A deep learning-based structural fracture damage simulation method and system

Abstract

The application belongs to the field of structure fracture damage simulation, and provides a structure fracture damage simulation method and system based on deep learning to solve the problem that the prediction accuracy of the whole process of complex fracture behavior depends on network architecture design and optimization algorithm, and the universality is limited. The structure fracture damage simulation method based on deep learning comprises the following steps: constructing a neural network model and setting initial parameters; optimizing the initial parameters of the neural network model based on a sample set and a loss function to obtain a trained neural network model; and predicting the initiation, expansion and bifurcation and merging of cracks in the structure domain based on the current structure geometric parameters, material parameters, boundary conditions and initial crack information by using the trained neural network model to obtain displacement field, stress field and damage evolution results. The method can enhance the adaptability of the model to different working conditions by introducing multi-scale and multi-physical field information.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of structural fracture damage simulation, and particularly relates to a structural fracture damage simulation method and system based on deep learning. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] In the field of computer-aided engineering (CAE), structural analysis and fracture damage prediction have long relied on traditional finite element method (FEM). The FEM method realizes the prediction of structural stress, strain and crack development by weakly equivalent partial differential equations to integral equations and numerical integration on discrete grids. However, in the processing of FEM method, high-precision simulation requires fine grid division in key areas such as crack tip and high stress concentration area, which requires large manual input and complex operation. Due to the approximation of the weak equivalence method, the FEM simulation results have deviations in the prediction of complex fracture behaviors such as crack initiation, propagation, branching and merging. When the model, material or load conditions change, the grid needs to be re-divided and complete numerical solution needs to be executed, lacking computational reusability. Although the integration of deep learning and computer-aided engineering can improve the calculation accuracy and efficiency, there are still problems of limited universality in the full-process prediction accuracy of complex fracture behaviors depending on network architecture design and optimization algorithm. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a structural fracture damage simulation method and system based on deep learning, which can enhance the adaptability of the model to different working conditions.

[0005] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0006] The first aspect of the present application provides a structural fracture damage simulation method based on deep learning.

[0007] In one or more embodiments, a structural fracture damage simulation method based on deep learning is provided, comprising:

[0008] A neural network model is constructed and initial parameters are set;

[0009] The initial parameters of the neural network model are optimized based on a sample set and a loss function, to obtain a trained neural network model; wherein the samples in the sample set are composed of structural geometric parameters, material parameters, boundary conditions, initial crack information, displacement fields, stress fields and damage evolution results; the loss function is a loss function considering the partial differential equation residual of the stress tensor, and the unified target of physical consistency, distribution consistency and prior constraint;

[0010] Based on the current structural geometric parameters, material parameters, boundary conditions and initial crack information, the trained neural network model is used to predict the initiation, propagation and branching and merging of cracks in the structure domain, to obtain the displacement field, stress field and damage evolution result.

[0011] As an implementation, the construction process of the loss function is:

[0012] An energy functional of the structure is constructed based on the criterion of minimizing energy; wherein the energy functional of the structure is obtained by multiplying the tensile energy part and the learnable degradation function representing the automatically adjusted fracture degradation speed, and then adding the compression energy part;

[0013] According to the crack characteristic length of the structure and the effective fracture toughness of the structure, a discretized energy functional of the structure is obtained;

[0014] The energy density in the energy functional of the structure is rasterized into a probability distribution, the second order wasserstein distance is calculated, and then combined with the partial differential equation residual of the stress tensor, the irreversible damage constraint, and the square of the difference between the derivative of the discretized energy functional of the damaged structure with respect to time and the external force input power, to construct the loss function.

[0015] As an implementation, the crack characteristic length of the structure is determined by the size of the strain gradient and the basic length parameter.

[0016] As an implementation, the effective fracture toughness of the structure is represented by the cumulative sum of the weights learned by the neural network model of the mode I crack fracture toughness and the mode II crack fracture toughness.

[0017] As an implementation, the expression of the loss function is:

[0018] ;

[0019] Wherein, is a partial differential equation residual operator, is a stress tensor; , , is a weight coefficient; is an external force input power; is an irreversible damage constraint; is a probability distribution; is derivative with respect to time; is a discretized energy functional; are displacement field and damage variable, respectively.

[0020] As an implementation, the discretized energy functional is expressed as:

[0021] ;

[0022] wherein, is strain energy per unit after numerical discretization of the structure; is a normalization constant; denotes a structure body in which damage occurs; is effective fracture toughness; is a crack characteristic length; is a damage variable gradient; is a ratio of a tensile crack in a crack mode.

[0023] As an implementation, the effective fracture toughness is expressed as:

[0024] ;

[0025] ;

[0026] wherein, is a mode I crack fracture toughness; is a mode II crack fracture toughness; is a strain tensor; is a tensile energy part; is a compression energy part; is a weight learned by a neural network model.

[0027] As an implementation, an expression of an irreversible damage constraint is:

[0028] ;

[0029] wherein, is an irreversible damage constraint; is a damage variable; is a historical maximum damage value; is a smoothing parameter; denotes a structure body in which damage occurs.

[0030] A second aspect of the present application provides a deep learning-based structure fracture damage simulation system.

[0031] In one or more embodiments, a deep learning-based structural fracture damage simulation system comprises:

[0032] a neural network model construction module configured to construct a neural network model and set initial parameters;

[0033] a neural network model training module configured to optimize the initial parameters of the neural network model based on a sample set and a loss function to obtain a trained neural network model; wherein the samples in the sample set are composed of structural geometric parameters, material parameters, boundary conditions, initial crack information, displacement fields, stress fields and damage evolution results; the loss function is a loss function that considers the partial differential equation residual of the stress tensor and the unified target of physical consistency, distribution consistency and prior constraints;

[0034] a structural fracture damage simulation prediction module configured to predict the initiation, propagation and bifurcation and merging of cracks in the structure domain based on the current structural geometric parameters, material parameters, boundary conditions and initial crack information using the trained neural network model to obtain the displacement field, stress field and damage evolution result.

[0035] A third aspect of the present application provides an electronic device.

[0036] An electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the deep learning-based structural fracture damage simulation method as described above when executing the program.

[0037] Compared with the prior art, the beneficial effects of the present application are:

[0038] The present application trains the neural network model using a loss function that considers the partial differential equation residual of the stress tensor and the unified target of physical consistency, distribution consistency and prior constraints, realizes the introduction of multi-scale and multi-physical field information, enhances the adaptability of the neural network model to different working conditions of structural damage, and can ensure that the prediction results are physically reasonable and high-precision; the trained neural network model is used to process the current structural geometric parameters, material parameters, boundary conditions and initial crack information, simulate and predict the corresponding displacement field, stress field and damage evolution result, realize the purpose of accurately capturing complex crack behavior (initiation, propagation, bifurcation and merging), and improve the reliability of structural engineering fracture damage simulation prediction. BRIEF DESCRIPTION OF DRAWINGS

[0039] The drawings accompanying the specification of the present application form a part thereof and serve to provide further understanding of the present application, the illustrative embodiments of the present application and its description serve to explain the present application and do not constitute an improper limitation of the present application.

[0040] Figure 1 is a flowchart of a deep learning-based structure fracture damage simulation method of an embodiment of the present application;

[0041] Figure 2 is a structural diagram of a deep learning-based structure fracture damage simulation system of an embodiment of the present application;

[0042] Figure 3 is a schematic diagram of an electronic device of an embodiment of the present application. DETAILED DESCRIPTION

[0043] The present application will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as would be commonly understood by one of ordinary skill in the art to which the present application belongs.

[0045] It should be noted that the terms used herein are only intended to describe specific embodiments and are not intended to limit exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should also be understood that when the terms "comprise" and / or "include" are used in the specification, they indicate the presence of a feature, step, operation, device, component, and / or combination thereof.

[0046] Term explanation:

[0047] The structural member of the present application can be a metal structural member, such as a bolt / screw, a shaft, a special-shaped member, and a welded structural member, etc. The structural member of the present application can also be a composite material structural member, such as a carbon fiber engine cover, a space carbon fiber tube, etc. After the selected structural member, its structural geometric parameters, material parameters, and boundary conditions can be obtained according to the properties of the structural member, and the initial crack information can be obtained by existing detection technologies such as optical microscope observation method and ultrasonic detection method.

[0048] Embodiment one

[0049] Figure 1 is a flowchart of a deep learning-based structure fracture damage simulation method of an embodiment of the present application, as shown in Figure 1 The deep learning-based structure fracture damage simulation method of the present embodiment can include the following steps S101-S103.

[0050] The specific implementation process of steps S101-S103 is as follows:

[0051] Step S101: Construct a neural network model and set initial parameters.

[0052] The input quantity of the neural network model is structural geometric parameters, material parameters, boundary conditions and initial crack information; the output is a displacement field, a stress field and a damage evolution result. The damage evolution result is a damage variable.

[0053] It should be noted that the specific structure of the neural network model can be selected according to actual conditions.

[0054] Step S102: optimizing initial parameters of the neural network model based on a sample set and a loss function to obtain a trained neural network model; wherein a sample in the sample set is composed of structural geometric parameters, material parameters, boundary conditions, initial crack information, a displacement field, a stress field and a damage evolution result; the loss function is a loss function considering a partial differential equation residual of a stress tensor, and a unified target of physical consistency, distribution consistency and prior constraint.

[0055] In the embodiment of the application, the sample set can be constructed according to experimental data and historical data.

[0056] In this embodiment, the construction process of the loss function is as follows:

[0057] Step a: constructing an energy functional of a structure based on the criterion of minimizing energy; wherein the energy functional of the structure is obtained by multiplying a tensile energy part and a learnable degradation function representing an automatic adjustment of a fracture degradation speed, and then adding a compression energy part;

[0058] The energy functional of the structure is:

[0059]

[0060] wherein, is a structure with damage; is a damage variable, 0 represents intact, and 1 represents complete fracture failure; is a strain tensor; is a tensile energy part; is a compression energy part; is a learnable degradation function, which is determined by a neural network model and can automatically adjust the fracture degradation speed.

[0061] Step b: obtaining a discretized energy functional of the structure according to a crack characteristic length of the structure and an effective fracture toughness of the structure.

[0062] wherein the crack characteristic length of the structure is determined by the size of the strain gradient and the basic length parameter.

[0063] According to the energy functional of the structure ​​Performing structural fracture mechanics analysis to determine the crack characteristic length of the structure: ;

[0064] wherein, l 0 is the basic length parameter, which is the characteristic length parameter adopted by classical fracture mechanics, and its value is usually 3-5 times the average size of the mesh near the crack propagation; is a learnable coefficient; is the size of the strain gradient.

[0065] Characteristic length controls the width of the crack band, when the strain is severe, the crack is more concentrated (i.e. smaller); in the area where the strain is relatively gentle, the crack is more dispersed (i.e. larger).

[0066] Through the neural network model learning and relying on the spatial gradient (i.e. the spatial variation of the load form), the toughness continuously, derivable and self-adaptive transition between the I-type crack (opening-type crack) and II-type crack (shear-type crack) modes, and adapts to the shear-tension coupled fracture. The effective fracture toughness of the structure is expressed as:

[0067] ;

[0068] ;

[0069] wherein, is the I-type crack mode fracture toughness; is the II-type crack mode fracture toughness; is the strain tensor; is the tensile energy part; is the compression energy part; is the weight learned by the neural network model.

[0070] It should be noted here that the I-type crack mode (opening-type crack) fracture toughness and the II-type crack mode (slip-type crack) fracture toughness can be characterized by the strain energy release rate. The effective fracture toughness of the structure can also be characterized by the strain energy release rate.

[0071] The corresponding structure is tested to obtain the I-type crack mode (opening-type crack) fracture toughness and the II-type crack mode (slip-type crack) fracture toughness. For example, through the end notched flexure method (ENF method), by preloading a layered sample through three-point bending, the load-displacement curve during crack propagation is measured, and the strain energy release rate is calculated.

[0072] Step c: discretize the energy density in the energy functional of the structure into a probability distribution, calculate the second-order Wasserstein distance, and combine the stress tensor partial differential equation residual, the irreversible damage constraint, and the square of the difference between the derivative of the discretized energy functional of the damaged structure with respect to time and the external force input power to construct the loss function.

[0073] discretize the energy functional of the structure discretize, discretized energy functional The expression is:

[0074] ;

[0075] In the formula, is the strain energy of the structure after numerical discretization by unit; is a normalization constant; represents the damaged structure; is the effective fracture toughness; is the crack characteristic length; is the damage variable gradient; is the proportion of tensile cracks in the crack mode. In the engineering application of the phase field fracture model, the value of 8 / 3 is often taken.

[0076] In engineering structures, cracks usually cannot heal themselves after they occur. To ensure the irreversibility of the cracks, the irreversible damage constraint is as follows:

[0077] ;

[0078] In the formula, is the irreversible damage constraint; is the damage variable; is the historical maximum damage value; is the smoothing parameter; represents the damaged structure.

[0079] discretize the energy functional of the structure discretize the energy density into a probability distribution, and calculate W2 using the differentiable Sinkhorn approximation:

[0080] ;

[0081] In the formula, is the predicted energy distribution of the model; is the reference energy distribution obtained by experiment or high-precision simulation; is the second-order Wasserstein distance. This method keeps the predicted crack dissipation zone distribution relatively consistent with the reference result.

[0082] Specifically, the expression of the loss function is:

[0083] ;

[0084] wherein, is a partial differential equation residual operator, is a stress tensor; , , is a weight coefficient; is an external force input power; is an irreversible damage constraint; is a probability distribution; is a derivative with respect to time; is a discretized energy functional; are displacement field and damage variable respectively.

[0085] The first term in the loss function ensures that the mechanical equilibrium is satisfied; the second term ensures that the crack is irreversible; the third term ensures that the energy distribution is aligned; and the fourth term ensures that the energy is conserved. The embodiment introduces distribution level alignment to improve the accuracy of crack patterns.

[0086] It should be noted that the trained model can be migrated to similar structures or new load conditions to achieve rapid prediction without complete retraining.

[0087] Step S103: Based on the current structure geometric parameters, material parameters, boundary conditions and initial crack information, the trained neural network model is used to predict the initiation, propagation and bifurcation and merging of cracks in the structure domain to obtain the displacement field, stress field and damage evolution results.

[0088] The embodiment uses a loss function that considers the partial differential equation residual of the stress tensor, and the unified goal of physical consistency, distribution consistency and prior constraint to train the neural network model, which introduces multi-scale and multi-physical field information, enhances the adaptability of the neural network model to different working conditions of structural damage, and ensures that the prediction results are physically reasonable and high-precision; The trained neural network model is used to process the current structure geometric parameters, material parameters, boundary conditions and initial crack information, and the corresponding displacement field, stress field and damage evolution results are simulated and predicted, which realizes the purpose of accurately capturing complex crack behavior (initiation, propagation, bifurcation and merging), and improves the reliability of structural engineering fracture damage simulation and prediction.

[0089] Embodiment Two

[0090] As shown in Figure 2 , the structural fracture damage simulation system based on deep learning provided by the embodiment can be implemented in a software manner, and the structural fracture damage simulation system based on deep learning comprises the following software modules:

[0091] The functions of various software modules in the deep learning-based structural fracture damage simulation system are introduced as follows:

[0092] The neural network model construction module 201 is configured to construct a neural network model and set initial parameters.

[0093] The neural network model training module 202 is configured to optimize the initial parameters of the neural network model based on a sample set and a loss function to obtain a trained neural network model; wherein the samples in the sample set are composed of structural geometric parameters, material parameters, boundary conditions, initial crack information, displacement fields, stress fields and damage evolution results; the loss function is a loss function considering the partial differential equation residual of the stress tensor, and the unified target of physical consistency, distribution consistency and prior constraint;

[0094] The structural fracture damage simulation prediction module 203 is configured to predict the initiation, propagation and bifurcation and merging of cracks in the structure domain based on the current structural geometric parameters, material parameters, boundary conditions and initial crack information using the trained neural network model to obtain the displacement field, stress field and damage evolution result.

[0095] Specifically, in the neural network model training module 202, in the embodiment of the present application, the sample set can be constructed according to experimental data and historical data.

[0096] The structure here can be a metal structural member or other structural member, which can be specifically set by those skilled in the art according to the actual situation, and will not be described in detail here.

[0097] In this embodiment, the construction process of the loss function is as follows:

[0098] Step a: construct the energy functional of the structure based on the criterion of minimizing the energy; wherein the energy functional of the structure is obtained by multiplying the tensile energy part and the learnable degradation function representing the self-adjusting fracture degradation speed, and then adding the compression energy part;

[0099] The energy functional of the structure is:

[0100] ;

[0101] wherein, is the structure with damage; is the damage variable, 0 represents perfect, and 1 represents complete fracture failure; is the strain tensor; is the tensile energy part; is the compression energy part; ​is a learnable degradation function determined by a neural network model, which can automatically adjust the crack degradation speed.

[0102] Step b: Obtain the discretized energy functional of the structure according to the crack characteristic length of the structure and the effective fracture toughness of the structure.

[0103] wherein the crack characteristic length of the structure is determined by the size of the strain gradient and the basic length parameter.

[0104] According to the energy functional of the structure Perform structure fracture mechanics analysis to determine the crack characteristic length of the structure: ;

[0105] wherein, l 0 is the basic length parameter, which is the characteristic length parameter used in classical fracture mechanics, and its value is usually 3-5 times the average size of the mesh near the crack propagation; is a learnable coefficient; is the size of the strain gradient.

[0106] Characteristic length controls the width of the crack zone. When the strain is severe, the crack is more concentrated (i.e. becomes smaller); in the area where the strain is relatively gentle, the crack is more dispersed (i.e. becomes larger).

[0107] Through the neural network model, the spatial gradient (i.e. the spatial variation of the load form) is learned and can be relied on, so that the toughness continuously, derivable and self-adaptive transition between the I-type crack (opening-type crack) and II-type crack (shear-type crack) modes, adapt to shear-tension coupled fracture. The effective fracture toughness of the structure is expressed as:

[0108] ;

[0109] ;

[0110] wherein, is the I-type crack mode fracture toughness; is the II-type crack mode fracture toughness; is the strain tensor; is the tensile energy part; is the compression energy part; is the weight learned by the neural network model.

[0111] Step c: discretize the energy density in the energy functional of the structure into a probability distribution, calculate the second order Wasserstein distance, and combine the stress tensor partial differential equation residual, the irreversible damage constraint, and the square of the difference between the derivative of the discretized energy functional of the damaged structure with respect to time and the external force input power to construct the loss function.

[0112] discretize the energy functional of the structure discretize, discretized energy functional The expression is:

[0113] ;

[0114] In the formula, is the strain energy of the structure after numerical discretization by unit; is a normalization constant; represents the damaged structure; is the effective fracture toughness; is the crack characteristic length; is the damage variable gradient; is the proportion of tensile cracks in the crack mode. In the engineering application of the phase field fracture model, the value of 8 / 3 is often taken.

[0115] In engineering structures, cracks usually cannot heal themselves after they occur. To ensure the irreversibility of the cracks, the irreversible damage constraint is as follows:

[0116] ;

[0117] In the formula, is the irreversible damage constraint; is the damage variable; is the historical maximum damage value; is the smoothing parameter; represents the damaged structure.

[0118] discretize the energy functional of the structure discretize the energy density into a probability distribution, and calculate W2 using the differentiable Sinkhorn approximation:

[0119] ;

[0120] In the formula, is the predicted energy distribution of the model; is the reference energy distribution obtained by experiment or high-precision simulation; is the second order Wasserstein distance. This method keeps the predicted crack dissipation zone distribution relatively consistent with the reference result.

[0121] The method keeps the predicted crack dissipation zone distribution relatively consistent with the reference result.

[0122] Specifically, the expression of the loss function is:

[0123] ;

[0124] wherein, is a partial differential equation residual operator, is a stress tensor; , , is a weight coefficient; is an external force input power; is an irreversible damage constraint; is a probability distribution; is a derivative with respect to time; is a discretized energy functional; are respectively a displacement field and a damage variable.

[0125] The first item in the loss function guarantees to meet the mechanical equilibrium; the second item guarantees the irreversibility of the crack; the third item guarantees the alignment of the energy distribution; and the fourth item guarantees the energy conservation. The embodiment introduces the alignment at the distribution level, thereby improving the accuracy of the crack pattern.

[0126] It should be noted that the trained model is migrated to a similar structure or a new load condition to realize rapid prediction without complete retraining.

[0127] The deep learning-based structure fracture damage simulation system uses the loss function considering the partial differential equation residual of the stress tensor, the unified target of physical consistency, distribution consistency and prior constraint to train the neural network model, realizes the introduction of multi-scale and multi-physical field information, enhances the adaptability of the neural network model to different working conditions of the structure damage, can guarantee that the prediction result is physically reasonable and high-precision; the trained neural network model is used to process the current structure geometric parameters, material parameters, boundary conditions and initial crack information, simulate and predict the corresponding displacement field, stress field and damage evolution result, realize the purpose of accurately capturing the complex crack behavior, and improve the reliability of the structure engineering fracture damage simulation and prediction.

[0128] It should be noted that each module in the deep learning-based structure fracture damage simulation system of the embodiment of the application corresponds to each step in the deep learning-based structure fracture damage simulation method in the above embodiment one by one, and the specific implementation process is the same, which will not be repeated here.

[0129] Embodiment three

[0130] The structure of the electronic device of the embodiment of the application will be described in detail below.Figure 3 The structural diagram of the electronic device provided by the embodiment of the present application can be understood as follows, Figure 3 Only exemplary structures of the electronic device are shown, not all structures, and part or all of the structures shown can be implemented as needed.

[0131] The electronic device provided by the embodiment of the present application comprises at least one processor 301, a memory 302, a user interface 303, and at least one network interface 304. The various components in the deep learning-based structural fracture damage simulation system are coupled together through a bus system 305. It can be understood that the bus system 305 is used to realize the connection communication between the components. In addition to including a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, all the buses are marked as the bus system 305 in Figure 3 .

[0132] The user interface 303 can include a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touchpad, or a touch screen, etc.

[0133] It can be understood that the memory 302 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. The memory 302 in the embodiment of the present application can store data to support the operation of the terminal. Examples of these data include any computer programs for operating on the terminal, such as operating systems and application programs. The operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application program can include various application programs.

[0134] In some embodiments, the deep learning-based structural fracture damage simulation system provided by the embodiment of the present application can be implemented in a combination of software and hardware. As an example, the deep learning-based structural fracture damage simulation system provided by the embodiment of the present application can be a processor in the form of a hardware decoding processor programmed to execute the deep learning-based structural fracture damage simulation method provided by the embodiment of the present application. For example, the processor in the form of a hardware decoding processor can use one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0135] As an example, the processor 301 can be an integrated circuit chip having a processing capability of signals, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor.

[0136] As an example of the hardware implementation of the structure fracture damage simulation system based on deep learning provided by the embodiment of the application, the apparatus provided by the embodiment of the application can directly use the processor 301 in the form of a hardware decoding processor to perform and complete, for example, one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), or other electronic elements to implement the structure fracture damage simulation method based on deep learning provided by the embodiment of the application.

[0137] The memory 302 in the embodiment of the application is used to store various types of data to support the operation of the structure fracture damage simulation system based on deep learning, or store program codes for executing the method shown in the embodiment of the application. Figure 1 Examples of these data include any executable instructions for operating on the structure fracture damage simulation system based on deep learning, such as executable instructions, and the program implementing the structure fracture damage simulation method based on deep learning in the embodiment of the application can be included in the executable instructions.

[0138] In particular, according to the embodiment of the application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiment of the application includes a computer program product comprising a computer program carrying on a computer readable medium, and the computer program contains program codes for executing the method shown in the embodiment of the application. Figure 1 In such an embodiment, the computer program can be downloaded and installed from a network by a communication part, and / or installed from a detachable medium. When the computer program is executed by the central processing unit, various functions defined in the apparatus of the application are performed.

[0139] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions specified in the flowchart block or blocks. Figure 1 The flowchart and / or block diagram in the variation of the present application can be implemented by computer program instructions. These program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing apparatus, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 Figure 1 The flowchart and / or block diagram in the variation of the present application can be implemented by computer program instructions. These program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing apparatus, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowchart and / or block diagram block or blocks.

[0140] The above merely provides the preferred embodiment of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A deep learning-based structural fracture damage simulation method, characterized by, include: Construct a neural network model and set its initial parameters; The initial parameters of the neural network model are optimized based on the sample set and the loss function to obtain the trained neural network model. The samples in the sample set consist of structural geometric parameters, material parameters, boundary conditions, initial crack information, displacement field, stress field and damage evolution results. The loss function is a loss function that considers the residuals of the partial differential equations of the stress tensor and has the unified goal of physical consistency, distribution consistency and prior constraints. Based on the current structural geometric parameters, material parameters, boundary conditions and initial crack information, the trained neural network model is used to predict the initiation, propagation and bifurcation of cracks in the structural domain, and the displacement field, stress field and damage evolution results are obtained. The process of constructing the loss function is as follows: Based on the criterion of minimizing energy, an energy functional of the structure is constructed. The energy functional of the structure is obtained by multiplying the tensile energy part by a learnable degradation function that characterizes the automatically adjusting fracture degradation rate, and then summing it with the compressive energy part. Based on the characteristic crack length and effective fracture toughness of the structure, the discretized energy functional of the structure is obtained. The energy density in the energy functional of the structure is rasterized into a probability distribution, the second-order Wasserstein distance is calculated, and then the loss function is constructed by combining the residual of the partial differential equation of the stress tensor, the irreversible damage constraint, and the square of the difference between the time derivative of the discretized energy functional of the damaged structure and the external force input power. The expression for the loss function is: ； wherein, is a partial differential equation residual operator, is a stress tensor; , , is a weight coefficient; is an external force input power; is an irreversible damage constraint; is a probability distribution; is a derivative with respect to time; is a discretized energy functional; are displacement field and damage variable, respectively. 2.The deep learning-based structural fracture damage simulation method of claim 1, wherein, The characteristic length of a crack in a structure is determined by the magnitude of the strain gradient and the foundation length parameter. 3.The deep learning-based structural fracture damage simulation method of claim 1, wherein, The effective fracture toughness of the structure is characterized by the weight accumulation and summation learned from the neural network model of fracture toughness in both the Type I and Type II crack modes.

4. The deep learning-based structural fracture damage simulation method as described in claim 1, characterized in that, Discretized energy functional The expression for the discretized energy functional is ； In the formula, is the strain energy per unit after numerical discretization of the structure; is a normalization constant; represents the structure that has occurred damage; is the effective fracture toughness; is the crack characteristic length; is the damage variable gradient; is the proportion of tensile cracks in the crack mode.

5. The deep learning-based structural fracture damage simulation method as described in claim 4, characterized in that, effective fracture toughness The expression for the effective fracture toughness is: ； ； wherein, is the mode I crack fracture toughness; is the mode II crack fracture toughness; is the strain tensor; is the tensile energy part; is the compressive energy part; is a weight learned by the neural network model. 6.The deep learning-based structural fracture damage simulation method of claim 1, wherein, The expression for the irreversible damage constraint is: ； wherein, is an irreversible damage constraint; is a damage variable; is a historical maximum damage value; is a smoothing parameter; denotes a structure in which damage occurs.

7. A structural fracture damage simulation system based on deep learning, characterized in that, The method employs the deep learning-based structural fracture damage simulation method as described in any one of claims 1-6, comprising: The neural network model building module is used to build a neural network model and set its initial parameters. The neural network model training module is used to optimize the initial parameters of the neural network model based on the sample set and the loss function to obtain the trained neural network model. The samples in the sample set consist of structural geometric parameters, material parameters, boundary conditions, initial crack information, displacement field, stress field and damage evolution results. The loss function is a loss function that considers the residuals of the partial differential equations of the stress tensor and has the unified goal of physical consistency, distribution consistency and prior constraints. The structural fracture damage simulation and prediction module is used to predict the initiation, propagation, and bifurcation and merging of cracks within the structural domain based on the current structural geometric parameters, material parameters, boundary conditions, and initial crack information, and to obtain the displacement field, stress field, and damage evolution results.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the deep learning-based structural fracture damage simulation method as described in any one of claims 1-6.

Images