A two-dimensional piezoelectric material design method, device and computer equipment

Abstract

This application is applicable to two-dimensional material technology, and provides a two-dimensional piezoelectric material design method, device and computer equipment, the method comprising: establishing a defect structure database, the defect structure database at least includes the correspondence between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient; inputting the target piezoelectric coefficient into the pre-trained two-dimensional piezoelectric material design model to obtain the target structure characteristics, the two-dimensional piezoelectric material corresponding to the target structure characteristics satisfies the target piezoelectric coefficient; the target structure characteristics at least include the distribution position and shape characteristics of the defect structure, and the two-dimensional piezoelectric material design model is trained based on the defect structure database. By introducing the idea that the defect structure can be compiled, the material selection range of the two-dimensional piezoelectric material is broadened, and the designability of the piezoelectric performance of the two-dimensional piezoelectric material is improved.

Description

Technical Field

[0001] The present application relates to the field of two-dimensional material technology, and specifically to a two-dimensional piezoelectric material design method, device and computer equipment. Background Art

[0002] Due to its ultra-thin structural characteristics and good electromechanical properties, two-dimensional piezoelectric materials can be integrated with semiconductor processes and conventional electronic technologies, and have broad application prospects in micro-nano motor structures. In traditional design methods, two-dimensional piezoelectric materials usually choose non-centrosymmetric structures, which greatly reduces the diversity of material selection on the one hand, and on the other hand, its electromechanical properties are not adjustable and have low environmental adaptability. On the basis of traditional methods, scholars have proposed to destroy the central symmetry of two-dimensional materials through defects and doping methods to broaden the range of material selection. However, this method has a large randomness in the change of material properties and low designability. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a two-dimensional piezoelectric material design method, device and computer equipment, which broaden the material selection range of two-dimensional piezoelectric materials and improve the designability of piezoelectric performance of two-dimensional piezoelectric materials by introducing the idea of ​​compilable defect structures.

[0004] The technical solutions provided by the embodiments of this application are as follows:

[0005] According to an embodiment of the first aspect of the present application, a two-dimensional piezoelectric material design method is proposed, comprising:

[0006] Establishing a defect structure database, the defect structure database at least includes the corresponding relationship between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient;

[0007] The target piezoelectric coefficient is input into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature, and the two-dimensional piezoelectric material corresponding to the target structural feature satisfies the target piezoelectric coefficient; the target structural feature includes at least the distribution position and shape characteristics of the defect structure, and the two-dimensional piezoelectric material design model is trained based on the defect structure database.

[0008] In a possible implementation of the first aspect, the defect structure database is established by the following method:

[0009] Construct multiple two-dimensional piezoelectric material models by setting the shape and distribution position of the defect structure;

[0010] Each two-dimensional piezoelectric material model is divided into regions, and according to whether there is a defect structure in each divided region and the shape characteristics of the defect structure, a two-dimensional digital matrix for representing the defect structure of each region is generated;

[0011] Calculating the equivalent piezoelectric coefficient of each defect structure in the two-dimensional piezoelectric material model;

[0012] The corresponding relationship between the defect structure characteristics and the equivalent piezoelectric coefficient is determined according to the two-dimensional digital matrix and the equivalent piezoelectric coefficient, and the corresponding relationship is stored in a pre-established defect structure database.

[0013] Specifically, a two-dimensional digital matrix is ​​generated to represent the defect structure of each region, including:

[0014] For each divided area, if there is no defective structure in the area, it is numbered 0, and if there is a defective structure in the area, it is numbered 1; for the area numbered 1, the number is further adjusted according to the characteristics of the defective structure.

[0015] In a possible implementation of the first aspect, the two-dimensional piezoelectric material design model includes a generator and a discriminator;

[0016] The generator is used to generate an intermediate structural feature according to the target piezoelectric coefficient, and the discriminator is used to determine whether the two-dimensional piezoelectric material corresponding to the intermediate structural feature generated by the generator meets the target piezoelectric coefficient, and if the target piezoelectric coefficient is met, the intermediate structural feature is used as the target structural feature.

[0017] In a possible implementation of the first aspect, the method further includes: performing molecular dynamics simulation according to the target structural features, and judging whether the piezoelectric coefficient of the two-dimensional piezoelectric material corresponding to the target structural features meets the target piezoelectric coefficient according to the simulation results.

[0018] Specifically, the target structure feature is a target structure grayscale image; and performing molecular dynamics simulation according to the target structure feature includes:

[0019] Reading the contour geometric features of the target structure grayscale image to obtain a structural feature matrix;

[0020] A molecular model is constructed according to the structural feature matrix, and a molecular dynamics simulation is performed using the molecular model.

[0021] More specifically, the two-dimensional piezoelectric material design model also includes a regressor; the regressor is used to receive an input structure grayscale image and output an equivalent piezoelectric coefficient of the structure grayscale image.

[0022] According to an embodiment of the second aspect of the present application, a two-dimensional piezoelectric material design device is provided, comprising:

[0023] A database establishment module is used to establish a defect structure database, which at least includes the corresponding relationship between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient;

[0024] A design module is used to input the target piezoelectric coefficient into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature, wherein the two-dimensional piezoelectric material corresponding to the target structural feature satisfies the target piezoelectric coefficient; the target structural feature at least includes the distribution position and shape characteristics of the defect structure, and the two-dimensional piezoelectric material design model is trained based on a defect structure database.

[0025] According to an embodiment of the third aspect of the present application, a computer device is proposed, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0026] According to an embodiment of the fourth aspect of the present application, a computer program product is provided. When the computer program product is run on a computer device, the computer device executes the method described in the first aspect.

[0027] As can be seen from the above scheme, the two-dimensional piezoelectric material design method provided by this application establishes a database of structural features and equivalent piezoelectric coefficients, and based on this database, trains a model that can design the two-dimensional piezoelectric material structure according to the specified piezoelectric coefficient, thereby realizing the automatic design of two-dimensional piezoelectric materials. On the one hand, the design method provided by this application is no longer limited to non-centrosymmetric materials, which broadens the range of material selection; on the other hand, it introduces the idea of ​​defect structure compilability, and obtains two-dimensional piezoelectric materials that meet the target piezoelectric coefficient through the design of specific defect structures, realizing the compilability of two-dimensional piezoelectric materials and improving the designability of piezoelectric performance of two-dimensional piezoelectric materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic flow chart of a two-dimensional piezoelectric material design method provided in an embodiment of the present application;

[0029] Figure 2 It is a schematic diagram of a process for establishing a defect structure database provided in an embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of a process of establishing a defect structure database provided by an embodiment of the present application;

[0031] Figure 4 It is a flowchart of a model training provided in an embodiment of the present application;

[0032] Figure 5 It is a schematic diagram of a generation result of a generator provided in an embodiment of the present application;

[0033] Figure 6 is a schematic diagram of generation results of another generator provided in an embodiment of the present application;

[0034] Figure 7 It is a schematic diagram of a contour geometric feature provided in an embodiment of the present application;

[0035] Figure 8 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0037] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0038] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0039] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0040] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0041] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0042] The technical solutions in the embodiments of the present application are described in detail below.

[0043] This application provides a two-dimensional piezoelectric material design method. Figure 1 Provide explanation. Figure 1 A schematic diagram of a two-dimensional piezoelectric material design method is shown, such as Figure 1 As shown, the method includes:

[0044] Step 101, establishing a defect structure database.

[0045] The defect structure is the component structure of the two-dimensional piezoelectric material designed in this application, and its types are relatively diverse. The defect structure database in this step 101 at least includes the correspondence between the defect structure characteristics and the equivalent piezoelectric coefficient. In order to construct the defect structure database, in one embodiment, a large number of two-dimensional piezoelectric material models containing different defect structures can be generated, and then the equivalent piezoelectric coefficient of each defect structure can be calculated based on each two-dimensional piezoelectric material model, so as to obtain the correspondence between the defect structure characteristics and the equivalent piezoelectric coefficient and record it in the defect structure database. To facilitate understanding of this embodiment, Figure 2 A schematic diagram of the establishment process of a defect structure database is shown in FIG. Figure 2 As shown, the method includes the following steps:

[0046] Step 1011, constructing multiple two-dimensional piezoelectric material models by setting the shape characteristics and distribution positions of the defect structures.

[0047] The shape of the defect structure can be a regular shape such as a circle, a rectangle, a triangle, or an irregular shape; the two-dimensional piezoelectric material model is a digital form of the two-dimensional piezoelectric material.

[0048] Step 1012, divide each two-dimensional piezoelectric material model into regions, and generate a two-dimensional digital matrix for representing the defect structure of each region according to whether there is a defect structure in each divided region and the shape characteristics of the defect structure.

[0049] Specifically, there are multiple ways to implement regional division of the constructed two-dimensional piezoelectric material model, such as square grid division, hexagonal grid division, sector division, etc., which can be selected according to the actual needs of different application scenarios and different basic structures of the two-dimensional piezoelectric material model.

[0050] For generating a two-dimensional digital matrix, in one embodiment, a number of 0 or 1 can be assigned to each region after the region division according to whether there is a defect structure in the region. Specifically, if there is no defect structure in the region, the number is 0, and if there is a defect structure in the region, the number is 1. For the region numbered 1, it is further subdivided according to the shape characteristics of the defect structure, that is, the number is adjusted accordingly according to the specific shape characteristics of the defect structure. In this way, the defect structure characteristics can be expressed as a two-dimensional digital matrix, giving the two-dimensional piezoelectric material a compilable characteristic.

[0051] To facilitate understanding of the generation process of two-dimensional digital matrices, Figure 3 A schematic diagram of the process of establishing a defect structure database is shown below. Figure 3 To explain:

[0052] like Figure 3 As shown on the left, the triangular defect structure is used as the research object here, and the two-dimensional piezoelectric material is divided into 4×4 grids, resulting in a total of 16 regions. Then, according to whether there is a defect structure in each region and the shape characteristics of the defect structure, a two-dimensional digital matrix is ​​generated. Specifically, the area without defect structure can be numbered as 0, the area with triangular defect structure and the triangle corner facing right can be numbered as 1, and the area with triangular defect structure and the triangle corner facing left can be numbered as 2. Thus, according to Figure 3 The two-dimensional digital matrix generated by the two-dimensional piezoelectric material on the left can be written as: [1 0 1 0; 0 0 0 1; 0 2 0 0; 0 0 0 2]

[0057] It should be noted that the above two-dimensional digital matrix generation process is only an example. According to the concept given in this application, changes and substitutions that can be easily made by those skilled in the art, such as adopting defect structures of various other shapes, adopting different types of defect structure distributions, etc., should all be deemed to be within the scope of protection of this application.

[0058] Step 1013, calculating the equivalent piezoelectric coefficient of each defect structure in the two-dimensional piezoelectric material model.

[0059] In one embodiment, in order to enrich the data in the database and provide a rich training set for subsequent model training, multiple two-dimensional material models containing different defect structures can be constructed randomly or according to specific rules, and the equivalent piezoelectric coefficient of each defect structure can be calculated respectively. Specifically, tens of thousands of two-dimensional material models containing different defect structures can be randomly constructed first, and then the equivalent piezoelectric coefficient of each defect structure can be calculated by software. The software here can be the molecular dynamics software LAMMPS.

[0060] Step 1014, determining the corresponding relationship between the defect structure and the equivalent piezoelectric coefficient according to the above two-dimensional digital matrix and the equivalent piezoelectric coefficient, and storing the corresponding relationship in a pre-established defect structure database.

[0061] So far, the Figure 2 Description of the process shown. Figure 2 The process shown can establish a database containing the correspondence between defect structures and equivalent piezoelectric coefficients, which can be used as a training set for neural networks later. Moreover, the method for establishing the defect structure database can not only be applied to the design of two-dimensional piezoelectric materials, but also obtain the structural characteristics of two-dimensional materials and the corresponding thermal conductivity, stiffness matrix, dielectric constant, etc. through molecular dynamics or first-principles calculations. Adding them together into the database as a training set for machine learning can achieve the prediction of other properties such as material mechanics and thermodynamics and the secondary design of two-dimensional materials.

[0062] Step 102, inputting the target piezoelectric coefficient into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature, wherein the two-dimensional piezoelectric material structure corresponding to the target structural feature satisfies the target piezoelectric coefficient.

[0063] The target structural features at least include the distribution position and shape characteristics of the defect structure; the target structural features can be in the form of a structural grayscale image, or other structural feature representation forms.

[0064] The two-dimensional piezoelectric material design model is obtained by training based on the above-mentioned defect structure database. When training the design model, a variety of training methods can be used. In one embodiment, in order to accurately predict the piezoelectric coefficient of a two-dimensional piezoelectric material model with a known defect structure distribution, and to train a generator that can independently perform structural design, a generative adversarial network (GAN) training method is used to train the design model. The training method involves a generator and a discriminator, wherein the generator is used to generate a model intended to deceive the discriminator, and the discriminator is used to estimate the coefficient of the determination model. After the training is completed, the generator is used to generate intermediate structural features according to the target piezoelectric coefficient, that is, to achieve the secondary design of the two-dimensional piezoelectric material model, and the discriminator is used to determine whether the piezoelectric coefficient of the two-dimensional piezoelectric material corresponding to the generated intermediate structural feature is within an acceptable range, and if so, the intermediate structural feature is used as the target structural feature. Specifically, the Tensorflow library can be used to write a GAN program based on the Python language for iterative learning. When the design model is used subsequently, the generator regenerates the target structural features of the two-dimensional piezoelectric material that meets the conditions based on the random value according to the target piezoelectric coefficient.

[0065] In order to verify the accuracy of the generated two-dimensional piezoelectric material structure, in one embodiment, a molecular dynamics simulation can be performed based on the target structural features generated by the two-dimensional piezoelectric material design model, and the piezoelectric coefficient of the two-dimensional piezoelectric material corresponding to the target structural features can be judged based on the simulation results to determine whether the piezoelectric coefficient meets the target piezoelectric coefficient. Specifically, whether the target piezoelectric coefficient is met can be determined based on whether the difference of the preset target piezoelectric coefficient is less than a threshold.

[0066] When the generated target structure features are in the form of a structural grayscale image, the following method can be used for molecular dynamics simulation: read the contour geometric features of the target structure grayscale image generated by the generator to obtain a structural feature matrix, build a molecular model based on the structural feature matrix, and perform molecular dynamics simulation using the molecular model. More specifically, a defect contour recognition program compiled based on the Opencv library reads the grayscale image of the target structure to obtain a clear defect geometric distribution; when performing molecular dynamics simulation, LAMMPS software can be used to build a molecular model based on the structural feature matrix, and then the accuracy of the model can be verified by molecular dynamics calculation.

[0067] To facilitate understanding of step 102, a specific example is provided below for explanation:

[0068] Figure 4 The following is a flow chart of the model training process in this example. Figure 4As shown in the figure, in this example, the two-dimensional piezoelectric material design model includes three components: a regressor, a generator, and a discriminator, where:

[0069] Regressor: The function of the regressor is to receive the input structural grayscale image and output the equivalent piezoelectric coefficient of the structural grayscale image. During training, the structural grayscale image used to describe the defect structure characteristics of the two-dimensional piezoelectric material and the corresponding equivalent piezoelectric coefficient are used as training data for training the regressor. The trained regressor can accurately predict the equivalent piezoelectric coefficient of the input structural grayscale image.

[0070] Generator: The generator is used to autonomously generate a structural grayscale image based on the value of the equivalent piezoelectric coefficient required by the input. The structural grayscale image generated by the generator is then calculated by the regressor to obtain the equivalent piezoelectric coefficient predicted by the regressor.

[0071] Discriminator: The structure grayscale image generated by the generator will be handed over to the discriminator to determine whether it meets the requirements of the required structure. At the same time, the discriminator is also trained from the defective structure database. If the structure grayscale image generated by the generator cannot be recognized by the discriminator, the failed case will be returned to the generator for the next round of training. Through the mutual confrontation between the generator and the discriminator, the structure grayscale image generated by the generator is getting closer and closer to the structure required by the target piezoelectric coefficient, and the discriminator's judgment on whether the generated structure meets the error standard is getting more and more accurate.

[0072] As for the specific structure of the two-dimensional piezoelectric material design model, in one embodiment, all three components are composed of neural networks. Among them, the regressor and the discriminator are convolutional neural networks, which are composed of an input layer, a pooling layer, a hidden layer, and an output layer. The pooling layer structure is specifically 3 layers, which are set to (3×3), (5×5) and (3×3) respectively. The goal of the discriminator is to minimize the loss function so that the true data can get as high a score as possible; the generator is a deconvolutional neural network, which is composed of an input layer, a pooling layer and an output layer. The pooling layer structure is specifically two layers, which are set to (2×2) and (3×3) respectively. The purpose of the generator is to minimize the performance of the discriminator so that the discriminator cannot recognize false data.

[0073] The loss function reflects the difference between the output value of the neural network and the true value in a cycle. It is used to judge the accuracy of the neural network. Mathematically, it is the modulus of the difference between the output value and the true value of the training set. The smaller the modulus, the higher the accuracy of the neural network. At the same time, the calculated loss function value will be returned to the neural network through the gradient descent method to adjust the weight matrix of the neural network.

[0074] The following takes the target piezoelectric coefficient as 1.125, that is, the requirement generator automatically generates a structural grayscale image with an equivalent piezoelectric coefficient of 1.125 as an example to illustrate the above training process.

[0075] Assume that after the first round of learning, the structure grayscale image given by the generator is as follows Figure 5 As shown, according to the calculation of the regressor and the judgment of the discriminator, the structural grayscale image does not meet the requirements, so the generated result is returned to the generator for the next round of cyclic learning.

[0076] Assume that after 200 rounds of cyclic learning, the generator generates several structural grayscale images again according to the set data, one of which is as follows Figure 6 As shown in Figure 2, after being calculated by the regressor and judged by the discriminator, the structural grayscale image meets the requirements, and thus the structural grayscale image is used as the target structural feature.

[0077] Furthermore, the contour geometric features of the target structure feature can be extracted through the contour feature recognition program to obtain Figure 7 The schematic diagram of the contour geometric feature is shown. Based on the contour geometric feature, a molecular model is established, and molecular dynamics calculations are performed using LAMMPS. The feasibility of the secondary design is verified by comparing the calculation results with the required piezoelectric coefficient value.

[0078] So far, the Figure 1 Description of the design method for two-dimensional piezoelectric materials shown.

[0079] according to Figure 1 The two-dimensional piezoelectric material design method shown in the figure establishes a database about structural features and equivalent piezoelectric coefficients, and based on this database, trains a model that can design the structure of two-dimensional piezoelectric materials according to the specified piezoelectric coefficient, thereby realizing the automatic design of two-dimensional piezoelectric materials. On the one hand, the design method provided by this application is no longer limited to non-centrosymmetric materials, which broadens the range of material selection; on the other hand, it introduces the idea of ​​defect structure compilability, and obtains two-dimensional piezoelectric materials that meet the target piezoelectric coefficient through the design of specific defect structures, thereby realizing the compilability of two-dimensional piezoelectric materials and improving the designability of piezoelectric performance of two-dimensional piezoelectric materials. Therefore, the output of the electromechanical signal of the two-dimensional piezoelectric material can be controlled by manual selection. While controlling the strength of the electromechanical signal output, the change in the polarization direction of the material under load can also be affected by the change in the defect distribution, making the output of the electrical signal more diverse.

[0080] The two-dimensional piezoelectric material provided in this application can be widely used in many fields. For example:

[0081] Signal sensor: In micro-nano electromechanical systems, due to size limitations, integrated components with electromechanical coupling performance have greater advantages in terms of structural size and construction difficulty compared to complex mechanical structures. By calibrating the input-output of electromechanical signals, two-dimensional piezoelectric film materials can perform the work of traditional sensors with complex structures. At the same time, its self-driving characteristics mean that it does not require the installation of additional power sources such as batteries, greatly reducing the difficulty and cost of maintenance.

[0082] Flexible electronic devices: Another advantage of two-dimensional film is its flexibility and good adhesion to the surface of the structure. At the same time, its ultra-thin structure does not affect the overall structural performance when it is attached to the surface of the structure. These characteristics make it have application prospects in wearable electronic components and flexible electronic devices, such as attaching to the surface of soft robots to detect mechanical signals, or detecting human physiological signals in the medical field, such as detecting the state of organs through flexible sensors attached to the surface of organs during heart surgery.

[0083] Energy harvesting: After secondary design, two-dimensional materials can have a larger equivalent piezoelectric coefficient than the original materials. In applications that convert mechanical energy into electrical energy, the energy conversion efficiency of the structure can be improved in turn. For applications that require devices to be self-powered, such as pacemakers, improvements to piezoelectric materials can effectively improve their energy conversion efficiency.

[0084] Based on the same concept as the two-dimensional piezoelectric material design method provided in this application, this application also provides a two-dimensional piezoelectric material design device, including:

[0085] A database establishment module, used to establish a defect structure database, the defect structure database at least includes the corresponding relationship between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient;

[0086] A design module is used to input the target piezoelectric coefficient into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature. The two-dimensional piezoelectric material corresponding to the target structural feature satisfies the target piezoelectric coefficient. The target structural feature at least includes the distribution position and shape characteristics of the defect structure. The two-dimensional piezoelectric material design model is trained based on a defect structure database.

[0087] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0088] An embodiment of the present application also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0089] Figure 8 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present application. Figure 8 As shown, the computer device of this embodiment includes: at least one processor 20 ( Figure 8 Only one is shown in the figure), a memory 21 and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 implements the steps in any of the above-mentioned two-dimensional piezoelectric material design method embodiments when executing the computer program 22. Those skilled in the art will appreciate that Figure 8 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0090] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0091] In some embodiments, the memory 21 may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 21 may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory 21 may also include both an internal storage unit of the computer device and an external storage device. The memory 21 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0092] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0093] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0094] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A two-dimensional piezoelectric material design method, characterized in that: include: Establishing a defect structure database, the defect structure database at least includes the corresponding relationship between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient; Inputting the target piezoelectric coefficient into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature, wherein the two-dimensional piezoelectric material corresponding to the target structural feature satisfies the target piezoelectric coefficient; The target structure features at least include the distribution position and shape characteristics of the defect structure, and the two-dimensional piezoelectric material design model is obtained by training based on the defect structure database; the two-dimensional piezoelectric material design model includes a generator and a discriminator; The generator is used to generate an intermediate structural feature according to the target piezoelectric coefficient, and the discriminator is used to determine whether the two-dimensional piezoelectric material corresponding to the intermediate structural feature generated by the generator meets the target piezoelectric coefficient, and if the target piezoelectric coefficient is met, the intermediate structural feature is used as the target structural feature.

2. The method according to claim 1, characterized in that The defect structure database is established by the following method: Construct multiple two-dimensional piezoelectric material models by setting the shape characteristics and distribution positions of defect structures; Each two-dimensional piezoelectric material model is divided into regions, and according to whether there is a defect structure in each divided region and the shape characteristics of the defect structure, a two-dimensional digital matrix for representing the defect structure of each region is generated; Calculating the equivalent piezoelectric coefficient of each defect structure in the two-dimensional piezoelectric material model; The corresponding relationship between the defect structure characteristics and the equivalent piezoelectric coefficient is determined according to the two-dimensional digital matrix and the equivalent piezoelectric coefficient, and the corresponding relationship is stored in a pre-established defect structure database.

3. The method according to claim 2, characterized in that The generating of a two-dimensional digital matrix for representing the defect structure of each region includes: For each divided area, if there is no defective structure in the area, it is numbered 0, and if there is a defective structure in the area, it is numbered 1; for the area numbered 1, the number is further adjusted according to the characteristics of the defective structure.

4. The method according to claim 1, characterized in that: The method further comprises: A molecular dynamics simulation is performed according to the target structural features, and it is determined according to the simulation results whether the piezoelectric coefficient of the two-dimensional piezoelectric material corresponding to the target structural features meets the target piezoelectric coefficient.

5. The method according to claim 4, characterized in that The target structure feature is a target structure grayscale image; and performing molecular dynamics simulation according to the target structure feature includes: Reading the contour geometric features of the target structure grayscale image to obtain a structural feature matrix; A molecular model is constructed according to the structural feature matrix, and a molecular dynamics simulation is performed using the molecular model.

6. The method according to claim 5, characterized in that The two-dimensional piezoelectric material design model also includes a regressor; The regressor is used to receive an input structure grayscale image and output an equivalent piezoelectric coefficient of the structure grayscale image.

7. A two-dimensional piezoelectric material design device, characterized in that: include: A database establishment module is used to establish a defect structure database, which at least includes the corresponding relationship between the defect structure characteristics of the two-dimensional piezoelectric material and the equivalent piezoelectric coefficient; A design module, used for inputting a target piezoelectric coefficient into a pre-trained two-dimensional piezoelectric material design model to obtain a target structural feature, wherein the two-dimensional piezoelectric material corresponding to the target structural feature satisfies the target piezoelectric coefficient; The target structure features at least include the distribution position and shape characteristics of the defect structure, and the two-dimensional piezoelectric material design model is obtained by training based on the defect structure database; the two-dimensional piezoelectric material design model includes a generator and a discriminator; The generator is used to generate an intermediate structural feature according to the target piezoelectric coefficient, and the discriminator is used to determine whether the two-dimensional piezoelectric material corresponding to the intermediate structural feature generated by the generator meets the target piezoelectric coefficient, and if the target piezoelectric coefficient is met, the intermediate structural feature is used as the target structural feature.

8. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer program product, characterized in that When the computer program product is executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 6.

Images