Scholarlink

<p>This article presents the design of a graphene-based microstrip patch antenna, operating frequency range: (1–5) THz for terahertz (THz) applications. This paper presents simulations and a machine learning (ML) approach to characterize the performance characteristics, such as S11, Voltage Standing Wave Ratio (VSWR), gain, radiation, and total efficiencies, as well as the radiation pattern in horizontal (H, XZ) and vertical (V, XY) planes. The Computer Simulation Tool (CST) full microwave studio is used to model the antenna with dimensions of Length (L) and <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation> Width (W): 93 μm <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation> 113 μm, a return loss around − 40 dB, with 11 multi-band frequencies, achieving a maximum gain of 7.5 dBi at 3.2 THz. To analyze the effect of geometric parameters like length (<InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(L_p\)</EquationSource> </InlineEquation>) and width (<InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(W_p\)</EquationSource> </InlineEquation>) of the patch and graphene properties such as chemical potential (<InlineEquation ID="IEq7"> <EquationSource Format="TEX">\(\mu _c\)</EquationSource> </InlineEquation>) and relaxation time (<InlineEquation ID="IEq8"> <EquationSource Format="TEX">\(\tau\)</EquationSource> </InlineEquation>) on the performance characteristics of the patch antenna, three ML models are developed, such as Artificial Neural Networks (ANN), Random Forest (<InlineEquation ID="IEq9"> <EquationSource Format="TEX">\(RF^*\)</EquationSource> </InlineEquation>), and Support Vector Machine (SVM). The training data is collected for 784 simulations. The ANN architecture is built with four features in the input layer and one output layer to predict performance characteristics. The performance of the developed models is evaluated using metrics such as Mean Squared Error (MSE) and R-Squared (R<sup>2</sup>). Out of three developed models, ANN predicts the performance within 0.7 milliseconds (ms) with high accuracy, achieving an R<sup>2</sup> of 0.99 for all performance characteristics. The predicted results discuss that the regression-based predictive models can capture the nonlinear relationship between antenna geometry and electromagnetic (EM) responses. These advantages, such as faster predictions and higher prediction accuracy, make these models, especially the ANN model, a replacement for traditional EM simulations by reducing computation time. Such qualities made the proposed ML models a powerful alternative to traditional simulation tools, making these antennas useful for next-generation wireless communication systems in the THz frequency range and beyond 6G.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting the performance of a graphene-based patch antenna using a machine learning model for terahertz applications

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月23日

查看全文
  • Gayatri Routhu,
  • Shaik Mohammed Abzal,
  • Manas Sarkar,
  • Sravani Nagireddy,
  • Mark Clemente Arenas,
  • Rupesh Kumar

摘要

This article presents the design of a graphene-based microstrip patch antenna, operating frequency range: (1–5) THz for terahertz (THz) applications. This paper presents simulations and a machine learning (ML) approach to characterize the performance characteristics, such as S11, Voltage Standing Wave Ratio (VSWR), gain, radiation, and total efficiencies, as well as the radiation pattern in horizontal (H, XZ) and vertical (V, XY) planes. The Computer Simulation Tool (CST) full microwave studio is used to model the antenna with dimensions of Length (L) and \(\times\) Width (W): 93 μm \(\times\) 113 μm, a return loss around − 40 dB, with 11 multi-band frequencies, achieving a maximum gain of 7.5 dBi at 3.2 THz. To analyze the effect of geometric parameters like length ( \(L_p\) ) and width ( \(W_p\) ) of the patch and graphene properties such as chemical potential ( \(\mu _c\) ) and relaxation time ( \(\tau\) ) on the performance characteristics of the patch antenna, three ML models are developed, such as Artificial Neural Networks (ANN), Random Forest ( \(RF^*\) ), and Support Vector Machine (SVM). The training data is collected for 784 simulations. The ANN architecture is built with four features in the input layer and one output layer to predict performance characteristics. The performance of the developed models is evaluated using metrics such as Mean Squared Error (MSE) and R-Squared (R2). Out of three developed models, ANN predicts the performance within 0.7 milliseconds (ms) with high accuracy, achieving an R2 of 0.99 for all performance characteristics. The predicted results discuss that the regression-based predictive models can capture the nonlinear relationship between antenna geometry and electromagnetic (EM) responses. These advantages, such as faster predictions and higher prediction accuracy, make these models, especially the ANN model, a replacement for traditional EM simulations by reducing computation time. Such qualities made the proposed ML models a powerful alternative to traditional simulation tools, making these antennas useful for next-generation wireless communication systems in the THz frequency range and beyond 6G.