-TF with feature parameters for the first time. New formulations are derived for establishing the adjoint neuro-TF model with poles and zeros as the transfer function parameters. More accurate gradients of the neuro-TF outputs with respect to design variables are subsequently achieved by the training with EM sensitivity. Two sets of feature parameters, i.e., feature frequencies and feature heights, are used in the proposed technique. The adjoint feature frequencies are proposed as the gradients of feature frequencies, which are calculated using the trained adjoint neural network outputs. New formulations are further derived for the gradients of feature heights using both trained adjoint neuro-TF and adjoint neural network outputs. To improve the robustness of the optimization process, the trust region algorithm is also introduced. By the coassistance of feature parameters and EM sensitivities, the proposed technique can achieve a further acceleration over the existing feature-assisted techniques. This article utilizes three microwave filter examples to demonstrate this technique.

关键词:

feature parameters Microwave circuits Optimization Poles and zeros neuro-transfer function (neuro-TF) Neural networks Microwave theory and techniques Electromagnetic (EM) design surrogate optimization Microwave filters sensitivity Sensitivity gradient-based optimization

作者机构:

  • [ 1 ] [Feng, Feng]Tianjin Univ, Tianjin Key Lab Imaging & Sensing Microelect Techn, Tianjin 300072, Peoples R China
  • [ 2 ] [Guo, Qianyi]Tianjin Univ, Tianjin Key Lab Imaging & Sensing Microelect Techn, Tianjin 300072, Peoples R China
  • [ 3 ] [Chen, Jing]Tianjin Univ, Tianjin Key Lab Imaging & Sensing Microelect Techn, Tianjin 300072, Peoples R China
  • [ 4 ] [Liu, Wei]Tianjin Univ, Tianjin Key Lab Imaging & Sensing Microelect Techn, Tianjin 300072, Peoples R China
  • [ 5 ] [Ma, Kaixue]Tianjin Univ, Tianjin Key Lab Imaging & Sensing Microelect Techn, Tianjin 300072, Peoples R China
  • [ 6 ] [Feng, Feng]Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
  • [ 7 ] [Guo, Qianyi]Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
  • [ 8 ] [Chen, Jing]Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
  • [ 9 ] [Liu, Wei]Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
  • [ 10 ] [Ma, Kaixue]Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
  • [ 11 ] [Zhang, Wei]Beijing Univ Posts & Telecommun, Sch Elect Engn, Beijing 100876, Peoples R China
  • [ 12 ] [Zhang, Jianan]Southeast Univ, State Key Lab Millimeter Waves, Nanjing 210096, Peoples R China
  • [ 13 ] [Na, Weicong]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 14 ] [Zhang, Qi-Jun]Carleton Univ, Dept Elect, Ottawa, ON K1S 5B6, Canada

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES

ISSN: 0018-9480

年份: 2023

期: 11

卷: 71

页码: 4749-4761

4 . 3 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:19

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 10

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:322/4970203
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司