Method and device for predicting thermal conductivity of composite material

Abstract

The invention is suitable for the technical field of crossing of material science and computer science, and provides a method and device for predicting the thermal conductivity of a composite material, and the method comprises the steps: obtaining the datamation structure characteristics of a to-be-predicted composite material microstructure; inputting the datamation structure feature into a pre-trained machine learning prediction model, and outputting a predicted macroscopic physical performance value by the machine learning prediction model; wherein the machine learning prediction model is obtained through training by utilizing a structure-performance database, the structure-performance database comprises a plurality of data pairs, and each data pair comprises a datamation structure feature representing the microstructure of the composite material; and a predetermined macroscopic physical performance value corresponding to the digitized structural feature. Therefore, when the performance of the composite material is predicted, the calculation efficiency and the prediction accuracy can be considered.

Description

Technical Field

[0001] The present application belongs to the interdisciplinary field of materials science and computer science, and in particular relates to a method and device for predicting the thermal conductivity of composite materials. Background Art

[0002] The macroscopic physical properties of composite materials, such as nickel-yttria-stabilized zirconia anodes used in solid oxide fuel cells, such as thermal conductivity, electrical conductivity, and mechanical strength, are determined by their complex internal microstructure. Accurately evaluating these properties is crucial for the design, performance optimization, and service reliability assessment of new materials.

[0003] At present, the technical means of evaluating the physical properties of composite materials mainly include experimental measurement and numerical simulation. Although the experimental measurement method has direct results, it is difficult to perform in-situ and accurate measurements in real working environments for materials that need to work under extreme working conditions such as high temperature and chemical reactions. In addition, the experimental cost is high and the cycle is long. Numerical simulation methods, such as the multi-scale simulation method that combines molecular dynamics and finite element analysis, can provide high calculation accuracy, but their calculation process is extremely complex, requires huge computing resources, and is extremely time-consuming. For example, predicting the thermal conductivity of a single sample may take days or even weeks. This low efficiency seriously restricts the speed of new material research and development and structural optimization iteration.

[0004] Therefore, the existing technology urgently needs a new method for predicting composite material properties that can balance computational efficiency and prediction accuracy. Summary of the Invention

[0005] The embodiments of the present application provide a method and apparatus for predicting thermal conductivity of composite materials, which can balance computational efficiency and prediction accuracy.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting thermal conductivity of a composite material, comprising: Obtaining the digitized structural characteristics of the composite material microstructure to be predicted; Inputting the digitized structural features into a pre-trained machine learning prediction model, and having the machine learning prediction model output predicted macroscopic physical performance values; Among them, the machine learning prediction model is obtained by training using a structure-performance database, which contains multiple data pairs, each data pair including a digitized structural feature characterizing the microstructure of the composite material and a predetermined macroscopic physical property value corresponding to the digitized structural feature.

[0007] In a possible implementation of the first aspect, the process of constructing the structure-performance database includes: Scan and 3D reconstruct the composite material used as a sample to obtain digitized structural characteristics; Calculate the material parameters of each component constituting the composite material under a preset working environment through molecular dynamics simulation; wherein the material parameters include the interfacial thermal resistance between the components; Performing finite element method heat conduction simulation on the digitized structural characteristics based on the material parameters to obtain corresponding macroscopic physical performance values; The digitized structural features are paired with corresponding macroscopic physical property values ​​to form the structure-property database.

[0008] In a possible implementation of the first aspect, scanning and three-dimensionally reconstructing the composite material as a sample to obtain digitized structural features includes: Scanning and three-dimensionally reconstructing the composite material using focused ion beam scanning electron microscopy imaging technology to generate a digital three-dimensional model including the spatial distribution of each phase; The digital three-dimensional model is converted into the digitized structural features.

[0009] In a possible implementation of the first aspect, the loss function of the machine learning prediction model includes a data fitting term and a physical law constraint term; The data fitting term is used to measure the difference between the macroscopic physical property value predicted by the machine learning prediction model and the macroscopic physical property value in the structure-performance database; The physical law constraint item is used to force the machine learning prediction model to generate a physical field distribution that satisfies a preset physical control equation when making predictions based on the digitized structural features.

[0010] In a possible implementation of the first aspect, the composite material is a nickel-yttria-stabilized zirconia anode for a solid oxide fuel cell; the macroscopic physical property value is thermal conductivity; and the physical control equation is a steady-state heat conduction equation.

[0011] In a possible implementation of the first aspect, performing a finite element method heat conduction simulation on the digitized structural features based on the material parameters to obtain corresponding macroscopic physical property values ​​includes: The material parameters are assigned to the physical phase region corresponding to the digitized structural characteristics, and the steady-state heat conduction equation is solved based on the finite element method to obtain the corresponding macroscopic physical performance values.

[0012] In a possible implementation of the first aspect, the physical field distribution includes a temperature field distribution; The steady-state heat conduction equation is solved based on the finite element method to obtain the corresponding macroscopic physical performance values, including: applying a constant heat flux density boundary condition on a heat input surface of the digital three-dimensional model, and applying a fixed temperature boundary condition on a heat dissipation surface of the digital three-dimensional model; iteratively solving the steady-state heat conduction equation until a temperature field distribution reaches a steady state, and calculating a temperature gradient according to the steady-state temperature field distribution; calculating a thermal conductivity according to the preset input heat flux density and the temperature gradient.

[0013] In a second aspect, an embodiment of the present application provides a composite material thermal conductivity prediction device, comprising: an acquisition module configured to acquire dataized structure features of a microstructure of a composite material to be predicted; a prediction output module configured to input the dataized structure features into a pre-trained machine learning prediction model, and output a predicted macroscopic physical property value from the machine learning prediction model. The machine learning prediction model is obtained by training using a structure-property database, and the structure-property database comprises a plurality of data pairs, each data pair comprising a dataized structure feature representing a microstructure of a composite material and a pre-determined macroscopic physical property value corresponding to the dataized structure feature.

[0014] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the composite material thermal conductivity prediction method of any one of the first aspect when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the composite material thermal conductivity prediction method of any one of the first aspect.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a computer device, causes the computer device to execute the composite material thermal conductivity prediction method of any one of the first aspect.

[0017] Compared with the prior art, the embodiment of the present application has the following beneficial effects: Based on this application's microscopic digitized structural features and machine learning prediction technology, the digitized structural features of the composite material's microstructure can be obtained and input into a trained machine learning prediction model to quickly and accurately output macroscopic physical property values. This bypasses the complex analytical process of modeling and calculating the composite material, avoiding the time-consuming and computationally expensive finite element simulation for each new structure, significantly reducing computational costs and significantly improving evaluation efficiency.

[0018] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 This is a flowchart of the offline training phase for generating a structure-performance database provided by an embodiment of the present application; Figure 2 This is an application flow chart of a composite material thermal conductivity prediction method provided in one embodiment of the present application; Figure 3 This is a schematic diagram of the technical principle of a method for predicting thermal conductivity of composite materials provided in one embodiment of the present application; Figure 4 This is a machine learning prediction model principle and data processing flow chart for thermal conductivity prediction provided by one embodiment of the present application; Figure 5 Schematic diagram of the structure of the composite material thermal conductivity prediction device provided in an embodiment of the present application; Figure 6 It is a structural diagram of the computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may 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 avoid obscuring the description of the present application with unnecessary detail.

[0022] 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 preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0023] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" 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 "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0025] 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.

[0026] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0027] The embodiment of the present application provides a complete implementation process of a composite material thermal conductivity prediction method. Specifically, taking the nickel-yttria stabilized zirconia porous anode, a key component in a solid oxide fuel cell, as an application object, how to construct and apply a high-precision machine learning prediction model to realize fast and accurate prediction of the macroscopic physical performance value (thermal conductivity) of the nickel-yttria stabilized zirconia porous anode in a real working environment is described in detail. The composite material in the technical solution can be a nickel-yttria stabilized zirconia anode for a solid oxide fuel cell, and the macroscopic physical performance value is thermal conductivity. The overall process of the technical solution can be divided into two main stages: one is an offline training stage, and the core task of the offline training stage is to construct a high-fidelity structure-performance database that can accurately reflect the physical reality, and to train a machine learning prediction model with data fitting ability and physical consistency by using the database; the other is an online application stage, and the core task of the online application stage is to use the machine learning prediction model obtained in the first stage to quickly predict the thermal conductivity of any new composite material microstructure provided.

[0028] Reference Figure 1 which shows an offline training stage process for generating a structure-performance database in the embodiment of the present application, and the process constitutes the basis for ensuring the accuracy of the final machine learning prediction model.

[0029] First, the accurate three-dimensional microstructure of the composite material needs to be obtained. In the embodiment, as shown in Figure 1 , 101 scans and three-dimensionally reconstructs the composite material as a sample to obtain data structure features. Specifically, a focused ion beam scanning electron microscope imaging technology is used to scan and three-dimensionally reconstruct the composite material to generate a digital three-dimensional model containing the spatial distribution of each phase, and the digital three-dimensional model is converted into the data structure features.

[0030] As can be understood, this technology combines the precise cutting capabilities of a focused ion beam with the high-resolution imaging capabilities of a scanning electron microscope. During operation, a prepared composite material sample (e.g., nickel-yttria-stabilized zirconia) is placed in the microscope's vacuum chamber. A focused gallium ion beam then cuts the sample surface layer by layer. After each extremely thin layer (e.g., 10-20 nanometers thick) is cut, the newly exposed cross-section is imaged by the scanning electron microscope. This continuous cutting-imaging cycle yields a series of two-dimensional cross-sectional images. These two-dimensional cross-sectional images are then aligned, segmented, and three-dimensionally reconstructed using specialized image processing software. Ultimately, multiple digital three-dimensional microstructures 102 are generated that accurately reflect the spatial distribution, morphology, and connectivity of the material's internal pores, nickel phase, and yttria-stabilized zirconia phases. Digital three-dimensional models 102 are then converted into the digitized structural features described above and stored as a three-dimensional voxel matrix. Each voxel is assigned a label identifying its phase (e.g., nickel, yttria-stabilized zirconia, or pores). The reconstructed digital three-dimensional model 102 is converted into digitized structural features that can be processed by a machine learning prediction model. In this embodiment, a convolutional neural network or other machine learning prediction model can be selected, so the microstructure needs to be converted into a three-dimensional data matrix. Specifically, the digital three-dimensional model 102 can be discretized into a three-dimensional grid of a preset size (e.g., 256×256×256 voxels). Each voxel in the grid is assigned a specific integer value based on its physical phase. For example, if the voxel is in the porous phase, it is assigned a value of 0; if it is in the nickel phase, it is assigned a value of 1; if it is in the yttria-stabilized zirconia phase, it is assigned a value of 2. In this way, the complex microstructure is converted into a three-dimensional data matrix containing a large number of numerical values, which constitutes the digitized structural features described in this application.

[0031] At the same time, in order to make the subsequent macro-performance simulation close to the actual physical conditions, it is necessary to calculate the material parameters of each component of the composite material under the preset working environment.

[0032] This embodiment introduces a molecular dynamics simulation shown as 103. Through the molecular dynamics simulation, material parameters 104 of each component constituting the composite material under a preset working environment are calculated; wherein the material parameters include the interfacial thermal resistance 105 between the components.

[0033] Specifically, since thermal conductivity depends on the intrinsic thermal conductivity of each component of the material and the heat transfer capacity of the interface between them, it is necessary to first accurately calculate these parameters at the atomic scale. In this embodiment, the composite material studied is nickel-yttria-stabilized zirconia, and the operating temperature is generally between 800 degrees Celsius and 1000 degrees Celsius. Molecular dynamics methods can be used to simulate pure nickel crystals and pure yttria-stabilized zirconia crystals at a set operating temperature to calculate their intrinsic thermal conductivity. and At the same time, an atomic model including the nickel / yttria-stabilized zirconia interface was constructed, and the interfacial thermal resistance (also called thermal resistance) at the nickel-yttria-stabilized zirconia phase interface was calculated by simulating the heat flow and temperature drop on both sides of the interface.

[0034] The interfacial thermal resistance 105 is a key microscopic parameter that affects the macroscopic thermal conductivity of the composite material, but accurate parameters are difficult to obtain in traditional finite element simulations. These parameters, obtained through molecular dynamics simulations in this application, together constitute the high-fidelity material parameters 104.

[0035] Subsequently, the results of the two parallel steps are combined, and a finite element method heat conduction simulation is performed in 106. Based on the material parameters, a finite element method heat conduction simulation is performed on the digitized structural features to obtain corresponding macroscopic physical performance values ​​107. Specifically: the material parameters are assigned to the physical phase region corresponding to the digitized structural features, and the steady-state heat conduction equation is solved based on the finite element method to obtain the corresponding macroscopic physical performance values. Further specifically: the physical field distribution includes a temperature field distribution; a constant heat flux density boundary condition is applied to the heat flux input surface of the digital three-dimensional model, and a fixed temperature boundary condition is applied to the heat dissipation surface of the digital three-dimensional model; the steady-state heat conduction equation is iteratively solved until the temperature field distribution reaches a steady state, and the temperature gradient is calculated based on the steady-state temperature field distribution; the thermal conductivity is calculated based on the preset input heat flux density and the temperature gradient.

[0036] In this embodiment of the present application, each digital three-dimensional model 102 obtained via 101 is first imported into finite element analysis software and meshed. Material parameters 104, including interface thermal resistance 105, calculated via 103, are then assigned to the corresponding phases (nickel phase, yttria-stabilized zirconia phase) and interface regions within the digital three-dimensional model 102. Next, a fixed temperature boundary condition (e.g., 1073K on one surface and 1063K on the opposite surface) is applied to two opposing surfaces of the digital three-dimensional model 102, while adiabatic boundary conditions are applied to the other surfaces. A constant heat flux boundary condition is also applied to the heat input surface of the digital three-dimensional model. Subsequently, by solving the steady-state heat conduction equation, the temperature field distribution within the entire digital three-dimensional model 102 and the total heat flux through the digital three-dimensional model 102 can be calculated. Using the applied temperature gradient and the calculated total heat flux, the macroscopic physical property value 107 corresponding to the digital three-dimensional model 102 of the three-dimensional microstructure can be calculated according to Fourier's law. By repeating this process for all the digital three-dimensional models 102 of the composite materials, a series of structure-property data can be obtained.

[0037] Each digital 3D model 102 is converted into a digitized structural feature. These digitized structural features (serving as input features) are paired with corresponding macroscopic physical property values ​​107 (serving as output labels) calculated through finite element method heat conduction simulation 106, forming data pairs. The collection of all such pairs forms a structure-performance database 108. The high-fidelity nature of this database is reflected in its input (which contains realistic microstructures) and output (which is simulation results based on real operating parameters) being as close to physical reality as possible.

[0038] In an optional embodiment, the loss function of the machine learning prediction model includes a data fitting term and a physical law constraint term; the data fitting term is used to measure the difference between the macroscopic physical performance value predicted by the machine learning prediction model and the macroscopic physical performance value in the structure-performance database; the physical law constraint term is used to encourage the machine learning prediction model to generate a physical field distribution that satisfies a preset physical control equation when making predictions based on the digitized structural features, and the physical control equation is a steady-state heat conduction equation.

[0039] In one embodiment of the present application, considering that the input data is a digitized structural feature, a three-dimensional convolutional neural network is preferably used as the feature extraction front end of the model. The network can be composed of multiple three-dimensional convolutional layers, activation function layers (such as linear rectifier units), and pooling layers, and can automatically learn and extract spatial structural features related to thermal conductivity from the input digitized structural features, such as the volume fraction, curvature, and connectivity of each phase. At the end of the three-dimensional convolutional neural network, several fully connected layers are connected to map the extracted high-dimensional features into a single scalar output, namely the predicted macroscopic physical property value.

[0040] Subsequently, the core training process begins, the goal of which is to optimize the internal parameters of the machine learning prediction model (such as the weights and biases of the convolution kernel) so that it can accurately predict. The training process uses a high-fidelity structure-performance database as the data source. It should be noted that, unlike traditional neural network training, the embodiment of the present application uses a special composite loss function to guide training. The loss function includes a data fitting term and a physical law constraint term.

[0041] The data fitting term is used to measure the difference between the model's predicted value and the true value in the database. Specifically, it can be calculated using the mean square error, and its mathematical expression is: ,in is the number of samples in the training batch, The model is The macroscopic physical properties values ​​predicted by the microstructure are is the corresponding macroscopic physical property value obtained by finite element method heat conduction simulation in the database 107. The goal of minimizing the data fitting term is to make the model prediction results fit the high-fidelity data as closely as possible.

[0042] The physical law constraint term is the key difference between the embodiment of this application and the pure data-driven model. The physical law constraint term is used to measure the degree of conformity between the physical field distribution generated internally by the machine learning prediction model during the prediction process and the preset physical control equation, so that the physical field distribution generated by the machine learning prediction model during the prediction process is close to the solution of the preset physical control equation. This loss term is intended to incorporate the physical law of heat conduction as a soft constraint into the training process of the model. In this embodiment, based on the steady-state heat conduction equation, that is, , to construct the physical law constraint terms. Among them, is the spatial position The temperature at is the local thermal conductivity at that point. To calculate this loss, a large number of configuration points can be randomly sampled within each three-dimensional microstructure domain. For each configuration point, the model not only needs to predict the macroscopic thermal conductivity, but also the neuron activation state inside it can be constructed to represent the local temperature field. The residual of this equation can be calculated by automatic differentiation technology. The physical law constraint term is the mean square value of the residual at all configuration points: ,in is the number of collocation points. The goal of minimizing the physical law constraint is to force the model’s predicted behavior (i.e., the internally generated physical field distribution, also known as the temperature field distribution) to obey the basic physical laws of heat conduction, even in regions without data labels.

[0043] Therefore, the total loss function is the weighted sum of these two terms: .in, and It is a hyperparameter that balances the importance of data fitting and physical constraints. During the training process, the model parameters are continuously adjusted to minimize the When the loss function converges or reaches the preset number of training rounds, the training process is complete, resulting in the aforementioned machine learning prediction model. Because this model simultaneously learns data patterns and physical laws, it has higher prediction accuracy, stronger generalization capabilities, and greater physical reliability.

[0044] Regarding the construction of the physical law constraint term in the loss function, the above embodiment describes a solution based on the steady-state heat conduction equation. As an optional implementation method, this embodiment will explain how to construct the physical law constraint term based on the transient heat conduction equation to cope with more complex physical scenarios. The complete form of the transient heat conduction equation is: ,in is the density, is the specific heat capacity, It's time, is an internal heat source. In the absence of an internal heat source, the equation simplifies to To utilize this equation, the output of the machine learning prediction model needs to be designed to simultaneously predict the temperature field , that is, temperature is not only a function of space, but also a function of time. Accordingly, the input of the model also needs to increase the time dimension Physical loss items The calculation method of is to calculate the mean square value of the residual of the transient equation at the collocation points sampled in the time and space domain: The model trained in this way can not only predict the effective thermal conductivity in steady state, but also the dynamic thermal response behavior of the material when subjected to thermal shock or cyclic thermal loads. This is of great significance for evaluating the material's thermal shock resistance and other properties. This different choice of the physical law of heat conduction (steady state or transient) enables the technical solution of this application to address more diverse and complex engineering problems.

[0045] In the embodiments of the present application, physical law constraints are introduced into the loss function of model training to incorporate prior knowledge of physics into the model training process. This is equivalent to providing the model with additional supervisory information beyond the training data, forcing the model's prediction behavior to comply with the laws of physics. This effectively prevents the model from overfitting when the training data is limited, enhances its ability to generalize to new, unseen structures, and ensures that the prediction results are physically reasonable and self-consistent, with higher reliability. This improves the accuracy, generalization ability, and physical reliability of the prediction model.

[0046] Next, go to the online application stage and refer to Figure 2 , shows an application flow chart of a composite material thermal conductivity prediction method provided in this application.

[0047] S201, obtaining digitized structural features of the composite material microstructure to be predicted.

[0048] In an embodiment of the present application, when a materials developer or engineer wishes to quickly evaluate the performance of a new, unsimulated nickel-yttria-stabilized zirconia anode design, focused ion beam scanning electron microscopy (FIB-SEM) imaging technology can be used to scan and three-dimensionally reconstruct the composite material, generating a digital three-dimensional model containing the spatial distribution of each phase. After obtaining the digital three-dimensional model, it is necessary to perform preprocessing to convert it into a standardized three-dimensional data matrix consistent with the data format used during training, i.e., a digitized structural feature. This preprocessing step is intended to ensure that the input data can be correctly received and processed by the model.

[0049] S202: Input the digitized structural feature into a pre-trained machine learning prediction model, and have the machine learning prediction model output a predicted macroscopic physical property value. The machine learning prediction model is trained using a structure-property database, wherein the structure-property database comprises a plurality of data pairs, each data pair comprising a digitized structural feature representing the microstructure of the composite material and a predetermined macroscopic physical property value corresponding to the digitized structural feature.

[0050] In an embodiment of the present application, the digitized structural features processed in the aforementioned steps are used as input and fed into the deployed machine learning prediction model. After receiving the input data, the machine learning prediction model directly outputs a scalar value through an efficient forward propagation calculation (i.e., the process of data flowing from the input layer to the output layer in the network), which is the macroscopic physical performance value. The entire prediction process takes a very short time, usually in seconds or milliseconds, in stark contrast to the finite element method heat conduction simulation that takes hours or even days. This allows R&D personnel to immediately obtain predicted values ​​to quickly evaluate the pros and cons of design solutions, thereby greatly accelerating the R&D iteration process.

[0051] In order to facilitate the understanding of this application, Figure 3 The technical principle diagram of a composite material thermal conductivity prediction method is illustrated.

[0052] Non-equilibrium molecular dynamics (NEMD) is a type of molecular dynamics simulation used to simulate the motion and transport properties of atoms and molecules in non-equilibrium states (e.g., in the presence of heat or particle flows). For convenience, NEMD will be referred to below.

[0053] Ni

[100] / YSZ

[100] , Ni

[100] / YSZ

[110] , Ni

[100] / YSZ

[111] : represent the crystal orientation matching relationship between Ni (nickel) and YSZ (yttria-stabilized zirconia).

[100] ,

[110] ,

[111] are crystallographic orientation indices, and / indicates that the crystal orientations on both sides are parallel. Different crystal orientation matching affects the atomic arrangement and thermal transport properties of the interface.

[0054] O (red), Zr (blue), Y (yellow), Ni (gray): Legends corresponding to oxygen atoms, zirconium atoms, yttrium atoms, and nickel atoms, respectively, used to identify the atomic composition of the YSZ phase (containing Zr, Y, O) and the Ni phase (containing Ni).

[0055] Heat sink and heat source: The heat absorption end and release end set in the simulation, which generate non-equilibrium heat flow (red arrow direction in the figure) to form a temperature gradient in the system, and are used to calculate parameters such as thermal conductivity and interface thermal resistance.

[0056] FIB-SEM: Focused Ion Beam-Scanning Electron Microscopy, FIB (for convenience, described as FIB hereinafter) can mill and etch the sample in micro-nano, and SEM (for convenience, described as SEM hereinafter) is used to collect high-resolution images of the sample surface. The combination of the two realizes the reconstruction of the three-dimensional microstructure of the material.

[0057] Reference mark: Marking points on the sample for image registration, ensuring that the images of each layer can be accurately aligned when FIB mills layer by layer and SEM images layer by layer, and ensuring the accuracy of three-dimensional reconstruction.

[0058] Sample: The actual Ni-YSZ composite material sample is the object of three-dimensional reconstruction.

[0059] X1, X2, X3: Represent the direction of the three-dimensional coordinate axis, which helps to describe the spatial position of sample milling and imaging, and ensures that three-dimensional reconstruction is carried out in the correct spatial coordinate system.

[0060] Three-dimensional reconstruction: The process of restoring the three-dimensional microstructure of the sample by FIB milling the sample layer by layer, SEM collecting two-dimensional images of each layer, and then image processing (registration, splicing, voxelization, etc.), and outputting a three-dimensional model containing phase distribution, pore, etc.

[0061] FEM: Finite Element Method, an engineering simulation method for numerically solving physical fields (such as thermal field and force field). The continuum is discretized into a finite number of elements, and the overall physical field distribution is obtained by solving the element equations. Here, based on the three-dimensional microstructure reconstructed by FIB-SEM, combined with the parameters obtained by NEMD (such as interface thermal resistance), the heat conduction process is simulated.

[0062] Thermal conductivity: A physical quantity representing the ability of a material to conduct heat (unit commonly W / (m・K)). In the figure, the color gradient (300K to 800K) and the three-dimensional model at different times (0μs, 4μs, 10μs, 100μs) show the evolution of the temperature field over time when heat is transmitted in the Ni-YSZ composite material, reflecting the influence of thermal conductivity on the heat transfer process - the higher the thermal conductivity, the faster the temperature diffusion and the smaller the temperature gradient.

[0063] The overall technical principle flow is as follows: 1) In the NEMD phase, atomic models of interfaces with different crystal orientations (e.g., [Ni100] / [YSZ100]) are constructed for Ni-YSZ composite structures. NEMD simulations are performed by setting heat sources and sinks at both ends of the model to generate non-equilibrium heat flow. The atomic thermal motion (vibrations, collisions) and energy transfer paths are tracked, and the thermal conductivities of the Ni and YSZ phases themselves are calculated (see above for the calculation method). Furthermore, the heat transfer resistance (i.e., interfacial thermal resistance) caused by the discontinuity of atomic arrangement at interfaces with different crystal orientations is calculated.

[0064] 2) In the FIB-SEM phase, the actual Ni-YSZ composite material sample is milled and imaged layer by layer using FIB-SEM to complete the 3D reconstruction and obtain a 3D digital model consistent with the actual material microstructure, which serves as the geometry and phase distribution input for macro-thermal simulation.

[0065] 3) In the FEM step, the parameters obtained by NEMD are assigned to the corresponding phase regions (Ni phase, YSZ phase, and phase interface) of the three-dimensional digital model reconstructed by FIB-SEM. The steady-state heat conduction equation is solved using the finite element method (FEM) to simulate the heat transfer process in the macrostructure of the composite material. The temperature field distribution at different times (0μs, 4μs, etc.) and different positions is calculated to obtain the influence of thermal conductivity on temperature diffusion.

[0066] 4) The color gradient in thermal conductivity (300K to 800K) illustrates the temperature field distribution. Three-dimensional models at different time points (0μs to 100μs) depict the dynamic process of heat conduction—from initial temperature unevenness (0μs likely close to the initial set temperature) to gradual heat diffusion and decreasing temperature gradient (e.g., significant diffusion begins at 4μs and approaches steady state at 100μs). Comparing simulation results with experimental measurements (such as laser flash scattering) verifies the accuracy of the model (NEMD+FIB-SEM+FEM), ultimately enabling cross-scale analysis from microscopic atomic motion to macroscopic thermal conductivity performance.

[0067] In summary, this is a cross-scale thermal performance research plan from microscopic mechanism (NEMD) → real structure (FIB-SEM) → macroscopic performance (FEM). NEMD is used to clarify the atomic-level heat transport laws, FIB-SEM is used to restore the true three-dimensional morphology of the material, and FEM is used to amplify the microscopic laws to the macroscopic level. Ultimately, the thermal conductivity and heat transfer characteristics of Ni-YSZ composites are accurately analyzed and predicted, providing multi-scale support for optimizing material design (such as adjusting the interface crystal orientation and controlling the microstructure).

[0068] In order to facilitate the understanding of this application, Figure 4 The principle of the machine learning prediction model and data processing flow chart for thermal conductivity prediction are shown.

[0069] Three-dimensional feature extraction: From the microstructure (the purple-blue three-dimensional microstructure in the figure), key parameters that affect thermal conductivity are screened and converted into digital structural features that can be learned by the model.

[0070] Thermal conductivity: This is the target performance that the model wants to predict and serves as the label value for model training (the colored gradient model in the figure represents the distribution of thermal conductivity at different locations).

[0071] Database: stores a collection of data pairs of digitized structural features and macroscopic physical properties (such as thermal conductivity), which are divided into the following categories according to their functions: Test set: After training, independent data is used to test the generalization ability of the model and evaluate the prediction accuracy.

[0072] Validation set: Monitor model overfitting during training and adjust hyperparameters (such as network depth and learning rate) to ensure that the model is effective for unknown data.

[0073] Training set: The core data of the model learning feature → thermal conductivity mapping law, and the network parameters are optimized through back propagation.

[0074] For the physical information neural network (i.e. the machine learning prediction model mentioned above), the blue node network in the figure is the feature extraction + mapping layer, which receives data structure features (x, y, z, t and other inputs, red circle nodes) and outputs the predicted thermal conductivity (green circle nodes, such as u, v, w, p and other multi-task outputs, and can also be single-task).

[0075] MSE stands for mean squared error, the data fitting term mentioned above, measuring the difference between the predicted thermal conductivity and the actual thermal conductivity in the database. PDE stands for partial differential equation, the physical law constraint term mentioned above. Automatic differentiation is used to calculate the residual between the model prediction and the physical governing equations, ensuring that the prediction conforms to the fundamental laws of thermal theory.

[0076] LossD < threshold tol indicates whether the total model loss (MSE + PDE constraint loss) is less than the set threshold tol. If not, backpropagation optimization continues; if yes, training terminates.

[0077] In the embodiments of the present application, the physical information neural network is based on the training set data, uses MSE loss to make the prediction conform to the true thermal conductivity, and at the same time, embeds the heat conduction PDE into the loss function to force the model to predict the temperature field / heat flow to meet the physical law (such as Fourier's law). By continuously iterating and optimizing the network parameters (such as weights and biases), the data fitting error and the physical equation residual are minimized until the total loss is less than a threshold. The trained model can quickly output the predicted thermal conductivity when inputting the data-based structural features of a new composite material (such as the data-based structural features of an untested Ni-YSZ microstructure), and then use the test set to verify the accuracy. If it meets the standard, it can be used for material design (such as screening microstructures with low / high thermal conductivity).

[0078] The traditional pure data-driven model (such as a general neural network) is prone to inaccurate prediction due to data distribution deviation, while the physical information neural network uses PDE constraints to bind physical laws (such as heat cannot be generated / disappeared in the air), so that even with limited data, the prediction can conform to the nature of heat conduction, solving the problem of small data + high performance prediction, and is particularly suitable for multi-scale material design (from micro-interface to macro-performance).

[0079] It can be understood that the core idea of the technical solution of the present application, i.e., constructing a structure-performance database and training a machine learning prediction model constrained by physical laws, has strong universality and scalability. Accordingly, based on the mechanical performance parameters and the electrical conductivity performance parameters, the data-based structural features are subjected to finite element method mechanical simulation and electric field simulation respectively to obtain corresponding macroscopic mechanical performance values and electrical conductivity values; the data-based structural features and the corresponding mechanical performance values and electrical conductivity values jointly constitute a multi-physical field data pair, and the structure-performance database is expanded (i.e., the data pair consisting of the data-based structural features and the corresponding mechanical performance values, and the data pair consisting of the data-based structural features and the corresponding electrical conductivity values, are added to the structure-performance database) to be used for training the machine learning prediction model, so that the machine learning prediction model can predict the mechanical performance, electrical conductivity performance and other macroscopic physical performance values of the composite material.

[0080] As an example, if the effective electrical conductivity of the composite material to be predicted needs to be predicted, only adaptive modification of the process in the above embodiments is required. In the data generation phase, molecular dynamics simulation will be used to calculate the intrinsic electrical conductivity of each component under a specific working condition, and finite element method simulation will no longer solve the steady-state heat conduction equation, but will solve the steady-state current continuity equation ( where is the electrical conductivity, is the electric potential). Thus, the data pairs stored in the structure-property database will be the data-ized structure features-effective conductivity pairs. During the model training stage, the physical law constraint term will also be constructed based on the current continuity equation. The final model will be able to quickly predict the effective conductivity according to the data-ized structure features of the composite microstructure to be predicted.

[0081] Similarly, if the mechanical properties of the material, such as the elastic modulus or Poisson's ratio, are to be predicted, the finite element method simulation will be replaced by a structural mechanics simulation for solving the elastic mechanics equilibrium equation. The data pairs stored in the database will be the data-ized structure features-elastic modulus pairs of the microstructure, and the physical law constraint term will be constructed based on the elastic mechanics constitutive relation and the equilibrium equation.

[0082] In summary, the methodology proposed in this application is universal and can include all macroscopic physical properties related to the microstructure of the composite material (whether thermal, electrical, mechanical properties, or fluid transport properties, etc.) in the prediction category. Only the calculation target of the molecular dynamics simulation (such as switching from thermal physical parameters to electrical, mechanical, or fluid-related parameters) and the control equation of the finite element method simulation (switching from the heat conduction equation to the current continuity equation, the elastic mechanics equilibrium equation, or the fluid mechanics equation) need to be adjusted, and the data pair type in the structure-property database and the physical law constraint term of the machine learning prediction model need to be updated simultaneously. The prediction capability can be quickly expanded without making revolutionary modifications to the core technical framework. This high degree of universality and scalability makes it widely adaptable to different material systems (such as carbon fiber reinforced resin matrix composites, ceramic matrix composites, etc.) and different performance prediction needs, providing a unified technical solution for the integrated rapid evaluation of the multi-physical properties of composites, and has broad application prospects in advanced material research and development, high-end equipment design, etc.

[0083] In addition, this application does not require targeted adjustments to achieve single performance prediction, but can simultaneously predict multiple macroscopic physical properties such as thermal, electrical, mechanical properties and fluid transmission properties of composite materials based on the same core technology framework. Specifically, during the structure-performance database construction phase, there is no need to generate single performance data pairs in batches. Instead, multi-dimensional performance data can be obtained synchronously through a multi-physics field coupling simulation: first, through molecular dynamics simulation, the thermophysical parameters (such as intrinsic thermal conductivity, interface thermal resistance), electrical parameters (such as intrinsic electrical conductivity, interface resistance), mechanical parameters (such as elastic stiffness tensor, interface bonding strength) and fluid-related parameters (such as fluid-solid interface contact angle, adsorption energy) of each component are simultaneously calculated under a preset working environment; these multi-dimensional parameters are then simultaneously assigned to the digital three-dimensional model corresponding to the digitized structural features, and through multi-physics field finite element simulation (such as thermal-electrical-mechanical-fluid coupling simulation), the steady-state heat conduction equation, current continuity equation, elastic mechanics equilibrium equation and fluid mechanics control equation are solved at one time, and multiple performance values ​​such as macroscopic thermal conductivity, electrical conductivity, elastic modulus, and permeability are simultaneously obtained; subsequently, the digitized structural features - multi-performance value set (including thermal, electrical, mechanical, and fluid performance values) are stored as a unified data pair in the structure-performance database, without the need to split the database or construct a separate training set. During the training phase of the machine learning prediction model, there's no need to train a separate model for a single property. Instead, a multi-task physical information neural network model is constructed. The model uses digitized structural features as a unified input and sets up multiple parallel output heads, corresponding to prediction targets for different properties such as thermal conductivity, electrical conductivity, elastic modulus, and permeability. Simultaneously, multiple sets of physical law constraints are embedded in the loss function, corresponding to the physical equations governing each property (such as the residuals of the heat conduction equation, the residuals of the current continuity equation, the residuals of the elastic equilibrium equation, and the residuals of the fluid dynamics equation). Together with the multi-task data fitting terms (which measure the difference between each property's predicted value and the true value in the database), these together form a composite loss function. During training, the model learns common microstructural features through shared feature extraction layers (such as 3D convolutional layers). Then, through dedicated output heads and corresponding physical constraints, it simultaneously grasps the correlation between different properties and microstructure. Ultimately, the model achieves the effect of simultaneously outputting prediction results for multiple macroscopic physical properties using a single input of digitized structural features.This multi-performance simultaneous prediction solution does not require targeted adjustments to the core technical framework (structure-performance database construction logic, physical constraint model training mechanism), but can greatly improve the efficiency of performance evaluation. Compared with predicting single performance one by one, it can reduce repeated microstructure scanning, simulation calculations and model training processes, and avoid waste of resources. At the same time, since multiple performance data come from the same set of microstructures and coupled simulations, it can more realistically reflect the intrinsic relationship between different properties (such as the coordinated change law of thermal conductivity and electrical conductivity), making the prediction results more in line with the multi-physical field coupling scenarios in the actual service of the material, and providing more comprehensive and efficient technical support for the comprehensive performance optimization and multi-field coupling design of composite materials.

[0084] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0085] Corresponding to the composite material thermal conductivity prediction method described in the above embodiment, Figure 3 The structural block diagram of the composite material thermal conductivity prediction device provided in an embodiment of the present application is shown. For the sake of convenience, only the parts related to the embodiment of the present application are shown.

[0086] Reference Figure 5 , the composite material thermal conductivity prediction device comprises: An acquisition module, used to obtain the digitized structural features of the composite material microstructure to be predicted; A prediction output module, configured to input the digitized structural features into a pre-trained machine learning prediction model, and output the predicted macroscopic physical performance value from the machine learning prediction model; Among them, the machine learning prediction model is obtained by training using a structure-performance database, which contains multiple data pairs, each data pair including a digitized structural feature characterizing the microstructure of the composite material and a predetermined macroscopic physical property value corresponding to the digitized structural feature.

[0087] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0089] 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.

[0090] 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 various method embodiments can be implemented.

[0091] An embodiment of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0093] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0094] Those skilled 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 beyond the scope of this application.

[0095] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer equipment and methods can be implemented in other ways. For example, the apparatus / computer equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, 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 the apparatus or unit, which can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0097] The above-described embodiments 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, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

[0098] Figure 6 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present application. Figure 6 As shown, the computer device of this embodiment includes: at least one processor 20 ( Figure 6 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 of any of the above-mentioned embodiments of the method for predicting thermal conductivity of composite materials when executing the computer program 22.

[0099] The computer device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that Figure 6 The computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, etc.

[0100] 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, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0101] The memory 21 can be an internal storage unit of the computer device in some embodiments, such as a hard disk or a memory of the computer device. The memory 21 can also be an external storage device of the computer device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 21 can include both an internal storage unit and an external storage device of the computer device. The memory 21 is used to store an operating system, an application program, a BootLoader, data, and other programs, etc., such as program codes of the computer program, etc. The memory 21 can also be used to temporarily store data that has been output or will be output.

Claims

1. A method for predicting thermal conductivity of composite materials, characterized in that: include: Obtaining the digitized structural characteristics of the composite material microstructure to be predicted; Inputting the digitized structural features into a pre-trained machine learning prediction model, and having the machine learning prediction model output predicted macroscopic physical performance values; Among them, the machine learning prediction model is obtained by training using a structure-performance database, which contains multiple data pairs, each data pair including a digitized structural feature characterizing the microstructure of the composite material and a predetermined macroscopic physical property value corresponding to the digitized structural feature.

2. The method for predicting thermal conductivity of composite materials according to claim 1, wherein: The process of constructing the structure-performance database includes: Scan and 3D reconstruct the composite material used as a sample to obtain digitized structural characteristics; Calculate the material parameters of each component constituting the composite material under a preset working environment through molecular dynamics simulation; wherein the material parameters include the interfacial thermal resistance between the components; Performing finite element method heat conduction simulation on the digitized structural characteristics based on the material parameters to obtain corresponding macroscopic physical performance values; The digitized structural features are paired with corresponding macroscopic physical property values ​​to form the structure-property database.

3. The method for predicting thermal conductivity of composite materials according to claim 2, wherein: The scanning and three-dimensional reconstruction of the composite material as a sample to obtain digitized structural features includes: Scanning and three-dimensionally reconstructing the composite material using focused ion beam scanning electron microscopy imaging technology to generate a digital three-dimensional model including the spatial distribution of each phase; The digital three-dimensional model is converted into the digitized structural features.

4. The method for predicting thermal conductivity of composite materials according to claim 3, wherein: The loss function of the machine learning prediction model includes a data fitting term and a physical law constraint term; The data fitting term is used to measure the difference between the macroscopic physical property value predicted by the machine learning prediction model and the macroscopic physical property value in the structure-performance database; The physical law constraint item is used to force the machine learning prediction model to generate a physical field distribution that satisfies a preset physical control equation when making predictions based on the digitized structural features.

5. The method for predicting thermal conductivity of composite materials according to claim 4, wherein: The composite material is a nickel-yttria-stabilized zirconia anode for a solid oxide fuel cell; the macroscopic physical property value is thermal conductivity; and the physical control equation is a steady-state heat conduction equation.

6. The method for predicting thermal conductivity of composite materials according to claim 5, wherein: The finite element method heat conduction simulation is performed on the digitized structural features based on the material parameters to obtain corresponding macroscopic physical performance values, including: The material parameters are assigned to the physical phase region corresponding to the digitized structural characteristics, and the steady-state heat conduction equation is solved based on the finite element method to obtain the corresponding macroscopic physical performance values.

7. The method for predicting thermal conductivity of composite materials according to claim 6, wherein: The physical field distribution includes temperature field distribution; The steady-state heat conduction equation is solved based on the finite element method to obtain the corresponding macroscopic physical performance values, including: Applying a constant heat flux density boundary condition to the heat flux input surface of the digital three-dimensional model, and applying a fixed temperature boundary condition to the heat dissipation surface of the digital three-dimensional model; Iteratively solving the steady-state heat conduction equation until the temperature field distribution reaches a steady state, and calculating the temperature gradient based on the steady-state temperature field distribution; The thermal conductivity is calculated based on the preset input heat flux density and the temperature gradient.

8. A device for predicting thermal conductivity of composite materials, characterized in that: include: An acquisition module, used to obtain the digitized structural features of the composite material microstructure to be predicted; A prediction output module, configured to input the digitized structural features into a pre-trained machine learning prediction model, and output the predicted macroscopic physical performance value from the machine learning prediction model; Among them, the machine learning prediction model is obtained by training using a structure-performance database, which contains multiple data pairs, each data pair including a digitized structural feature characterizing the microstructure of the composite material and a predetermined macroscopic physical property value corresponding to the digitized structural feature.

9. 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 7 when executing the computer program.

10. A computer program product, characterized in that When the computer program product is run on a computer device, the computer device is caused to perform the method according to any one of claims 1 to 7.

Images