Multi-scale progressive failure analysis method for composite material structure fused with machine learning model

Abstract

The invention relates to the field of composite material damage analysis methods, in particular to a machine learning model-fused composite material structure multi-scale progressive damage analysis method, which comprises the following steps of: on the basis of a homogenization theory, combining a finite element method with a machine learning model, and establishing a multi-scale interactive calculation framework; based on a continuous medium damage mechanics theory, establishing a multi-scale progressive damage model of the composite material; and based on the finite element model, realizing multi-scale progressive failure analysis of the composite material structure through a secondary development program. Based on the homogenization theory and the continuous medium damage mechanics theory, the multi-scale progressive damage analysis method for the composite material structure is established, the K-means + + clustering machine learning model is fused, macro / micro-scale interactive calculation can be achieved, meanwhile, the calculation amount of macro / micro-scale repeated iterative solution can be reduced, and the method is suitable for large-scale and small-scale multi-scale progressive damage analysis of the composite material structure. And the calculation efficiency is improved while the calculation precision is ensured.

Description

Technical Field

[0001] The present invention relates to the field of composite material failure analysis methods, and specifically to a multi-scale progressive failure analysis method for composite material structures integrating a machine learning model. Background Art

[0002] Compared with traditional metal materials, fiber-reinforced resin-based composite materials have the advantages of high specific stiffness and specific strength, excellent fatigue resistance, and strong corrosion resistance, and have been widely used in aerospace and other fields. In recent years, with the increasing application of composite materials in aircraft load-bearing structures, their damage and failure during use have become a key issue, posing a threat to the safety and reliability of aircraft. Therefore, reliable methods are needed to evaluate the load-bearing capacity and failure process of composite structures.

[0003] The progressive failure analysis method based on the finite element method can effectively predict the strength and damage evolution process of composite structures, and has attracted widespread attention from scholars and industry at home and abroad. The macroscopic mechanical response of composite structures depends on the microstructure and properties of the constituent materials, and also determines the microscopic stress-strain field and damage distribution. Its entire failure process usually covers different scales, including various damage modes at the microscale (such as matrix cracking, interface debonding and fiber breakage) and overall structural failure at the macroscale. Therefore, a multi-scale method is needed to study the progressive failure process of composite structures.

[0004] However, when the existing technology is actually used, the interactive calculation of the two scales requires repeated iterative solutions of macro / micro scale stress-strain response and damage, and the huge amount of calculation will bring difficulties to practical applications. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-scale progressive failure analysis method for composite structures that integrates a machine learning model to solve the problem that the huge amount of computation required to iteratively solve macro / micro scale stress-strain response and damage will bring difficulties to practical applications.

[0006] To achieve the above object, the present invention provides the following technical solution: a multi-scale progressive failure analysis method for composite material structure integrating machine learning model, comprising the following steps:

[0007] S1. Based on the homogenization theory, the finite element method and the machine learning model are combined to establish a multi-scale interactive calculation framework, specifically:

[0008] S11. At the microscopic scale, a representative volume unit is selected and periodic boundary conditions are imposed on it, and the coupling relationship between the macroscopic and microscopic scale models is established based on the homogenization theory.

[0009] S12. By introducing the K-means++ clustering model, the strain information of potential damage Gaussian points in the macro model is clustered and analyzed, and a multi-scale interactive calculation framework is established;

[0010] S2. Based on the theory of continuum damage mechanics, a multi-scale progressive damage model for composite materials is established. Specifically:

[0011] S21. For the microscopic representative volume unit model, the maximum stress criterion is used as the damage initiation criterion in the fiber region, and the modified Von Mises criterion is used as the damage initiation criterion in the matrix region. After identifying the damage initiation of the fiber and matrix materials, the damage evolution model is used to calculate the damage coefficient, and the material properties are gradually degraded.

[0012] S22. For the macro model, set potential damage judgment conditions to determine whether the Gaussian point needs to call the micro representative volume unit model for calculation, and use the three-dimensional Hashin criterion as the potential damage judgment condition;

[0013] S3. Based on the finite element model, the multi-scale progressive failure analysis of composite materials is realized through the secondary development program, specifically:

[0014] S31. According to the structure configuration, size and microstructure composition of the composite material, establish the finite element model of the macrostructure and microscopic representative volume unit respectively;

[0015] S32. Firstly, a preliminary stress-strain analysis is performed on the microscopic representative volume unit model, and the equivalent elastic constants of the composite material in the undamaged state are obtained by homogenization calculation, which are then transferred to the macroscopic model;

[0016] S33, perform stress-strain analysis on the macro model, use potential damage judgment conditions to identify Gaussian points that may be damaged, and use K-means++ model to perform cluster analysis on them;

[0017] S34, passing the clustered strain information to the microscopic representative volume unit model, performing microscopic progressive failure analysis, calculating the global average stress and the equivalent elastic constant after damage by homogenization, passing them to the macroscopic model, and entering step S33;

[0018] S35, repeating the process of step S33 and step S34 until the macro structure fails, and obtaining the mechanical response results of the composite material structure and the multi-scale progressive failure process.

[0019] Preferably, the coupling relationship expression of the macro / micro scale model established based on the homogenization theory in step S11 is:

[0020]

[0021] In the formula, ui is the displacement component of the point on the boundary of the microscopic RVE model, with the superscript j + and j - Respectively represent the positive and negative directions along the direction;

[0022] is the distance between parallel boundary surfaces;

[0023] is the microscopic global average strain, which is equal to the macroscopic strain transmitted at the corresponding Gaussian point of the macroscopic model; the constitutive relation of the fiber material in RVE is expressed as:

[0024]

[0025] In the formula, Δε and Δσ are microscopic strain increment and stress increment respectively;

[0026] C ε is the microscopic local tangent stiffness matrix;

[0027] x is the microscopic coordinate, V is the computational domain of the microscopic RVE model;

[0028] The expressions of global average strain and stress obtained by homogenization are:

[0029]

[0030] In the formula, is the macro coordinate;

[0031] ε and σ are the local strain and stress tensors in the microscopic RVE model, respectively;

[0032] and are the global average strain and stress tensors of the microscopic RVE model, and are also the macroscopic strain and stress tensors, respectively;

[0033] The constitutive relation expression at the macroscopic scale is:

[0034]

[0035] In the formula, and are the macroscopic strain increment and stress increment, respectively;

[0036] is the macroscopic local tangent stiffness matrix;

[0037] is the computational domain of the macro model.

[0038] Preferably, in step S12, cluster analysis is performed on the strain information of potential damage Gaussian points in the macro model, specifically:

[0039] The K-means++ clustering model is used to cluster these damage Gaussian points based on the strain state data, and the cluster centers are determined by repeated probability calculation and roulette wheel selection until all cluster centers remain unchanged.

[0040] Preferably, the fiber area damage initiation criteria in step S21 include:

[0041] Fiber stretch damage

[0042]

[0043] Fiber compression damage

[0044]

[0045] In the formula, is the fiber longitudinal stress, T f and C f are the tensile strength and compressive strength of the fiber, respectively;

[0046] The matrix region damage initiation criteria in step S21 include:

[0047]

[0048]

[0049] In the formula, I 1 and I 2 are the first stress invariant and the second stress invariant of the matrix, σ 11 , σ 22 and σ 33 is the normal stress in three directions of the matrix, σ 12 , σ 23 and σ 13 is the shear stress of the matrix, T m and C m are the tensile strength and compressive strength of the matrix, respectively.

[0050] Preferably, in step S21, a damage evolution model is used to calculate the damage coefficient, and the material properties are gradually degraded, specifically: equivalent displacement is used as the damage variable, the damage coefficient is determined by calculating the equivalent displacement in the damage initial state and the complete failure state, and the elastic constant of the material is multiplied by a degradation coefficient to achieve gradual degradation of the material properties.

[0051] Preferably, the three-dimensional Hashin criterion in step S22 includes:

[0052] Fiber damage:

[0053]

[0054] Matrix damage:

[0055]

[0056] In the formula, σ 11 , σ 22 and σ 33 is the normal stress;

[0057] σ 12 , σ 13 and σ 23 is the shear stress;

[0058] X T and X C are the longitudinal tensile and compressive strengths of the composites, respectively;

[0059] Y T and Y C are the transverse tensile and compressive strengths of the composites, respectively;

[0060] S 12 , S 13 and S 23 is the shear strength of the composite material.

[0061] Preferably, when establishing the finite element models of the macrostructure and the micro-representative volume unit in step S31, an external load is applied to the macrostructure model, and a periodic boundary condition is applied to the micro-representative volume unit model.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] 1. Based on the homogenization theory and the continuous medium damage mechanics theory, the present invention establishes a multi-scale progressive failure analysis method for composite material structures, and incorporates the K-means++ clustering machine learning model to propose a new multi-scale progressive failure algorithm. On the one hand, it can realize interactive calculations at the macro / micro scale, and on the other hand, it can reduce the amount of calculations required for repeated iterative solutions at the macro / micro scale, thereby improving the calculation efficiency while ensuring the calculation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A step diagram of a multi-scale progressive failure analysis method for composite material structure integrating a machine learning model according to the present invention;

[0065] Figure 2 This is a flow chart of a multi-scale progressive failure analysis method for composite material structures that integrates a machine learning model. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] See also Figure 1-2 The present invention provides a technical solution: a multi-scale progressive failure analysis method for composite material structures integrating a machine learning model, comprising the following steps:

[0068] S1. Based on the homogenization theory, the finite element method and the machine learning model are combined to establish a multi-scale interactive calculation framework, specifically:

[0069] S11. At the microscopic scale, considering that the composite material has a periodic repetitive structure, a representative volume element (RVE) is taken, which consists of two parts: fiber and matrix. In order to ensure the continuity of displacement and stress, it is necessary to apply periodic boundary conditions to the RVE, which can be expressed as:

[0070]

[0071] In the formula, u i is the displacement component of the point on the boundary of the microscopic RVE model, with the superscript j + and j - Respectively represent the positive and negative directions along the direction;

[0072] is the distance between parallel boundary surfaces;

[0073] is the microscopic global average strain, which is equal to the macroscopic strain transmitted at the corresponding Gaussian point of the macroscopic model. The fiber material in RVE can be regarded as a transversely isotropic material, while the matrix material in RVE can be regarded as an isotropic material. The constitutive relationship can be expressed as:

[0074]

[0075] In the formula, Δε and Δσ are microscopic strain increment and stress increment respectively;

[0076] C ε is the microscopic local tangent stiffness matrix, x is the microscopic coordinate, and V is the computational domain of the microscopic RVE model.

[0077] Based on the strain and stress field results calculated in the micro RVE model, the global average strain and stress are obtained by homogenization:

[0078]

[0079] In the formula, is the macro coordinate;

[0080] ε and σ are the local strain and stress tensors in the microscopic RVE model, respectively;

[0081] and are the global average strain and stress tensors of the microscopic RVE model, and are also the macroscopic strain and stress tensors, respectively.

[0082] Based on the calculated global average strain and stress, the macroscopic equivalent elastic constants of the composite material can be estimated through the constitutive relation of the elastic body, and then transferred to the corresponding Gaussian points in the macroscopic model. At the macroscopic scale, the constitutive relation expression is:

[0083]

[0084] In the formula, and are the macroscopic strain increment and stress increment, respectively;

[0085] is the macroscopic local tangent stiffness matrix;

[0086] is the computational domain of the macro model.

[0087] S12. In the process of multi-scale progressive failure analysis of composite structures, it is necessary to update the elastic constants and stress-strain redistribution at the local damage position in the macro model by repeating the above-mentioned multi-scale interactive calculation based on homogenization theory. If each Gaussian point of the macro model is associated with a micro RVE model, it will bring huge computational complexity.

[0088] In fact, for undamaged Gaussian points in the macro model, there is no need to call the micro RVE model to update the calculation of the macro equivalent elastic constants. Therefore, the potential damage judgment condition is set in the macro model, and the micro RVE model is called only for the Gaussian points that meet the condition. Considering that under the action of incremental external loads, the number of Gaussian points with potential damage in the macro model will increase significantly with the expansion of damage, and many of these points have similar strain states, in order to reduce the computational cost, the K-means++ clustering model is used to cluster these damaged Gaussian points based on the strain state data.

[0089] Among them, the first cluster center c 1 is from the data set (x 1 ,x 2 ,...,x n ) is randomly selected. Then, the data point x is calculated i To cluster center c1 The Euclidean distance is then calculated, and the shortest distance between the data point and the current cluster center is calculated. The probability of each data point being selected as the next cluster center can then be calculated by formula (5):

[0090]

[0091] According to the selection probability of each data point obtained by calculation, the next cluster center is selected by the commonly used roulette method. By repeating the above probability calculation and roulette selection, k initial cluster centers can be selected from the data set. Then, the distance between the data point and each initial cluster center can be calculated by formula (5). According to the principle of the shortest distance to the cluster center, the data point is assigned to the cluster with the nearest cluster center.

[0092] Then, the cluster center is updated by averaging the data points in each cluster, which can be expressed as:

[0093]

[0094] Finally, repeat the above data clustering process and cluster center update until all cluster centers remain unchanged.

[0095] S2. Based on the theory of continuum damage mechanics, a multi-scale progressive damage model for composite materials is established. Specifically:

[0096] S21. At the microscopic scale, for the fiber region in the RVE model, the maximum stress criterion is used as the fiber damage initiation criterion:

[0097] Fiber stretch damage

[0098]

[0099] Fiber compression damage

[0100]

[0101] In the formula, is the fiber longitudinal stress, T f and C f are the tensile strength and compressive strength of the fiber, respectively;

[0102] For the matrix region in the RVE model, the modified Von Mises criterion is used as the matrix damage initiation criterion:

[0103]

[0104]

[0105] In the formula, I 1 and I 2 are the first stress invariant and the second stress invariant of the matrix, σ 11 , σ 22 and σ 33 is the normal stress in three directions of the matrix, σ 12 , σ 23 and σ 13 is the shear stress of the matrix, T m and C m are the tensile strength and compressive strength of the matrix, respectively.

[0106] After identifying the initiation of fiber and matrix material damage through the above criteria, the damage evolution model is used to calculate the damage coefficient:

[0107]

[0108] Where δ is the equivalent displacement;

[0109] δ 0 and δ f are the equivalent displacements at the damage initiation state and the complete failure state, respectively.

[0110] The damage coefficient d ranges from [0,1]. As the damage coefficient increases, the material properties gradually degrade. This is achieved by multiplying the elastic constant of the material by a degradation coefficient γ. The relationship between d and γ is:

[0111] γ=1-d (12)

[0112] According to the elastic constants of the degraded material, the damage stiffness matrix of the calculated material is updated, and the damage constitutive model is:

[0113]

[0114] S22. In the multi-scale interactive calculation process of progressive destruction of composite structures, the damage state of Gaussian points in the macro model depends on the damage analysis results of the RVE model, and there is no need for macro damage initiation criteria and damage evolution models.

[0115] However, in order to reduce the calculation cost, it is necessary to set the potential damage judgment condition in the macro model. This condition is only used to preliminarily judge whether the Gauss point needs to call the micro RVE model for calculation. The commonly used three-dimensional Hashin criterion is used:

[0116] Fiber damage:

[0117]

[0118] Matrix damage:

[0119]

[0120] In the formula, σ 11 , σ 22 and σ 33 is the normal stress;

[0121] σ 12 , σ 13 and σ 23 is the shear stress;

[0122] X T and X C are the longitudinal tensile and compressive strengths of the composites, respectively;

[0123] Y T and Y C are the transverse tensile and compressive strengths of the composites, respectively;

[0124] S 12 , S 13 and S 23 is the shear strength of the composite material.

[0125] S3. Realize multi-scale progressive failure analysis of composite materials through secondary development program. For the algorithm flow chart, please refer to Figure 2 , specifically:

[0126] S31. According to the structure configuration and size of the composite material and the microstructure composition, finite element models of the macrostructure and the micro RVE are established respectively, wherein an external load is applied to the macrostructure model and a periodic boundary condition is applied to the micro RVE model;

[0127] S32. In the multi-scale progressive failure analysis of composite structures, a preliminary stress-strain analysis is first performed on the micro RVE model, and the calculation results are homogenized to obtain the equivalent elastic constants of the composite material in the undamaged state, which are then transferred to the macro model;

[0128] S33, after receiving the information transmitted by the micro RVE model, the macro model performs stress-strain analysis and uses potential damage judgment conditions to identify Gaussian points that may be damaged. Based on the strain state of these Gaussian points, the K-means++ clustering model is used to perform cluster analysis;

[0129] S34, passing the strain information after cluster analysis to the micro RVE model, performing micro progressive failure analysis, calculating the global average stress and the equivalent elastic constant of the composite material after damage based on the homogenization theory, and passing the information to the macro model, and entering step S33;

[0130] S35, repeating the process of step S33 and step S34 until the macro structure fails, and obtaining the mechanical response results of the composite material structure and the multi-scale progressive failure process.

[0131] Based on the homogenization theory, the present invention combines the finite element method and the machine learning model to establish a multi-scale interactive calculation framework. At the microscale, considering the periodic repetitive structure of the composite material, the representative volume element (RVE) is taken for modeling and analysis. By applying periodic boundary conditions to the RVE, the coupling relationship of the macro / micro scale model is established based on the homogenization theory. At the same time, the K-means++ clustering model is introduced to perform cluster analysis on the strain information of potential damage Gaussian points in the macro model, thereby reducing the amount of calculation.

[0132] Secondly, based on the theory of continuous medium damage mechanics, a multi-scale progressive damage model for composite materials was established. At the microscopic scale, different damage initiation criteria and damage evolution models were used for the fiber and matrix regions to simulate the microscopic damage process of composite materials. At the macroscopic scale, potential damage judgment conditions were set to preliminarily determine whether the Gaussian point needs to call the microscopic RVE model for calculation.

[0133] Finally, the multi-scale progressive failure analysis of composite structures was realized through the secondary development program. According to the composite structure configuration and size as well as the microstructure composition, the finite element models of the macrostructure and micro RVE were established respectively. Through multi-scale interactive calculation and cluster analysis, the elastic constants and stress-strain distribution of the local damage position in the macro model were continuously updated until the macro structure failed.

[0134] The present invention improves the calculation efficiency while ensuring the calculation accuracy, provides effective technical support for multi-scale damage assessment of composite materials structures, and has important engineering application value and academic significance.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0136] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A multi-scale progressive failure analysis method for composite structures integrating a machine learning model, characterized by: The following steps are involved: S1. Based on the homogenization theory, the finite element method and the machine learning model are combined to establish a multi-scale interactive calculation framework, specifically: S11. At the microscopic scale, a representative volume unit is selected and periodic boundary conditions are imposed on it, and the coupling relationship between the macroscopic and microscopic scale models is established based on the homogenization theory. S12. By introducing the K-means++ clustering model, the strain information of potential damage Gaussian points in the macro model is clustered and analyzed, and a multi-scale interactive calculation framework is established; S2. Based on the theory of continuum damage mechanics, a multi-scale progressive damage model for composite materials is established. Specifically: S21. For the microscopic representative volume unit model, the maximum stress criterion is used as the damage initiation criterion in the fiber region, and the modified Von Mises criterion is used as the damage initiation criterion in the matrix region. After identifying the damage initiation of the fiber and matrix materials, the damage evolution model is used to calculate the damage coefficient, and the material properties are gradually degraded. S22. For the macro model, set potential damage judgment conditions to determine whether the Gaussian point needs to call the micro representative volume unit model for calculation, and use the three-dimensional Hashin criterion as the potential damage judgment condition; S3. Based on the finite element model, the multi-scale progressive failure analysis of composite materials is realized through the secondary development program, specifically: S31. According to the structure configuration, size and microstructure composition of the composite material, establish the finite element model of the macrostructure and microscopic representative volume unit respectively; S32. Firstly, a preliminary stress-strain analysis is performed on the microscopic representative volume unit model, and the equivalent elastic constants of the composite material in the undamaged state are obtained by homogenization calculation, which are then transferred to the macroscopic model; S33, perform stress-strain analysis on the macro model, use potential damage judgment conditions to identify Gaussian points that may be damaged, and use K-means++ model to perform cluster analysis on them; S34, passing the clustered strain information to the microscopic representative volume unit model, performing microscopic progressive failure analysis, calculating the global average stress and the equivalent elastic constant after damage by homogenization, passing them to the macroscopic model, and entering step S33; S35, repeating the process of step S33 and step S34 until the macro structure fails, and obtaining the mechanical response results of the composite material structure and the multi-scale progressive failure process.

2. According to claim 1, a multi-scale progressive failure analysis method for composite material structures integrating a machine learning model is characterized by: The coupling relationship expression of the macro / micro scale model established based on the homogenization theory in step S11 is: In the formula, u i is the displacement component of the point on the boundary of the microscopic RVE model, with the superscript j + and j - Represent the positive and negative directions along the direction respectively; is the distance between parallel boundary surfaces; is the microscopic global average strain, which is equal to the macroscopic strain transmitted at the corresponding Gaussian point of the macroscopic model; the constitutive relation of the fiber material in RVE is expressed as: In the formula, Δε and Δσ are microscopic strain increment and stress increment respectively; C ε is the microscopic local tangent stiffness matrix; x is the microscopic coordinate, V is the computational domain of the microscopic RVE model; The expressions of global average strain and stress obtained by homogenization are: In the formula, is the macro coordinate; ε and σ are the local strain and stress tensors in the microscopic RVE model, respectively; and are the global average strain and stress tensors of the microscopic RVE model, and are also the macroscopic strain and stress tensors, respectively; The constitutive relation expression at the macroscopic scale is: In the formula, and are the macroscopic strain increment and stress increment, respectively; is the macroscopic local tangent stiffness matrix; is the computational domain of the macro model.

3. The multi-scale progressive failure analysis method for composite material structures integrating a machine learning model according to claim 1, characterized in that: In step S12, cluster analysis is performed on the strain information of potential damage Gaussian points in the macro model, specifically: The K-means++ clustering model is used to cluster these damage Gaussian points based on the strain state data, and the cluster centers are determined by repeated probability calculation and roulette wheel selection until all cluster centers remain unchanged.

4. The multi-scale progressive failure analysis method for composite material structures integrating a machine learning model according to claim 1 is characterized in that: The fiber area damage initiation criteria in step S21 include: Fiber stretch damage Fiber compression damage In the formula, is the fiber longitudinal stress, T f and C f are the tensile strength and compressive strength of the fiber, respectively; The matrix region damage initiation criteria in step S21 include: Where I1 and I2 are the first stress invariant and the second stress invariant of the matrix, respectively, σ 11 , σ 22 and σ 33 is the normal stress in three directions of the matrix, σ 12 , σ 23 and σ 13 is the shear stress of the matrix, T m and C m are the tensile strength and compressive strength of the matrix, respectively.

5. The multi-scale progressive failure analysis method for composite material structures integrating a machine learning model according to claim 1, characterized in that: In the step S21, the damage evolution model is used to calculate the damage coefficient, and the material properties are gradually degraded. Specifically, the equivalent displacement is used as the damage variable, the damage coefficient is determined by calculating the equivalent displacement in the damage initial state and the complete failure state, and the elastic constant of the material is multiplied by a degradation coefficient to achieve the gradual degradation of the material properties.

6. The multi-scale progressive failure analysis method for composite material structures integrating a machine learning model according to claim 1, characterized in that: The three-dimensional Hashin criterion in step S22 includes: Fiber damage: Matrix damage: In the formula, σ 11 , σ 22 and σ 33 is the normal stress; σ 12 , σ 13 and σ 23 is the shear stress; X T and X C are the longitudinal tensile and compressive strengths of the composites, respectively; Y T and Y C are the transverse tensile and compressive strengths of the composites, respectively; S 12 , S 13 and S 23 is the shear strength of the composite material.

7. The multi-scale progressive failure analysis method for composite material structures integrating a machine learning model according to claim 1, characterized in that: When establishing the finite element models of the macrostructure and the micro-representative volume unit in step S31, an external load is applied to the macrostructure model, and a periodic boundary condition is applied to the micro-representative volume unit model.

Images