Efficient Broadband Monostatic RCS Computation of Morphing S-Shape Cavity Using Artificial Neural Networks

Weng, Rui; Sun, Dingyi; Yang, Wu; Chen, Xinlei; Lu, Wei‐Bing

doi:10.1109/lawp.2022.3208664

Cited by 4 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The digitally encoded RIS achieves different far‐field pattern properties by modulating the phase. [ 50 ] According to the pattern product principle to calculate the scattering pattern of the digital coding RIS consisting of M × N meta‐atoms, the scattering pattern in far filed can be written as

\begin{equation}{E}_{scatter}(\theta ,\varphi ) = \sum_{n = 1}^N {\sum_{m = 1}^M {{{\widehat e}}_x{A}_x(m,n){e}^{ - j({\varphi }_x(m,n) + kmd\sin \theta \cos \varphi + knd\sin \theta \sin \varphi )}} } \end{equation}

where θ and φare the elevation and azimuth angle of the direction, respectively. A x ( m , n )and φ x ( m , n ) denote the amplitude and phase of the (Mth, Nth) meta‐atom in x‐polarization.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Self‐Powered Reconfigurable Intelligent Metasurface

Mu,

Chang,

Wang

et al. 2024

Adv Materials Technologies

View full text Add to dashboard Cite

In recent years, reconfigurable intelligent metasurface (RIS) has gained much attention due to its flexibility in modulating the phase, amplitude, and polarization of electromagnetic waves. It is widely used for wireless power and information transmission. However, RIS requires an external wired power supply or batteries to activate their modulation capabilities, as they do not generate the required energy themselves. This paper presents a self‐powered RIS that does not require an external wired power supply or batteries. The modulation capability is activated by harvesting radio frequency (RF) energy. The self‐powered RIS consists of an energy‐metatom, which is loaded with a PIN diode for flexible phase modulation. The inclusion of an absorber/energy port on the energy‐metatom allows for independent RF energy harvesting. The RIS consisting of energy‐metatoms can cut out all wired power supplies and batteries so that it can dynamically regulate electromagnetic waves by self‐powered means. As a proof‐of‐concept, a prototype composed of 10 × 10 energy‐metatoms is fabricated. The measured results are in good agreement with the simulated. This self‐powered RIS can be used as an “infinite‐lifetime” power supply for dynamic electromagnetic modulation in the RIS.

show abstract

\begin{equation}{E}_{scatter}(\theta ,\varphi ) = \sum_{n = 1}^N {\sum_{m = 1}^M {{{\widehat e}}_x{A}_x(m,n){e}^{ - j({\varphi }_x(m,n) + kmd\sin \theta \cos \varphi + knd\sin \theta \sin \varphi )}} } \end{equation}

Section: Resultsmentioning

confidence: 99%

“…The digitally encoded RIS achieves different far-field pattern properties by modulating the phase. [50] According to the pattern product principle to calculate the scattering pattern of the digital coding RIS consisting of M × N meta-atoms, the scattering pattern in far filed can be written as…”

Section: Wireless Information Transmission In Reflection Modementioning

confidence: 99%

A Self‐Powered Reconfigurable Intelligent Metasurface

Mu,

Chang,

Wang

et al. 2024

Adv Materials Technologies

View full text Add to dashboard Cite

show abstract

“…Considering the capability of neural networks to improve forward and backward scatter calculations, Zhang Xu et al constructed the EM-FCNN network, utilizing hyperparameters to control the surface roughness of the model and achieve high-speed scattering field calculations [12]. In terms of computing RCS using artificial neural networks, Rui Weng et al implemented a computational model for the RCS of a deformed S-shaped cavity using artificial neural networks [13]. These studies demonstrate the significant potential of neural network applications in accelerating electromagnetic simulation calculations [14,[18][19][20][21][22].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Low RCS optimization is a crucial aspect of designing electrically large targets, such as ships. While computational electromagnetics has made significant advancements over the years, the computational speed of calculating RCS for the electrically large targets has greatly improved [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. Existing methods that utilize neural networks for electromagnetic calculations have varying applicability.…”

Section: Introductionmentioning

confidence: 99%

“…Certain methods focus on radar signal processing [3,4]. Although these methods are useful for calculating scattering in small electric targets, they encounter difficulties when applied to RCS calculations for the electrically large targets [5][6][7][8][9][10][11]13]. The EM-FCNN method can be used for calculating the RCS of electrically large targets; however, it requires suitable physical prior data during neural network training and the acquisition of the input model's point cloud matrix [12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancement of Electromagnetic Scattering Computation Acceleration Using LSTM Neural Networks

Yang,

Xinyang,

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper presents the electromagnetic long short-term memory neural network (EM-LSTMNN) approach to accelerate radar cross-section (RCS) calculations in optimizing low RCS for electrically large targets. The proposed method converts the conventional electromagnetic numerical calculation into an efficient numerical calculation using the LSTM neural network, resulting in a significant improvement in RCS computation speed. To assess the effectiveness of this approach, a downscaled model of a large-sized ship is employed as the target for low RCS optimization. Each modification made to the target’s mesh data during the optimization process is stored in the dataset as a new element. As the ship scaling model undergoes modifications during the optimization process, the new mesh data are recorded, thus adding a new element to the dataset at each time step. This forms a time series representation of the mesh model. By utilizing the dataset collected throughout the optimization process, the proposed EM-LSTMNN model is trained using data-driven approaches, with a training time of approximately 106 s. It is worth noting that this training time is significantly smaller compared to existing methods that employ fully connected neural networks. The performance of the proposed approach is demonstrated by comparing the RCS calculation results obtained through this method with those obtained through traditional electromagnetic simulations.

show abstract