Deep Learning for Inverse Design of Broadband Quasi-Yagi Antenna

Zhou, Wen-Ying; Mei, Zhong Lei; Lu, Mai; Zhu, Ya-Bo

doi:10.1155/2023/7819156

Cited by 2 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, there have been many studies on human RF electromagnetic exposure caused by different antennas [10][11][12][13][14][15]. In reference [16], an electronic band gap (EBG) applied to wearable antennas was designed to reduce the specific absorption rate.…”

Section: Introductionmentioning

confidence: 99%

Electromagnetic exposure analysis of the subway passenger under the civil communication system radiation

Zhou,

Zhang,

2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

In order to assess the electromagnetic exposure safety of passengers under the civil communication system of the subway, the radio-frequency (RF) electromagnetic environment of subway carriage is established by using COMSOL Multiphysics software, it includes a 1-1/4 " leaky coaxial cable (LCX1) and a 1-5/8" leaky coaxial cable (LCX2), which are designed to be the exposure sources, and twelve passengers at different position. The electromagnetic environment model has been verified through field measurement. The exposure dose distribution of twelve passengers is compared and analyzed, when LCX1 and LCX2 works respectively. The simulated results show that, to compare with LCX2, the electromagnetic dose absorbed by the passengers is reduced by 9.19% and 22.50% at 2100 MHz and 2600 MHz respectively. The specific absorption rate (SAR) of passengers obtains the maximum value of 1.91×10−4 W/Kg and the temperature rise to 0.214 K when the LCX1 works at 3400 MHz. By comparing with the public exposure limitation of the International Commission of Non-Ionizing Radiation Protection (ICNIRP), it demonstrates the electromagnetic exposure safety of the passengers under the civil communication system. More importantly, the proposed LCX1 not only could add the 5G signal cover but also lower the SAR absorbed by the passengers, which indicates that the public electromagnetic exposure dose could be reduced by adjusting the radiation performances of exposure source, which provide a new way for electromagnetic protecting.

show abstract

Section: Introductionmentioning

confidence: 99%

Electromagnetic exposure analysis of the subway passenger under the civil communication system radiation

Zhou,

Zhang,

2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Te multiperformance optimization of an antenna array was estimated by a multibranch ANN model and a multistage collaborative ML algorithm, respectively [17,18]. Recently, the deep neural network (DNN) was used to design nanostructure for phase manipulation [19,20], and inversely designed the broadband quasi-Yagi antenna [21]. ML has been applied in antenna design as a good calculation tool.…”

Section: Introductionmentioning

confidence: 99%

Two-Step Decoupling Design of a Microstrip Antenna Array by Using Waveguided Complementary Split-Ring Resonators and a Fully Connected Neural Network

Zhou

Mei

et al. 2023

International Journal of Antennas and Propagation

Self Cite

View full text Add to dashboard Cite

To suppress the mutual coupling between closely-spaced patches, we propose a two-step decoupling design approach for a microstrip antenna array with the dimensions of 44.9 × 30.495 mm2. The first step is designing a decoupling unit on the basis of waveguided complementary split-ring resonators (WCSRRs) to improve isolation. The second step is presenting an optimization method by using a fully connected neural network (FCNN) to enhance design efficiency. By inserting WCSRRs structure between two patches with the edge-to-edge distance of 0.24λ0 (port-to-port distance with 0.66λ0), where λ0 is the wavelength of free space at a resonant frequency of 9 GHz, the mutual coupling can be reduced to −29.38 dB, which is confirmed by the EM simulation. We use the simulation results of the array geometries and EM performances to train FCNN at first and then use the trained FCNN to predict the array geometric parameters for the optimal EM response when the edge-to-edge distance between patches is further reduced to 0.21λ0 and 0.18λ0 (port-to-port distance reduced to 0.60λ0 and 0.56λ0). The measured isolation of the predicted microstrip antenna array is increased to 41.05 dB and 52.33 dB, respectively. Compared to the EM simulation, our FCNN approach has a higher accuracy and lower computational complexity. Therefore, the proposed array predicted by FCNN has a better decoupling performance. All the simulated and predicted results are validated via the measurement to demonstrate the effectiveness of our design scheme. The advantages of our work include the good decoupling performance of the proposed WCSRRs and the convenient optimization of the FCNN from physical response to optimal antenna array geometry design.

show abstract

Deep Learning for Inverse Design of Broadband Quasi-Yagi Antenna

Cited by 2 publications

References 34 publications

Electromagnetic exposure analysis of the subway passenger under the civil communication system radiation

Electromagnetic exposure analysis of the subway passenger under the civil communication system radiation

Two-Step Decoupling Design of a Microstrip Antenna Array by Using Waveguided Complementary Split-Ring Resonators and a Fully Connected Neural Network

Contact Info

Product

Resources

About