Composite material thermochemical ablation calculation method based on physical information neural network

Abstract

The invention provides a composite material thermochemical ablation calculation method based on a physical information neural network, and relates to the technical field of macroscopic thermochemical ablation prediction. The method comprises the following steps: constructing a macroscopic thermochemical ablation reaction equation of the carbon-carbon composite material; constructing a thermal chemical ablation heat conduction equation of the carbon-carbon composite material; constructing a physical information neural network model; constructing a macroscopic geometric model of the carbon-carbon composite material; training a physical information neural network model; inputting the macroscopic thermochemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model to obtain a macroscopic thermochemical ablation behavior prediction result of the carbon-carbon composite material; according to the method, the thermal conduction physical law is embedded into the neural network, deep fusion of data driving and physical constraint is achieved, rapid and high-precision prediction of thermal chemical ablation of the composite material is achieved, and the method has a huge application prospect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of macroscopic thermo-chemical ablation behavior prediction of carbon-carbon composites, and particularly relates to a composite material thermo-chemical ablation calculation method based on a physical information neural network. BACKGROUND

[0002] In the field of aerospace, spacecraft and the like face extremely complex thermal environments. C / C composites have become key materials for thermal protection systems due to their excellent high-temperature mechanical properties, low density and thermal shock resistance. However, under high-temperature, high-speed airflow and other working conditions, C / C composites will undergo complex macroscopic thermo-chemical ablation phenomena, including material mass loss, surface morphology change and the like, which are directly related to the structural safety of the aircraft and the success or failure of the mission. Accurate understanding of the ablation rules is crucial for the design of the thermal protection system. At present, numerical calculation methods are mainly used to solve the macroscopic thermo-chemical ablation of C / C composites. On the one hand, the empirical formula method relies on specific working condition experimental data fitting, has poor generalization ability, and cannot effectively capture the coupling effects of thermal conduction, gas diffusion, chemical reaction and other multi-physical fields, making it difficult to adapt to complex and variable actual flight environments. On the other hand, the method of coupling computational fluid dynamics and ablation model can solve the interaction between the fluid domain and the solid domain, but requires manual definition of a large number of reaction mechanisms, diffusion coefficients and other parameters, resulting in high calculation cost. At the same time, the dynamic ablation boundary needs to frequently reconstruct the grid, resulting in large numerical errors and reducing the calculation accuracy and efficiency.

[0003] Therefore, there is an urgent need for a new composite material macroscopic thermo-chemical ablation behavior prediction method to solve the problems encountered in the prior art. SUMMARY

[0004] The present application provides a composite material thermo-chemical ablation calculation method based on a physical information neural network, which realizes fast and high-precision simulation of the ablation process by fusing data-driven and physical constraints.

[0005] According to a first aspect disclosed by the present application, the present application provides a composite material thermo-chemical ablation calculation method based on a physical information neural network, comprising: constructing a carbon-carbon composite material macroscopic thermo-chemical ablation reaction equation; based on the macroscopic thermo-chemical ablation reaction equation, constructing a carbon-carbon composite material thermo-chemical ablation heat conduction equation; based on the macroscopic thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation, constructing a loss function using a mean square error method, and constructing a physical information neural network model; constructing a carbon-carbon composite material macroscopic geometric model; inputting the carbon-carbon composite material macroscopic geometric model into the physical information neural network model for iterative training to obtain a trained physical information neural network model; The macroscopic thermo-chemical ablation behavior prediction result of the carbon-carbon composite material is obtained by inputting the macroscopic thermo-chemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model.

[0006] The beneficial effects of the above technical solutions are: the present application mainly aims at the problems of multi-physical field coupling difficulty, low calculation efficiency, and poor physical consistency in the numerical calculation of C / C composite material macroscopic thermo-chemical ablation. By embedding the heat conduction physical law into the neural network, the deep fusion of data driving and physical constraints is realized, the dependence on ultra-fine grid and a large amount of experimental data in traditional methods is broken through, and the problems of high calculation cost, complex dynamic boundary processing, and insufficient prediction accuracy of small sample are effectively solved. The present application provides an efficient and reliable calculation method for the rapid design and accurate optimization of hypersonic aircraft and spacecraft thermal protection systems, and promotes the engineering application and technical development of C / C composite materials in extreme thermal environments.

[0007] In a possible implementation, the construction of the carbon-carbon composite material macroscopic thermo-chemical ablation reaction equation includes: Based on the thermo-chemical ablation reaction mechanism of the carbon-carbon composite material and the element mass conservation equation and the thermo-chemical equilibrium equation, the carbon-carbon composite material element macroscopic thermo-chemical ablation reaction equation is constructed; specifically:

[0008] wherein, is the dimensionless mass ablation rate of the wall surface, is the mass concentration of the element, is the mass concentration of the element, represents the molecular weight of the element, represents the average molecular weight, is the total pressure, represents the number of gas components considered in the surface system, represents the number of atoms of the element, represents the partial pressure.

[0009] In a possible implementation, the construction of the carbon-carbon composite material macroscopic thermo-chemical ablation reaction equation includes: Based on the thermo-chemical ablation reaction process of the carbon-carbon composite material and the homogeneity and isotropy of the carbon-carbon composite material, the thermo-chemical ablation heat conduction equation is constructed; specifically:

[0010] wherein, is the density of the carbon-carbon composite material, is the specific heat capacity of the carbon-carbon composite material, T is the temperature, t is the time, and k is the thermal conductivity; The second type of boundary condition is used on the surface of the carbon-carbon composite material, specifically:

[0011] wherein q is the heat flux of the carbon-carbon composite material; The third type of boundary condition is used on the lower boundary of the carbon-carbon composite material, specifically:

[0012] wherein k is the thermal conductivity, h is the convective heat transfer coefficient, is the ambient temperature; Based on the thermal-chemical ablation mass transfer of the carbon-carbon composite material, the mass ablation rate of the surface of the carbon-carbon composite material is calculated according to the dimensionless mass ablation rate; specifically:

[0013] wherein, is the recovery enthalpy, and for the carbon-carbon composite material ; Based on the mass ablation rate, the surface recession rate of the carbon-carbon composite material is calculated; specifically:

[0014] wherein, is the surface recession rate of the carbon-carbon composite material.

[0015] In a feasible implementation, based on the macroscopic thermal-chemical ablation reaction equation and the thermal-chemical ablation heat conduction equation, a loss function is constructed using the mean square error method, and a physical information neural network model is constructed; including: Based on the obtained macroscopic thermal-chemical ablation reaction equation and the thermal-chemical ablation heat conduction equation, a loss function is constructed using the mean square error method, and a physical information neural network model is constructed, which inputs spatial coordinates and time and outputs the temperature field of the carbon-carbon composite material at each time of the thermal-chemical ablation behavior. The physical information neural network model is used to predict the temperature field of the carbon-carbon composite material at different times of the ablation behavior.

[0016] In a feasible implementation, based on the obtained macroscopic thermal-chemical ablation reaction equation and the thermal-chemical ablation heat conduction equation, a loss function is constructed using the mean square error method, and a physical information neural network model is constructed, which inputs spatial coordinates and time and outputs the temperature field of the carbon-carbon composite material at each time of the thermal-chemical ablation behavior. The physical information neural network model is used to predict the temperature field of the carbon-carbon composite material at different times of the ablation behavior; specifically: The space coordinates and time are taken as inputs, and pass through a fully connected layer, each neuron in the fully connected layer is connected with all neurons in the previous layer, each connection corresponds to a weight parameter, and each neuron corresponds to a bias parameter, and the obtained weight parameter and bias parameter are substituted into the physical information neural network, and the specific calculation formula is:

[0017] wherein f is an activation function; w and b are unknown parameters to be optimized of the physical information neural network model, and are weight and bias values of the physical information neural network respectively, and n is a parameter of the physical information neural network; The automatic differentiation technique is used to calculate the derivative terms in the heat conduction equation and the boundary condition; According to the derivative terms, a loss function of the physical information neural network is constructed by using a mean square error; the loss function includes a heat conduction equation residual error, a boundary condition residual error and an initial condition residual error, and a physical information neural network model with an output of a temperature field of the carbon-carbon composite material at each time of a thermo-chemical ablation behavior is obtained. In a feasible implementation, the fully connected layer includes 4 hidden layers, the number of neurons in each hidden layer is 40, and the activation function is Tanh.

[0018] In a feasible implementation, the loss function is composed of a heat conduction equation residual error, a boundary condition residual error and an initial condition residual error, and the calculation formula is:

[0019]

[0020]

[0021] wherein, is the density of the carbon-carbon composite material, is the specific heat capacity of the carbon-carbon composite material, T is the temperature, t is the time, and k is the thermal conductivity, is a network parameter, is the number of data points in the calculation domain, is the number of upper boundary and lower boundary condition training data points, is the number of initial condition training data points, q is the heat flux of the carbon-carbon composite material, and h is the convective heat transfer coefficient, is the ambient temperature, is the temperature at the initial time.

[0022] In a feasible implementation, the carbon-carbon composite material macroscopic geometric model is constructed, and the construction includes: A macroscopic geometric model of carbon-carbon composite material is established, and material properties are given; the material properties include density, specific heat capacity and thermal conductivity; The internal boundary and initial conditions of the model are sampled, and a heat flow is applied to the upper surface of the model, and a convective heat transfer boundary condition is applied to the lower surface.

[0023] In a feasible implementation, the macroscopic geometric model of carbon-carbon composite material is input into the physical information neural network model for iterative training to obtain a trained physical information neural network model; including: Based on the constructed physical information neural network model, a loss function introducing a augmented Lagrangian method is constructed; Based on the loss function introducing the augmented Lagrangian method, a gradient descent optimization algorithm is used to train the constructed physical information neural network to obtain optimal loss function weights and neural network parameters, and a final physical information neural network model with an output of temperature field of carbon-carbon composite material at each time of thermo-chemical ablation behavior is obtained.

[0024] In a feasible implementation, the loss function introducing the augmented Lagrangian method is composed of a heat conduction equation residual, a boundary condition residual and an initial condition residual, wherein the initial condition and the boundary condition residual introduce the initial condition and the boundary condition by the augmented Lagrangian method, and the calculation formula is:

[0025]

[0026]

[0027]

[0028] wherein, is the density of carbon-carbon composite material, is the specific heat capacity of carbon-carbon composite material, T is temperature, is time, is spatial coordinate, k is thermal conductivity, is network parameter, is the number of data points in the calculation domain, is the number of upper boundary and lower boundary condition training data points, is the number of initial condition training data points, q is the heat flux of carbon-carbon composite material, h is the convective heat transfer coefficient, represents the predicted temperature field, is the ambient temperature, is the initial time temperature, represents the residual of the heat conduction equation, and respectively denote the initial condition loss and the boundary loss after introducing the augmented Lagrange, is a predefined constant, is a Lagrange multiplier (regularization coefficient).

[0029] In an implementable embodiment, the method further comprises: inputting the macroscopic thermo-chemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model to obtain temperature changes at different times; based on the temperature, calculating the carbon-carbon composite material recession rate at different temperatures according to a carbon-carbon composite material recession rate calculation formula to obtain a carbon-carbon composite material macroscopic thermo-chemical ablation behavior prediction result.

[0030] According to a second aspect of the present application, the present application provides a composite material thermo-chemical ablation calculation device based on a physical information neural network, comprising: a macroscopic thermo-chemical ablation reaction equation construction module for constructing a macroscopic thermo-chemical ablation reaction equation; a carbon-carbon composite material thermo-chemical ablation heat conduction equation construction module for constructing a carbon-carbon composite material thermo-chemical ablation heat conduction equation; a physical information neural network model construction module for constructing a physical information neural network model based on the macroscopic thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation by using a mean square error method to construct a loss function; a carbon-carbon composite material macroscopic geometric model construction module for constructing a carbon-carbon composite material macroscopic geometric model; a model training module for inputting the carbon-carbon composite material macroscopic geometric model into the physical information neural network model for iterative training to obtain a trained physical information neural network model; a carbon-carbon composite material macroscopic thermo-chemical ablation behavior prediction module for inputting a macroscopic thermo-chemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model to obtain a carbon-carbon composite material macroscopic thermo-chemical ablation behavior prediction result.

[0031] According to a third aspect of the present application, an electronic device is provided, comprising a processor and a memory connected in communication with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method of any one of the first aspect.

[0032] According to a fourth aspect disclosed in the present application, a computer readable storage medium is provided, and the computer readable storage medium stores computer execution instructions, and the computer execution instructions are used to implement the method in any one of the first aspect when executed by a processor.

[0033] According to a fifth aspect disclosed in the present application, a computer program product is provided, and the computer program product comprises a computer program, and the computer program is used to implement the method in any one of the first aspect when executed by a processor.

[0034] Compared with the prior art, the present application has the following beneficial effects: The present application embeds the heat conduction physical law into the neural network, realizes the deep integration of data driving and physical constraints, breaks through the dependence of traditional methods on ultra-fine grids and a large amount of experimental data, and effectively solves the problems of high calculation cost, complex dynamic boundary processing, and insufficient prediction accuracy of small samples. At the same time, it ensures that the prediction result strictly follows the physical laws such as conservation of mass and conservation of energy, provides an efficient and reliable calculation means for rapid design and accurate optimization of hypersonic aircraft and spacecraft thermal protection systems, and promotes the engineering application and technical development of C / C composite materials in extreme thermal environments. BRIEF DESCRIPTION OF DRAWINGS

[0035] The drawings incorporated into the specification and forming a part thereof show embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0036] Figure 1 A flowchart of a composite material thermo-chemical ablation calculation method provided by an embodiment of the present application is shown in the figure. Figure 2 A structure diagram of mass conservation of surface elements of a composite material provided by an embodiment of the present application is shown in the figure. Figure 3 A schematic diagram of a constructed physical information neural network model provided by an embodiment of the present application is shown in the figure. Figure 4 A structure diagram of a composite material geometric model provided by an embodiment of the present application is shown in the figure. Figure 5 A structure diagram of internal and boundary output sampling points of a constructed physical information neural network model provided by an embodiment of the present application is shown in the figure. Figure 6 A schematic diagram of a predicted temperature field and surface recession change of a composite material at different times provided by an embodiment of the present application is shown in the figure. Figure 7 A structure diagram of a composite material thermo-chemical ablation calculation device provided by an embodiment of the present application is shown in the figure. Figure 8 A structure diagram of an electronic device provided by an embodiment of the present application is shown in the figure.

[0037] The present application has been shown and described with reference to the preferred embodiments. Equivalent mechanisms of the application can be implemented or performed with other structures or methods. Other structures or methods that are functionally equivalent to those described herein can be substituted for the ones described and illustrated. Although a general description of the application has been made above, various modifications can be made to, and equivalents of, the above described implementations. Therefore, no limitation is implied based on the description as recited in the specification. Without intent to limit the scope of the application, examples of instruments and methods applicable to an example mode for operation can include select ones numerated or other like equipment. No limitation is intended based on the instrument and / or methods illustrated and / or described. DETAILED DESCRIPTION

[0038] The exemplary embodiments will be described in detail with reference to the drawings. The following description is merely exemplary in nature and is not intended to limit the present application or its application and uses. Furthermore, there is no intention to be bound by any expressed or implied theory presented in the preceding background of the application or the following detailed description.

[0039] In order to improve the efficient calculation method of the macroscopic thermo-chemical ablation behavior of composite materials, the application provides a composite material macroscopic thermo-chemical ablation behavior calculation method based on physical information neural network; the application realizes rapid and high-precision simulation of the carbon-carbon composite material macroscopic thermo-chemical ablation process by fusing data driving and physical constraints.

[0040] The technical scheme of the composite material thermo-chemical ablation calculation method based on physical information neural network provided by the application will be described in detail below through specific embodiments. It should be noted that the following embodiments can exist independently, or can be combined with each other. For the same or similar content, it can not be repeated in different embodiments.

[0041] Figure 1 A flowchart of a composite material thermo-chemical ablation calculation method based on physical information neural network provided by an embodiment of the application is shown in FIG. 1. Figure 1 In some embodiments, the flow of the composite material thermo-chemical ablation calculation method based on physical information neural network includes the following steps: S101, constructing a carbon-carbon composite material macroscopic thermo-chemical ablation reaction equation; S102, based on the macroscopic thermo-chemical ablation reaction equation, constructing a carbon-carbon composite material thermo-chemical ablation heat conduction equation; S103, based on the macroscopic thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation, constructing a loss function by using a mean square error method, and constructing a physical information neural network model; S104, constructing a carbon-carbon composite material macroscopic geometric model; S105, constructing a carbon-carbon composite material macroscopic geometric model; S106, input the macroscopic thermo-chemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model, and obtain a carbon-carbon composite material macroscopic thermo-chemical ablation behavior prediction result.

[0042] In step S101, the specific steps of constructing the carbon-carbon composite material macroscopic thermo-chemical ablation reaction equation are as follows: Based on the thermo-chemical ablation reaction mechanism of carbon-carbon composite material and the element mass conservation equation and the thermo-chemical equilibrium equation, the element macroscopic thermo-chemical ablation reaction equation of carbon-carbon composite material is constructed; specifically: C / C composite material is composed of carbon fiber and carbon matrix, and contains mainly carbon except a small amount of impurities; with the change of temperature from low to high, the thermo-chemical ablation reaction of C / C composite material mainly includes the oxidation of carbon, the carbon-nitrogen reaction and the sublimation process of carbon; based on these ablation mechanisms, the mass ablation rate of the material can be obtained by solving the element mass conservation equation and the thermo-chemical equilibrium equation; as shown in Figure 2 The mass loss flux of the element mainly includes the diffusion mass flux and the convection mass flux, and its expression is:

[0043]

[0044] wherein, is the mass loss rate of the solid element on the ablation surface, is the diffusion of the element, is the element mass concentration in the solid mass loss, is the gas mass flow rate overflowing the surface, is the mass concentration of the element, is the gas flow density of the boundary layer; is the gas velocity of the boundary layer; is the dimensionless mass exchange coefficient; is the dimensionless mass ablation rate of the wall surface; in the above formula can also be expressed by the gas mass fraction in the system, that is:

[0045] wherein, is the molecular weight of the element; is the average molecular weight; is the total pressure; is the number of gas components considered in the surface system; is the number of atoms of the element; is the partial pressure; The thermo-chemical ablation equation of each element in the system can be obtained by combining the above equations:

[0046] In step S102, based on the macroscopic thermo-chemical ablation reaction equation, a carbon-carbon composite material thermo-chemical ablation heat conduction equation is constructed; the specific steps are: Based on the thermo-chemical ablation reaction process of carbon-carbon composite material and the homogeneity and isotropy of carbon-carbon composite material, a thermo-chemical ablation heat conduction equation is constructed; specifically: A large amount of heat is generated in the ablation boundary layer based on the thermo-chemical ablation equation, and when these heat enters the interior of the structure, it is a heat and mass transfer process. At this time, the surface thermo-chemical ablation of C / C composite material will cause mass loss and carry away surface heat, which is a multi-physical field problem involving heat and mass transfer. When solving the problem of thermo-chemical ablation heat transfer on a macroscopic scale, C / C composite material is usually regarded as a homogeneous isotropic material, and its heat conduction equation is:

[0047] wherein, is the density of C / C composite material; is the specific heat capacity of C / C composite material; T is the temperature; t is the time; k is the thermal conductivity; wherein, the second type of boundary condition is adopted on the ablation surface, that is:

[0048] wherein, q is the heat flux of C / C composite material; the energy balance through the ablation wall is determined; The convective heat transfer boundary condition (third type of boundary condition) is adopted on the lower boundary, that is:

[0049] wherein, k is the thermal conductivity, h is the convective heat transfer coefficient, is the environmental temperature; For the mass transfer problem of thermo-chemical ablation of C / C composite material, the mass ablation rate of the material surface is calculated according to the dimensionless mass ablation rate:

[0050] wherein, is the recovery enthalpy, and for carbon-carbon composite material ; Based on the above mass ablation rate formula, the surface recession rate of C / C composite material is: .

[0051] In step S103, based on the macroscopic thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation, a loss function is constructed by using a mean square error method, and a physical information neural network model is constructed; the specific steps are as follows: Based on the obtained macroscopic thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation, a loss function is constructed by using a mean square error method, and a physical information neural network model is constructed, which inputs spatial coordinates and time and outputs the temperature field of the carbon-carbon composite material at each time of the thermo-chemical ablation behavior; the physical information neural network model is used to predict the temperature field of the carbon-carbon composite material at different times of the ablation behavior; Specifically, according to an embodiment of the present application, based on the above-mentioned thermo-chemical ablation theory and heat and mass transfer equation and deep neural network framework, the equation is solved, and the corresponding heat conduction physical information neural network model is established; first, the spatial coordinates x and the time t are input, and then pass through the full connection layer, wherein each neuron in the full connection layer is connected with all the neurons of the previous layer, each connection corresponds to a weight parameter, and each neuron corresponds to a bias parameter; the obtained weight parameter and bias parameter are substituted into the physical information neural network, and the corresponding mathematical expression is:

[0052] Wherein, f is an activation function, which can be ReLU, Sigmoid and Tanh, etc.; w and b are unknown parameters to be optimized in the neural network model, which are the weight and bias of the neural network, respectively; n is the parameter of the physical information neural network; wherein the full connection layer includes 4 hidden layers, the number of neurons in each hidden layer is 40, and the activation function is Tanh; Then, the automatic differentiation technique is used to solve the derivative terms in the heat conduction equation and the boundary conditions, and the temperature T is obtained as the output layer, so as to obtain the physical information neural network model with the temperature field of the carbon-carbon composite material at each time of the thermo-chemical ablation behavior as the output; in the physical information neural network, the construction of the loss function is the core step of integrating the physical law into deep learning; therefore, the mean square error loss is used to construct the loss function, that is, the loss of each part in the heat conduction equation, the boundary condition and the initial condition is calculated, and finally the gradient descent algorithm in the deep neural network is used to optimize the network parameters; the specific process is as shown in Figure 3 Wherein, the loss function mainly includes the heat conduction equation residual, the upper boundary and the lower boundary residual, and the initial condition residual, and the mathematical expression can be written as:

[0053]

[0054]

[0055]

[0056] wherein, is the density of the C / C composite material, is the specific heat capacity of the C / C composite material, T is the temperature, t is the time, k is the thermal conductivity, is the network parameter, is the number of data points in the domain, is the number of training data points of the upper and lower boundary conditions, is the number of training data points of the initial conditions, q is the heat flux of the C / C composite material, h is the convective heat transfer coefficient, is the ambient temperature, is the temperature at the initial time; In step S104, a carbon-carbon composite material macroscopic geometric model is constructed; the specific steps are: According to one embodiment of the present application, a macroscopic geometric model of the C / C composite material is established, and the model is given material properties, such as Figure 4 as shown, for example, density, specific heat capacity and thermal conductivity; then the internal, boundary and initial conditions of the model are sampled, as shown in Figure 5 ; finally, heat flux is applied to the upper surface of the model, and convective heat transfer boundary conditions are applied to the lower surface.

[0057] In step S105, the carbon-carbon composite material macroscopic geometric model is input into the physical information neural network model for iterative training to obtain a trained physical information neural network model; the specific steps are: The carbon-carbon composite material macroscopic geometric model is input into the physical information neural network model for iterative training to obtain a trained physical information neural network model; Based on the constructed physical information neural network model, a loss function introducing the augmented Lagrangian method is constructed; Based on the loss function introducing the augmented Lagrangian method, a gradient descent optimization algorithm is used to train the constructed physical information neural network to obtain the optimal loss function weight and neural network parameter, and the final physical information neural network model whose output is the temperature field of the carbon-carbon composite material at each time of thermal-chemical ablation behavior is obtained; According to one embodiment of the present application, the specific process is: when solving the heat conduction equation based on the physical information neural network and the macroscopic geometric model, the initial conditions and boundary conditions are applied in the form of loss, that is, "soft constraint"; this type of constraint sometimes cannot effectively apply the initial conditions and boundary conditions, especially for transient heat conduction problems; if the initial conditions and boundary conditions cannot be effectively applied, the training of the network is easy to fall into wrong solution and trivial solution; therefore, the augmented Lagrangian method is introduced in the residual of the initial conditions and boundary conditions to effectively apply the initial conditions and boundary conditions; then the loss function can be rewritten as:

[0058]

[0059]

[0060]

[0061] wherein, is the density of the C / C composite material, is the specific heat capacity of the C / C composite material, and T is the temperature, is the time, is the spatial coordinate, and k is the thermal conductivity, is the network parameter, is the number of data points in the calculation domain, is the number of training data points for the upper boundary and lower boundary conditions, is the number of training data points for the initial conditions, q is the heat flux of the C / C composite material, and h is the convective heat transfer coefficient, is the ambient temperature, is the temperature at the initial time, represents the residual of the heat conduction equation, and respectively represent the initial condition loss and the boundary loss after introducing the augmented Lagrange, is a predefined constant, is a lower bound that exists; Based on the improved loss function described above, the constructed physical information neural network is trained using a gradient descent optimization algorithm, and the network parameters are constantly updated to , and approximate the minimum value, so that the loss function is minimized, ensuring that the physical laws of the heat conduction equation are satisfied at all domain data points, thereby realizing the solution of the heat conduction equation.

[0062] In step S106, the macroscopic thermo-chemical ablation carbon-carbon composite material to be detected is input into the trained physical information neural network model to obtain the prediction result of the macroscopic thermo-chemical ablation behavior of the carbon-carbon composite material; the specific steps are as follows: Based on the trained physical information neural network described above, the macroscopic thermo-chemical ablation carbon-carbon composite material to be detected is input into the trained physical information neural network model to obtain the temperature change at different times; then based on the temperature, the C / C composite material recession rate at different temperatures is obtained according to the carbon-carbon composite material surface recession rate calculation formula, such as Figure 6The physical information neural network is compared with the existing comsol numerical simulation results, and the calculation accuracy and efficiency of the physical information neural network are improved without dividing the grid.

[0063] The application embeds the heat conduction physical law into the neural network, realizes the deep integration of data driving and physical constraints, breaks through the dependence of traditional methods on ultra-fine grids and a large amount of experimental data, effectively solves the problems of high calculation cost, complex dynamic boundary processing and insufficient small sample prediction accuracy; at the same time, by strictly following the physical laws such as mass conservation and energy conservation, an efficient and reliable calculation means is provided for rapid design and accurate optimization of hypersonic aircraft and spacecraft thermal protection systems, and the engineering application and technical development of C / C composite materials in extreme thermal environments are promoted.

[0064] Figure 7 is a structural schematic diagram of a composite material thermo-chemical ablation calculation device based on a physical information neural network provided by an embodiment of the application, referring to Figure 7 The thermo-chemical ablation calculation device includes various functional modules for implementing the foregoing thermo-chemical ablation calculation method, and any functional module can be realized by software and / or hardware.

[0065] In some embodiments, the composite material thermo-chemical ablation calculation device 1000 based on the physical information neural network includes a macro thermo-chemical ablation reaction equation construction module 1001, a carbon-carbon composite material thermo-chemical ablation heat conduction equation construction module 1002, a physical information neural network model construction module 1003, a carbon-carbon composite material macro geometric model construction module 1004, a model training module 1005, and a carbon-carbon composite material macro thermo-chemical ablation behavior prediction module 1006; wherein: The macro thermo-chemical ablation reaction equation construction module 1001 is configured to construct a macro thermo-chemical ablation reaction equation; The carbon-carbon composite material thermo-chemical ablation heat conduction equation construction module 1002 is configured to construct a carbon-carbon composite material thermo-chemical ablation heat conduction equation; The physical information neural network model construction module 1003 is configured to construct a physical information neural network model based on the macro thermo-chemical ablation reaction equation and the thermo-chemical ablation heat conduction equation, and construct a loss function using a mean square error method; The carbon-carbon composite material macro geometric model construction module 1004 is configured to construct a carbon-carbon composite material macro geometric model; The model training module 1005 is configured to input the carbon-carbon composite material macro geometric model into the physical information neural network model for iterative training to obtain a trained physical information neural network model; The carbon-carbon composite macroscopic thermo-chemical ablation behavior prediction module 1006 is configured to input the macroscopic thermo-chemical ablation carbon-carbon composite to be detected into the trained physical information neural network model to obtain a carbon-carbon composite macroscopic thermo-chemical ablation behavior prediction result.

[0066] The composite material thermo-chemical ablation calculation device 1000 provided by the embodiments of the present application is configured to execute the technical solutions provided by the foregoing method embodiments for predicting the thermo-chemical ablation of composite materials, and has similar implementation principles and technical effects to those of the foregoing method embodiments, which will not be described here again.

[0067] It should be noted that the division of each module of the foregoing device is only a logical functional division, and all or part of the modules can be integrated onto one physical entity or physically separated when actually implemented. Furthermore, the modules can all be implemented in the form of software invoked by a processing element, or all be implemented in the form of hardware, or part of the modules be implemented in the form of software invoked by a processing element and part of the modules be implemented in the form of hardware.

[0068] Figure 8 A structural schematic diagram of an electronic device provided by the embodiments of the present application is shown in FIG. 11. Figure 8 The electronic device 1100 includes a processor 1101 and a memory 1102 communicatively connected to the processor 1101. The memory 1102 stores computer execution instructions. The processor 1101 executes the computer execution instructions stored in the memory 1102 to implement the technical solutions of the foregoing method for predicting the thermo-chemical ablation of composite materials.

[0069] In the electronic device 1100 described above, the memory 1102 and the processor 1101 are directly or indirectly electrically connected to realize the transmission or interaction of data. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines, such as through bus connection. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus. The memory 1102 stores computer execution instructions for implementing the above-mentioned composite material macroscopic thermo-chemical ablation behavior prediction method, including at least one software function module stored in the memory 1102 in the form of software or firmware, and the processor 1101 executes various function applications and data processing by running the software program and module stored in the memory 1102.

[0070] The memory 1102 at least includes one type of readable storage medium, not limited to Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory 1102 is used to store programs, and the processor 1101 executes the programs after receiving execution instructions. Further, the software program and module in the above-mentioned memory 1102 can also include an operating system, which can include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and can communicate with various hardware or software components to provide an operating environment for other software components.

[0071] The processor 1101 can be an integrated circuit chip having a processing capability of signals. The processor 1101 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application specific integrated circuit (ASIC), etc. The processor can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor, or the processor 1101 can also be any conventional processor or the like.

[0072] The electronic device 1100 is configured to implement the technical solutions provided by the composite material thermal chemical ablation prediction method embodiments, and the implementation principles and technical effects are similar to those of the method embodiments, which will not be described here.

[0073] The embodiments of the present application also provide a computer readable storage medium, which stores computer execution instructions, and when the processor executes the computer execution instructions, the technical solutions of the composite material thermal chemical ablation prediction method are realized.

[0074] The computer readable storage medium described above can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The computer readable storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0075] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium, and can write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the control device of the composite material macroscopic thermal chemical ablation behavior calculation device.

[0076] The embodiment of the present application further provides a computer program product comprising a computer program which, when executed by a processor, is configured to implement the technical solutions of the composite material thermal chemical ablation prediction method.

[0077] In the above embodiments, those skilled in the art can understand that the implementation of the above method embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When implemented by software, it can be realized in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless network, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0078] It should be understood that the present application is not limited to the precise construction that has been described above and illustrated in the accompanying drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for calculating the thermochemical ablation of composite materials based on a physical information neural network, characterized in that, include: Construct macroscopic thermochemical ablation reaction equations for carbon-carbon composite materials; Based on the macroscopic thermochemical ablation reaction equation, a thermochemical ablation heat conduction equation for carbon-carbon composite materials is constructed. Based on the macroscopic thermochemical ablation reaction equation and the thermochemical ablation heat conduction equation, a loss function is constructed using the mean square error method, and a physical information neural network model is built. Construct a macroscopic geometric model of carbon-carbon composite materials; The macroscopic geometric model of the carbon-carbon composite material is input into the physical information neural network model for iterative training to obtain the trained physical information neural network model. The macroscopic thermochemical ablation behavior of the carbon-carbon composite material to be tested is input into the trained physical information neural network model to obtain the prediction results of the macroscopic thermochemical ablation behavior of the carbon-carbon composite material.

2. The method according to claim 1, characterized in that, The macroscopic thermochemical ablation reaction equation for constructing carbon-carbon composite materials includes: Based on the thermochemical ablation reaction mechanism of carbon-carbon composite materials and the elemental mass conservation equation and thermochemical equilibrium equation, a macroscopic thermochemical ablation reaction equation for carbon-carbon composite materials is constructed; specifically: in, It is the dimensionless mass ablation rate of the wall surface. Mass concentration of elements Mass concentration of elements Indicates the molecular weight of an element. This represents the average molecular weight. It is the total pressure. This indicates the number of gas components considered in the surface system. Indicates the number of atoms of an element. This indicates partial pressure.

3. The method according to claim 1, characterized in that, The construction of a thermal conduction equation for the thermal ablation of carbon-carbon composite materials based on the macroscopic thermochemical ablation reaction equation includes: Based on the thermochemical ablation reaction process of carbon-carbon composite materials and the homogeneity and isotropy of carbon-carbon composite materials, a thermochemical ablation heat conduction equation is constructed; specifically: in, The density of carbon-carbon composite materials, t is the specific heat capacity of carbon-carbon composite material, where T is temperature, t is time, and k is thermal conductivity. The second type of boundary condition is applied to the surface of the carbon-carbon composite material, specifically: Where q is the heat flux of the carbon-carbon composite material; A third type of boundary condition is used at the lower boundary of the carbon-carbon composite material, specifically: Where k is the thermal conductivity and h is the convective heat transfer coefficient. The ambient temperature; Based on the thermochemical ablation mass transfer of carbon-carbon composite materials, the mass ablation rate of the carbon-carbon composite surface is calculated according to the dimensionless mass ablation rate; specifically: in, To restore enthalpy, and for carbon-carbon composite materials ; Based on the aforementioned mass ablation rate, the surface retreat rate of the carbon-carbon composite material was calculated; specifically: in, The surface receding rate of carbon-carbon composite materials.

4. The method according to claim 3, characterized in that, Based on the aforementioned macroscopic thermochemical ablation reaction equation and thermochemical ablation heat conduction equation, a loss function is constructed using the mean square error method, and a physical information neural network model is built; including: Based on the obtained macroscopic thermochemical ablation reaction equation and thermochemical ablation heat conduction equation, a loss function is constructed using the mean square error method. A physical information neural network model is established with spatial coordinates and time as inputs and the temperature field at various moments of the thermochemical ablation behavior of carbon-carbon composite materials as outputs. The physical information neural network model is then used to predict the temperature field at different moments of the ablation behavior of carbon-carbon composite materials.

5. The method according to claim 4, characterized in that, Based on the obtained macroscopic thermochemical ablation reaction equation and thermochemical ablation heat conduction equation, a loss function is constructed using the mean square error method. A physical information neural network model is then established, with spatial coordinates and time as inputs and the temperature field at various moments in the thermochemical ablation behavior of the carbon-carbon composite material as the output. This physical information neural network model is used to predict the temperature field at different moments in the ablation behavior of the carbon-carbon composite material. Specifically: Taking spatial coordinates and time as input, the data is passed through a fully connected layer. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and each connection corresponds to a weight parameter. Each neuron corresponds to a bias parameter. Substituting the obtained weight parameters and bias parameters into the physical information neural network, the specific calculation formula is as follows: Where f is the activation function; w and b are the unknown parameters to be optimized in the physical information neural network model, which are the weights and biases of the physical information neural network, respectively, and n is the parameter of the physical information neural network. Automatic differentiation techniques are used to calculate the derivative terms in the heat conduction equation and boundary conditions. Based on the derivative term, a loss function for the physical information neural network is constructed using mean square error. The loss function includes the residuals of the heat conduction equation, the boundary conditions, and the initial conditions, resulting in a physical information neural network model whose output is the temperature field at various moments of the thermochemical ablation behavior of carbon-carbon composite materials.

6. The method according to claim 5, characterized in that, The fully connected layer includes four hidden layers, each with 40 neurons and an activation function of Tanh.

7. The method according to claim 5, characterized in that, The loss function consists of the residuals of the heat conduction equation, the residuals of the boundary conditions, and the residuals of the initial conditions, and its calculation formula is as follows: in, The density of carbon-carbon composite materials, denoted as , where T is the specific heat capacity of the carbon-carbon composite material, t is the temperature, t is the time, and k is the thermal conductivity. For network parameters, To calculate the number of data points within the domain, The number of training data points for the upper and lower boundary conditions. q represents the number of initial training data points, q represents the heat flux of the carbon-carbon composite material, and h represents the convective heat transfer coefficient. For ambient temperature, The initial temperature.

8. The method according to claim 7, characterized in that, The construction of the macroscopic geometric model of carbon-carbon composite materials includes: A macroscopic geometric model of carbon-carbon composite materials is established and material properties are assigned to it; the material properties include density, specific heat capacity and thermal conductivity. Next, sampling points are taken for the internal boundary and initial conditions of the model. Heat flow is applied to the upper surface of the model, and convective heat transfer boundary conditions are applied to the lower surface.

9. The method according to claim 8, characterized in that, The macroscopic geometric model of the carbon-carbon composite material is input into the physical information neural network model for iterative training to obtain the trained physical information neural network model; including: Based on the constructed physical information neural network model, a loss function using the augmented Lagrange method is introduced. Based on the loss function of the augmented Lagrange method, the constructed physical information neural network is trained using the gradient descent optimization algorithm to obtain the optimal loss function weights and neural network parameters, resulting in the final physical information neural network model whose output is the temperature field at various times of the thermochemical ablation behavior of carbon-carbon composite materials.

10. The method according to claim 9, characterized in that, The loss function introduced by the augmented Lagrangian method consists of the residuals of the heat conduction equation, the boundary conditions, and the initial conditions. The initial and boundary conditions residuals are applied using the augmented Lagrangian method, and their calculation formulas are as follows: in, For the density of carbon-carbon composite materials, The specific heat capacity of the carbon-carbon composite material is given by T, where T is the temperature. For time, Let k be the spatial coordinates and k be the thermal conductivity. For network parameters, To calculate the number of data points within the domain, The number of training data points for the upper and lower boundary conditions. q represents the number of initial training data points, q represents the heat flux of the carbon-carbon composite material, and h represents the convective heat transfer coefficient. This represents the predicted temperature field. For ambient temperature, The initial temperature. This represents the residual of the heat conduction equation. and Let these represent the initial conditional loss and boundary loss after introducing the augmented Lagrange multiplier, respectively. For predefined constants, It is a Lagrange multiplier.

11. The method according to claim 1, characterized in that, The step of inputting the macroscopic thermochemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model to obtain the prediction result of the macroscopic thermochemical ablation behavior of the carbon-carbon composite material includes: The macroscopic thermochemical ablation carbon-carbon composite material to be tested is input into the trained physical information neural network model to obtain the temperature changes at different times. Based on the temperature, the surface retreat rate of carbon-carbon composite materials is calculated according to the formula for calculating the retreat rate of carbon-carbon composite materials at different temperatures, and the prediction results of the macroscopic thermochemical ablation behavior of carbon-carbon composite materials are obtained.

12. A composite material thermochemical ablation calculation device based on a physical information neural network, characterized in that, include: The macroscopic thermochemical ablation reaction equation construction module is used to construct macroscopic thermochemical ablation reaction equations. A module for constructing thermochemical ablation heat conduction equations for carbon-carbon composite materials is used to construct thermochemical ablation heat conduction equations for carbon-carbon composite materials. The physical information neural network model construction module is used to construct a physical information neural network model based on the macroscopic thermochemical ablation reaction equation and the thermochemical ablation heat conduction equation, using the mean square error method to construct a loss function. The macroscopic geometric model building module for carbon-carbon composite materials is used to build macroscopic geometric models of carbon-carbon composite materials. The model training module is used to input the macroscopic geometric model of the carbon-carbon composite material into the physical information neural network model for iterative training to obtain the trained physical information neural network model. The macroscopic thermochemical ablation behavior prediction module for carbon-carbon composite materials is used to input the macroscopic thermochemical ablation carbon-carbon composite material to be detected into the trained physical information neural network model to obtain the prediction results of the macroscopic thermochemical ablation behavior of the carbon-carbon composite material.

13. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 11.

Images