Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Construction method of electromagnetic metasurface under the condition of unit close coupling based on deep learning

A metasurface, deep learning technology, applied in the direction of design optimization/simulation, can solve problems such as large computing time and memory, and achieve the effects of convenient processing and integration, small size, and improved design efficiency

Active Publication Date: 2021-06-22
NANJING UNIV OF SCI & TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This metasurface design also ignores the influence of the close coupling of the cells on the efficiency of the electromagnetic metasurface, and it takes a lot of computing time and memory to build all the corresponding cells of the spectrum.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Construction method of electromagnetic metasurface under the condition of unit close coupling based on deep learning
  • Construction method of electromagnetic metasurface under the condition of unit close coupling based on deep learning
  • Construction method of electromagnetic metasurface under the condition of unit close coupling based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] The present invention is an electromagnetic metasurface design method under the condition of unit close coupling, taking a one-dimensional focusing metalens as an example, including the following steps:

[0069] Step 1. Design the unit and period, determine the range of side length variation of the unit by simulation, make the phase curve cover 0-2π, and determine the period that makes the designed unit transmission coefficient the best, combined with figure 1 ,Specific steps are as follows:

[0070] Step 1.1, design unit, combine figure 1 (a), set the side length variation of the unit, and set the unit cycle scanning range to sample in the range of 0.3-0.5 wavelengths;

[0071] Step 1.2: Perform a simulation comparison of the parameters set in step 1.1, select units whose phase can cover 0-2π, and make these units meet the period of the transmission coefficient>0.9, and obtain the phase curve of the unit through simulation, such as figure 1 (b);

[0072] Step 2. Per...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a deep learning-based method for constructing an electromagnetic metasurface under unit near-coupling conditions. The method is as follows: in the microwave or optical band, select the unit period so that the unit transmittance or reflectance is greater than the threshold, and by changing the unit properties, the phase change of the wavefront covers a range of 2π; the target unit and the surrounding units are regarded as a subunit Array, 3-bit quantization of the unit, and establish the data set of the transmission field or reflection field of the target unit; design the neural network model, the input is the unit of different attributes, the output is the corresponding transmission or reflection field, and the training generates the neural network that meets the accuracy requirements Network model; build an electromagnetic metasurface, use the neural network to establish the relationship between the unit attribute and the transmission field or reflection field, and calculate the electric field value at the target to be optimized; use the optimization algorithm to optimize the electromagnetic metasurface and adjust the electromagnetic metasurface The efficiency of electromagnetic wave regulation. The invention significantly improves the electromagnetic wave control efficiency of the electromagnetic metasurface.

Description

technical field [0001] The invention relates to a numerical calculation technology of electromagnetic characteristics of a moving target, in particular to an electromagnetic metasurface construction method based on deep learning under unit near-coupling conditions. Background technique [0002] Metasurfaces, two-dimensional manifestations of metamaterials, have attracted extensive attention due to their ability to provide unprecedented lightwave manipulation at the subwavelength scale. The metasurface planar lens uses the principle that the incident light resonates with the metasurface unit to cause a phase change, and the phase can be adjusted by changing the shape and material of the surface unit. Moreover, the sub-wavelength size characteristics of the metasurface can break the limitations brought about by the bulk and bulk of traditional optical devices, and realize more fantastic ideas. [0003] Due to various reasons, the actual phase of the metasurface deviates from ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27
CPCG06F30/27
Inventor 李猛猛章羽晨曦陈如山丁大志马子轩王绍然宁子豪房欣宇杨天胡燕萌
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products