CN108733924B - Intelligent design method of digital coding metamaterial unit - Google Patents

Intelligent design method of digital coding metamaterial unit Download PDF

Info

Publication number
CN108733924B
CN108733924B CN201810486978.1A CN201810486978A CN108733924B CN 108733924 B CN108733924 B CN 108733924B CN 201810486978 A CN201810486978 A CN 201810486978A CN 108733924 B CN108733924 B CN 108733924B
Authority
CN
China
Prior art keywords
unit
metamaterial
polarized wave
reflection
deep learning
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810486978.1A
Other languages
Chinese (zh)
Other versions
CN108733924A (en
Inventor
崔铁军
张茜
刘彻
万向
张磊
杨艳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201810486978.1A priority Critical patent/CN108733924B/en
Publication of CN108733924A publication Critical patent/CN108733924A/en
Application granted granted Critical
Publication of CN108733924B publication Critical patent/CN108733924B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Abstract

The invention discloses an intelligent design method of a digital coding metamaterial unit, which comprises the following steps: 1) carrying out digital coding on the basic pattern of the 1bit unit for constructing the metamaterial, and predicting unit polarized wave reflection phases when different modules in the 1bit unit are distributed by adopting a deep learning design algorithm; 2) according to the functional requirements of the metamaterial, the polarized wave phase difference theta of the 1-bit unit structure for constructing the metamaterial is determined, and the 1-bit unit structure with the polarized wave phase difference theta is designed by combining the binary particle swarm optimization algorithm module and the deep learning module. The design method realizes the automatic design of the ideal reflection phase of the multi-bit unit based on deep learning, has high efficiency, simplicity and good expansibility, can replace software simulation, shortens the complexity and time corresponding to the information of the coding unit, and quickly, simply and conveniently designs the multi-beam multi-polarization artificial electromagnetic surface.

Description

Intelligent design method of digital coding metamaterial unit
Technical Field
The invention relates to a design method of a metamaterial unit, in particular to an intelligent design method of a digital coding metamaterial unit, and belongs to the field of machine learning and digital coding metamaterial.
Background
An artificial composite material in which electromagnetic waves have special conduction or radiation characteristics (negative refraction, zero refraction) when propagating is called a novel artificial electromagnetic material (Metamaterials), and the novel artificial electromagnetic material can be artificially designed and meets the requirements of specific equivalent dielectric constant and magnetic permeability. In order to realize different functions of the metamaterial, the phase change is realized by adjusting the metamaterial unit structure, and then the distribution condition of the units with different reflection phases is adjusted, so that incident waves can radiate pencil beams or endowed beams with high directionality through the array structure.
The phase response for a coding unit (16 × 16 random lattice unit) is determined by the coding of the unit, which for an axisymmetric unit would be 264A code and corresponding phase information. Full-wave simulation software CST Microwave Studio slave 2 is generally adopted in the prior art64The design method for obtaining the required code as the metamaterial unit code in the code consumes huge time and energy.
The concept of deep learning was proposed by Hinton et al in 2006 and developed rapidly in recent years, and the breakthrough application results are endlessly varied. The deep learning is a method based on the characterization learning of data in the machine learning, and can automatically model high-dimensional data, so that the trouble of manually extracting features is avoided, and the efficiency of system design and operation is improved.
The Particle Swarm Optimization (PSO) algorithm is a Swarm intelligence evolution calculation method proposed by Dr.Kennedy and Eberhart in 1995. Particle swarm optimization algorithms initially propose optimization problems suitable for solving continuous spaces. On the basis of the continuous particle swarm optimization, Binary Particle Swarm Optimization (BPSO) is proposed to solve many practical problems of combination optimization. In the binary particle swarm optimization algorithm, the position code of the particle is in a binary manner, that is, each dimension component of the particle is represented by "0" and "1".
Based on the above, the inventor combines a deep learning method and a particle swarm optimization algorithm to form the technology of the invention.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems of complex acquisition of coding unit information and long acquisition time of the existing metamaterial coding unit design method, the intelligent design method of the digital coding metamaterial unit is provided.
The technical scheme is as follows: the invention relates to an intelligent design method of a digital coding metamaterial unit, which comprises the following steps:
1) carrying out digital coding on the basic pattern of the 1bit unit for constructing the metamaterial, and predicting unit polarized wave reflection phases when different modules in the 1bit unit are distributed by adopting a deep learning design algorithm;
2) according to the functional requirements of the metamaterial, the polarized wave phase difference theta of the 1-bit unit structure for constructing the metamaterial is determined, and the 1-bit unit structure with the polarized wave phase difference theta is designed by combining the binary particle swarm optimization algorithm module and the deep learning module.
In the step 1), random discrete crystal lattices can be selected to be used as a basic pattern of 1bit unit particles, the basic pattern is composed of an air module and a metal module, the air module is marked as '0', the metal module is marked as '1', and a 1bit unit coding pattern is obtained. Specifically, a special neural network from unit coding to reflection phase is constructed on the basis of Resnet, 0 and 1 in 1-bit unit coding patterns correspond to 0 and 1 in a deep learning design algorithm, 1-bit unit coding patterns distributed by different modules are converted into 0-1 matrixes to serve as network input, the reflection phase is discretized to 360 states at intervals, and reflection phases corresponding to various 1-bit unit coding patterns serve as network output, so that unit polarized wave reflection phases when different modules in 1-bit units are distributed are predicted.
In the step 2), the 1-bit unit is composed of a "0" unit and a "1" unit, and the 1-bit unit with the polarization wave phase difference θ is: the phase difference of the reflection phases of the TM polarized wave and the TE polarized wave of the two units "0" and "1" constituting the 1bit unit is both θ, and the phase difference of the reflection phases of the same polarized waves of the two units is 180 °.
The design method combining the binary particle swarm optimization algorithm module and the deep learning module comprises the following steps: generating an initial particle swarm by adopting a binary particle swarm optimization algorithm module, updating the speed and the position of the particles, and calculating the fitness in each iteration; and (4) quickly calculating and outputting the reflection phase of the unit by adopting a deep learning design algorithm.
The specific design steps are as follows:
1) to be provided with
Figure BDA0001666968460000021
i＝1,2 as fitness function, optimizing the coding pattern of unit particle to obtain fitness1I 1, a "0" cell in a 1bit cell is obtained, wherein,
Figure BDA0001666968460000022
and
Figure BDA0001666968460000023
respectively representing the reflection phases of TM and TE polarized waves of the cell;
(2) outputting the reflection phase of the '0' unit and entering a second round of optimization;
(3) based on the reflection phase of the '0' unit obtained by the first round of optimization, in the second round of optimization design, so as to
Figure BDA0001666968460000024
i is 1,2 and
Figure BDA0001666968460000025
optimizing the pattern of unit particles as a fitness function to obtain fit1And fitness2Obtaining a '1' unit in the 1bit unit; wherein the content of the first and second substances,
Figure BDA0001666968460000026
Figure BDA0001666968460000027
the reflection phases of the TE polarized waves of the cell "0" and the cell "1" are respectively indicated.
Has the advantages that: compared with the prior art, the invention has the advantages that: the design method realizes the automatic design of the ideal reflection phase of the multi-bit unit based on deep learning, has high efficiency, simplicity and good expansibility, can replace software simulation, and shortens the complexity and time corresponding to the information of the coding unit; meanwhile, a meaningful attempt for an artificial electromagnetic material intelligent algorithm is provided.
Drawings
FIG. 1 is a schematic diagram of an axisymmetric structure of a metamaterial unit according to the present invention;
FIG. 2 is a flow chart of feature dimension change and feature extraction after a 1bit unit coding pattern is input into a deep learning neural network;
FIG. 3 is a flow chart of a method for designing a 1bit unit structure by combining a binary particle swarm optimization algorithm module and a deep learning module in the invention;
FIG. 4 is a schematic structural diagram of two groups of 1bit units with polarized wave reflection phase differences of 0 ° and 180 ° designed by the present invention;
FIG. 5 is a schematic structural diagram of two groups of 1bit units with polarized wave reflection phase differences of-45 ° and 135 ° designed by the present invention;
FIG. 6 is a schematic structural diagram of two groups of 1bit units with polarization wave reflection phase differences of-90 ° and 90 ° designed by the present invention;
FIG. 7 is a schematic structural diagram of two groups of 1bit units with polarized wave reflection phase differences of-135 ° and 45 ° designed by the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
The intelligent design method of the digitally encoded metamaterial unit is explained by taking a metamaterial unit designed on a three-beam multi-polarization artificial electromagnetic surface capable of radiating three beams of left-hand circular polarization, right-hand circular polarization and linear polarization as an example.
1) Carrying out digital coding on the basic pattern of the 1bit unit for constructing the metamaterial, and predicting unit polarized wave reflection phases when different modules in the 1bit unit are distributed by adopting a deep learning design algorithm;
first, we select a random discrete lattice as the base pattern of unit particles, as shown in FIG. 1. The lattice pattern comprises 16 x 16 squares, where the grey squares are metal blocks and the white squares are air blocks, i.e. not covered with any material. The grey small square is marked as '1', the white small square is marked as '0', and the grey small square corresponds to '1' and '0' in the deep learning design algorithm and is marked as 1bit unit coding. The two-dimensional arrangement of different "0" and "1", i.e. different cell codes, determines the reflection phase of the cell particles. In thatIn our design, the element coding uses axisymmetric coding, and thus there will be 264The code pattern also corresponds to a plurality of reflection phases.
In a deep learning module, a special 101-layer network is designed based on Resnet, and a 1-bit unit coding pattern is converted into a 0-1 matrix to be used as network input; the reflection phase is discretized to 360 states at intervals, and the reflection phase corresponding to the 1-bit unit code is used as network output. Through a large amount of data training, the network learns the relation from encoding to phase and meets the precision requirement. Fig. 2 shows the change of feature dimensions and the extraction process of features after unit codes are input to the neural network, and 2048 feature points are finally extracted, and the features are converted into predictions of output phases through a fully connected network. Table 1 shows the specific convolution operations involved in each structural block of the constructed neural network, increasing the acceptance domain of feature extraction and making the extracted features more and more sophisticated by the constant stacking of small convolution kernels.
TABLE 1 specific convolution operations involved in each structural block of the neural network constructed
Figure BDA0001666968460000041
2) According to the functional requirements of the metamaterial, the polarized wave phase difference theta required to be met by constructing the 1-bit unit structure of the metamaterial is determined, and the 1-bit unit structure with the polarized wave phase difference theta is designed by combining the binary particle swarm optimization algorithm module and the deep learning module.
The metamaterial unit designed by the invention is used for constructing a three-beam multi-polarization artificial electromagnetic surface, and the three-beam multi-polarization artificial electromagnetic surface is obtained by encoding a 1-bit unit array of a 3-bit group. A composition of 1-bit encoding is defined as two units whose reflection phases are different by 180 °, for example, two sets of units whose θ is 0 ° and 180 °, or two sets of units whose θ is 45 ° and-135 °, and the like; the composition of a 2-bit code is defined as four cells whose reflection phases differ by 90 °, for example four sets of cells of θ ═ 90 °, 0 °, 90 ° and 180 °; the composition of 3bit coding is defined as eight units with 45 ° phase difference of reflection, for example, eight groups of units with θ ═ 135 °, -90 °, -45 °, 0 °, -45 °, 90 °, 135 ° and 180 °, i.e., the present invention needs to design an eight group 1bit unit structure with polarization wave phase difference of θ -135 °, -90 °, -45 °, 0 °, -45 °, 90 °, 135 ° and 180 °.
The phase difference between the reflection phase of the x-polarized wave (TM, polarized wave) and the reflection phase of the y-polarized wave (TE, polarized wave) of two cells "0" and "1" constituting a 1-group 1-bit cell is θ, and the phase difference between the radiation phases of the same polarization of the two cells is 180 °. The "0" and "1" cells in the 1-group 1-bit cells correspond to the binary particle codes "0" and "1" in the binary particle swarm optimization.
FIG. 3 is a design flow based on a binary particle swarm optimization algorithm module and a deep learning module, so as to obtain a 1-bit anisotropic coding unit with a fixed reflection phase difference in the orthogonal direction. The design program comprises two modules, a discrete particle swarm optimization (BPSO) module and a deep learning module, wherein the binary particle swarm optimization module is used for generating an initial particle swarm, updating the speed and the position of the particles and calculating the fitness in each iteration; the deep learning is used for fast calculation and output of the reflection phase of the unit. The specific design steps are as follows:
(1) to be provided with
Figure BDA0001666968460000051
i is 1,2 as the fitness function, and optimizing the unit particle pattern to obtain the fitness function1I 1, obtaining "0" in 1bit unit, namely, the reflection phase difference of its TM and TE polarized waves is closest to θ;
Figure BDA0001666968460000052
and
Figure BDA0001666968460000053
the reflection phases of the TM and TE polarized waves of the cell are shown, respectively.
(2) Outputting the reflection phase of the '0' unit, and performing a second round of optimization;
(3) based on the reflection phase of the '0' unit obtained by the first round of optimization, in the second round of optimization design, so as to
Figure BDA0001666968460000054
i is 1,2 and
Figure BDA0001666968460000055
optimizing the pattern of unit particles as a fitness function to obtain fit1And fitness2The minimum value of (1) in the 1-bit unit is obtained, namely the reflection phase difference of TM and TE polarized waves of the 1-bit unit is close to theta, and the phase difference of 0 and 1 of the two units of 1bit is close to 180 degrees;
by the design method, 8 groups of 1bit units with the polarization wave phase difference theta of-135 degrees, -90 degrees, -45 degrees, -0 degrees, -45 degrees, -90 degrees, -135 degrees and 180 degrees can be obtained, and the units are shown in figures 4-7. All the obtained 1-bit units of the 3-bit group can be combined to realize a three-beam multi-polarization (left-hand circular polarization, right-hand circular polarization and linear polarization) artificial electromagnetic surface.

Claims (4)

1. An intelligent design method of a digital coding metamaterial unit is characterized by comprising the following steps:
1) carrying out digital coding on the basic pattern of the 1bit unit for constructing the metamaterial, and predicting unit polarized wave reflection phases when different modules in the 1bit unit are distributed by adopting a deep learning design algorithm;
constructing a special neural network from unit coding to reflection phase on the basis of Resnet, wherein '0' and '1' in 1-bit unit coding patterns correspond to '0' and '1' in a deep learning design algorithm, 1-bit unit coding patterns distributed by different modules are converted into 0-1 matrixes to be used as network input, the reflection phase is discretized to 360 states at intervals, and reflection phases corresponding to various 1-bit unit coding patterns are used as network output, so that unit polarized wave reflection phases when different modules are distributed in 1-bit units are predicted;
2) determining a polarized wave phase difference theta of a 1-bit unit structure for constructing the metamaterial according to the functional requirements of the metamaterial, and designing the 1-bit unit structure with the polarized wave phase difference theta by combining a binary particle swarm optimization algorithm module and a deep learning module;
the design combined with the binary particle swarm optimization algorithm module and the deep learning module comprises the following steps:
(1) to be provided with
Figure FDA0003538685440000011
Optimizing the encoding pattern of the unit particle as a fitness function to obtain a fit1I 1, a "0" cell in a 1bit cell is obtained, wherein,
Figure FDA0003538685440000012
and
Figure FDA0003538685440000013
respectively representing the reflection phases of TM and TE polarized waves of the cell;
(2) outputting the reflection phase of the '0' unit and entering a second round of optimization;
(3) based on the reflection phase of the '0' unit obtained by the first round of optimization, in the second round of optimization design, so as to
Figure FDA0003538685440000014
And
Figure FDA0003538685440000015
optimizing the pattern of unit particles as a fitness function to obtain fit1And fitness2Obtaining a '1' unit in the 1bit unit; wherein the content of the first and second substances,
Figure FDA0003538685440000016
Figure FDA0003538685440000017
the reflection phases of the TE polarized waves of the cell "0" and the cell "1" are respectively indicated.
2. The intelligent design method of a digital coding metamaterial unit as claimed in claim 1, wherein in step 1), random discrete lattices are selected as a basic pattern of 1-bit unit particles, the basic pattern is composed of an air module and a metal module, the air module is marked as "0", the metal module is marked as "1", and a 1-bit unit coding pattern is obtained.
3. The intelligent design method of the digital coding metamaterial unit according to claim 2, wherein in step 2), the 1-bit unit with the polarized wave phase difference θ is: the phase difference of the reflection phases of the TM polarized wave and the TE polarized wave of two units "0" and "1" constituting a 1-group 1-bit unit is θ, and the phase difference of the reflection phases of the same polarized wave of the two units is 180 °.
4. The intelligent design method for the digitally encoded metamaterial unit as claimed in claim 3, wherein in step 2), the design method combining the binary particle swarm optimization algorithm module and the deep learning module is: generating an initial particle swarm by adopting a binary particle swarm optimization algorithm module, updating the speed and the position of the particles, and calculating the fitness in each iteration; and (4) quickly calculating and outputting the reflection phase of the unit by adopting a deep learning design algorithm.
CN201810486978.1A 2018-05-21 2018-05-21 Intelligent design method of digital coding metamaterial unit Active CN108733924B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810486978.1A CN108733924B (en) 2018-05-21 2018-05-21 Intelligent design method of digital coding metamaterial unit

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810486978.1A CN108733924B (en) 2018-05-21 2018-05-21 Intelligent design method of digital coding metamaterial unit

Publications (2)

Publication Number Publication Date
CN108733924A CN108733924A (en) 2018-11-02
CN108733924B true CN108733924B (en) 2022-05-10

Family

ID=63937666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810486978.1A Active CN108733924B (en) 2018-05-21 2018-05-21 Intelligent design method of digital coding metamaterial unit

Country Status (1)

Country Link
CN (1) CN108733924B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110110398B (en) * 2019-04-19 2023-05-12 西安工程大学 Super-surface automatic design method based on convolution self-encoder
CN110245413A (en) * 2019-06-11 2019-09-17 西北工业大学 A kind of design method of Meta Materials absorbent structure neural network based
CN110518361B (en) * 2019-08-22 2021-01-12 西安电子科技大学 2-bit phase-adjustable reflection super-surface unit
CN110718755B (en) * 2019-10-16 2021-01-05 东南大学 Integrated low-profile digital coding antenna
CN110647024B (en) * 2019-10-30 2020-10-09 武汉大学 Method for realizing circuitous phase coding multiplexing based on super-surface array structure
CN113270157A (en) * 2021-05-20 2021-08-17 兰州大学 Mechanical metamaterial design and optimization method based on machine learning
CN117610317B (en) * 2024-01-19 2024-04-12 湖北工业大学 Multi-bit super-surface phase arrangement optimization method based on deep learning

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1650688A1 (en) * 2004-10-20 2006-04-26 International Business Machines Corporation Automatic addition of power connections to chip power supply network
WO2006108768A1 (en) * 2005-04-15 2006-10-19 France Telecom Method and device for decoding a variable length code taking into account an a priori probability information
CN104868252A (en) * 2015-06-05 2015-08-26 东南大学 1-bit microwave anisotropic electromagnetic coding meta-material
WO2015169109A1 (en) * 2014-05-06 2015-11-12 国家电网公司 A transformer noise suppression method
CN106410418A (en) * 2016-08-11 2017-02-15 东南大学 Dual-functional anisotropic electromagnetic encoding metamaterial applied to microwave band, and basic unit structure and design method
CN107704673A (en) * 2017-09-26 2018-02-16 中国人民解放军空军工程大学 Wideband encoding Meta Materials Fast design method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9626459B2 (en) * 2014-01-24 2017-04-18 International Business Machines Corporation Detecting hotspots using machine learning on diffraction patterns

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1650688A1 (en) * 2004-10-20 2006-04-26 International Business Machines Corporation Automatic addition of power connections to chip power supply network
WO2006108768A1 (en) * 2005-04-15 2006-10-19 France Telecom Method and device for decoding a variable length code taking into account an a priori probability information
WO2015169109A1 (en) * 2014-05-06 2015-11-12 国家电网公司 A transformer noise suppression method
CN104868252A (en) * 2015-06-05 2015-08-26 东南大学 1-bit microwave anisotropic electromagnetic coding meta-material
CN106410418A (en) * 2016-08-11 2017-02-15 东南大学 Dual-functional anisotropic electromagnetic encoding metamaterial applied to microwave band, and basic unit structure and design method
CN107704673A (en) * 2017-09-26 2018-02-16 中国人民解放军空军工程大学 Wideband encoding Meta Materials Fast design method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Coding Metasurface for Shaping Beams through Software-Based Approach;Q. Zhang;《11th International Congress on Engineered Material Platforms for Novel Wave Phenomena – Metamaterials》;20170902;第394-396页 *
太赫兹信息超材料与超表面;刘峻峰;《雷达学报》;20180205;第7卷(第1期);第46-55页 *

Also Published As

Publication number Publication date
CN108733924A (en) 2018-11-02

Similar Documents

Publication Publication Date Title
CN108733924B (en) Intelligent design method of digital coding metamaterial unit
CN108763708B (en) Method for designing multi-beam multi-polarization artificial electromagnetic surface based on deep learning
Dong et al. Fast multi-objective optimization of multi-parameter antenna structures based on improved BPNN surrogate model
Weile et al. Genetic algorithm optimization applied to electromagnetics: A review
Gosal et al. Transmitarray antenna design using forward and inverse neural network modeling
Nan et al. Design of UWB antenna based on improved deep belief network and extreme learning machine surrogate models
CN111611683A (en) Electromagnetic super-surface design method and device based on deep learning
CN110083934B (en) Electromagnetic super-surface design method based on support vector machine algorithm
Hodge et al. Multi-discriminator distributed generative model for multi-layer RF metasurface discovery
CN107844632A (en) Bare cloth linear array grating lobe suppression method based on harmonic search algorithm
CN111143983B (en) Low side lobe comprehensive optimization method for sparse antenna array based on improved water circulation algorithm
CN111199126A (en) Rapid optimization design method of patch antenna
CN110290542A (en) Marine UAV Communication coverage optimization method and system
CN110059376B (en) Cylindrical surface conformal array based rapid optimization design method and system
Bayraktar et al. A versatile design strategy for thin composite planar double-sided high-impedance surfaces
CN106777601A (en) Based on the planar array antenna Pattern Synthesis method that MIFT is combined with QP algorithms
CN114117565A (en) Deep learning-based planar array antenna radiation directional diagram synthesis method
CN107704673B (en) Rapid design method for broadband coding metamaterial
Chi et al. L-GhostNet: Extract Better Quality Features
Wang et al. On-demand inverse design of acoustic metamaterials using probabilistic generation network
CN109547083B (en) Flat-top beam forming method based on neural network
Ding et al. Antenna optimization based on auto-context broad learning system
CN116205143A (en) Design method for realizing antenna pattern based on physical information neural network
Fang et al. Design of reconfigurable periodic structures based on machine learning
CN113553711B (en) Design method of conformal array antenna with any curved surface

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant