A method and system for determining parameters of a double-opened resonant ring structure in a circular ring

Abstract

The application discloses a kind of circular ring inlay double-opening resonant ring structure parameter determination method and system, the method includes the following steps: experimental data set is generated based on CST simulation;Each set of experimental data in the experimental data set includes the geometric parameter experimental value and absorption performance parameter experimental value of circular ring inlay double-opening resonant ring structure;Training neural network model based on the experimental data set, obtain the neural network model after training;The input of the neural network model is absorption performance parameter, and the output of the neural network model is geometric parameter;Based on the neural network model after training, the geometric parameter design value of circular ring inlay double-opening resonant ring structure corresponding to absorption performance parameter requirement index is determined.The present application realizes the high efficiency design of the geometric parameter of circular ring inlay double-opening resonant ring structure based on neural network model, and improves its absorption performance, reaches the target of absorption rate close to 100% absorption and high quality factor.

Description

Technical Field

[0001] This invention relates to the field of terahertz absorber design technology, and in particular to a method and system for determining the structural parameters of a circular ring with embedded double-opening resonant rings. Background Technology

[0002] In recent years, Artificial Neural Networks (ANNs) have demonstrated powerful learning capabilities in computer vision, image recognition, and natural language processing. Their advantage lies in solving non-intuitive problems by exploring the underlying patterns through large amounts of data, achieving excellent predictive results. Therefore, they hold great potential in the design of Microwave Metamaterial Absorbers (MMAs). Using neural networks in the design and optimization of MMAs can effectively improve design efficiency and facilitate finding the optimal result.

[0003] Metamaterials are periodically arranged artificial electromagnetic materials. Their specially designed structures exhibit properties not found in ordinary materials, such as negative refraction, negative permeability, and negative conductivity. One notable application of metamaterials is the electromagnetic wave "perfect absorber." By rationally designing the device's geometry and material parameters, it can couple with the electromagnetic components of incident electromagnetic waves, thereby achieving 100% absorption of electromagnetic waves within a specific frequency band. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for determining the structural parameters of a circular ring with embedded double-opening resonant rings, so as to achieve high-efficiency design of the geometric parameters of the circular ring with embedded double-opening resonant rings and improve its absorption performance.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] This invention provides a method for determining the structural parameters of a circular ring-embedded double-opening resonant ring structure. The circular ring-embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring. The method includes the following steps:

[0007] Experimental datasets are generated based on CST simulations. Each set of experimental data in the dataset includes experimental values ​​of geometric parameters and absorption performance parameters of a circular ring with an embedded double-opening resonant ring structure. The absorption performance parameters include the quality factor Q and the absorptivity A, while the geometric parameters include the inner diameter r1 of the metal circular ring, the inner side length L1 of the open resonant ring, and the opening width G.

[0008] A neural network model is trained based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter.

[0009] Based on the trained neural network model, the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index are determined.

[0010] Optionally, the loss function used to train the neural network model is the mean square error between the output of the neural network model and the experimental values ​​of the geometric parameters.

[0011] Optionally, determining the geometric parameter design values ​​of the circular ring-embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model specifically includes:

[0012] Input the absorption performance parameter requirement index into the trained neural network model, obtain the geometric parameter prediction value output by the trained neural network model, and perform CST simulation on the geometric parameter prediction value to obtain the absorption performance parameter simulation value.

[0013] Determine the error rate between the required absorption performance parameters and the simulated values ​​of the absorption performance parameters;

[0014] Determine whether the error rate is less than a preset threshold;

[0015] If so, the predicted value of the geometric parameters is output as the geometric parameter design value of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index.

[0016] If not, the predicted values ​​of the geometric parameters and the simulated values ​​of the absorption performance parameters are added to the experimental dataset as a set of experimental data, and the process returns to the step "Train the neural network model based on the experimental dataset to obtain the trained neural network model".

[0017] Optionally, the neural network model includes an input layer, five hidden layers, and an output layer; the number of nodes in the five hidden layers are 6, 9, 12, 9, and 6, respectively.

[0018] A system for determining the structural parameters of a circular ring with an embedded double-opening resonant ring, the system being applied to the above-described method, the system comprising:

[0019] The simulation module is used to generate experimental datasets based on CST simulation. Each set of experimental data in the experimental dataset includes experimental values ​​of geometric parameters and absorption performance parameters of the circular ring embedded double-opening resonant ring structure. The absorption performance parameters include the quality factor Q and the absorptivity A, and the geometric parameters include the inner diameter r1 of the metal circular ring, the inner side length L1 of the open resonant ring, and the opening width G.

[0020] The training module is used to train a neural network model based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter.

[0021] The geometric parameter determination module is used to determine the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model.

[0022] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described above.

[0023] A computer-readable storage medium storing a computer program that, when executed, implements the above-described method.

[0024] A circular ring embedded double-opening resonant ring structure, the circular ring embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring;

[0025] The geometric parameters of the circular ring embedded double-opening resonant ring structure are determined using the method described above.

[0026] A terahertz metamaterial absorber, the terahertz metamaterial absorber comprising a metal bottom layer, an intermediate dielectric layer and a metal microstructure layer arranged sequentially from bottom to top;

[0027] The metal microstructure layer comprises a plurality of periodically arranged metal microstructures;

[0028] The metal microstructure is a circular ring with an embedded double-opening resonant ring structure.

[0029] The geometric parameters of the circular ring embedded double-opening resonant ring structure are determined using the method described above.

[0030] Optionally, the thickness of the metal microstructure layer and the metal bottom layer is 0.2 μm, the thickness of the intermediate dielectric layer is 50 μm, the period of the metal microstructure is 100 μm, the outer diameter of the metal ring with the embedded double-opening resonant ring structure is 50 μm, and the outer side length of the double-opening resonant ring is 60 μm.

[0031] Optionally, both the metal microstructure layer and the metal substrate are made of copper, and the intermediate dielectric layer is made of FR-4 epoxy resin.

[0032] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0033] This invention provides a method and system for determining the parameters of a circular ring-embedded double-opening resonant ring structure. The method includes the following steps: generating an experimental dataset based on CST simulation; each set of experimental data in the dataset includes experimental values ​​of the geometric parameters and absorption performance parameters of the circular ring-embedded double-opening resonant ring structure; training a neural network model based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameters, and the output of the neural network model is the geometric parameters; and determining the design values ​​of the geometric parameters of the circular ring-embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirements based on the trained neural network model. This invention achieves highly efficient design of the geometric parameters of the circular ring-embedded double-opening resonant ring structure based on a neural network model, and improves its absorption performance, achieving the goal of near-100% perfect absorption and a high quality factor. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating a method for determining the structural parameters of a circular ring-embedded double-opening resonant ring according to an embodiment of the present invention;

[0036] Figure 2 A schematic diagram illustrating a method for determining the structural parameters of a circular ring with embedded double openings, provided in an embodiment of the present invention.

[0037] Figure 3 This is a schematic diagram of a circular ring with an embedded double-opening resonant ring structure provided in an embodiment of the present invention;

[0038] Figure 4 The absorption rate curve of the circular ring embedded double-opening resonant ring structure provided in the embodiment of the present invention is shown in the range of 1.1 to 1.3 THz. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] The purpose of this invention is to provide a method and system for determining the structural parameters of a circular ring with embedded double-opening resonant rings, so as to achieve high-efficiency design of the geometric parameters of the circular ring with embedded double-opening resonant rings and improve its absorption performance.

[0041] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Example 1

[0043] like Figure 1 and Figure 2 As shown, Embodiment 1 of the present invention provides a method for determining the structural parameters of a circular ring-embedded double-opening resonant ring, the method comprising the following steps:

[0044] Step 101: Generate an experimental dataset based on CST simulation; each set of experimental data in the experimental dataset includes experimental values ​​of geometric parameters and absorption performance parameters of the circular ring embedded double-opening resonant ring structure; the absorption performance parameters include quality factor Q and absorptivity A, and the geometric parameters include the inner diameter r1 of the metal circular ring, the inner side length L1 of the open resonant ring, and the opening width G.

[0045] Based on the design parameter setting range in Table 1, a total of 1000 sets of experimental data were generated through CST simulation, and divided into training set and test set in a 7:3 ratio.

[0046] Table 1 Design Parameter Range

[0047]

[0048] Step 102: Train a neural network model based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter.

[0049] The quality factor Q and the absorption rate A are used as inputs to the neural network model. The structural parameters r1 (inner diameter of the metal ring), L1 (inner side length of the open resonant ring), and G (opening width) are used as outputs to determine the number of hidden layers and nodes in each hidden layer. The neural network model is constructed and trained to generate a structural parameter prediction network (PPN). The learning rate of the neural network model is set to 0.01, the number of training iterations is 1000, and the cost function is the mean square error. The formula for calculating the mean square error is Equation (1).

[0050]

[0051] Where MSE is the mean square error, r 1，prediction L1，prediction and G prediction These are the predicted values ​​for the inner diameter of the metal ring, the inner side length of the open resonant ring, and the opening width, respectively, which are the inner diameter of the metal ring, the inner side length of the open resonant ring, and the opening width output by the neural network model; r 1，experiment L 1，experiment G experiment These are the experimental values ​​for the inner diameter of the metal ring, the inner side length of the open resonant ring, and the opening width, respectively.

[0052] Step 103: Based on the trained neural network model, determine the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index.

[0053] Input the required absorption performance parameters (target Q and A) into the PPN obtained through training. Calculate the geometric parameters, i.e., the predicted geometric parameter values, through the PPN. Then, use CST to simulate and verify the predicted geometric parameter values ​​to obtain the results: the simulated quality factor Q* and the simulated absorptivity A*. Use the error rate (ER) as the loss function to evaluate the error rate between the required parameters and the pre-simulation parameters. The calculation formula is shown in Equation (2). If the accuracy requirements are met, the required terahertz metamaterial absorber is obtained; if the accuracy requirements are not met, the sample data is added to the experimental dataset, and the neural network model is trained again. This process is repeated until the output geometric parameters meet the accuracy requirements.

[0054]

[0055] Where ER is the error rate, A simulation For the simulated value of the quality factor, A requirement Q is the quality factor requirement indicator, i.e., the target value of the quality factor. requirement Q is the absorption rate requirement indicator, i.e., the target absorption rate value. simulation These are the simulated absorption rates.

[0056] Based on the above principles, step 103, which involves determining the geometric parameter design values ​​of the circular ring-embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model, specifically includes: inputting the absorption performance parameter requirement index into the trained neural network model to obtain the geometric parameter prediction values ​​output by the trained neural network model; performing CST simulation on the geometric parameter prediction values ​​to obtain the absorption performance parameter simulation values; determining the error rate between the absorption performance parameter requirement index and the absorption performance parameter simulation values; determining whether the error rate is less than a preset threshold; if yes, then outputting the geometric parameter prediction values ​​as the geometric parameter design values ​​of the circular ring-embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index; if no, then adding the geometric parameter prediction values ​​and the absorption performance parameter simulation values ​​as a set of experimental data to the experimental dataset, and returning to step "training the neural network model based on the experimental dataset to obtain the trained neural network model".

[0057] The parameters of the neural network model, determined after training, are shown in Table 2. The neural network model includes an input layer, five hidden layers, and an output layer; the number of nodes in the five hidden layers are 6, 9, 12, 9, and 6, respectively.

[0058] Table 2 Hidden Layer Settings

[0059]

[0060] Example 2

[0061] Embodiment 2 of the present invention provides a system for determining the structural parameters of a circular ring with embedded double-opening resonant rings. The system is applied to the method of Embodiment 1, and the system includes:

[0062] The simulation module is used to generate experimental datasets based on CST simulation. Each set of experimental data in the experimental dataset includes experimental values ​​of geometric parameters and absorption performance parameters of the circular ring embedded double-opening resonant ring structure. The absorption performance parameters include quality factor Q and absorptivity A, and the geometric parameters include the inner diameter r1 of the metal circular ring, the inner side length L1 of the open resonant ring, and the opening width G.

[0063] The training module is used to train a neural network model based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter.

[0064] The geometric parameter determination module is used to determine the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model.

[0065] Example 3

[0066] Embodiment 3 of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0067] Example 4

[0068] Embodiment 4 of the present invention provides a computer-readable storage medium storing a computer program, which, when executed, implements the above-described method.

[0069] Example 5

[0070] like Figure 3 As shown, Embodiment 5 of the present invention provides a circular ring embedded double-opening resonant ring structure, the circular ring embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring; the geometric parameters of the circular ring embedded double-opening resonant ring structure are determined using the method of Embodiment 1.

[0071] Example 6

[0072] Embodiment 6 of the present invention provides a terahertz metamaterial absorber, the terahertz metamaterial absorber comprising, from bottom to top, a metal bottom layer, an intermediate dielectric layer and a metal microstructure layer; the metal microstructure layer comprises a plurality of periodically arranged metal microstructures; the metal microstructure is a circular ring embedded with a double-opening resonant ring structure; the geometric parameters of the circular ring embedded with a double-opening resonant ring structure are determined by the method of Embodiment 1.

[0073] The metal substrate is an all-metal patch. When electromagnetic waves are incident from the top layer to the bottom layer, the metal microstructure of the top layer absorbs and dissipates the electromagnetic waves. Figure 3 As shown, the ring-embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring.

[0074] The structural parameters of the terahertz metamaterial absorber in this embodiment of the invention are as follows: the thickness of the metal microstructure layer and the metal substrate is 0.2 μm, the thickness of the intermediate dielectric layer is 50 μm, the period p of the metal microstructure is 100 μm, the outer diameter r2 of the metal ring is 50 μm, and the outer side length L2 of the double-opening resonant ring is 60 μm. In this embodiment, the material of the metal microstructure layer and the metal substrate is copper, and the material of the intermediate dielectric layer is FR-4 epoxy resin.

[0075] The structural parameters of the variable terahertz metamaterial absorber in this embodiment of the invention are as follows: inner diameter r1 of the metal ring, inner side length L1 of the open resonant ring, and opening width G.

[0076] The quality factor Q and the absorptivity A are used as network inputs, and the inner diameter r1 of the metal ring, the inner side length L1 of the open resonant ring, and the opening width G are used as the outputs of the neural network model. The number of hidden layers and the number of nodes in each hidden layer are determined. The neural network model is constructed and trained to obtain the Parameters Predicting Network (PPN). The learning rate of the network is set to 0.01, the number of training iterations is 1000, and the cost function is the mean squared error.

[0077] This invention relates to a terahertz metamaterial absorber with a top-layer pattern of a circular ring and an open-ended resonant ring. The structural parameters of the terahertz metamaterial absorber are reverse-engineered using a neural network model. This neural network model consists of an input layer, an output layer, and five hidden layers. The inputs are the desired absorption rate and quality factor, and the three geometric structural parameters are set as the outputs based on electromagnetic resonance theory. The terahertz metamaterial absorber includes two metal layers and an intermediate dielectric layer. The bottom layer is an all-metal patch, and the top layer has a metal microstructure layer composed of a circular ring and a double-opening resonant ring, ensuring efficient absorption of incident electromagnetic waves. Simulation results show that the absorber achieves an absorption rate of 99.99% at a frequency of 1.192 THz (e.g., ...). Figure 4 As shown in the figure, the quality factor can reach 31.7 at a frequency of 1.22THz.

[0078] The present invention allows design parameters to be predicted by a neural network model, improving the design efficiency of the absorber. Under vertical electromagnetic wave incident from the top to the bottom layer, the proposed absorber utilizes a special metallic microstructure in the top layer to completely dissipate the incident electromagnetic wave within the absorber.

[0079] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0080] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining the structural parameters of a circular ring with embedded double-opening resonant rings, characterized in that, The circular ring embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring. The method includes the following steps: Experimental datasets are generated based on CST simulations. Each set of experimental data in the dataset includes experimental values ​​of geometric parameters and absorption performance parameters of a circular ring with an embedded double-opening resonant ring structure. The absorption performance parameters include the quality factor Q and the absorptivity A, and the geometric parameters include the inner diameter of the metal ring. inner side length of the open-loop resonator and opening width G ; A neural network model is trained based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter. Based on the trained neural network model, determine the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index. The determination of the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model specifically includes: Input the absorption performance parameter requirement index into the trained neural network model to obtain the predicted geometric parameters output by the trained neural network model; CST simulation was performed on the predicted values ​​of the geometric parameters to obtain the simulated values ​​of the absorption performance parameters; Determine the error rate between the required absorption performance parameters and the simulated values ​​of the absorption performance parameters; Determine whether the error rate is less than a preset threshold; If so, the predicted value of the geometric parameters is output as the geometric parameter design value of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index. If not, the predicted values ​​of the geometric parameters and the simulated values ​​of the absorption performance parameters are added to the experimental dataset as a set of experimental data, and the process returns to the step "Train the neural network model based on the experimental dataset to obtain the trained neural network model".

2. The method for determining the structural parameters of a circular ring with embedded double-opening resonant rings according to claim 1, characterized in that, The loss function used to train a neural network model is the mean square error between the output of the neural network model and the experimental values ​​of the geometric parameters.

3. The method for determining the structural parameters of a circular ring with embedded double-opening resonant rings according to claim 1, characterized in that, The neural network model includes an input layer, five hidden layers, and an output layer; the number of nodes in the five hidden layers are 6, 9, 12, 9, and 6, respectively.

4. A system for determining the structural parameters of a circular ring with an embedded double-opening resonant ring, characterized in that, The system is applied to the method according to any one of claims 1-3, and the system comprises: The simulation module is used to generate experimental datasets based on CST simulations. Each set of experimental data in the dataset includes experimental values ​​of the geometric parameters and absorption performance parameters of a circular ring with an embedded double-opening resonant ring structure. The absorption performance parameters include the quality factor Q and the absorptivity A, and the geometric parameters include the inner diameter of the metal ring. inner side length of the open-loop resonator and opening width G ; The training module is used to train a neural network model based on the experimental dataset to obtain the trained neural network model; the input of the neural network model is the absorption performance parameter, and the output of the neural network model is the geometric parameter. The geometric parameter determination module is used to determine the geometric parameter design values ​​of the circular ring embedded double-opening resonant ring structure corresponding to the absorption performance parameter requirement index based on the trained neural network model.

5. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed, implements the method as described in any one of claims 1 to 3.

7. A circular ring with an embedded double-opening resonant ring structure, characterized in that, The circular ring embedded double-opening resonant ring structure includes a metal ring and a double-opening resonant ring located inside the metal ring. The geometric parameters of the circular ring embedded double-opening resonant ring structure are determined by the method described in any one of claims 1-3.

8. A terahertz metamaterial absorber, characterized in that, The terahertz metamaterial absorber comprises, from bottom to top, a metal bottom layer, an intermediate dielectric layer, and a metal microstructure layer; The metal microstructure layer comprises multiple periodically arranged metal microstructures; The metal microstructure is a circular ring with an embedded double-opening resonant ring structure. The geometric parameters of the circular ring embedded double-opening resonant ring structure are determined by the method described in any one of claims 1-3.

9. The terahertz metamaterial absorber according to claim 8, characterized in that, The thickness of the metal microstructure layer and the metal substrate is 0.2 μm, the thickness of the intermediate dielectric layer is 50 μm, the period of the metal microstructure is 100 μm, the outer diameter of the metal ring with the embedded double-opening resonant ring structure is 50 μm, and the outer side length of the double-opening resonant ring is 60 μm.

Images