Foaming material performance prediction system and method based on multi-scale modeling

Abstract

The invention provides a foaming material performance prediction system and method based on multi-scale modeling, and relates to the technical field of foaming material performance prediction.The method comprises the steps that structural data of a target foaming material is collected, data classification is conducted on the structural data, and a multi-scale feature database is obtained; carrying out modeling according to the multi-scale feature database to obtain a scale structure model, carrying out analogue simulation through the scale structure model and preset simulation data to obtain a scale structure response, and carrying out cross-scale integration according to the scale structure response to obtain a scale integration layer; performing response extraction on the scale integration layer to obtain scale sound points, and constructing a performance prediction layer through the scale sound points; and performing performance prediction on the target foaming material according to the performance prediction layer and the structural data of the target foaming material, and outputting performance prediction data of the target foaming material. According to the method, integrated modeling of structural design and performance evaluation of the foaming material can be realized, and the accuracy and stability of performance prediction of the foaming material are improved.

Description

Technical Field

[0001] This application relates to the field of performance prediction technology for foamed materials, and more specifically, to a system and method for predicting the performance of foamed materials based on multi-scale modeling. Background Technology

[0002] Foamed materials are widely used in aerospace, building insulation, and automotive cushioning due to their lightweight, high specific strength, good thermal insulation, and energy absorption properties. In existing technologies, the performance evaluation of foamed materials typically relies on empirical formulas based on structural parameters (such as density, porosity, and cell size) or predictions using single-scale simulation models. These methods have some reference value in preliminary engineering analyses and are widely used in certain standardized material systems.

[0003] With a deeper understanding of the relationship between the structure and performance of foamed materials, existing prediction methods based on single-scale or simplified structural models are no longer sufficient to accurately reflect the multi-scale synergistic effects of materials under complex real-world conditions. Existing technologies for predicting the performance of foamed materials generally suffer from the following drawbacks: reliance on single-scale structural parameters makes it difficult to accurately reflect the synergistic impact of multi-level structures on performance; prediction models are mostly based on empirical formulas or linear fitting, lacking integrated modeling for foamed material structural design and performance evaluation, and lacking physical mechanism support, resulting in limited prediction accuracy and difficulty in adapting to material systems with different structural types. Therefore, how to achieve integrated modeling for foamed material structural design and performance evaluation, and improve the accuracy and stability of foamed material performance prediction, has become a challenge for the industry. Summary of the Invention

[0004] This application provides a system and method for predicting the performance of foamed materials based on multi-scale modeling, which can realize integrated modeling of foamed material structural design and performance evaluation, and improve the accuracy and stability of foamed material performance prediction.

[0005] In a first aspect, this application provides a method for predicting the performance of foamed materials based on multi-scale modeling, the method comprising the following steps: Structural data of the target foamed material is collected, and the structural data is classified to obtain a multi-scale feature database of the target foamed material. Modeling is performed based on the multi-scale feature database of the target foamed material to obtain structural models at various scales. Then, simulation is performed using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Cross-scale integration is performed based on the scale response domain to obtain the scale integration layer of the target foamed material. The response of the scale integration layer is extracted to obtain the response points of the target foamed material at each scale. The performance prediction layer of the target foamed material is constructed by using the response points at each scale and preset physical parameters. Based on the performance prediction layer and structural data of the target foam material, the performance of the target foam material is predicted, and the performance prediction data of the target foam material is output.

[0006] In this embodiment, the collection of structural data of the target foaming material specifically includes: Microstructure data of the target foaming material were obtained using a scanning electron microscope. Mesoscopic structural data of the target foaming material were obtained using X-ray microcomputed tomography equipment; Macroscopic structural data of the target foaming material are obtained by recording material preparation parameters; The structural data of the target foaming material is constructed based on the microstructure data, the mesostructure data, and the macrostructure data.

[0007] In this embodiment, the structural data is classified to obtain a multi-scale feature database of the target foaming material, specifically including: The structural data is divided into multi-scale categories to obtain micro-feature data, meso-feature data, and macro-feature data. A multi-scale feature database of the target foaming material is determined based on the microscopic feature data, the mesoscopic feature data, and the macroscopic feature data.

[0008] In this embodiment, cross-scale integration is performed based on the scale response domain to obtain a scale-integrated layer of the target foaming material, specifically including: The scale response domain is standardized to obtain all standardized responses; Each standardized response is subjected to inter-scale response transfer mapping to obtain the cross-scale response parameters. By integrating various cross-scale response parameters, a scale-integrated layer of the target foam material is obtained.

[0009] In this embodiment, response extraction of the scale integration layer is performed by using preset sensitive weights to sensitively respond to each cross-scale response parameter in the scale integration layer, thereby obtaining the response points of each scale of the target foaming material.

[0010] In this embodiment, a performance prediction layer for the target foamed material is constructed using various scale sound points and preset physical parameters, specifically including: Based on the response points at various scales and preset physical parameters, construct prediction functions for various properties of the target foamed material; The performance prediction layer of the target foam material is obtained by integrating various performance prediction functions.

[0011] In this embodiment, the performance prediction layer includes an elastic modulus prediction channel and a thermal conductivity prediction channel.

[0012] Secondly, this application provides a multi-scale modeling-based foamed material performance prediction system for executing a multi-scale modeling-based foamed material performance prediction method, the foamed material performance prediction system comprising: The data acquisition module is used to collect structural data of the target foamed material, classify the structural data, and obtain a multi-scale feature database of the target foamed material. The scale integration module is used to model the target foamed material based on the multi-scale feature database to obtain structural models at various scales. Then, it performs simulations using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Based on the scale response domain, it performs cross-scale integration to obtain the scale integration layer of the target foamed material. The prediction construction module is used to extract the response of the scale integration layer to obtain the response points of the target foamed material at each scale, and to construct the performance prediction layer of the target foamed material through the response points at each scale and preset physical parameters. The performance prediction module predicts the performance of the target foam material based on the performance prediction layer and structural data of the target foam material, and outputs the performance prediction data of the target foam material.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described method for predicting the performance of foamed materials based on multi-scale modeling.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned method for predicting the performance of foamed materials based on multi-scale modeling.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: Structural data of the target foamed material is collected and classified to obtain a multi-scale feature database of the target foamed material. Modeling is performed based on this database to obtain structural models at various scales. Simulations are then conducted using these models and pre-set simulation data to obtain the scale response domain of the target foamed material. Cross-scale integration is performed based on the scale response domain to obtain a scale integration layer. Response extraction is performed on the scale integration layer to obtain response points at various scales of the target foamed material. A performance prediction layer is constructed using these response points and pre-set physical parameters. Performance prediction of the target foamed material is performed based on the performance prediction layer and the structural data, and the performance prediction data is output.

[0016] Therefore, this application firstly, by collecting structural data of the target foamed material and performing multi-scale classification, a multi-scale feature database with clear structural hierarchy and comprehensive parameters is established. This effectively distinguishes the key structural features of the material at the micro, meso, and macro scales, thus providing a foundation for subsequent multi-scale modeling and response analysis. Secondly, by establishing structural models at three levels—micro, meso, and macro—based on the multi-scale feature database, and using unified simulation parameters to perform mechanical and thermal simulations on each scale structural model, the structural response characteristics of the material at different scales can be accurately obtained. Furthermore, through standardization processing and a response transfer mapping mechanism, the inter-scale fusion of structural response parameters is achieved, constructing a scale integration layer. This effectively solves the problems of inconsistent scale coupling and unclear information transfer between multi-scale models, enabling the establishment of a response mapping between microscopic bubble wall effects, mesoscopic cell behavior, and macroscopic performance, and extracting comprehensive response characteristics reflecting the overall structural performance, thus providing a basis for subsequent... Performance prediction provides parameter support, improving the accuracy of the prediction model. Then, by sensitively identifying the cross-scale response parameters in the scale integration layer, the scale response points that play a dominant role in the changes of material properties at different structural scales are extracted. This effectively achieves the screening and dimensionality reduction of complex response features, ensuring that subsequent performance modeling focuses on high-contribution parameters, improving prediction efficiency and model simplicity. Combined with preset physical parameters, a performance prediction function with structural physics interpretability is constructed and integrated into the performance prediction layer, enabling accurate prediction of key performance indicators such as the elastic modulus and thermal conductivity of foamed materials. Finally, by sequentially inputting the structural data of the target foamed material into the established scale integration layer and performance prediction layer, an end-to-end prediction process from multi-scale structural features to performance results is realized. This effectively avoids the error accumulation caused by manual parameter adjustment and feature screening, and can achieve automated inference and rapid output based on a standardized model, greatly improving prediction efficiency and stability.

[0017] In summary, the technical solution adopted in this application can realize integrated modeling of foam material structure design and performance evaluation, and improve the accuracy and stability of foam material performance prediction. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of the method for predicting the performance of foamed materials based on multi-scale modeling provided in this application; Figure 2 This is an exemplary flowchart of obtaining a scale-integrated layer of the target foamed material according to the present application; Figure 3 This is an exemplary flowchart of constructing a performance prediction layer for a target foamed material according to the present application; Figure 4 This is a module structure diagram of the foam material performance prediction system based on multi-scale modeling provided in this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing a method for predicting the performance of foamed materials based on multi-scale modeling, as provided in this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a system and method for predicting the performance of foamed materials based on multi-scale modeling. The core of this system involves collecting structural data of the target foamed material, classifying the structural data to obtain a multi-scale feature database of the target foamed material, modeling based on this database to obtain structural models at various scales, and then performing simulations using these models and preset simulation data to obtain the scale response domain of the target foamed material. Cross-scale integration is then performed based on the scale response domain to obtain a scale integration layer of the target foamed material. Response extraction is performed on the scale integration layer to obtain the response points at various scales of the target foamed material. A performance prediction layer is constructed using these response points and preset physical parameters. Performance prediction of the target foamed material is then performed based on the performance prediction layer and the structural data of the target foamed material, outputting the performance prediction data. This approach enables integrated modeling of foamed material structural design and performance evaluation, and improves the accuracy and stability of foamed material performance prediction.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a method for predicting the performance of foamed materials based on multi-scale modeling according to this embodiment of the present application. The method for predicting the performance of foamed materials includes the following steps: In step S1, structural data of the target foamed material is collected, and the structural data is classified to obtain a multi-scale feature database of the target foamed material.

[0023] In this embodiment, the structural data of the target foaming material is collected, which can be achieved through the following steps: Microstructure data of the target foaming material were obtained using a scanning electron microscope. Mesoscopic structural data of the target foaming material were obtained using X-ray microcomputed tomography equipment; Macroscopic structural data of the target foaming material are obtained by recording material preparation parameters; The structural data of the target foaming material is constructed based on the microstructure data, the mesostructure data, and the macrostructure data.

[0024] In practice, the microstructure data of the target foamed material is acquired through scanning electron microscopy (SEM), specifically by obtaining images of the microstructure of the foamed material and extracting cell size, porosity, and wall thickness using image segmentation algorithms. Secondly, the mesostructure data of the target foamed material is acquired using X-ray microcomputed tomography (Micro-CT), specifically by obtaining the three-dimensional distribution of cells, connecting channels, and structural arrangement characteristics. Then, the macrostructure data of the target foamed material is acquired through material preparation parameter recording, specifically by collecting scale information including material density, volume, boundary dimensions, and loading direction. Finally, the structural data of the target foamed material is constructed based on the microstructure data, mesostructure data, and macrostructure data; that is, the cell size, porosity, wall thickness, three-dimensional distribution, connecting channels, structural arrangement characteristics, material density, volume, boundary dimensions, and loading direction of the target foamed material can be used as its structural data.

[0025] In this embodiment, classifying the structural data to obtain a multi-scale feature database of the target foaming material can be achieved through the following steps: The structural data is divided into multi-scale categories to obtain micro-feature data, meso-feature data, and macro-feature data. A multi-scale feature database of the target foaming material is determined based on the microscopic feature data, the mesoscopic feature data, and the macroscopic feature data.

[0026] In specific implementation, firstly, the structural data can be divided into multi-scale categories to obtain microscopic feature data, mesoscopic feature data, and macroscopic feature data. That is, the cell size, porosity, and wall thickness of the target foamed material in the structural data can be classified as microscopic feature data, the three-dimensional distribution, connection channels, and structural arrangement characteristics of the target foamed material can be classified as mesoscopic feature data, and the material density, volume, boundary dimensions, and loading direction of the target foamed material can be used as macroscopic feature data. Then, a multi-scale feature database of the target foamed material can be determined based on the microscopic feature data, the mesoscopic feature data, and the macroscopic feature data. That is, the microscopic feature data, the mesoscopic feature data, and the macroscopic feature data can be standardized to obtain microscopic feature subsets, mesoscopic feature subsets, and macroscopic feature subsets, which are then uniformly organized into a multi-scale feature database structure to construct a multi-scale feature database of the target foamed material. The multi-scale feature database uses the foamed material number as an index to record the microscopic feature subsets, mesoscopic feature subsets, and macroscopic feature subsets respectively.

[0027] It should be noted that by collecting structural data of the target foamed material and performing multi-scale classification, a multi-scale feature database with clear structural hierarchy and comprehensive parameters can be established. This can effectively distinguish the key structural features of the material at the micro, meso, and macro scales, thus providing a basic support for subsequent multi-scale modeling and response analysis.

[0028] In step S2, a model is built based on the multi-scale feature database of the target foamed material to obtain structural models at various scales. Then, simulation is performed using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Cross-scale integration is performed based on the scale response domain to obtain the scale integration layer of the target foamed material.

[0029] In this embodiment, modeling is performed based on the multi-scale feature database of the target foamed material to obtain structural models at various scales. Specifically, a three-dimensional structure with representative cell morphologies (spherical, ellipsoidal, irregular, etc.) can be constructed using CAD modeling software based on the microscopic feature subset from the multi-scale feature database of the target foamed material. A solid mesh is then generated using a finite element preprocessing tool to obtain the micro-scale structural model. Furthermore, the mesoscopic feature subset from the multi-scale feature database of the target foamed material is used, and the Weaire-Phelan structural unit is selected using CAD modeling software and copied according to the structural arrangement features. Based on the number of connecting channels, connecting pipe structures are inserted between adjacent cells. According to the loading direction of the target foam material, an anisotropic configuration is set, and a mesoscale structural model is output. Through the macroscopic feature subset in the multi-scale feature database of the target foam material, the overall structural model of the foam material is established using CAD modeling software. The structural parameters output by the microscale structural model and the mesoscale structural model are used as material properties of the overall structure, and a macroscale structural model is output. Thus, the microscale structural model, the mesoscale structural model, and the macroscale structural model are used as the structural models of the target foam material at various scales.

[0030] In this embodiment, simulations are performed using structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Specifically, mechanical and thermal simulations of the structural models at various scales of the target foamed material can be performed using simulation software, and unified simulation parameters can be set. That is, mechanical and thermal simulations are performed on the microscale structural models to obtain microscale simulation response results. The microscale simulation response results include the local maximum stress of the bubble wall, the bubble wall thickness, the bubble wall heat flux density, and the equivalent thermal resistance. Thus, the microscale simulation response results are used as the microscale structural response of the target foamed material. Mechanical and thermal simulations are performed on the mesoscale structural models to obtain mesoscale simulation response results. The mesoscale simulation response results include the unit cell equivalent modulus. The microscale, mesoscale, and macroscale structural responses of the target foamed material are analyzed, including elastic modulus, yield strength, and macroscopic thermal conductivity. These macroscopic simulation results are then used as the mesoscale structural responses of the target foamed material. Mechanical and thermal simulations are performed on the macroscale structural model to obtain macroscopic simulation response results, which include elastic modulus, yield strength, and macroscopic thermal conductivity. These macroscopic response results are then used as the macroscopic structural responses of the target foamed material. The microscale, mesoscale, and macroscale structural responses of the target foamed material constitute a response set, which is then used as the scale response domain. It should be noted that the scale response domain refers to the set of mechanical and thermal simulation response results of the target foamed material under the corresponding scale structure.

[0031] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart of obtaining the scale integration layer of the target foamed material in an embodiment of this application. In this embodiment, cross-scale integration based on the scale response domain is performed to obtain the scale integration layer of the target foamed material, which can be achieved by the following steps: In step S21, the scale response domain is standardized to obtain all standardized responses; In step S22, each standardized response is subjected to inter-scale response transfer mapping to obtain each cross-scale response parameter; In step S23, the various cross-scale response parameters are integrated to obtain the scale-integrated layer of the target foam material.

[0032] In practical implementation, firstly, the scale response domain can be standardized to obtain all standardized responses. Specifically, for all data in the scale response domain, the mean of the corresponding data in the scale structure response can be subtracted, and the result can be divided by the variance of the corresponding data. This result serves as the standardized response data for the corresponding data in the scale structure response, thus obtaining all standardized response data in the scale response domain. Then, each standardized response can be subjected to inter-scale response transfer mapping to obtain the various cross-scale response parameters. Specifically, the modulus cross-scale response parameters can be obtained using the following formula:

[0033] in, Indicates the modulus response parameters across scales; Indicates the elastic modulus; Indicates the equivalent modulus of a single cell; The maximum stress in the bubble wall and the thermal conductivity cross-scale response parameters can be obtained using the following formula:

[0034] in, This represents the thermal conductivity cross-scale response parameters; Indicates macroscopic thermal conductivity; Indicates uniformity of heat distribution; The heat flux density of the bubble wall is represented by the modulus cross-scale response parameter and the thermal conductivity cross-scale response parameter, which are then used as cross-scale response parameters. It should be noted that the modulus cross-scale response parameter refers to the comprehensive response quantity characterizing the degree of influence of different scale structures on the overall stiffness of the material; the thermal conductivity cross-scale response parameter refers to the comprehensive response quantity reflecting the synergistic relationship of multi-scale structures in thermal conductivity. Finally, the various cross-scale response parameters can be integrated to construct a scale integration layer. That is, the modulus cross-scale response parameter and the thermal conductivity cross-scale response parameter can be further normalized, and the normalized results can be combined into a vector to obtain the cross-scale response set. The calculation process of the above cross-scale response set is used as the scale integration layer, and the obtained cross-scale response set is used as the output of the scale integration layer.

[0035] It should be noted that by establishing structural models at three levels—microscopic, mesoscopic, and macroscopic—based on a multi-scale feature database, and using unified simulation parameters to perform mechanical and thermal simulations on structural models at each scale, the structural response characteristics of materials at different scales can be accurately obtained. Furthermore, through standardization processing and a response transfer mapping mechanism, the inter-scale fusion of structural response parameters is achieved, constructing a scale integration layer. This effectively solves the problems of inconsistent scale coupling and unclear information transfer between multi-scale models, and establishes a response mapping between microscopic bubble wall effects, mesoscopic cell behavior, and macroscopic performance. It extracts comprehensive response characteristics that reflect the overall structural performance, providing parameter support for subsequent performance prediction and improving the accuracy of the prediction model.

[0036] In step S3, the response of the scale integration layer is extracted to obtain the response points of the target foamed material at each scale. The performance prediction layer of the target foamed material is constructed by using the response points at each scale and preset physical parameters.

[0037] In this embodiment, response extraction of the scale integration layer is performed by using preset sensitive weights to sensitively respond to each cross-scale response parameter in the scale integration layer, thereby obtaining the response points of each scale of the target foaming material.

[0038] In practical implementation, the various cross-scale response parameters in the scale integration layer can be sensitively responded to by preset sensitive weights to obtain the scale response points of the target foamed material. That is, the various sensitive weights and sensitive thresholds of the target foamed material can be preset based on historical experience. Then, the modulus cross-scale response parameters and thermal conductivity cross-scale response parameters in the cross-scale response set are multiplied by the corresponding sensitive weights, and the calculation results are compared with the sensitive thresholds. The cross-scale response parameters corresponding to the calculation results greater than the sensitive thresholds are taken as the scale response points of the target foamed material. If there is no data greater than the sensitive threshold, the cross-scale response parameters corresponding to the calculation results closest to the sensitive thresholds are taken as the scale response points of the target foamed material. Thus, the scale response points of the target foamed material are obtained. It should be noted that the scale response point refers to the response characteristic parameter that plays a dominant role in the change of material properties at the corresponding structural scale.

[0039] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart of constructing the performance prediction layer of the target foamed material in an embodiment of this application. In this embodiment, the construction of the performance prediction layer of the target foamed material through various scale response points and preset physical parameters can be achieved by the following steps: In step S31, various performance prediction functions for the target foamed material are constructed based on the response points at each scale and the preset physical parameters. In step S32, the performance prediction layer of the target foam material is obtained by integrating the various performance prediction functions.

[0040] In practice, firstly, performance prediction functions for the target foamed material can be constructed based on the response points at each scale and preset physical parameters. That is, for each response point at a scale, the performance prediction function of the target foamed material is determined by the standardized response corresponding to the response point and the preset physical parameters. For example, when the response point at a scale corresponds to the modulus cross-scale parameter, the prediction function for the elastic modulus of the target foamed material is as follows:

[0041] in, This represents the predicted value of the elastic modulus; Indicates the equivalent modulus of a single cell; Indicates the thickness of the bubble wall; Indicates the preset physical parameters; This represents the maximum stress in the foam wall, where the preset physical parameter refers to the coefficient that adjusts the degree of influence of micro-stress on performance; when the response point at this scale corresponds to the thermal conductivity cross-scale parameter, the prediction function for the thermal conductivity of the target foamed material is as follows:

[0042] This represents the predicted value of thermal conductivity. This represents the heat flux density of the bubble wall; Indicates the thickness of the bubble wall; Indicates uniformity of heat distribution; This represents the total heat input, where the total heat input is a preset physical parameter. The process of determining the predicted value of the elastic modulus of the target foamed material is used as the elastic modulus prediction function, and the process of determining the predicted value of the thermal conductivity of the target foamed material is used as the thermal conductivity prediction function. This yields various performance prediction functions for the target foamed material. It should be noted that the predicted value of the elastic modulus is calculated using the prediction function, and the predicted value of the thermal conductivity is calculated using the prediction function. Then, by integrating these performance prediction functions, a performance prediction layer for the target foamed material can be obtained. This performance prediction layer includes an elastic modulus prediction channel and a thermal conductivity prediction channel. That is, the calculation process of the elastic modulus prediction value can be used as the elastic modulus prediction channel, and the calculation process of the thermal conductivity prediction value can be used as the thermal conductivity prediction channel. Thus, the elastic modulus prediction channel and the thermal conductivity prediction channel of the target foamed material are used as the performance prediction layer, and the output result is the predicted performance value of the target foamed material.

[0043] It should be noted that by performing sensitivity identification on the cross-scale response parameters in the scale integration layer, the scale response points that play a dominant role in the changes of material properties at different structural scales are extracted. This effectively achieves the screening and dimensionality reduction of complex response features, ensuring that subsequent performance modeling focuses on high-contribution parameters, improving prediction efficiency and model simplicity. Combined with preset physical parameters, a performance prediction function with structural physics interpretation is constructed and integrated into the performance prediction layer, which can achieve accurate prediction of key performance indicators such as elastic modulus and thermal conductivity of foamed materials.

[0044] In step S4, the performance of the target foam material is predicted based on the performance prediction layer and structural data of the target foam material, and the performance prediction data of the target foam material is output.

[0045] In practical implementation, the structural data of the target foamed material can be input into the scale integration layer to obtain the output result of the scale integration layer, namely the cross-scale response set. Then, the cross-scale response set is input into the performance prediction layer, which outputs the predicted value of the target foamed material. The predicted value of the target foamed material can be the predicted value of the elastic modulus and the predicted value of the thermal conductivity of the target foamed material; it can also be the predicted value of the elastic modulus or the predicted value of the thermal conductivity of the target foamed material. Thus, the predicted value of the target foamed material is used as the performance prediction data of the target foamed material to complete the performance prediction of the target foamed material.

[0046] It should be noted that by sequentially inputting the structural data of the target foamed material into the established scale integration layer and performance prediction layer, an end-to-end prediction process from multi-scale structural features to performance results is realized, effectively avoiding the accumulation of errors caused by manual intervention and feature selection. Moreover, it can achieve automated reasoning and rapid output based on a standardized model, greatly improving prediction efficiency and reliability.

[0047] Therefore, this application firstly, by collecting structural data of the target foamed material and performing multi-scale classification, a multi-scale feature database with clear structural hierarchy and comprehensive parameters is established. This effectively distinguishes the key structural features of the material at the micro, meso, and macro scales, thus providing a foundation for subsequent multi-scale modeling and response analysis. Secondly, by establishing structural models at three levels—micro, meso, and macro—based on the multi-scale feature database, and using unified simulation parameters to perform mechanical and thermal simulations on each scale structural model, the structural response characteristics of the material at different scales can be accurately obtained. Furthermore, through standardization processing and a response transfer mapping mechanism, the inter-scale fusion of structural response parameters is achieved, constructing a scale integration layer. This effectively solves the problems of inconsistent scale coupling and unclear information transfer between multi-scale models, enabling the establishment of a response mapping between microscopic bubble wall effects, mesoscopic cell behavior, and macroscopic performance, and extracting comprehensive response characteristics reflecting the overall structural performance, thus providing a basis for subsequent... Performance prediction provides parameter support, improving the accuracy of the prediction model. Then, by sensitively identifying the cross-scale response parameters in the scale integration layer, the scale response points that play a dominant role in the changes of material properties at different structural scales are extracted. This effectively achieves the screening and dimensionality reduction of complex response features, ensuring that subsequent performance modeling focuses on high-contribution parameters, improving prediction efficiency and model simplicity. Combined with preset physical parameters, a performance prediction function with structural physics interpretability is constructed and integrated into the performance prediction layer, enabling accurate prediction of key performance indicators such as the elastic modulus and thermal conductivity of foamed materials. Finally, by sequentially inputting the structural data of the target foamed material into the established scale integration layer and performance prediction layer, an end-to-end prediction process from multi-scale structural features to performance results is realized. This effectively avoids the error accumulation caused by manual parameter adjustment and feature screening, and can achieve automated inference and rapid output based on a standardized model, greatly improving prediction efficiency and stability.

[0048] In summary, the technical solution adopted in this application can realize integrated modeling of foam material structure design and performance evaluation, and improve the accuracy and stability of foam material performance prediction.

[0049] Example 2: This application provides a reference system for predicting the performance of foamed materials based on multi-scale modeling. Figure 4 As shown, this figure is a block structure diagram of the foam material performance prediction method according to this embodiment of the present application. The foam material performance prediction method includes: The data acquisition module 100 acquires structural data of the target foamed material, classifies the structural data, and obtains a multi-scale feature database of the target foamed material. The scale integration module 200 models the target foamed material based on its multi-scale feature database to obtain structural models at various scales. Then, it performs simulations using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Based on the scale response domain, it performs cross-scale integration to obtain the scale integration layer of the target foamed material. The prediction construction module 300 extracts the response of the scale integration layer to obtain the response points of the target foamed material at each scale, and constructs the performance prediction layer of the target foamed material through the response points at each scale and preset physical parameters. The performance prediction module 400 predicts the performance of the target foam material based on the performance prediction layer and structural data of the target foam material, and outputs the performance prediction data of the target foam material.

[0050] The foregoing has detailed examples of the multi-scale modeling foam material performance prediction system and method provided in the embodiments of this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art 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.

[0051] In embodiment three, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing computer programs, and the processor for calling and running the computer programs from the memory, so that the computer device executes the above-described method for predicting the performance of foamed materials based on multi-scale modeling.

[0052] In this embodiment, reference Figure 5 The dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic diagram of the structure of a computer device for predicting the performance of foamed materials based on multi-scale modeling, according to an embodiment of this application. The above-described method for predicting the performance of foamed materials based on multi-scale modeling in the above embodiment can be used... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device may be a terminal device, a server or a chip.

[0053] Processor 501 can be a general-purpose processor or a special-purpose processor. For example, processor 501 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 505 to realize signal input (reception) and output (transmission).

[0054] For example, the computer device may be a chip, and the communication unit 505 may be the input and / or output circuit of the chip, or the communication unit 505 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0055] For example, the computer device may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0056] The computer device may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0057] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0058] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in processor 501. Processor 501 can be a central processing unit, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable logic device, such as discrete gate, transistor logic device, or discrete hardware component.

[0059] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] In embodiment four, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described method for predicting the performance of foamed materials based on multi-scale modeling.

[0061] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0062] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method for predicting the performance of foamed materials based on multi-scale modeling, characterized in that, The prediction method includes the following steps: Structural data of the target foamed material is collected, and the structural data is classified to obtain a multi-scale feature database of the target foamed material. Modeling is performed based on the multi-scale feature database of the target foamed material to obtain structural models at various scales. Then, simulation is performed using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. The scale response domain refers to the set domain of the mechanical and thermal simulation response results of the target foamed material under the corresponding scale structure. Cross-scale integration is performed based on the scale response domain to obtain the scale integration layer of the target foamed material. The response of the scale integration layer is extracted to obtain the response points of the target foamed material at each scale. The response points refer to the response characteristic parameters that play a dominant role in the change of material properties at the corresponding structural scale. The performance prediction layer of the target foamed material is constructed by the response points of each scale and the preset physical parameters. Based on the performance prediction layer and structural data of the target foam material, the performance of the target foam material is predicted, and the performance prediction data of the target foam material is output.

2. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, The specific structural data collected for the target foaming material includes: Microstructure data of the target foaming material were obtained using a scanning electron microscope. Mesoscopic structural data of the target foaming material were obtained using X-ray microcomputed tomography equipment; Macroscopic structural data of the target foaming material are obtained by recording material preparation parameters; The structural data of the target foaming material is constructed based on the microstructure data, the mesostructure data, and the macrostructure data.

3. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, The structural data is classified to obtain a multi-scale feature database of the target foaming material, specifically including: The structural data is divided into multi-scale categories to obtain micro-feature data, meso-feature data, and macro-feature data. A multi-scale feature database of the target foaming material is determined based on the microscopic feature data, the mesoscopic feature data, and the macroscopic feature data.

4. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, Based on the scale response domain, cross-scale integration is performed to obtain the scale-integrated layer of the target foamed material, which specifically includes: The scale response domain is standardized to obtain all standardized responses; Each standardized response is subjected to inter-scale response transfer mapping to obtain various cross-scale response parameters. These cross-scale response parameters include modulus cross-scale response parameters and thermal conductivity cross-scale response parameters. Modulus cross-scale response parameters refer to the comprehensive response quantity that characterizes the degree of influence of different scale structures on the overall stiffness of the material. Thermal conductivity cross-scale response parameters refer to the comprehensive response quantity that reflects the synergistic relationship of multi-scale structures in thermal conductivity performance. By integrating various cross-scale response parameters, a scale-integrated layer of the target foam material is obtained.

5. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, Response extraction of the scale integration layer is achieved by applying preset sensitivity weights to the various cross-scale response parameters in the scale integration layer, thereby obtaining the response points of the target foamed material at various scales.

6. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, The performance prediction layer for the target foamed material is constructed by using sound points at various scales and preset physical parameters, specifically including: Based on the response points at various scales and preset physical parameters, construct prediction functions for various properties of the target foamed material; The performance prediction layer of the target foam material is obtained by integrating various performance prediction functions.

7. The method for predicting the performance of foamed materials based on multi-scale modeling as described in claim 1, characterized in that, The performance prediction layer includes an elastic modulus prediction channel and a thermal conductivity prediction channel.

8. A foamed material performance prediction system based on multi-scale modeling, used to execute the foamed material performance prediction method based on multi-scale modeling as described in any one of claims 1 to 7, characterized in that, The foaming material performance prediction system includes: The data acquisition module is used to collect structural data of the target foamed material, classify the structural data, and obtain a multi-scale feature database of the target foamed material. The scale integration module is used to model the target foamed material based on the multi-scale feature database to obtain structural models at various scales. Then, it performs simulations using the structural models at various scales and preset simulation data to obtain the scale response domain of the target foamed material. Based on the scale response domain, it performs cross-scale integration to obtain the scale integration layer of the target foamed material. The prediction construction module is used to extract the response of the scale integration layer to obtain the response points of the target foamed material at each scale, and to construct the performance prediction layer of the target foamed material through the response points at each scale and preset physical parameters. The performance prediction module is used to predict the performance of the target foam material based on the performance prediction layer and the structural data of the target foam material, and output the performance prediction data of the target foam material.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs a method for predicting the performance of foamed materials based on multi-scale modeling as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement a method for predicting the performance of foamed materials based on multi-scale modeling as described in any one of claims 1 to 7.

Images