Application of Artificial Neural Network Base Enhanced MLP Model for Scattering Parameter Prediction of Dual-band Helical Antenna

IF 0.6 4区计算机科学 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC

Applied Computational Electromagnetics Society Journal Pub Date : 2023-09-18 DOI:10.13052/2023.aces.j.380504

Ahmet Uluslu

{"title":"Application of Artificial Neural Network Base Enhanced MLP Model for Scattering Parameter Prediction of Dual-band Helical Antenna","authors":"Ahmet Uluslu","doi":"10.13052/2023.aces.j.380504","DOIUrl":null,"url":null,"abstract":"Many design optimization problems have problems that seek fast, efficient and reliable based solutions. In such cases, artificial intelligence-based modeling is used to solve costly and complex problems. This study is based on the modeling of a multiband helical antenna using the Latin hypercube sampling (LHS) method using a reduced data enhanced multilayer perceptron (eMLP). The proposed helical antenna is dual-band and has resonance frequencies of 2.4 GHz and 2.75 GHz. The enhanced structure of the artificial neural network (ANN) was tested using 4 different training algorithms and a maximum of 10 different MLP architectures to determine the most suitable model in a simple and quick way. Then, performance comparison with other ANN networks was made to confirm the success of the model. Considering the high cost of antenna simulations, it is clear that the proposed model will save a lot of time. In addition, thanks to the selected sampling model, a wide range of modeling can be done with minimum data. When the target and prediction data are compared, it is seen that these data overlap to a large extent. As a result of the study, it was seen that the ANN modeling and the 125 samples used, were as accurate as an electromagnetic (EM) simulator for other input parameters in a wide range selected.","PeriodicalId":8207,"journal":{"name":"Applied Computational Electromagnetics Society Journal","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Computational Electromagnetics Society Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.13052/2023.aces.j.380504","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Many design optimization problems have problems that seek fast, efficient and reliable based solutions. In such cases, artificial intelligence-based modeling is used to solve costly and complex problems. This study is based on the modeling of a multiband helical antenna using the Latin hypercube sampling (LHS) method using a reduced data enhanced multilayer perceptron (eMLP). The proposed helical antenna is dual-band and has resonance frequencies of 2.4 GHz and 2.75 GHz. The enhanced structure of the artificial neural network (ANN) was tested using 4 different training algorithms and a maximum of 10 different MLP architectures to determine the most suitable model in a simple and quick way. Then, performance comparison with other ANN networks was made to confirm the success of the model. Considering the high cost of antenna simulations, it is clear that the proposed model will save a lot of time. In addition, thanks to the selected sampling model, a wide range of modeling can be done with minimum data. When the target and prediction data are compared, it is seen that these data overlap to a large extent. As a result of the study, it was seen that the ANN modeling and the 125 samples used, were as accurate as an electromagnetic (EM) simulator for other input parameters in a wide range selected.

查看原文本刊更多论文

基于人工神经网络的增强MLP模型在双频螺旋天线散射参数预测中的应用

许多设计优化问题都存在着寻求快速、高效、可靠的基础解决方案的问题。在这种情况下，基于人工智能的建模被用来解决昂贵而复杂的问题。本研究基于拉丁超立方体采样(LHS)方法，采用简化数据增强多层感知器(eMLP)对多波段螺旋天线进行建模。所提出的螺旋天线为双频，共振频率为2.4 GHz和2.75 GHz。使用4种不同的训练算法和最多10种不同的MLP架构对人工神经网络(ANN)的增强结构进行了测试，以简单快速地确定最合适的模型。然后，与其他人工神经网络进行性能比较，以证实该模型的成功。考虑到天线仿真的高成本，显然所提出的模型将节省大量的时间。此外，由于选择了采样模型，可以用最少的数据完成大范围的建模。将目标数据和预测数据进行比较，可以看出这些数据有很大程度的重叠。研究结果表明，在广泛的选择范围内，对于其他输入参数，ANN建模和使用的125个样本与电磁(EM)模拟器一样准确。

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

Applied Computational Electromagnetics Society Journal 工程技术-电信学

CiteScore

1.60

自引率

28.60%

发文量

审稿时长

9 months

期刊介绍： The ACES Journal is devoted to the exchange of information in computational electromagnetics, to the advancement of the state of the art, and to the promotion of related technical activities. A primary objective of the information exchange is the elimination of the need to "re-invent the wheel" to solve a previously solved computational problem in electrical engineering, physics, or related fields of study. The ACES Journal welcomes original, previously unpublished papers, relating to applied computational electromagnetics. All papers are refereed. A unique feature of ACES Journal is the publication of unsuccessful efforts in applied computational electromagnetics. Publication of such material provides a means to discuss problem areas in electromagnetic modeling. Manuscripts representing an unsuccessful application or negative result in computational electromagnetics is considered for publication only if a reasonable expectation of success (and a reasonable effort) are reflected. The technical activities promoted by this publication include code validation, performance analysis, and input/output standardization; code or technique optimization and error minimization; innovations in solution technique or in data input/output; identification of new applications for electromagnetics modeling codes and techniques; integration of computational electromagnetics techniques with new computer architectures; and correlation of computational parameters with physical mechanisms.