Method and device for constructing heat flow field of hydrogen rocket diffuser, medium and equipment

Abstract

The invention discloses a hydrogen rocket diffuser heat flow field construction method and device, a medium and equipment, and relates to the technical field of aerospace propulsion. According to the method, secondary throat diffuser ground high-modulus test numerical simulation is firstly carried out to obtain a large amount of secondary throat diffuser heat flow field sample data, then XX is taken as a physical constraint, a DNN network is trained through the sample data, and a diffuser heat flow field prediction model is obtained. According to the method, the heat flow field of the secondary throat diffuser is quickly and accurately reconstructed through the diffuser heat flow field prediction model, the construction precision and efficiency of the heat flow field of the secondary throat diffuser are improved, and the requirements of quick flow field analysis and real-time working condition evaluation in aerospace engine design can be met.

Description

Technical Field

[0001] The present invention relates to the field of aerospace propulsion technology, and in particular to a method, device, medium and equipment for constructing a thermal flow field of a hydrogen rocket diffuser. Background Art

[0002] Currently, hydrogen rockets, with their high specific impulse and low pollution characteristics, have become a core choice for launch vehicle propulsion systems in modern aerospace engine design. As a key component for regulating the gas flow field and improving engine performance, the secondary throat diffuser (SSDF) requires precise reconstruction of its internal thermal flow field (including temperature, pressure, velocity, and wall heat flux density distribution) for engine thermal protection design, combustion efficiency optimization, and reliability assessment.

[0003] Conventional thermal flow field analysis relies on computational fluid dynamics (CFD) methods, which solve governing equations such as the Navier-Stokes equations and the energy conservation equation to determine the flow field distribution. However, this method suffers from computational overhead (a single simulation can take hours to days), high hardware resource requirements (requiring a high-performance computing cluster), and insufficient real-time performance when faced with complex geometries (such as variable-section expansion sections and multiphase flow coupling) and extreme operating conditions (high pressure, low temperature, and severe turbulence). This makes it difficult to meet the demands for rapid flow field construction and evaluation in iterative engine design. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, medium and equipment for constructing the thermal flow field of a hydrogen rocket diffuser to address the above technical problems.

[0005] The present invention adopts the following technical solutions:

[0006] The present invention provides a method for constructing a thermal flow field of a hydrogen rocket diffuser, comprising:

[0007] Obtain equipment parameters, operating parameters, and environmental parameters of secondary throat diffusers for ground high-speed model tests;

[0008] Based on the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers, a physical model for the corresponding secondary throat diffuser ground high-modulus test was established, and computational fluid dynamics numerical simulation was performed to obtain the corresponding secondary throat diffuser thermal flow field data;

[0009] The equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers are input into the DNN network to obtain the predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with the conservation of mass and energy in the thermal flow field as constraints and the optimization goal of minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field to obtain a diffuser thermal flow field prediction model.

[0010] The equipment parameters, operating parameters and environmental parameters of the secondary throat diffuser when the rocket engine is working are input into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is working.

[0011] Optionally, the equipment parameters of the secondary throat diffuser include: diffuser size of the secondary throat diffuser;

[0012] The operating parameters of the secondary throat diffuser include: test environment, total pressure of the combustion chamber, total temperature of the gas, gas composition inside the diffuser, and physical properties of the gas composition;

[0013] The environmental parameters of the ground high-modulus test of the secondary throat diffuser include: the ambient temperature and the ambient pressure when the diffuser is working.

[0014] Optionally, establishing a physical model for a ground high-modulus test of a corresponding secondary throat diffuser based on equipment parameters, operating parameters, and environmental parameters of the various secondary throat diffusers specifically includes:

[0015] Establish the structure of the secondary throat diffuser in the working scenario under various equipment parameters of the secondary throat diffuser;

[0016] Determine the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is operating based on the corresponding operating parameters and environmental parameters;

[0017] According to the structure of the corresponding secondary throat diffuser in the working scene, a geometric model is established and meshing is performed;

[0018] Based on the divided grid and the corresponding environmental parameters, the boundary conditions are set, and the physical model of the corresponding secondary throat diffuser ground high-modulus test is established in combination with the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is working.

[0019] Optionally, performing computational fluid dynamics numerical simulation to obtain corresponding thermal flow field data of the secondary throat diffuser specifically includes:

[0020] Computational fluid dynamics numerical simulation is performed based on the physical model of the corresponding secondary throat diffuser ground high-modulus test to solve the mass conservation equation, momentum conservation equation, energy conservation equation and turbulent component transport equation to obtain the corresponding secondary throat diffuser thermal flow field data;

[0021] Among them, the secondary throat diffuser thermal flow field data includes: secondary throat diffuser thermal flow field hydrogen pressure distribution, secondary throat diffuser thermal flow field hydrogen axial velocity distribution, secondary throat diffuser thermal flow field hydrogen radial velocity distribution, secondary throat diffuser outlet pressure and outlet temperature.

[0022] Optionally, the inputting of equipment parameters, operating parameters, and environmental parameters of the multiple secondary throat diffusers into the DNN network specifically includes:

[0023] According to the Laida criterion, outlier detection and elimination were performed on the equipment parameters, operating parameters, environmental parameters and corresponding thermal flow field data of various secondary throat diffusers.

[0024] The standard deviation normalization method is used to convert the abnormal data into a standard normal distribution, and the standardized equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers are input into the DNN network.

[0025] Optionally, the training of the DNN network with mass conservation and energy conservation as constraints and minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field as the optimization goal specifically includes:

[0026] The total loss is determined to train the DNN network using the following formula, with mass conservation and energy conservation as constraints and minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field as the optimization goal:

[0027]

[0028] in, is the total loss, MSE is the mean square error between the predicted value and the true value of the physical quantity, is the mass conservation constraint (which measures the divergence of the mass flux of the fluid in the x and y directions), C energy is the energy conservation constraint term (the difference between the actual energy change at each grid point (i, j) and the energy change that should occur when following the law of conservation of energy is calculated. The total deviation of the entire flow field in terms of energy conservation is obtained by summing over all grid points), ρ is the hydrogen density, u is the velocity component in the x-direction, v is the velocity component in the y-direction, x is the horizontal coordinate, y is the vertical coordinate, (i, j) is the grid point after the two-dimensional flow field is discretized, e is the specific internal energy, k is the thermal conductivity of hydrogen, ▽ is the gradient operator, T is the hydrogen temperature, and S is the heat source term constant.

[0029] Optionally, the method further includes:

[0030] The hydrogen pressure distribution, hydrogen axial velocity distribution, and hydrogen radial velocity distribution of the thermal flow field of the secondary throat diffuser when the rocket engine is working are visualized; and a cloud map is used to display the thermal flow field distribution of the secondary throat diffuser when the rocket engine is working.

[0031] The present invention provides a device for constructing a thermal flow field of a hydrogen rocket diffuser, comprising:

[0032] An acquisition module is used to obtain the equipment parameters and operating parameters of various secondary throat diffusers and the environmental parameters of the secondary throat diffuser ground high-modulus test;

[0033] The simulation module is used to establish a physical model for the ground high-modulus test of a variety of secondary throat diffusers based on their equipment parameters, operating parameters, and environmental parameters, and to perform computational fluid dynamics numerical simulation to obtain the corresponding thermal flow field data of the secondary throat diffuser.

[0034] The model training module is used to input the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers into the DNN network to obtain the predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with the conservation of mass and energy in the thermal flow field as constraints and the optimization goal of minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field to obtain a diffuser thermal flow field prediction model.

[0035] The real-time prediction module is used to input the equipment parameters, operating parameters and environmental parameters of the secondary throat diffuser when the rocket engine is working into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is working.

[0036] The present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for constructing the thermal flow field of a hydrogen rocket diffuser.

[0037] The present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for constructing the thermal flow field of a hydrogen rocket diffuser is implemented.

[0038] At least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects:

[0039] The present invention first conducts numerical simulation of a high-modulus ground test of a secondary throat diffuser to obtain a large amount of sample data of the thermal flow field of the secondary throat diffuser. Then, the DNN network is trained through the sample data with the conservation of mass and energy of the thermal flow field as physical constraints to obtain a diffuser thermal flow field prediction model. The thermal flow field of the secondary throat diffuser is reconstructed quickly and accurately through the diffuser thermal flow field prediction model, thereby improving the construction accuracy and efficiency of the thermal flow field of the secondary throat diffuser, and being able to meet the needs of rapid flow field analysis and real-time working condition evaluation in aerospace engine design. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1 A schematic flow chart of a method for constructing a thermal flow field for a hydrogen rocket diffuser provided by the present invention;

[0042] Figure 2 A schematic diagram of a DNN network architecture with physical constraints provided by the present invention;

[0043] Figure 3 A schematic diagram of the training loss and error trends of various indicators under a certain working condition provided by the present invention;

[0044] Figure 4a ~i is a schematic diagram comparing the reconstructed temperature field and the CFD simulation results under a certain working condition in the present invention;

[0045] Figure 5 A schematic diagram of a thermal flow field construction device for a hydrogen rocket diffuser provided by the present invention;

[0046] Figure 6 A schematic diagram of a computer device for implementing a method for constructing a thermal flow field of a hydrogen rocket diffuser provided by the present invention. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] In recent years, the application of deep learning technology in the field of fluid mechanics has gradually emerged. By constructing nonlinear mapping relationships between flow field parameters through data-driven methods, computational efficiency can be significantly improved.

[0049] The technical solutions provided by various embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0050] Figure 1 The figure is a flow chart of a method for constructing a thermal flow field of a hydrogen rocket diffuser according to the present invention, which specifically includes the following steps:

[0051] S101: Obtain equipment parameters, operating parameters, and environmental parameters of a ground high-modulus test of multiple secondary throat diffusers.

[0052] S102: Based on the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers, a physical model of a corresponding secondary throat diffuser ground high-modulus test is established, and computational fluid dynamics numerical simulation is performed to obtain thermal flow field data of the corresponding secondary throat diffuser.

[0053] S103: The equipment parameters, operating parameters and environmental parameters of various secondary throat diffusers are input into the DNN network to obtain the predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with the conservation of mass and energy of the thermal flow field as constraints and the minimization of the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field as the optimization goal to obtain a diffuser thermal flow field prediction model.

[0054] S104: Inputting the equipment parameters, operating parameters, and environmental parameters of the secondary throat diffuser when the rocket engine is operating into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is operating.

[0055] For the sake of convenience, the following description will only be based on the server as the execution subject. The server mentioned in the present invention can be a server set up on a business platform, or a device such as a desktop computer or a laptop computer that can execute the solution of the present invention.

[0056] In one or more embodiments of the present invention, the server may first perform numerical simulation of a high-modulus ground test of a secondary throat diffuser to obtain a large amount of sample data of the thermal flow field of the secondary throat diffuser, and then train the DNN network through the sample data with mass conservation and energy conservation as physical constraints to obtain a diffuser thermal flow field prediction model.

[0057] When performing numerical simulations, the equipment parameters and operating parameters of various secondary throat diffusers, as well as the environmental parameters of the secondary throat diffuser ground high-model test, can be first obtained. Based on these parameters, full-scale, multi-operational simulations can be performed to obtain rich sample data. In one or more embodiments of the present invention, the equipment parameters of the secondary throat diffuser may include: diffuser dimensions; the operating parameters of the secondary throat diffuser may include: the test environment, total combustion chamber pressure, total gas temperature, gas composition within the diffuser, and physical properties of the gas composition; and the environmental parameters of the secondary throat diffuser ground high-model test may include: the ambient temperature and pressure during diffuser operation.

[0058] Afterwards, a physical model can be established based on the acquired data. Specifically, in one or more embodiments of the present invention, the structure of the corresponding secondary throat diffuser in the working scene under the equipment parameters of a variety of secondary throat diffusers can be established first; then, according to the corresponding operating parameters and environmental parameters, the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is working are determined; thereby, according to the structure of the corresponding secondary throat diffuser in the working scene, a geometric model is established and meshing is performed; based on the divided grid and the corresponding environmental parameters, boundary conditions are set, and combined with the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is working, a physical model of the corresponding secondary throat diffuser ground high-modulus test is established.

[0059] Among them, the flow state of the flow field in the secondary throat diffuser, including pressure, temperature and Mach number, can be determined according to the physical properties of the gas and the operating parameters of the diffuser.

[0060] The equivalent nozzle inlet diameter and flow velocity of the secondary throat diffuser can be calculated by the following formula:

[0061]

[0062] Where V eq is the flow velocity at the equivalent nozzle inlet; V e is the flow velocity of the secondary throat diffuser, d eq is the diameter of the equivalent nozzle inlet; d e is the diameter of the equivalent nozzle inlet of the secondary throat diffuser, p0 is the inlet pressure of the secondary throat diffuser during operation; p atm is the ambient back pressure of the secondary throat diffuser; γ is the specific heat ratio of the gas.

[0063] Afterwards, numerical simulation can be performed based on the established physical model. In one or more embodiments of the present invention, computational fluid dynamics (CFD) numerical simulation can be performed according to the physical model of the corresponding secondary throat diffuser ground high-model test to solve the mass conservation equation, momentum conservation equation, energy conservation equation and turbulent component transport equation to obtain the corresponding secondary throat diffuser thermal flow field data; wherein, the secondary throat diffuser thermal flow field data includes: secondary throat diffuser thermal flow field hydrogen pressure distribution, secondary throat diffuser thermal flow field hydrogen axial velocity distribution, secondary throat diffuser thermal flow field hydrogen radial velocity distribution, secondary throat diffuser outlet pressure and outlet temperature.

[0064] After obtaining the required sample data, the server can train a pre-selected model using the sample data to obtain a thermal flow field prediction model.

[0065] In one or more embodiments of the present invention, the previously acquired sample data may be preprocessed. Specifically, outlier detection and elimination may be performed on various secondary throat diffuser device parameters, operating parameters, environmental parameters, and corresponding secondary throat diffuser thermal flow field data based on the Laida criterion (3σ principle). For example, the mean μ and standard deviation σ are calculated for each parameter dimension, and data points whose absolute value exceeds μ ± 3σ are eliminated.

[0066] Then, the standard deviation standardization (Z-score standardization) method is used to convert the abnormal data into a standard normal distribution with a mean of 0 and a standard deviation of 1 using the following formula:

[0067] In the formula, x is the original data, x′ is the standardized data; μ train is the mean of the training set, σ train The standard deviation of the training set is used to ensure that the normalization parameters of the test set are consistent with those of the training set. Of course, the data set can also be divided into 8:1:1 ratios: for example, if there are 1200 sets of valid data, 960 sets are used as training sets, 120 sets are used as validation sets, and 120 sets are used as test sets.

[0068] Subsequently, the standardized equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers can be input into the DNN network, and the predicted loss can be determined based on the preprocessed thermal flow field data of the corresponding secondary throat diffuser to train the DNN network.

[0069] For example, a sequential neural network model (Sequential model) containing four fully connected layers (Dense layers) can be constructed using TensorFlow and Keras, where the first three layers use the tanh activation function and the last layer outputs three predicted values (pressure, axial velocity, and radial velocity). Figure 2 This is a schematic diagram of a DNN network architecture with physical constraints in the present invention. After discretizing the two-dimensional flow field, the mass conservation constraint term is:

[0070]

[0071] Where ρ is the hydrogen density, which is calculated by the ideal gas state equation ρ = P / (RT) (R is the gas constant, P is the total pressure of the hydrogen inlet, and T is the hydrogen temperature), u is the velocity component in the x direction, v is the velocity component in the y direction, x is the horizontal coordinate, y is the vertical coordinate, and (i, j) is the grid point after the two-dimensional flow field is discretized. is the mass conservation constraint (which measures the divergence of the mass flux of the fluid in the x and y directions).

[0072] Considering heat conduction and convection, the energy conservation constraint is:

[0073]

[0074] Where, is the energy conservation constraint (it measures the difference between the actual energy change at each grid point (i, j) and the energy change that should occur if the law of energy conservation is followed. The sum of all grid points gives the overall deviation of the energy conservation of the entire flow field), e is the specific internal energy, and k is the empirical value of the thermal conductivity of hydrogen. is the gradient operator, T is the hydrogen temperature, and S is the heat source constant. The heat source term S is simplified to a constant based on the chemical reaction kinetics model.

[0075] The loss function calculation formula is:

[0076]

[0077] Where, is the total loss, and MSE is the mean square error between the predicted value and the true value of the physical quantity.

[0078] Based on the above loss function, training can be performed using the Adam optimizer. For example, the initial learning rate can be 0.01. To prevent overfitting and improve training efficiency, the code can set an EarlyStopping callback function to stop training after the validation loss stops improving for 200 epochs. Simultaneously, the ReduceLROnPlateau callback function is used to reduce the learning rate to 88% of the original value if the validation loss does not improve within 25 epochs. The minimum learning rate is 0.00001. Figure 3 This is a schematic diagram of the training loss and the error trend of each indicator under a certain working condition in the present invention; the root mean square error (RMSE) and structural similarity index (SSIM) are used to evaluate the reconstruction accuracy, and the formula is:

[0079]

[0080] Among them, y i For model prediction, is the sample label (i.e. the numerical simulation thermal flow field result), μ x 、μ y are the mean, σ x ,σ y is the standard deviation, σ xy is the covariance, C1 and C2 are constants.

[0081] After training the DNN model to generate a diffuser thermal flow field prediction model, in practical applications, the device parameters, operating parameters, and environmental parameters of the secondary throat diffuser during rocket engine operation can be input into the diffuser thermal flow field prediction model to quickly determine the thermal flow field of the secondary throat diffuser during rocket engine operation. Accordingly, the predicted thermal flow field of the secondary throat diffuser can include the hydrogen pressure distribution, hydrogen axial velocity distribution, and hydrogen radial velocity distribution of the secondary throat diffuser during rocket engine operation.

[0082] In addition, in one or more embodiments of the present invention, the hydrogen pressure distribution, hydrogen axial velocity distribution, and hydrogen radial velocity distribution of the thermal flow field of the secondary throat diffuser when the rocket engine is working can be visualized; and the thermal flow field distribution of the secondary throat diffuser when the rocket engine is working can be displayed as a cloud map.

[0083] That is, the structural parameters and operating parameters of the secondary throat diffuser collected in real time in actual applications are input into the diffuser thermal flow field prediction model. After denormalization processing, the reconstructed thermal flow field data is output, and the absolute error between the predicted results and the interpolation calculation results is calculated. The comparison between the original data and the predicted results is displayed through visualization. Figure 4a ~i is a schematic diagram comparing the reconstructed temperature field and the CFD simulation results under a certain working condition in the present invention, Figure 4a This is a schematic diagram of the pressure field of the CFD model. Figure 4b To quickly predict the model pressure field, Figure 4c is the absolute error of the pressure field, Figure 4d This is a schematic diagram of the axial velocity field of the CFD model. Figure 4e To quickly predict the axial velocity field of the model, Figure 4f is the absolute error diagram of the axial velocity field, Figure 4g This is a schematic diagram of the radial velocity field of the CFD model. Figure 4h This is a diagram for quickly predicting the radial velocity field of the model. Figure 4i It is an illustration of the absolute error of the radial velocity field.

[0084] based on Figure 1 The method for constructing the thermal flow field of a hydrogen rocket diffuser shown in the figure, the present invention first performs numerical simulation of a ground high-modulus test of a secondary throat diffuser to obtain a large amount of sample data of the thermal flow field of the secondary throat diffuser, and then trains the DNN network through the sample data with mass conservation and energy conservation as physical constraints to obtain a diffuser thermal flow field prediction model, so as to quickly and accurately reconstruct the thermal flow field of the secondary throat diffuser through the diffuser thermal flow field prediction model, thereby improving the construction accuracy and efficiency of the thermal flow field of the secondary throat diffuser, and being able to meet the needs of rapid flow field analysis and real-time working condition evaluation in aerospace engine design.

[0085] When applying the method for constructing the thermal flow field of a hydrogen rocket diffuser provided by the present invention, it is not necessary to Figure 1 The steps are executed in the order shown. The specific execution order of the steps can be determined according to needs, and the present invention does not limit this.

[0086] The above is a method for constructing a thermal flow field of a hydrogen rocket diffuser provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding device for constructing a thermal flow field of a hydrogen rocket diffuser, such as Figure 5 shown.

[0087] Figure 5 A schematic diagram of a thermal flow field construction device for a hydrogen rocket diffuser provided by the present invention, comprising:

[0088] An acquisition module 201 is used to acquire equipment parameters and operating parameters of various secondary throat diffusers and environmental parameters of a ground high-modulus test of the secondary throat diffuser;

[0089] The simulation module 202 is used to establish a physical model for a ground high-modulus test of a corresponding secondary throat diffuser based on the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers, and to perform computational fluid dynamics numerical simulation to obtain thermal flow field data of the corresponding secondary throat diffuser;

[0090] The model training module 203 is configured to input equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers into a DNN network to obtain a predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with mass conservation and energy conservation of the thermal flow field as constraints and with minimizing the deviation between the predicted thermal flow field and the corresponding thermal flow field of the secondary throat diffuser as the optimization goal to obtain a diffuser thermal flow field prediction model.

[0091] The real-time prediction module 204 is used to input the equipment parameters, operating parameters and environmental parameters of the secondary throat diffuser when the rocket engine is working into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is working.

[0092] Regarding the specific definition of the hydrogen rocket diffuser thermal flow field construction device, please refer to the definition of the hydrogen rocket diffuser thermal flow field construction method above, which will not be repeated here. The various modules in the above-mentioned hydrogen rocket diffuser thermal flow field construction device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0093] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A method for constructing the thermal flow field of a hydrogen rocket diffuser is provided.

[0094] The present invention also provides Figure 6 The structural diagram of the computer equipment shown in FIG. Figure 6 As shown in the figure, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 A method for constructing the thermal flow field of a hydrogen rocket diffuser is provided.

[0095] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0096] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present invention.

Claims

1. A method for constructing a thermal flow field of a hydrogen rocket diffuser, characterized in that: include: Obtain equipment parameters, operating parameters, and environmental parameters of secondary throat diffusers for ground high-speed model tests; Based on the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers, a physical model for the corresponding secondary throat diffuser ground high-modulus test was established, and computational fluid dynamics numerical simulation was performed to obtain the corresponding secondary throat diffuser thermal flow field data; The equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers are input into the DNN network to obtain the predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with the conservation of mass and energy in the thermal flow field as constraints and the optimization goal of minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field to obtain a diffuser thermal flow field prediction model. The equipment parameters, operating parameters and environmental parameters of the secondary throat diffuser when the rocket engine is working are input into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is working.

2. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 1, wherein: The equipment parameters of the secondary throat diffuser include: diffuser size of the secondary throat diffuser; The operating parameters of the secondary throat diffuser include: test environment, total pressure of the combustion chamber, total temperature of the gas, gas composition inside the diffuser, and physical properties of the gas composition; The environmental parameters of the ground high-modulus test of the secondary throat diffuser include: the ambient temperature and the ambient pressure when the diffuser is working.

3. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 1, wherein: The physical model of the ground high-modulus test of the corresponding secondary throat diffuser is established based on the equipment parameters, operating parameters and environmental parameters of the various secondary throat diffusers, specifically including: Establish the structure of the secondary throat diffuser in the working scenario under various equipment parameters of the secondary throat diffuser; Determine the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is operating based on the corresponding operating parameters and environmental parameters; According to the structure of the corresponding secondary throat diffuser in the working scene, a geometric model is established and meshing is performed; Based on the divided grid and the corresponding environmental parameters, the boundary conditions are set, and the physical model of the corresponding secondary throat diffuser ground high-modulus test is established in combination with the hydrogen flow state and hydrogen flow rate inside the secondary throat diffuser when the rocket engine is working.

4. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 1, wherein: The computational fluid dynamics numerical simulation is performed to obtain the corresponding thermal flow field data of the secondary throat diffuser, specifically including: Computational fluid dynamics numerical simulation is performed based on the physical model of the corresponding secondary throat diffuser ground high-modulus test to solve the mass conservation equation, momentum conservation equation, energy conservation equation and turbulent component transport equation to obtain the corresponding secondary throat diffuser thermal flow field data; Among them, the secondary throat diffuser thermal flow field data includes: secondary throat diffuser thermal flow field hydrogen pressure distribution, secondary throat diffuser thermal flow field hydrogen axial velocity distribution, secondary throat diffuser thermal flow field hydrogen radial velocity distribution, secondary throat diffuser outlet pressure and outlet temperature.

5. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 1, wherein: The device parameters, operating parameters and environmental parameters of the multiple secondary throat diffusers are input into the DNN network, specifically including: According to the Laida criterion, outlier detection and elimination were performed on the equipment parameters, operating parameters, environmental parameters and corresponding thermal flow field data of various secondary throat diffusers. The standard deviation normalization method is used to convert the abnormal data into a standard normal distribution, and the standardized equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers are input into the DNN network.

6. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 1, wherein: The DNN network is trained with the mass conservation and energy conservation of the thermal flow field as constraints and the minimization of the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field as the optimization goal, specifically including: The total loss is determined to train the DNN network using the following formula, with mass conservation and energy conservation as constraints and minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field as the optimization goal: in, is the total loss, MSE is the mean square error between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field, represents the mass conservation constraint, represents the energy conservation constraint term, ρ is the hydrogen density, u is the hydrogen velocity component in the x direction, v is the hydrogen velocity component in the y direction, x is the horizontal coordinate, y is the vertical coordinate, (i, j) is the grid point after the two-dimensional flow field is discretized, e is the specific internal energy, k is the thermal conductivity of hydrogen, is the gradient operator, T is the hydrogen temperature, and S is the heat source constant.

7. The method for constructing a thermal flow field of a hydrogen rocket diffuser according to claim 4, wherein: The method further comprises: The hydrogen pressure distribution, hydrogen axial velocity distribution, and hydrogen radial velocity distribution of the thermal flow field of the secondary throat diffuser when the rocket engine is working are visualized; and a cloud map is used to display the thermal flow field distribution of the secondary throat diffuser when the rocket engine is working.

8. A device for constructing a thermal flow field of a hydrogen rocket diffuser, characterized in that: include: An acquisition module is used to obtain the equipment parameters and operating parameters of various secondary throat diffusers and the environmental parameters of the secondary throat diffuser ground high-modulus test; The simulation module is used to establish a physical model for the ground high-modulus test of a variety of secondary throat diffusers based on their equipment parameters, operating parameters, and environmental parameters, and to perform computational fluid dynamics numerical simulation to obtain the corresponding thermal flow field data of the secondary throat diffuser. The model training module is used to input the equipment parameters, operating parameters, and environmental parameters of various secondary throat diffusers into the DNN network to obtain the predicted thermal flow field of the secondary throat diffuser. The DNN network is trained with the conservation of mass and energy in the thermal flow field as constraints and the optimization goal of minimizing the deviation between the predicted thermal flow field and the corresponding secondary throat diffuser thermal flow field to obtain a diffuser thermal flow field prediction model. The real-time prediction module is used to input the equipment parameters, operating parameters and environmental parameters of the secondary throat diffuser when the rocket engine is working into the diffuser thermal flow field prediction model to obtain the thermal flow field of the secondary throat diffuser when the rocket engine is working.

9. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

Images