An Intelligent Antenna Synthesis Method Based on Machine Learning

Shi, Dan; Lian, Cheng; Cui, Keyi; Chen, Yazhou; Liu, Xiaoyong

doi:10.1109/tap.2022.3182693

Cited by 55 publications

(28 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, gain has an error of 0.04%. 5 Zhang et al used the parallel surrogate model-assisted hybrid differential evolution-based ML algorithm to optimize the SIW-based end-fire antenna. It works at 36-40.0 GHz frequency range.…”

Section: Introductionmentioning

confidence: 99%

Effective modeling of metasurface‐loaded circularly polarized dielectric resonator‐based MIMO antenna for sub‐6.0‐GHz band using machine learning algorithms

Pachori,

Prakash,

Kumar

2024

Int J Communication

View full text Add to dashboard Cite

SummaryIn this article, a dual‐port dielectric resonator antenna (DRA) is modeled using machine learning (ML) algorithms, that is, deep neural network (DNN), random forest, and XGBoost. The unique properties of the proposed article are as follows: (i) Two different diversity techniques, that is, pattern (with the help of metallic wall) and polarization (mirror image of the aperture), improve the isolation value between the ports; (ii) ML algorithms are used to optimize and predict the reflection coefficient as well as mutual coupling of the proposed antenna. The accuracy of ML algorithms is verified by using the HFSS EM simulator and experimental validation. Error is less than 1%–2% between the value predicted from ML algorithms and HFSS/experimental results. The proposed design is working well in between 2.4 and 4.02 GHz with a 3‐dB axial ratio from 2.84 to 2.95 GHz. All these features make the radiator employable to the sub‐6.0‐GHz frequency band.

show abstract

Section: Introductionmentioning

confidence: 99%

Effective modeling of metasurface‐loaded circularly polarized dielectric resonator‐based MIMO antenna for sub‐6.0‐GHz band using machine learning algorithms

Pachori,

Prakash,

Kumar

2024

Int J Communication

View full text Add to dashboard Cite

show abstract

“…Jing Gao [2] proposed a semi‐supervised co‐training algorithm based on GP and SVM. Dan Shi [4] proposed a smart antenna synthesis method, which automatically selects appropriate antenna types according to antenna performance requirements and uses SVMs to provide optimal geometric parameters.…”

Section: Introductionmentioning

confidence: 99%

Microstrip antenna modelling based on image‐based convolutional neural network

Tian

Meng

et al. 2023

Electronics Letters

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have a strong feature extraction ability for images and present a high level of efficiency and accuracy in object detection and image recognition. When CNN is used to model microwave devices, the existing literature generally uses its size parameters as one‐dimensional (1‐D) input, which does not give full play to the image‐processing ability of CNN. In order to make full use of the characteristics of CNN, this letter converts the 1‐D input of microwave devices into the form of an image model, that is, the 1‐D input is transformed into a two‐dimensional (2‐D) matrix composed of 0 and 1 as the input. The image model is combined with CNN, called image‐based CNN (ICNN), which establishes a deep learning surrogate model between the physical parameters and electrical properties of microwave devices and improves the accuracy and generalization ability of the model. Taking the resonant frequency of the microstrip antenna as a simulation example, modelling was carried out by the proposed ICNN and compared with the mainstream machine learning methods. The results show that the proposed method has high convergence and fitting accuracy.

show abstract

“…The parametric modeling and optimization capabilities of artificial intelligence methods such as neural networks have attracted much attention in the field of antennas. [1][2][3][4][5][6][7] In recent years, to enhance the design freedom of antennas, nonparametric modeling, and optimization methods have also gradually become a research hotspot. However, nonparametric problems with large-scale variables are very challenging for artificial neural networks.…”

Section: Introductionmentioning

confidence: 99%

Topology optimization design of antennas with complex radiation characteristics

Guo

Ding

2023

Micro & Optical Tech Letters

View full text Add to dashboard Cite

Antennas with complex radiation characteristics can enhance the adaptability of radiofrequency systems in complex electromagnetic environments. However, The realization of complex targets is extremely challenging for conventional antenna design methods. It is difficult to find a suitable initial topology of the antenna with complex radiation characteristics. Therefore, in this paper, topology optimization is used to explore the initial structure with complex radiation properties. A two‐dimensional lossy thin layer model based on the transitional boundary condition is constructed, and target field functions for complex radiation are proposed. To verify the effectiveness of the algorithm, a high gain antenna with 10.2 dBi is realized, which has the highest aperture efficiency compared with the literature in similar directions. Then, for more complex targets, the radiation patterns of arbitrary direction null, arbitrary direction beam, and equal‐amplitude dual beam are realized, respectively. The topology optimization algorithm provides a new approach for the design of complex multitarget antennas.

show abstract

An Intelligent Antenna Synthesis Method Based on Machine Learning

Cited by 55 publications

References 37 publications

Effective modeling of metasurface‐loaded circularly polarized dielectric resonator‐based MIMO antenna for sub‐6.0‐GHz band using machine learning algorithms

Effective modeling of metasurface‐loaded circularly polarized dielectric resonator‐based MIMO antenna for sub‐6.0‐GHz band using machine learning algorithms

Microstrip antenna modelling based on image‐based convolutional neural network

Topology optimization design of antennas with complex radiation characteristics

Contact Info

Product

Resources

About