A method and device for predicting mechanical properties of material interface phase, electronic equipment and storage medium

Abstract

The present application provides a kind of material interface phase mechanical property prediction method, device, electronic equipment and storage medium, the prediction method includes: obtaining the micro parameter corresponding to test sample, micro parameter includes filler mechanical parameter, matrix mechanical parameter and interface evaluation parameter;Based on micro parameter, high-throughput calculation is used to obtain the macro parameter corresponding to micro parameter;With micro parameter as input parameter, macro parameter as output parameter, generate the prediction model corresponding to macro parameter;The value of the micro parameter to be measured of the sample to be measured is taken, and the prediction model is substituted into the micro parameter to be measured of the sample to be measured to be measured to obtain the interface mechanical property corresponding to the sample to be measured.The prediction method establishes the prediction model relationship between micro parameter and macro parameter by high-throughput calculation and other means, so as to realize the reverse deduction of micro parameter by macro calculation and test.The prediction method has low running cost, simple operation, and high accuracy of the obtained numerical value.

Description

Technical Field

[0001] This invention belongs to the field of materials analysis and relates to a method, apparatus, electronic device and storage medium for predicting the mechanical properties of material interface phases. Background Technology

[0002] Composite materials, particularly those composed of fillers and matrix materials, are a common type. For these composites, macroscopic parameters such as mechanical, thermodynamic, and electrical properties can be measured using conventional testing methods and equipment. However, in the current technology, there is no accurate and simple testing method for measuring the microscopic parameters of these composites, especially those at the filler-matrix interface.

[0003] Epoxy molding compounds (EMCs) used in advanced electronic packaging structures are common composite materials composed of fillers and matrix materials. The most widely used epoxy molding compounds are composites of epoxy resin and SiO2, with SiO2 accounting for approximately 60%–90% of the epoxy molding compound. On the one hand, SiO2 filler can improve the Young's modulus and thermal conductivity of epoxy resin; on the other hand, increasing the filler content reduces the coefficient of thermal expansion of the epoxy molding compound. The thermodynamic properties of epoxy molding compounds, including Young's modulus, Poisson's ratio, thermal conductivity, and coefficient of thermal expansion, further affect the reliability of packaged devices. Although various experimental schemes for formulation design have been discussed, the data have not been compiled into a database; that is, all current experiments are discrete trial-and-error attempts and cannot quantitatively select material components and optimize performance. To explore the influence of material microstructure on macroscopic mechanics more quickly and efficiently, many theoretical and numerical models have been proposed, such as the commonly used Mori-Tanaka method, Hashin-Shtrikman bounds, and self-consistent models. However, these methods cannot fully account for complex stochastic structures in homogenization analyses of parameters such as Young's modulus. Numerical models can effectively overcome these shortcomings. For example, the finite element method or methods based on the fast Fourier transform can perform global field numerical simulations of complex composite material systems, obtaining the local stress-strain distribution of the material.

[0004] Currently, accurate prediction of mechanical parameters based on either theoretical or numerical models requires consideration of the mechanical dimensions and thickness of the interfacial phase, as well as the influence of these parameters. However, while atomic force microscopy can currently distinguish the thickness of the interfacial phase, measuring mechanical parameters such as Young's modulus and Poisson's ratio at the filler-matrix interface remains a challenge. Summary of the Invention

[0005] To address the technical problems existing in the prior art, this invention provides a method, apparatus, electronic device, and storage medium for predicting the mechanical properties of material interface phases. This prediction method establishes a predictive model relationship between microscopic and macroscopic parameters through high-throughput computation and other means, thereby enabling the reverse derivation of microscopic parameters through macroscopic calculations and tests. This prediction method has low operating costs, is simple to operate, and obtains highly accurate numerical values.

[0006] To achieve the above-mentioned technical effects, the present invention adopts the following technical solution:

[0007] One objective of this invention is to provide a method for predicting the mechanical properties of material interface phases, the method comprising:

[0008] Obtain the microscopic parameters corresponding to the test sample, including the mechanical parameters of the filler, the mechanical parameters of the matrix, and the estimated parameters of the interface;

[0009] Based on the micro parameters, the corresponding macro parameters are obtained by high-throughput computation.

[0010] Using microscopic parameters as input parameters and macroscopic parameters as output parameters, a prediction model corresponding to the macroscopic parameters is generated.

[0011] The values ​​of the microscopic parameters to be measured for the sample to be tested are obtained and substituted into the prediction model to perform reverse screening of the microscopic parameters to be measured for the sample to be tested, thereby obtaining the interfacial mechanical properties corresponding to the sample to be tested.

[0012] As a preferred technical solution of the present invention, high-throughput calculation includes: taking values ​​for the mechanical parameters of the packing material, the mechanical parameters of the matrix, and the interface estimation parameters within a reasonable range; arranging and combining different values ​​to obtain a micro-parameter database; and performing high-throughput calculation using the micro-parameter database to obtain a macro-parameter database.

[0013] As a preferred technical solution of the present invention, the method for generating a prediction model corresponding to macroscopic parameters includes machine learning.

[0014] As a preferred technical solution of the present invention, the machine learning method includes:

[0015] Using the mechanical parameters of the filler, the mechanical parameters of the matrix, and the interface estimation parameters as initial features, a first prototype function corresponding to each initial feature is generated;

[0016] The initial features are combined and processed to obtain several feature combinations;

[0017] For each feature combination and the first prototype function, a second prototype function is generated;

[0018] The second prototype function is filtered to obtain the second preferred prototype function;

[0019] The second preferred prototype function is curve-fitted to obtain the prediction model.

[0020] As a preferred technical solution of the present invention, generating a second prototype function for each feature combination and the first prototype function includes: filtering the first prototype function corresponding to each initial feature to obtain a first preferred prototype function; and generating a second prototype function for each feature combination and the first preferred prototype function.

[0021] As a preferred technical solution of the present invention, the method for screening the first prototype function and the second prototype function includes the determination coefficient screening.

[0022] As a preferred technical solution of the present invention, the reverse screening method includes: taking values ​​for the microscopic parameters to be tested and substituting them into the prediction model to obtain the predicted macroscopic parameters of the sample to be tested;

[0023] The predicted macroscopic parameters are compared with the actual macroscopic parameters of the sample to be tested, and qualified macroscopic parameters are selected.

[0024] The measured micro parameters corresponding to the qualified macroscopic parameters are used as the prediction results of the interface mechanical properties.

[0025] The mechanical properties of the interface in the micro-parameters to be measured, which are the predicted macro-parameters that are closest to the actual macro-parameters, are taken as the final result.

[0026] A second objective of this invention is to provide a device for predicting the mechanical properties of material interface phases, the device comprising:

[0027] The parameter acquisition module is used to obtain the microscopic parameters corresponding to the test sample;

[0028] A high-throughput computing module is used to obtain the macroscopic parameters corresponding to the microscopic parameters using high-throughput computing based on the microscopic parameters;

[0029] The prediction model generation module is used to generate a prediction model corresponding to macroscopic parameters by taking microscopic parameters as input parameters and macroscopic parameters as output parameters.

[0030] The reverse screening module takes the values ​​of the microscopic parameters to be tested of the sample and inputs them into the prediction model to perform reverse screening of the microscopic parameters to obtain the corresponding interfacial mechanical properties of the sample.

[0031] A third objective of this invention is to provide an electronic device comprising:

[0032] At least one processor; and a memory communicatively connected to the at least one processor;

[0033] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for predicting the mechanical properties of the material interface phase, one of the purposes provided.

[0034] Compared with the prior art, the present invention has at least the following beneficial effects:

[0035] (1) This invention provides a method for predicting the mechanical properties of material interface phases. This method establishes a predictive model relationship between micro parameters and macro parameters through high-throughput calculation and other means, thereby realizing the reverse derivation of micro parameters through macro calculation and testing.

[0036] (2) The present invention provides a method for predicting the mechanical properties of the material interface phase. The prediction method has low operating cost, simple operation, and accurate numerical values. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the structural model provided in Embodiment 1 of the present invention.

[0038] Figure 2 This is a flowchart illustrating the machine learning method provided in Embodiment 1 of the present invention.

[0039] Figure 3 This is a schematic diagram of the electronic device provided in Example 3.

[0040] Figure 3 In the diagram, 10-electronic device, 11-processor, 12-ROM, 13-RAM, 14-bus, 15-I / O interface, 16-input unit, 17-output unit, 18-storage unit, 19-communication unit.

[0041] The present invention will now be described in further detail. However, the examples described below are merely simplified examples of the present invention and do not represent or limit the scope of protection of the present invention. The scope of protection of the present invention is determined by the claims. Detailed Implementation

[0042] The technical solution of this application will be further described below through specific implementation methods.

[0043] This invention provides a method for predicting the mechanical properties of material interface phases, the method comprising:

[0044] Obtain the microscopic parameters corresponding to the test sample, including the mechanical parameters of the filler, the mechanical parameters of the matrix, and the estimated parameters of the interface;

[0045] Based on the micro parameters, the corresponding macro parameters are obtained by high-throughput computation.

[0046] Using microscopic parameters as input parameters and macroscopic parameters as output parameters, a prediction model corresponding to the macroscopic parameters is generated.

[0047] The values ​​of the microscopic parameters to be measured for the sample to be tested are obtained and substituted into the prediction model to perform reverse screening of the microscopic parameters to be measured for the sample to be tested, thereby obtaining the interfacial mechanical properties corresponding to the sample to be tested.

[0048] In one specific embodiment of the present invention, the microscopic parameters of the test sample can be obtained by establishing a standard model. For example, multiple standard models of a matrix material with filler are prepared, each standard model having a different filler filling degree, and the size and mechanical properties of the filler in each standard model are measured; optionally, the thickness of the filler-matrix interface phase is further measured.

[0049] In one specific embodiment of the present invention, multiple solid models can be set, and the filler filling degree of each solid model is different. For example, the number of solid models can be 2, 3, 4, 5, 6, 7 or 8, etc., and the filler filling degree (volume fraction) can be 5%, 10%, 15%, 20%, 25% or 30%, etc., but is not limited to the listed values. Other unlisted values ​​within the above ranges are also applicable.

[0050] In one specific embodiment of the present invention, the matrix materials commonly used in composite materials are all applicable to this method, such as epoxy resin, acrylic resin, silicone resin, phenolic resin and isocyanate resin, etc.

[0051] In one specific embodiment of the present invention, the filler is generally selected as filler particles, and the size of the filler refers to the particle size distribution of the filler particles.

[0052] In one specific embodiment of the present invention, commonly used fillers for composite materials are all suitable for this method, such as silica, calcium carbonate, or silicon dioxide.

[0053] In one specific embodiment of the present invention, the particle size distribution of the filler can be determined using a Malvern tester.

[0054] In one specific embodiment of the present invention, the mechanical properties of the solid model can be measured using a universal testing machine.

[0055] In one specific embodiment of the present invention, the mechanical properties of the solid model include Young's modulus and / or Poisson's ratio.

[0056] In one specific embodiment of the present invention, the thickness of the filler-matrix interface phase of the solid model can be measured using an atomic force microscope.

[0057] In one specific embodiment of the present invention, high-throughput calculation includes: taking values ​​for the mechanical parameters of the packing material, the mechanical parameters of the matrix, and the interface estimation parameters within a reasonable range; arranging and combining different values ​​to obtain a micro-parameter database; and performing high-throughput calculation using the micro-parameter database to obtain a macro-parameter database.

[0058] In one specific embodiment of the present invention, before performing high-throughput calculations, a structural model can be established based on the filling ratio of the solid model, and the values ​​of the filler mechanical parameters, matrix mechanical parameters, and interface estimation parameters can be determined based on the test results of the solid model.

[0059] In one specific embodiment of the present invention, in the structural model, the filler is completely randomly distributed, and the size of the filler and the thickness of the filler-matrix interface phase satisfy the measurement results of the solid model.

[0060] In one specific embodiment of the present invention, the reasonable range refers to the range of mechanical properties that conform to the physical and chemical properties of the filler, the matrix, and the filler-matrix interface. The number of values ​​can be selected according to the specific needs of high-throughput calculations, and is not further limited here. For example, the number of mechanical property values ​​for the filler is 3 to 10, the number of mechanical property values ​​for the matrix is ​​3 to 10, and the number of mechanical property values ​​for the filler-matrix interface is 20 to 200.

[0061] In one specific embodiment of the present invention, the high-throughput calculation also requires assigning values ​​to the Poisson's ratio of the filler and the matrix, as well as the thickness of the filler-matrix interface. These values ​​can be assigned based on the measurement results of the solid model.

[0062] In one specific embodiment of the present invention, the method for generating a prediction model corresponding to macroscopic parameters includes machine learning.

[0063] In one specific embodiment of the present invention, the machine learning method includes:

[0064] Using the mechanical parameters of the filler, the mechanical parameters of the matrix, and the interface estimation parameters as initial features, a first prototype function corresponding to each initial feature is generated;

[0065] The initial features are combined and processed to obtain several feature combinations;

[0066] For each feature combination and the first prototype function, a second prototype function is generated;

[0067] The second prototype function is filtered to obtain the second preferred prototype function;

[0068] The second preferred prototype function is curve-fitted to obtain the prediction model.

[0069] In one specific embodiment of the present invention, the prototype function may include f(x) = k1x and f(x) = k2x. -1 f(x) = k3x 1 / 2 f(x) = k4x -1 / 2 f(x) = k5x 2 f(x) = k6x -2 f(x) = k7x 3 f(x) = k8x -3 f(x) = k9ln(x), f(x) = k 10 / ln(x), f(x)=k 11 e x f(x) = k 12 e -x However, it is not limited to the prototype functions mentioned above; other suitable prototype functions can also be applied to this method.

[0070] In one specific embodiment of the present invention, the first prototype function corresponding to each initial feature is filtered to obtain a first preferred prototype function; for each feature combination and the first preferred prototype function, a second prototype function is generated.

[0071] In one specific embodiment of the present invention, the method for filtering the first prototype function and the second prototype function includes determination coefficient filtering.

[0072] In one specific embodiment of the present invention, the least squares regression method is used to calculate the determination coefficient of each prototype function in the first prototype function group for each feature, and the first preferred prototype function is selected based on the determination coefficient.

[0073] In one specific embodiment of the present invention, the least squares regression method is used to calculate the coefficient of determination (R²) of the prototype function. 2 The method involves calculating the sum of squared residuals between the actual values ​​and the model predictions, given the input parameters.

[0074] In one specific embodiment of the present invention, the least squares regression method is used to calculate the coefficient of determination (R²) of the prototype function. 2 The formula for ) can be shown as follows:

[0075]

[0076] Where n is the number of samples, y i These are actual measured values. The predicted value of the model. This represents the average of the actual measured values.

[0077] In one specific embodiment of the present invention, at least three prototype functions are selected from the first prototype functions as the first preferred prototype functions. For example, the number of prototype functions in the first optimal prototype function group can be 3, 4, 5, 6, or 7, etc., but is not limited to the listed values; other unlisted values ​​within this range are also applicable.

[0078] In one specific embodiment of the present invention, the method of combining the initial features includes addition, subtraction, multiplication, and division, or taking the reciprocal, natural logarithm, square, or cube before performing addition, subtraction, multiplication, or division. Preferably, each feature is arranged and combined before multiplication. For example, if the mechanical property characteristics of the filler, matrix, and filler-matrix interface are set to x1, x2, and x3 respectively, then the feature combinations obtained after multiplication are x1, x2, x3, x1*x2, x1*x3, x2*x3, and x1*x2*x3.

[0079] In one specific embodiment of the present invention, the first preferred prototype function of each feature is combined by calculation and then combined with the first preferred prototype function to form a second prototype function.

[0080] In one specific embodiment of the present invention, the least squares regression method is used to calculate the determination coefficients of each prototype function in the second prototype function of each feature combination, and the second preferred prototype function of each feature combination is selected based on the determination coefficients.

[0081] In one specific embodiment of the present invention, at least 10 prototype functions are selected from the second prototype functions as the second preferred prototype functions, such as 10, 12, 15, 18 and 20, etc., but not limited to the listed values. Other unlisted values ​​within the above ranges are also applicable, with 15 being the preferred number.

[0082] In one specific embodiment of the present invention, the curve fitting method is preferably the curve_fit method.

[0083] In one specific embodiment of the present invention, the curve_fit method is used to generate a prediction model between the input and output parameters from a second preferred prototype function. The curve_fit method is derived from the SciPy documentation.

[0084] In one specific embodiment of the present invention, the reverse screening method includes: taking values ​​for the microscopic parameters to be tested and substituting them into the prediction model to obtain the predicted macroscopic parameters of the sample to be tested;

[0085] The predicted macroscopic parameters are compared with the actual macroscopic parameters of the sample to be tested, and qualified macroscopic parameters are selected.

[0086] The measured micro parameters corresponding to the qualified macroscopic parameters are used as the prediction results of the interface mechanical properties.

[0087] The mechanical properties of the interface in the micro-parameters to be measured, which are the predicted macro-parameters that are closest to the actual macro-parameters, are taken as the final result.

[0088] In one specific embodiment of the present invention, taking values ​​for the microscopic parameters to be measured refers to taking values ​​for the mechanical properties of the filler, the matrix, and the filler-matrix interface.

[0089] In one specific embodiment of the present invention, based on the actual mechanical properties of the filler and the matrix, a reasonable range of mechanical properties of the filler-matrix interface can be obtained. Values ​​are taken within this reasonable range at small intervals (e.g., 0.1 GPa). The actual mechanical properties of the filler and matrix, as well as the values ​​of the mechanical properties of the filler-matrix interface, are used as input parameters and substituted into the prediction model to obtain the predicted results of the mechanical property parameters of the structural model. The mechanical property value of the filler-matrix interface in the input parameters corresponding to the predicted result that is closest to the actual result is the final predicted result of the mechanical properties of the filler-matrix interface.

[0090] To better illustrate the present invention and facilitate understanding of its technical solutions, typical but non-limiting embodiments of the present invention are as follows:

[0091] Example 1

[0092] This embodiment provides a method for predicting the mechanical properties of an interface phase, the method comprising:

[0093] Preparation of solid models: Using silica particles as fillers and epoxy resin as a matrix, solid models with filler volume filling ratios of 20%, 30%, and 40% were prepared by high-speed stirring. A silane coupling agent with a mass fraction of 2% (Z-6040) was added to ensure the dispersion of the filler particles. The particle size distribution of silica particles was determined using a Malvern spectrometer. The Young's modulus and Poisson's ratio of the solid models were tested using a universal mechanical testing machine. The thickness of the filler-matrix interface phase was measured using an atomic force microscope.

[0094] Structural model establishment: A structural model is established based on the filling ratio of the solid model. In the structural model, the filler is completely randomly distributed, and the size of the filler and the thickness of the filler-matrix interface phase satisfy the measurement results of the solid model. For example... Figure 1 As shown.

[0095] High-throughput calculation: The Young's modulus of silica particles was set to 65 GPa, 70 GPa, and 75 GPa, and the Young's modulus of the epoxy resin matrix was set to 1.5 GPa, 2 GPa, and 2.5 GPa. The Poisson's ratio of silica particles was set to 0.17, and the Poisson's ratio of the epoxy resin matrix was set to 0.37. The thickness of the silica particle-epoxy resin interfacial phase was 71.3 nm. The Young's modulus of the silica particle-epoxy resin interfacial phase was set within the range of 2.98–71 GPa. 100 values ​​were randomly selected to obtain an input parameter database with 900 sets of numerical parameters. The data in the input parameter database were used as input parameters for high-throughput calculation, and the Young's modulus of the structural model was used as the output parameter.

[0096] Machine learning: its process is as follows Figure 2 As shown, the Young's modulus of the silica particles, the epoxy resin matrix, and the silica particle-epoxy resin matrix interface are set as features, namely x1, x2, and x3. Each feature generates 12 prototype functions, resulting in the first prototype function group for each feature. The prototype functions include f(x) = k1x, f(x) = k2x, etc. -1 f(x) = k3x 1 / 2 f(x) = k4x -1 / 2 f(x) = k5x 2 f(x) = k6x -2 f(x) = k7x 3 f(x) = k8x -3 f(x) = k9ln(x), f(x) = k 10 / ln(x), f(x)=k 11 e x f(x) = k 12 e -x Where f(x) represents the output parameter, x is the characteristic parameter, and k1~k 12 The coefficients are used. Least squares regression (LSR) is used to calculate the coefficients of determination for all prototype functions in each feature, and the three prototype functions with the largest coefficients are selected to form the first optimal prototype function group for the corresponding feature.

[0097] The three features are arranged and multiplied to obtain feature combinations, including x1, x2, x3, x1*x2, x1*x3, x2*x3, and x1*x2*x3. Each prototype function from the first optimal prototype function set of each feature is substituted into each feature combination to obtain the second prototype function set for each feature combination. The least squares regression method is used to calculate the determination coefficients of the prototype functions in the second prototype function set for each feature combination. The three prototype functions with the largest determination coefficients are selected to form the second optimal prototype function set for the corresponding feature combination.

[0098] The determination coefficients of the prototype functions in the second optimal prototype function group for each feature combination and the first optimal prototype function group for each feature are compared. The 15 prototype functions with the largest determination coefficients are selected to obtain the third optimal prototype function group. The curve_fit method is used to generate a prediction model between the input parameters and the output parameters from the third optimal prototype function group, and the model coefficients are obtained.

[0099] Reverse screening: Based on the actual Young's moduli of carbon dioxide particles and the epoxy resin matrix, the reasonable range of Young's modulus for the carbon dioxide particle-epoxy resin interface is 2.98–71 GPa. Values ​​are taken within this range in 0.1 GPa intervals. The actual Young's moduli of the carbon dioxide particles and epoxy resin matrix, as well as the Young's modulus of the carbon dioxide particle-epoxy resin interface, are used as input parameters and substituted into the prediction model to obtain the predicted Young's modulus of the structural model. The Young's modulus value of the carbon dioxide particle-epoxy resin interface in the input parameters corresponding to the prediction result that most closely matches the Young's modulus measurement result of the corresponding solid model is taken as the final predicted Young's modulus of the carbon dioxide particle-epoxy resin interface.

[0100] Example 2

[0101] This embodiment provides a device for predicting the mechanical properties of material interface phases, the device comprising:

[0102] The parameter acquisition module is used to obtain the microscopic parameters corresponding to the test sample;

[0103] A high-throughput computing module is used to obtain the macroscopic parameters corresponding to the microscopic parameters using high-throughput computing based on the microscopic parameters;

[0104] The prediction model generation module is used to generate a prediction model corresponding to macroscopic parameters by taking microscopic parameters as input parameters and macroscopic parameters as output parameters.

[0105] The reverse screening module takes the values ​​of the microscopic parameters to be tested of the sample and inputs them into the prediction model to perform reverse screening of the microscopic parameters to obtain the corresponding interfacial mechanical properties of the sample.

[0106] Example 3

[0107] This embodiment provides an electronic device, such as... Figure 3The diagram shown is a structural schematic of an electronic device 10 used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0108] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14; an I / O interface 15 is also connected to the bus 14.

[0109] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0110] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 executes the method for predicting the interface phase mechanical properties provided in Embodiment 1.

[0111] In some embodiments, the method for predicting the mechanical properties of the interface phase can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for predicting the mechanical properties of the interface phase can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for predicting the mechanical properties of the interface phase by any other suitable means (e.g., by means of firmware).

[0112] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0117] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0118] The applicant declares that the detailed structural features of the present invention are illustrated through the above embodiments, but the present invention is not limited to the above detailed structural features, that is, it does not mean that the present invention must rely on the above detailed structural features to be implemented. Those skilled in the art should understand that any improvements to the present invention, equivalent substitutions for the components selected in the present invention, additions of auxiliary components, selection of specific methods, etc., all fall within the protection scope and disclosure scope of the present invention.

[0119] The preferred embodiments of the present invention have been described in detail above. However, the present invention is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present invention, various simple modifications can be made to the technical solution of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0120] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable way without contradiction. In order to avoid unnecessary repetition, the present invention will not describe the various possible combinations separately.

[0121] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A method for predicting the mechanical properties of a material interface phase, characterized in that, The prediction method includes: The microscopic parameters corresponding to the test sample are obtained, including the mechanical parameters of the filler, the mechanical parameters of the matrix, and the interface estimation parameters. Based on the micro parameters, the corresponding macro parameters are obtained using high-throughput computation. Using the micro parameters as input parameters and the macro parameters as output parameters, a prediction model corresponding to the macro parameters is generated; The values ​​of the microscopic parameters to be tested for the sample are obtained and substituted into the prediction model to perform reverse screening of the microscopic parameters to be tested for the sample, thereby obtaining the interfacial mechanical properties of the sample. The reverse screening method includes: taking values ​​for the microscopic parameters to be tested and substituting them into the prediction model to obtain the predicted macroscopic parameters of the sample to be tested; The predicted macroscopic parameters are compared with the actual macroscopic parameters of the sample to be tested, and qualified macroscopic parameters are selected. The measured micro parameters corresponding to the qualified macroscopic parameters are used as the prediction results of the interface mechanical properties. The mechanical properties of the interface in the micro-parameters to be measured, which are the predicted macro-parameters that are closest to the actual macro-parameters, are taken as the final result.

2. The prediction method according to claim 1, characterized in that, The high-throughput calculation includes: taking values ​​for the mechanical parameters of the packing material, the mechanical parameters of the matrix, and the interface estimation parameters within a reasonable range; arranging and combining different values ​​to obtain a micro-parameter database; and performing high-throughput calculations using the micro-parameter database to obtain a macro-parameter database.

3. The prediction method according to claim 1, characterized in that, The methods for generating the prediction models corresponding to the macroscopic parameters include machine learning.

4. The prediction method according to claim 3, characterized in that, The machine learning methods include: Using the mechanical parameters of the filler, the mechanical parameters of the matrix, and the interface estimation parameters as initial features, a first prototype function corresponding to each of the initial features is generated; The initial features are combined and processed to obtain several feature combinations; For each of the aforementioned feature combinations and the first prototype function, a second prototype function is generated; The second prototype function is filtered to obtain the second preferred prototype function; The second preferred prototype function is curve-fitted to obtain the prediction model.

5. The prediction method according to claim 4, characterized in that, The step of generating a second prototype function for each of the feature combinations and the first prototype function includes: The first prototype function corresponding to each initial feature is filtered to obtain the first preferred prototype function; For each of the aforementioned feature combinations and the first preferred prototype function, a second prototype function is generated.

6. The prediction method according to claim 5, characterized in that, The method for filtering the first prototype function and the second prototype function includes the coefficient of determination filtering.

7. A device for predicting the mechanical properties of material interface phases, characterized in that, The prediction device is used in the method for predicting the mechanical properties of the material interface phase as described in claim 1, and the prediction device comprises: The parameter acquisition module is used to obtain the microscopic parameters corresponding to the test sample; A high-throughput computing module is used to obtain the macroscopic parameters corresponding to the microscopic parameters using high-throughput computing based on the microscopic parameters; The prediction model generation module is used to generate a prediction model corresponding to the macroscopic parameters, using the microscopic parameters as input parameters and the macroscopic parameters as output parameters. The reverse screening module takes the values ​​of the microscopic parameters to be tested of the sample and inputs them into the prediction model to perform reverse screening of the microscopic parameters to be tested, thereby obtaining the interfacial mechanical properties of the sample.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the method for predicting the mechanical properties of the material interface phase as described in any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed by a processor, implement the method for predicting the mechanical properties of the material interface phase as described in any one of claims 1-6.

Images