A Novel Proximal Policy Optimization Approach for Filter Design

被引：0

作者：

Fan, Dongdong ^{[1
]}

Ding, Shuai ^{[1
,2
]}

Zhang, Haotian ^{[2
]}

Zhang, Weihao ^{[4
]}

Jia, Qingsong ^{[2
]}

Han, Xu ^{[2
]}

Tang, Hao ^{[2
]}

Zhu, Zhaojun ^{[2
]}

Zhou, Yuliang ^{[3
]}

机构：

[1] Univ Elect Sci & Technol China, Shenzhen Inst Adv Study, Shenzhen 518110, Peoples R China

[2] Univ Elect Sci & Technol China, Inst Appl Phys, Chengdu 610054, Peoples R China

[3] Univ Elect Sci & Technol China, Sch Aeronaut & Astronaut, Chengdu 610054, Peoples R China

[4] Univ Elect Sci & Technol China, Sch Mat & Energy, Chengdu 610054, Peoples R China

来源：

APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL | 2024年 / 39卷 / 05期

关键词：

bandpass filters (BPF); coupling matrix synthesis; Proximal Policy Optimization (PPO); NEURAL-NETWORKS;

D O I：

10.13052/2024.ACES.J.390502

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper proposes a proximal policy optimization (PPO) algorithm for coupling matrix synthesis of microwave filters. With the improvement of filter design requirement, the limitations of traditional methods such as limited applicability are becoming more and more obvious. In order to improve the filter synthesis efficiency, this paper constructs a reinforcement learning algorithm based on Actor-Critic network architecture, and designs a unique filter coupling matrix synthesis reward function and action function, which can solve combinatorial optimization problems stably.

引用

页码：390 / 395

页数：6

共 17 条

[1] Intelligent Tuning of Microwave Cavity Filters Using Granular Multi-Swarm Particle Swarm Optimization
Bi, Leyu
Cao, Weihua
Hu, Wenkai
Wu, Min
[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2021, 68 (12) : 12901 - 12911
[2] Cameron R. J., 2018, Microwave filters for communication systems: fundamentals, design, and applications
[3] Space Mapping Design Framework Exploiting Tuning Elements
Cheng, Qingsha S.
Bandler, John W.
Koziel, Slawomir
[J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2010, 58 (01) : 136 - 144
[4] Dahl GE, 2013, INT CONF ACOUST SPEE, P8609, DOI 10.1109/ICASSP.2013.6639346
[5] Parametric Modeling of EM Behavior of Microwave Components Using Combined Neural Networks and Pole-Residue-Based Transfer Functions
Feng, Feng
Zhang, Chao
Ma, Jianguo
Zhang, Qi-Jun
[J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2016, 64 (01) : 60 - 77
[6] Glorot X., 2011, 14 INT C ART INT STA, DOI DOI 10.1002/ECS2.1832
[7] The vanishing gradient problem during learning recurrent neural nets and problem solutions
Hochreiter, S
[J]. INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS, 1998, 6 (02) : 107 - 116
[8] Accelerated Microwave Design Optimization With Tuning Space Mapping
Koziel, Slawomir
Meng, Jie
Bandler, John W.
Bakr, Mohamed H.
Cheng, Qingsha S.
[J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2009, 57 (02) : 383 - 394
[9] Deep learning
LeCun, Yann
Bengio, Yoshua
Hinton, Geoffrey
[J]. NATURE, 2015, 521 (7553) : 436 - 444
[10] Liang D, 2021, 2021 IEEE MTT-S INTERNATIONAL MICROWAVE FILTER WORKSHOP (IMFW), P46, DOI 10.1109/IMFW49589.2021.9642287

← 1 2 →