Three-band metamaterial wave absorber based on artificial intelligence aided design

Abstract

The invention relates to a three-band metamaterial wave absorber based on artificial intelligence aided design, and belongs to the technical field of artificial electromagnetic materials. The invention aims to solve the problems of low absorption efficiency, narrow bandwidth, large thickness and sensitivity to incident wave polarization state of the traditional wave-absorbing material. The wave absorber adopts a periodically arranged array unit structure, each unit is composed of a metal resonance layer, a dielectric layer and a metal back plate from top to bottom, and the metal resonance layer comprises two coaxial closed resonance rings and four 90-degree fan-shaped metal patches which are symmetrically distributed. Structural size parameters are optimized through an artificial intelligence aided design method, the advantages of three-band high absorptivity, polarization insensitivity, ultra thinness and compactness are achieved, and the sensor has the remarkable effects of being simple in structure, low in cost and easy to manufacture and is suitable for high-performance electromagnetic wave absorption and sensing application.

Description

Technical Field

[0001] This invention belongs to the field of artificial electromagnetic materials technology, and relates to a three-band metamaterial absorber designed with artificial intelligence assistance. Background Technology

[0002] With the rapid development of electronic information technology, the problem of electromagnetic interference in space is becoming increasingly serious. Traditional absorbing materials have inherent disadvantages such as low absorption efficiency, narrow operating bandwidth, and large physical thickness, making it difficult to meet the urgent needs of lightweight equipment, broadband absorption, and multifunctional integration in today's complex electromagnetic environment.

[0003] Against this backdrop, metamaterials have emerged. Metamaterials are artificial structural materials composed of periodically arranged subwavelength resonant units, possessing unique electromagnetic properties not found in natural materials, such as negative permeability and negative dielectric constant. Their electromagnetic properties depend primarily on the artificially designed structure rather than the constituent materials themselves; therefore, unprecedentedly flexible manipulation of electromagnetic waves can be achieved through ingenious structural design.

[0004] However, early metamaterial absorbers typically achieved narrowband absorption at a single frequency, and their absorption performance was extremely sensitive to the incident angle and polarization state of electromagnetic waves. This strong dependence severely limited their practical applications in real-world scenarios. With the deepening research on metasurfaces, higher demands have been placed on metamaterial absorbers with high absorptivity and insensitivity to polarization. Research shows that by integrating multiple similar or differently sized resonant structures on the same plane, multi-band absorption can be achieved. Furthermore, this type of design is insensitive to the incident angle of electromagnetic waves, providing a feasible path for developing practical multi-band absorbers.

[0005] Nevertheless, traditional parameter scanning optimization methods are inefficient and struggle to find the globally optimal combination of structural parameters within a vast design space. Therefore, designing a multi-frequency metamaterial absorber that is polarization insensitive, has high absorption rate, and can rapidly determine optimal parameters using efficient algorithms has become a critical technical challenge that urgently needs to be addressed in this field. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a three-band metamaterial absorber designed with artificial intelligence assistance.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] This invention provides an artificial intelligence-aided design for a three-band metamaterial absorber, which consists of an array of multiple square-structured units. x direction and yThe array is arranged in a periodic pattern, and each array unit consists of a metal resonant layer, a dielectric layer, and a metal backplate with a depth greater than the skin depth of the incident wave, from top to bottom.

[0009] The invention is further characterized in that the metal resonant layer consists of two parts: one part is two coaxial closed resonant rings with different inner and outer side lengths, and the other part is four 90° fan-shaped metal patches inside the metal rings. x Axisymmetric, about y Axisymmetric.

[0010] Dielectric layer and metal backing plate in x Length of direction and y Length of direction L All are 10mm to 20mm.

[0011] Thickness of metal back plate t g The diameter is 0.035mm to 0.175mm, the material is copper, and the conductivity ε = 5.8e+007S / m.

[0012] Thickness of the metal resonant layer tm The diameter is 0.035mm to 0.175mm, the material is copper, and the conductivity ε = 5.8e+007S / m.

[0013] Thickness of dielectric layer H The thickness ranges from 0.6mm to 1.6mm, and the material used is FR4.

[0014] outer side length of the outer closed resonant ring a 3 is 8mm~10mm, inner side length b 3 is 7mm to 9mm thick and is made of copper.

[0015] Outer side length of the inner closed resonant ring a 2 is 5mm~7mm, inner side length b 2 is 4mm to 6mm in diameter and is made of copper.

[0016] The radius of the four 90° sector-shaped metal patches a 1 is 1mm to 2mm thick, and the material used is copper.

[0017] Because the optimization process of absorber structural parameters is complex, a script file was written using VBA code under the controlled variable method to establish a model that can be called by finite element analysis software, generate all possible combinations, avoid duplicate data, check whether there is already a file with the same name, perform condition filtering, retain only the combination that meets the constraints, control the total number of samples, and perform joint simulation analysis with Python-CST. The optimal solution is obtained by calculating the absorption rate, and finally the structural dimensions are determined.

[0018] The beneficial effects of this invention are as follows: First, this absorber achieves structural innovation and a comprehensive improvement in performance. Its metal resonant layer comprises two coaxial closed resonant rings and four symmetrically distributed fan-shaped metal patches. This unique composite structure can excite strong electromagnetic resonances at three discrete frequency points, thereby generating multiple high-absorption-rate resonance peaks. Due to the high symmetry of the overall structure, the absorber exhibits significant insensitivity to the polarization direction of electromagnetic waves; that is, it maintains stable and excellent absorption performance regardless of whether the incident wave is in TE or TM mode. Simultaneously, the absorber uses a metal backplate to completely block transmission, allowing electromagnetic wave energy to be efficiently absorbed primarily through dielectric loss and ohmic loss.

[0019] Secondly, this invention introduces a highly efficient AI-aided design method, overcoming the bottlenecks of traditional parameter optimization techniques. By parameterizing multiple key structural dimensions, a dataset of all permutations and combinations conforming to geometric constraints is automatically generated using scripts. This dataset is then analyzed in batches using electromagnetic simulation software. This method can systematically traverse a vast design space, quickly and accurately locating the globally optimal combination of structural dimensions. This intelligent design process significantly improves R&D efficiency and design accuracy.

[0020] Furthermore, this absorber possesses significant advantages in terms of practicality and industrialization. Its simple and compact structure, along with its ultra-thin overall thickness, facilitates integration into modern electronic devices. All constituent materials are common industrial materials such as copper and FR4, resulting in low cost and ease of manufacturing through standard processes, laying the foundation for large-scale production applications.

[0021] Finally, this absorber demonstrates broad application prospects. Its resonant response at each resonance peak is extremely sharp, indicating a high quality factor. This makes it highly sensitive to subtle frequency changes or variations in the environmental dielectric constant, thus possessing enormous application potential in high-precision sensing fields such as chemical substance detection and biomolecular recognition.

[0022] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0023] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1This is a schematic diagram of the unit three-dimensional structure of a three-band metamaterial absorber designed with artificial intelligence aids, provided in an embodiment of the present invention. Figure 2 This is a top view of the structural unit; Figure 3 This is a side view of a unit of a three-band metamaterial absorber designed with artificial intelligence aids, provided in an embodiment of the present invention. Figure 4 A flowchart illustrating the determination of optimal dimensions for a three-band metamaterial absorber designed with artificial intelligence assistance, provided as an embodiment of the present invention; Figure 5 The preferred solution obtained by the artificial intelligence-aided design of a three-band metamaterial absorber provided in this embodiment of the invention under the condition of vertical microwave incidence is... S 11 The relationship curve between reflection parameters and frequency; Figure 6 The present invention provides an embodiment of an artificial intelligence-aided design of a three-band metamaterial absorber, under microwave vertical incidence, and compares the absorption rates in TE and TM modes during simulation.

[0024] Reference numerals: 1: Outer closed resonant ring, 2: Inner closed resonant ring, 3: Four 90° sector-shaped metal patches, 4: Dielectric layer, 5: Metal backplate. Detailed Implementation

[0025] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0026] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0027] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0028] Figure 1 This is a schematic diagram of the unit three-dimensional structure of a three-band metamaterial absorber designed with artificial intelligence aids, provided in an embodiment of the present invention. It includes an outer closed resonant ring 1, an inner closed resonant ring 2, four 90° fan-shaped metal patches 3, a dielectric layer 4, and a metal backplate 5. Figure 2 This is a top view of the structural unit. a 3 represents the outer side length of the outer closed-loop resonant ring. b 3 represents the inner side length of the outer closed-loop resonant ring. a 2 represents the outer side length of the inner closed-loop resonant ring. b 2 represents the inner side length of the inner closed-loop resonant ring. a 1 represents the radius of the four 90° sector-shaped metal patches. L For dielectric layer and metal backplane in x Length in direction and in y The length of the direction.

[0029] Figure 3 This is a unit side view of a three-band metamaterial absorber designed with artificial intelligence aids, provided in an embodiment of the present invention. tm represents the thickness of the metal resonant layer. H The thickness of the dielectric layer, t g The thickness is the metal backing plate.

[0030] Figure 4 This is a flowchart illustrating the determination of the optimal size of a three-band metamaterial absorber designed with artificial intelligence assistance, as provided in an embodiment of the present invention.

[0031] Figure 5 The preferred solution obtained by the artificial intelligence-aided design of a three-band metamaterial absorber provided in this embodiment of the invention under the condition of vertical microwave incidence is... S 11 The relationship curve between reflection parameters and frequency; Figure 6This is a comparison curve of the absorption rate of a three-band metamaterial absorber designed with artificial intelligence aids under microwave vertical incidence, provided in an embodiment of the present invention, in TE mode and TM mode during simulation.

[0032] Please see Figures 1-6 This is a three-band metamaterial absorber designed with artificial intelligence assistance.

[0033] Example 1 This embodiment provides a detailed description of a three-band metamaterial absorber designed with artificial intelligence as proposed in this invention.

[0034] like Figure 1 As shown, the present invention describes a three-band metamaterial absorber designed with artificial intelligence assistance, which consists of several array units arranged periodically. Each unit comprises, from top to bottom, a metal resonant layer, a dielectric layer, and a metal backplate with a depth greater than the skin depth. The metal resonant layer consists of two parts: one part is two coaxial closed resonant ring structures with different inner and outer side lengths, and the other part is four 90° sector-shaped metal patches. The metal patches are located within the closed resonant ring structures, symmetrical about the center of the array unit, and are respectively attached to the inner sides of the four sides of the square, forming a "cross-shaped" dielectric gap between adjacent sectors.

[0035] In this embodiment, the length direction of the absorber array composed of several absorbing units is defined as follows: x Direction, width direction is y Direction. The horizontal axis of all array elements points to... x Direction and parallel to x Direction: The vertical axis of all array elements points to... y Direction. All absorber array elements are along... x , y The directional periodic arrangement results in a metamaterial absorber that operates in the 3.6 GHz to 19.8 GHz band.

[0036] Because the two closed resonant rings and four 90° sector-shaped metal patches in the metal resonant layer act essentially independently in the absorption spectrum, they do not affect each other's resonance peaks. Therefore, as Figure 4 As shown, an innovative approach is adopted to optimize the structural parameters using artificial intelligence-aided design. In Python, the outer side length a3 of the outer closed resonant ring and the inner side length of the outer closed resonant ring in the absorber structure are calculated. b 3. Length of the outer side of the inner closed-loop resonant ring a 2. Inner side length of the inner closed-loop resonant ring b 2. Radius of the sector-shaped metal patch a 1. Side lengths of the dielectric layer and the metal backing plate L Thickness of the metal backing plate t g Dielectric layer thicknessH and the thickness of the metal resonator layer tm These nine parameters are used as independent variables. A dataset is built using the method of controlling variables, and constraints are established within it to ensure the correct structure.

[0037] In this embodiment, based on the subwavelength requirement, the physical dimension range and simulation step size of the structural parameters are initially set. The structural parameter range and step size are input into Python, and the outer side length of the outer closed resonant ring is denoted as... a 3, its range is 8mm~10mm, with a step size of 0.5mm; the inner side length of the outer closed resonant ring is denoted as... b 3, its range is 7mm~9mm, with a step size of 0.5mm; the outer side length of the inner closed resonant ring is denoted as... a 2, its range is 5mm to 7mm, with a step size of 0.5mm; the inner side length of the inner closed resonant ring is denoted as... b 2, its range is 4mm to 6mm, with a step size of 0.5mm; the radius of the four 90° sector-shaped metal patches is denoted as... a 1, its range is 1mm to 2mm, with a step size of 0.25mm; the side lengths of the dielectric layer and the metal backing plate are denoted as... L Its range is 10mm to 20mm, with a step size of 1mm; the thickness of the metal backing plate is denoted as... t g Its range is 0.035mm to 0.175mm, with a step size of 0.035mm; the dielectric layer thickness is denoted as... H Its range is 0.6mm to 1.6mm, with a step size of 0.2mm; the thickness of the metal backing plate is denoted as... t g Its range is 0.035mm to 0.175mm, with a step size of 0.035mm.

[0038] After specifying the parameter range and step size, apply geometric logic constraints to determine the outer side length of the outer closed resonant ring. a 3. It needs to be greater than the inner side length of the outer closed resonant ring. b 3. Length of the outer side of the inner closed-loop resonant ring a 2 needs to be greater than the inner side length of the inner closed resonant ring. b 2. Inner side length of the outer closed resonant ring b 3. It needs to be greater than the outer side length of the inner closed-loop resonant ring. a 2, that is a 3> b 3. a 2> b 2. b 3> a 2. Remove physically invalid or duplicate structural data, build an automatically adjustable parameterized model in Python, and generate a dataset of all possible permutations and combinations of parameters.

[0039] In this embodiment, VBA commands are called in Python to perform modeling and boundary condition setting in the encoder. The dataset of structural parameter groups is substituted into the dataset, and joint electromagnetic simulation is performed to obtain the electromagnetic response parameters at the three resonance peaks of each data set. S 11 , S 11 The parameters typically have one thousand frequency response points, with one point evenly selected at 0.25 GHz intervals. The electromagnetic response parameters are configured in the script file. S 11 The resonant peak is defined and a training model is established to obtain the frequency and electromagnetic response parameters at the resonant peak. S 11 The average absorption rate at the three resonance peaks corresponding to each set of data is calculated, and the optimal solution is the data set with the highest average absorption rate, which is the physical size of the structure.

[0040] After determining the structural physical dimensions corresponding to the optimal solution, other performance evaluations of the absorber were performed, including TE and TM polarization insensitivity simulations. Due to the structural symmetry, the absorber exhibits polarization insensitivity.

[0041] Preferably, such as Figure 2 As shown, in this embodiment, the dielectric layer and metal backplane of a single array unit are... x direction and y The length of the direction is denoted as L The range is 10mm to 20mm, preferably 10mm.

[0042] Preferably, in this embodiment, the outer side length of the outer closed-loop resonant ring structure of a single array unit is denoted as . a 3, its range is 8mm to 10mm, preferably 10mm; the inner side length of the outer closed resonant ring is denoted as... b 3, the range is 7mm to 9mm, preferably 9mm.

[0043] Preferably, in this embodiment, the outer side length of the inner closed-loop resonant ring structure of a single array unit is denoted as a2, and its range is 5mm to 7mm, preferably 6mm; the inner side length of the inner closed-loop resonant ring is denoted as... b 2. Its range is 4mm to 6mm, preferably 5mm.

[0044] Preferably, in this embodiment, the radii of the four 90° fan-shaped metal patch structures of a single array unit are denoted as [missing information]. a 1. Its range is 1mm to 2mm, preferably 1.5mm.

[0045] Preferably, such as Figure 3 As shown, the thickness of the metal backplate of a single array unit in this embodiment is denoted as . tg The dielectric layer thickness ranges from 0.035 mm to 0.175 mm, preferably 0.035 mm; the dielectric layer thickness of a single array unit is denoted as... H Its range is 0.6–1.6 mm, preferably 0.8 mm; the thickness of the metal resonant layer of a single array unit is denoted as... tm The range is 0.035mm to 0.175mm, preferably 0.035mm.

[0046] Preferably, in this embodiment, both the top metal layer and the bottom metal backplate are made of copper, a metal with loss characteristics, and its conductivity in the microwave band is ε = 5.8e+007 S / m. Its good conductivity and magnetism can control the resonant frequency and coupling characteristics of the absorber, thereby improving the absorber's absorption rate and reducing energy loss.

[0047] Preferably, the material of the intermediate dielectric layer is FR4, which has a relative permittivity of 4.3 and a tangent loss of 0.025 in the microwave band. This helps to achieve the required electrical dimensions of the array unit structure to reach the required resonant frequency. It also has excellent compatibility with the metal layer, low cost, and wide application.

[0048] Typically, the absorptivity A(ω) is an indicator for evaluating the absorption performance of an absorber, and it is defined as follows:

[0049] in R It's reflectivity. T It's transmittance. S 11 It is the reflection coefficient. S 21 This is the transmission coefficient. Because the structure has a metal backplate, the transmittance T = 0 (electromagnetic waves cannot penetrate). In this case, the absorptivity simplifies to: .like Figure 5 As shown, the optimal solution obtained by the absorber under vertical microwave incidence is... S 11 The parameter-frequency relationship curves show that the absorption rates at the three resonant peaks of the metamaterial absorber invented in this embodiment—4.785 GHz, 8.25 GHz, and 18.81 GHz—are 99.95%, 98.67%, and 99.71%, respectively. This demonstrates that the invention possesses good absorption performance, absorbing waves at multiple resonant peaks, and as... Figure 6 As shown, the absorption rate comparison curves of the three-band metamaterial absorber in TE mode and TM mode were further studied. Due to its symmetrical structure, the absorber has the advantage of polarization insensitivity, which meets the requirements of multiple applications. Moreover, the Q factor at the resonance peak is relatively high, which has the potential for sensing applications.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A three-band metamaterial absorber designed with artificial intelligence assistance, characterized in that: The absorber consists of an array of multiple cubic structure units. x direction and y The array is arranged in a periodic pattern, and each array unit consists of a metal resonant layer, a dielectric layer and a metal backplate from top to bottom.

2. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 1, characterized in that: The metal resonant layer comprises two coaxial closed resonant rings and four 90° sector-shaped metal patches.

3. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 2, characterized in that: The four 90° sector-shaped metal patches are located inside the two closed resonant rings, respectively attached to the inner sides of the four sides of the square, and a cross-shaped dielectric gap is formed between adjacent sectors.

4. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 3, characterized in that: The four 90° sector-shaped metal patches are symmetrical about the center of the array unit. x Axisymmetric and about y Axisymmetric.

5. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 4, characterized in that: The array unit is a subwavelength structure, and its size is the wavelength corresponding to the lowest absorption frequency. ~ .

6. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 5, characterized in that: The dielectric layer and the metal backplate are in x Length of direction L and y Length of direction L All are 10mm~20mm.

7. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 6, characterized in that: The thickness of the metal back plate t g The diameter ranges from 0.035mm to 0.175mm, the material is copper, and the electrical conductivity is 5.8×10⁻⁶. 7 S / m.

8. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 7, characterized in that: The thickness of the metal resonant layer tm The diameter is 0.035mm to 0.175mm, and the material is copper.

9. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 8, characterized in that: The thickness of the dielectric layer H The thickness is 0.6mm~1.6mm, and the material is epoxy resin FR4.

10. The three-band metamaterial absorber designed with artificial intelligence assistance according to claim 9, characterized in that: The structural dimensions of the absorber are determined by an artificial intelligence-aided design optimization method. The method includes initially setting the physical dimension range and simulation step size of the structural parameters according to the subwavelength requirements, establishing a parameter model using VBA scripts, generating a full permutation and combination dataset and performing deduplication and constraint screening, performing electromagnetic simulation analysis in conjunction with Python-CST, and calculating the optimal solution with the absorption rate as the objective function, thereby determining the final structural dimensions.

Images