A machine learning and genetic algorithm-based notch band design method for ultra-wideband antennas

IF 2.5 4区工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

Journal of Computational Electronics Pub Date : 2025-04-30 DOI:10.1007/s10825-025-02327-0

Chengjie Li, Ruxin Zheng, Yaogen Li, Yixing Gu, Mingjie Sheng, Shiping Tang

{"title":"A machine learning and genetic algorithm-based notch band design method for ultra-wideband antennas","authors":"Chengjie Li, Ruxin Zheng, Yaogen Li, Yixing Gu, Mingjie Sheng, Shiping Tang","doi":"10.1007/s10825-025-02327-0","DOIUrl":null,"url":null,"abstract":"<div><p>In this article, an innovative optimization design method for ultra-wideband (UWB) antennas that leverages machine learning models and intelligent optimization algorithms is presented. The method aims to improve the efficiency and reduce the cost of antenna design. By incorporating U-shaped slots and rectangular slot resonators, the UWB antenna achieves dual-notch frequency bands. This method is based on a machine learning model to establish the relationship between structural parameters and performance parameters, and then uses a method to create a dataset based on prior knowledge. Comparing the performance of three machine learning models, Gaussian process regression, support vector machine regression, and BP neural network, the (BP) neural network model and genetic algorithm are finally adopted for the optimization of the geometric structure of ultra-wideband antennas. The optimized antenna demonstrates dual-band suppression capabilities at center frequencies of 3.9 GHz and 5.4 GHz, effectively mitigating interference in the satellite communication C-band and the WLAN band, respectively. The effectiveness of the optimization strategy combining machine learning with a genetic algorithm was validated through full-wave simulations.</p></div>","PeriodicalId":620,"journal":{"name":"Journal of Computational Electronics","volume":"24 3","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computational Electronics","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10825-025-02327-0","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

In this article, an innovative optimization design method for ultra-wideband (UWB) antennas that leverages machine learning models and intelligent optimization algorithms is presented. The method aims to improve the efficiency and reduce the cost of antenna design. By incorporating U-shaped slots and rectangular slot resonators, the UWB antenna achieves dual-notch frequency bands. This method is based on a machine learning model to establish the relationship between structural parameters and performance parameters, and then uses a method to create a dataset based on prior knowledge. Comparing the performance of three machine learning models, Gaussian process regression, support vector machine regression, and BP neural network, the (BP) neural network model and genetic algorithm are finally adopted for the optimization of the geometric structure of ultra-wideband antennas. The optimized antenna demonstrates dual-band suppression capabilities at center frequencies of 3.9 GHz and 5.4 GHz, effectively mitigating interference in the satellite communication C-band and the WLAN band, respectively. The effectiveness of the optimization strategy combining machine learning with a genetic algorithm was validated through full-wave simulations.

查看原文本刊更多论文

基于机器学习和遗传算法的超宽带天线陷波带设计方法

本文提出了一种利用机器学习模型和智能优化算法的超宽带（UWB）天线创新优化设计方法。该方法旨在提高天线设计效率，降低天线设计成本。通过结合u型槽和矩形槽谐振器，UWB天线实现了双陷波频段。该方法是基于机器学习模型建立结构参数和性能参数之间的关系，然后使用基于先验知识的方法创建数据集。对比高斯过程回归、支持向量机回归和BP神经网络三种机器学习模型的性能，最终采用BP神经网络模型和遗传算法对超宽带天线的几何结构进行优化。优化后的天线在中心频率为3.9 GHz和5.4 GHz时具有双频抑制能力，分别有效地抑制了卫星通信c频段和WLAN频段的干扰。通过全波仿真验证了机器学习与遗传算法相结合的优化策略的有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Computational Electronics ENGINEERING, ELECTRICAL & ELECTRONIC-PHYSICS, APPLIED

CiteScore

4.50

自引率

4.80%

发文量

142

审稿时长

>12 weeks

期刊介绍： he Journal of Computational Electronics brings together research on all aspects of modeling and simulation of modern electronics. This includes optical, electronic, mechanical, and quantum mechanical aspects, as well as research on the underlying mathematical algorithms and computational details. The related areas of energy conversion/storage and of molecular and biological systems, in which the thrust is on the charge transport, electronic, mechanical, and optical properties, are also covered. In particular, we encourage manuscripts dealing with device simulation; with optical and optoelectronic systems and photonics; with energy storage (e.g. batteries, fuel cells) and harvesting (e.g. photovoltaic), with simulation of circuits, VLSI layout, logic and architecture (based on, for example, CMOS devices, quantum-cellular automata, QBITs, or single-electron transistors); with electromagnetic simulations (such as microwave electronics and components); or with molecular and biological systems. However, in all these cases, the submitted manuscripts should explicitly address the electronic properties of the relevant systems, materials, or devices and/or present novel contributions to the physical models, computational strategies, or numerical algorithms.