Knowledge-Based Neural Network for Thinned Array Modeling With Active Element Patterns

Hong, Yang; Shao, Wei; Lv, Yan-He; Wang, Bing‐Zhong; Peng, Lin; Bao-jun, Jiang

doi:10.1109/tap.2022.3187518

Cited by 8 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This makes it challenging to accurately determine the coupling effect. Although some methods attempt to estimate different scenarios using small-scale subarrays, 21,22 these approaches reduce the design flexibility of the sparse array.…”

Section: Problem Statementmentioning

confidence: 99%

“…All the examples were conducted on a desktop with an AMD 12-core 3900X CPU, an NVIDIA GeForce RTX4070 Ti GPU, and 32-GB RAM. To evaluate the error between the predicted pattern and the actual pattern, we used The mean absolute percentage error (MAPE), which is defined in 21,22 :…”

Section: Numerical Validation and Simulation Analysismentioning

confidence: 99%

“…This makes it challenging to accurately determine the coupling effect. Although some methods attempt to estimate different scenarios using small‐scale subarrays, 21,22 these approaches reduce the design flexibility of the sparse array. The objective function in Equation () represents an NP‐hard problem. Since the initial array is typically densely arranged to search for accurate sparse solutions, the search space becomes large.…”

Section: Problem Statementmentioning

confidence: 99%

“…For example, ANNs establish the relationship between subarray element positions and the resulting pattern, accounting for mutual coupling effects. The trained surrogate model of the subarray can then be combined with convex optimization algorithms (COA), 21 genetic algorithms (GA), 22 or a combination of both 19 to achieve sparse optimization for the entire array. In recent years, an encoder‐decoder‐based ANN framework, including the widely known large‐scale language model Transformer, 23 has gained prominence.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sparse linear array synthesis using artificial neural network and nonconvex optimization

Li,

Zhou,

Liao

2024

Micro & Optical Tech Letters

View full text Add to dashboard Cite

The concept of sparse array synthesis has attracted considerable attention due to its potential to reduce hardware costs in array design and enhance the efficiency of array aperture utilization. In contrast to conventional artificial neural networks (ANNs), a more efficient encoder–decoding ANN framework is proposed in this letter for designing sparse linear arrays. The decoder is pretrained with a randomly generated training set, enabling its ability to rapidly predictiction of far‐field patterns. This process considers the actual coupling effect among the antenna elements. The output of the encoder is used as the input of the decoder to synthesize the sparse arrays by providing the desired pattern to the encoder. During the training process, a novel ‐norm minimization nonconvex optimization method is integrated into the proposed framework to reduce the number of activated elements. The effectiveness and efficiency of the method are demonstrated through numerical and full‐wave simulations for synthesizing various linear sparse arrays, including large‐scale arrays. In comparison to existing algorithms, our proposed method exhibits superior computational efficiency and predicted accuracy with fewer elements.

show abstract

Section: Problem Statementmentioning

confidence: 99%

Section: Numerical Validation and Simulation Analysismentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse linear array synthesis using artificial neural network and nonconvex optimization

Li,

Zhou,

Liao

2024

Micro & Optical Tech Letters

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks (ANNs) have a great potential for electromagnetic (EM) modeling and design in microwave components [1,2], antennas [3,4], arrays [5−8], filters [9−11], metasurfaces [12−14], multi-physics fields [15,16], and finite-differences time-domain (FDTD) simulations [17−20]. The trained neural network model, mapping the relationship between geometric parameters and EM responses, can obtain the simulation result accurately and quickly.…”

Section: Introductionmentioning

confidence: 99%

Feature selection for determining input parameters in antenna modeling

Zhixian,

Wei,

et al. 2023

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

In this paper, a feature selection method for determining input parameters in antenna modeling is proposed. In antenna modeling, the input feature of artificial neural network (ANN) is geometric parameters. The selection criteria contain correlation and sensitivity between the geometric parameter and the electromagnetic (EM) response. Maximal information coefficient (MIC), an exploratory data mining tool, is introduced to evaluate both linear and nonlinear correlations. The EM response range is utilized to evaluate the sensitivity. The wide response range corresponding to varying values of a parameter implies the parameter is highly sensitive and the narrow response range suggests the parameter is insensitive. Only the parameter which is highly correlative and sensitive is selected as the input of ANN, and the sampling space of the model is highly reduced. The modeling of a wideband and circularly polarized antenna is studied as an example to verify the effectiveness of the proposed method. The number of input parameters decreases from 8 to 4. The testing errors of |S 11 | and axis ratio are reduced by 8.74% and 8.95%, respectively, compared with the ANN with no feature selection.

show abstract

Full-Range Amplitude–Phase Metacells for Sidelobe Suppression of Metalens Antenna Using Prior-Knowledge-Guided Deep- Learning -Enabled Synthesis

Liu

Chen

2023

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

Knowledge-Based Neural Network for Thinned Array Modeling With Active Element Patterns

Cited by 8 publications

References 31 publications

Sparse linear array synthesis using artificial neural network and nonconvex optimization

Sparse linear array synthesis using artificial neural network and nonconvex optimization

Feature selection for determining input parameters in antenna modeling

Full-Range Amplitude–Phase Metacells for Sidelobe Suppression of Metalens Antenna Using Prior-Knowledge-Guided Deep- Learning -Enabled Synthesis

Contact Info

Product

Resources

About