基于卷积神经网络的微带滤波器结构参数估计

doi:10.13229/j.cnki.jdxbgxb20210440

摘要/Abstract

摘要：

针对神经网络微波建模耗时难的问题，提出了一种基于卷积神经网络的微带滤波器结构参数估计方法。采用单开路短截线加载矩形环谐振器和横向信号干扰技术分析和设计了一款双频带、三频带和四频带的微带滤波器，并利用电磁仿真软件提取数据。将微带滤波器的S参数和结构参数分别作为模型的输入和输出进行训练，并通过训练好的模型进行结构参数预测。利用卷积神经网络设计微带滤波器的方法，能够有效解决目前基于神经网络设计微带滤波器时输入参数较多、全连接造成模型复杂以及耗时长等问题。仿真结果表明，该方法设计的微带滤波器S参数有较高的准确率。

关键词: 电磁学, 环形谐振器, 带通滤波器, 卷积神经网络, 结构参数估计

Abstract:

Aiming at the issue of microwave modeling based on neural network， a structure parameter estimation method for microstrip bandpass filter based on convolution neural network is proposed. A dual band， three band and four band microstrip filter was designed and analyzed by adopting single open stub loaded rectangular ring resonator and transverse signal interference technology. Applying electromagnetic simulation software extracted the model training data and the S-parameters and structure parameters of microstrip filter are designed as the input and output of the proposed convolution neural network， respectively. Furthermore， the trained model was used to predict the structure parameters of microstrip filter. The proposed method adopts convolutional neural network to design the microstrip filter， which can effectively solve the problems of many input parameters， complex model caused by full connection and long time-consuming when using neural network to design microstrip filter. The simulation results show that the S-parameters of the microstrip filter designed by this method have high accuracy.

Key words: electromagnetic, ring resonator, band pass filter, convolutional neural network, structure parameter estimation

中图分类号:

TN713

张友俊,程顺延. 基于卷积神经网络的微带滤波器结构参数估计[J]. 吉林大学学报(工学版), 2022, 52(12): 3022-3028.

You-jun ZHANG,Shun-yan CHENG. Structure parameter estimation of microstrip filter based on convolutional neural network[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(12): 3022-3028.

图/表 10

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

参考文献 18

1	Pan Guang-yuan, Wu Yang, Yu Ming, et al. Inverse modeling for filters using a regularized deep neural network approach[J]. IEEE Microwave and Wireless Components Letters, 2020, 30(5): 457-460.
2	Feng Feng, Zhang Chao, Na Wei-cong, et al. Adaptive feature zero assisted surrogate-based EM optimization for microwave filter design[J]. IEEE Microwave and Wireless Components Letters, 2019, 29(1): 2-4.
3	Jin Jing, Feng Feng, Zhang Wei, et al. Recent advances in deep neural network technique for high-dimensional microwave modeling[C]∥2020 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), Hangzhou, China, 2020: No.9343496.
4	Jin K H, Mccann M T, Froustey E, et al. Deep convolutional neural network for inverse problems in imaging[J]. IEEE Transactions on Image Processing, 2017, 26(9):4509-4522.
5	刘太君, 陈豪, 苏日娜, 等. 基于神经网络的宽带功放动态非线性行为建模[J]. 微波学报, 2020, 36(1): 131-136.
	Liu Tai-jun, Chen Hao, Su Ri-na, et al. Modeling of dynamic nonlinear behavior of broadband amplifiers based on neural networks[J]. Journal of Microwaves, 2020, 36(1): 131-136.
6	Liu Wen-yuan, Na Wei-cong, Feng Feng, et al. A wiener-type dynamic neural network approach to the modeling of nonlinear microwave devices and its applications[C]∥2020 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), Hangzhou, China, 2020: No.2657501.
7	Kazemi N, Abdolrazzaghi M, Musilek P, et al. A temperature-compensated high-resolution microwave sensor using artificial neural network[J]. IEEE Microwave and Wireless Components Letters, 2020, 30(9): 919-922.
8	Na Wei-cong, Feng Feng, Zhang Chao, et al. A unified automated parametric modeling algorithm using knowledge-based neural network and l₁ optimization[J]. IEEE Transactions on Microwave Theory and Techniques, 2017, 65(3): 729-745.
9	Zhang Wei, Feng Feng, Jin Jing, et al. Parallel multiphysics optimization for microwave devices exploiting neural network surrogate[J]. IEEE Microwave and Wireless Components Letters, 2021, 31(4): 341-344.
10	Ohira M, Ao Y, Ma Z, et al. Automated microstrip bandpass filter design using feedforward and inverse models of neural network[C]∥2018 Asia-Pacific Microwave Conference (APMC), Kyoto, Japan, 2018: 1292-1294.
11	Du Hao, Yang Qian, Dai Xin-yue, et al. A structure parameter estimation method for microstrip bpf based on multilayer fcn[J]. IEEE Microwave and Wireless Components Letters, 2020, 30(6): 581-584.
12	Jin Jing, Zhang Chao, Feng Feng, et al. Deep neural network technique for high-dimensional microwave modeling and applications to parameter extraction of microwave filters[J]. IEEE Transactions on Microwave Theory and Techniques, 2019, 67(10): 4140-4155.
13	Zhao Ping, Wu Ke. Homotopy optimization of microwave and millimeter-wave filters based on neural network model.[J]. IEEE Transactions on Microwave Theory and Techniques, 2020, 68(4): 1390-1400.
14	Zhang Chao, Jin Jing, Na Wei-cong, et al. Multivalued neural network inverse modeling and applications to microwave filters[J]. IEEE Transactions on Microwave Theory and Techniques, 2018, 66(8): 1-17.
15	钟辉, 李红, 李振建, 等. 基于卷积神经网络的图像拼接篡改检测算法[J]. 吉林大学学报:工学版, 2020, 50(4): 1428-1434.
	Zhong Hui, Li Hong, Li Zhen-jian, et al. Image stitching tamper detection algorithm based on convolutional neural network[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(4): 1428-1434.
16	Li Kai, Jiang Shui-qiao. Simple transversal signal-interference dual-/tri-/quad-band filters using single rectangular loop resonator[C]∥2019 International Conference on Communications, Information System and Computer Engineering(CISCE), National University of Defense Technology, Haikou, China, 2019: 168-170.
17	张友俊, 刘晓元. 基于信号干扰理论的差分带通滤波器[J]. 吉林大学学报:工学版, 2017, 47(3): 1003-1008.
	Zhang You-jun, Liu Xiao-yuan. Novel differential wideband bandpass filter based on signal interference technology[J]. Journal of Jilin University (Engineering and Technology Edition), 2017, 47(3): 1003-1008.
18	Mikase R, Ohira M, Ma Z, et al. A novel microstrip symmetric diagonal cross-coupling quadruplet bandpass filter using even/odd- mode stepped impedance resonators[C]∥2018 IEEE/MTT-S International Microwave Symposium-IMS, Philadelphia, PA, USA, 2018: 712-715.

相关文章 15

[1]	申铉京,张雪峰,王玉,金玉波. 像素级卷积神经网络多聚焦图像融合算法[J]. 吉林大学学报(工学版), 2022, 52(8): 1857-1864.
[2]	高明华,杨璨. 基于改进卷积神经网络的交通目标检测方法[J]. 吉林大学学报(工学版), 2022, 52(6): 1353-1361.
[3]	杨怀江,王二帅,隋永新,闫丰,周跃. 简化型残差结构和快速深度残差网络[J]. 吉林大学学报(工学版), 2022, 52(6): 1413-1421.
[4]	王学智,李清亮,李文辉. 融合迁移学习的土壤湿度预测时空模型[J]. 吉林大学学报(工学版), 2022, 52(3): 675-683.
[5]	李向军,涂洁莹,赵志宾. 基于多尺度融合卷积神经网络的熔解曲线有效性分类[J]. 吉林大学学报(工学版), 2022, 52(3): 633-639.
[6]	李先通,全威,王华,孙鹏程,安鹏进,满永兴. 基于时空特征深度学习模型的路径行程时间预测[J]. 吉林大学学报(工学版), 2022, 52(3): 557-563.
[7]	高文志,王彦军,王欣伟,张攀,李勇,董阳. 基于卷积神经网络的柴油机失火故障实时诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 417-424.
[8]	张龙,徐天鹏,王朝兵,易剑昱,甄灿壮. 基于卷积门控循环网络的齿轮箱故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 368-376.
[9]	杨军,高志明. 基于无监督变形网络的三维模型稠密对应关系计算[J]. 吉林大学学报(工学版), 2022, 52(12): 2971-2983.
[10]	申铉京,刘同壮,王玉,刘嘉伟. 基于卷积网络结构重参数化的车位状态检测算法[J]. 吉林大学学报(工学版), 2022, 52(12): 2898-2905.
[11]	车翔玖,陈赫元. 基于改进YOLOv4的多目标光盘检测算法[J]. 吉林大学学报(工学版), 2022, 52(11): 2662-2668.
[12]	曹洁,何智栋,余萍,王进花. 数据不平衡分布下轴承故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(11): 2523-2531.
[13]	郭志军,刘帅. 基于卷积神经网络的数字图像模糊增强算法[J]. 吉林大学学报(工学版), 2022, 52(10): 2399-2404.
[14]	潘晓英,魏德,赵逸喆. 基于Mask R⁃CNN和上下文卷积神经网络的肺结节检测[J]. 吉林大学学报(工学版), 2022, 52(10): 2419-2427.
[15]	段亮,宋春元,刘超,魏苇,吕成吉. 基于机器学习的高速列车轴承温度状态识别[J]. 吉林大学学报(工学版), 2022, 52(1): 53-62.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

真实值			预测值			误差/%
L₃/mm	L₄/mm	S/mm	L₃/mm	L₄/mm	S/mm	误差/%
12.00	20.00	0.90	12.44	20.32	0.93	2.8
11.50	3.00	1.30	10.87	3.10	1.64	4.9
14.00	17.00	2.10	13.78	17.13	2.20	1.5

方法	均方误差	数据提取时间/h	训练时间/h	总耗时/h
文献［10］	6.59	13.00	0.25	13.25
文献［11］	142.80	-	6.40	6.40
本文	0.51	13.00	0.16	13.16