A method, device and equipment for obtaining a three-dimensional simulation sample of a thrust chamber

Abstract

The application discloses a method, device and equipment for obtaining a thrust chamber three-dimensional simulation sample, and relates to the technical field of liquid rocket engines, and aims to solve the problem of low efficiency of obtaining a thrust chamber three-dimensional simulation sample in the prior art. The method comprises the following steps: obtaining a first type of three-dimensional simulation result under a first target number of working condition points for a thrust chamber in a liquid rocket engine; obtaining a second type of three-dimensional simulation result under a second target number of working condition points; the first target number of working condition points is at least ten times the second target number of working condition points; and performing data fusion on the first type of three-dimensional simulation result under the first target number of working condition points and the second type of three-dimensional simulation result under the second target number of working condition points to obtain a thrust chamber three-dimensional simulation sample under the first target number of working condition points. In this way, the efficiency of obtaining a thrust chamber three-dimensional simulation sample can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of liquid rocket engine, and particularly relates to a method, device and equipment for obtaining a three-dimensional simulation sample of a thrust chamber. BACKGROUND

[0002] In the digital twin of a liquid rocket engine, a twin of a core component, i.e., a thrust chamber, of the liquid rocket engine needs to be constructed, and the performance of the thrust chamber can be monitored and analyzed in real time through the twin of the thrust chamber.

[0003] In the process of constructing the twin of the thrust chamber, a three-dimensional simulation result of the thrust chamber is first obtained through three-dimensional modeling simulation technology, and the simulation result at least includes a pressure field, a temperature field and a Mach number. The three-dimensional simulation result reflects the performance problem of the thrust chamber. After the three-dimensional simulation result is obtained, a reduction technology is used to reduce the three-dimensional simulation result to a three-dimensional feature model.

[0004] In the process of repeatedly using three-dimensional modeling simulation to obtain a large amount of three-dimensional simulation results of the thrust chamber, for example, 180 three-dimensional simulation results under 180 different working condition points can be obtained, and according to 20 million grids, for example, a single simulation calculation needs about 5 hours. The working condition preparation, the start of simulation calculation and the collection of the three-dimensional simulation result are performed once a day, and it takes about 200 days to complete the three-dimensional simulation calculation under the 180 different working condition points. This process consumes too much time and costs a lot of manpower. SUMMARY

[0005] The present application aims to provide a method, device and equipment for obtaining a three-dimensional simulation sample of a thrust chamber, which can improve the acquisition efficiency of the three-dimensional simulation sample of the thrust chamber.

[0006] In order to achieve the above-mentioned purpose, the present application provides a method, device and equipment for obtaining a three-dimensional simulation sample of a thrust chamber, as follows:

[0007] In the first aspect, the present application provides a method for obtaining a three-dimensional simulation sample of a thrust chamber, comprising:

[0008] The first target number of working condition points are obtained for the thrust chamber in the liquid rocket engine, and the first type of three-dimensional simulation result is obtained.

[0009] obtain the first type of three-dimensional simulation result under the first target number of working condition points.

[0010] perform data fusion on the first type of three-dimensional simulation result under the first target number of working condition points and the second type of three-dimensional simulation result under the second target number of working condition points, to obtain a thruster chamber three-dimensional simulation sample under the first target number of working condition points.

[0011] Optionally, the obtaining of the first type of three-dimensional simulation result under the first target number of working condition points comprises:

[0012] obtain the first type of three-dimensional simulation result under the first number of working condition points from the historical thruster chamber three-dimensional simulation data;

[0013] if the first number is less than the first target number, determine a first difference value between the first target number and the first number;

[0014] perform three-dimensional simulation on the thruster chamber under the first difference value number of working condition points based on the first actual grid number, to obtain the first type of three-dimensional simulation result under the first difference value number of working condition points;

[0015] add the first type of three-dimensional simulation result under the first difference value number of working condition points and the first type of three-dimensional simulation result under the first number of working condition points, to obtain the first type of three-dimensional simulation result under the first target number of working condition points.

[0016] Optionally, the obtaining of the second type of three-dimensional simulation result under the second target number of working condition points comprises:

[0017] obtain the second type of three-dimensional simulation result under the second number of working condition points from the historical thruster chamber three-dimensional simulation data;

[0018] if the second number is less than the second target number, determine a second difference value between the second target number and the second number;

[0019] perform three-dimensional simulation on the thruster chamber under the second difference value number of working condition points based on the second actual grid number, to obtain the second type of three-dimensional simulation result under the second difference value number of working condition points;

[0020] The second type of three-dimensional simulation result under the second target number of working condition points is obtained by adding the second type of three-dimensional simulation result under the second difference number of working condition points and the second type of three-dimensional simulation result under the second number of working condition points.

[0021] Optionally, the data fusion of the first type of three-dimensional simulation result under the first target number of working condition points and the second type of three-dimensional simulation result under the second target number of working condition points comprises:

[0022] The first type of three-dimensional simulation result under the first target number of working condition points and the second type of three-dimensional simulation result under the second target number of working condition points are fused by using a multi-source data fusion algorithm based on transfer learning.

[0023] Optionally, the method for obtaining the three-dimensional simulation sample of the thrust chamber further comprises:

[0024] The three-dimensional simulation sample of the thrust chamber under the first target number of working condition points is reduced in order.

[0025] Compared with the prior art, the method for obtaining the three-dimensional simulation sample of the thrust chamber provided by the application can reduce the three-dimensional simulation calculation time, improve the acquisition rate and acquisition efficiency of the three-dimensional simulation sample of the thrust chamber, and obtain the three-dimensional simulation sample of the thrust chamber under the first target number of working condition points by fusing the first type of three-dimensional simulation result under the same number of working condition points as the first target number and the second type of three-dimensional simulation result under the second target number of working condition points which is less than the first target number.

[0026] In a second aspect, the application provides a device for obtaining a three-dimensional simulation sample of a thrust chamber, comprising:

[0027] The first obtaining module is configured to obtain a first type of three-dimensional simulation result under a first target number of working condition points for a thrust chamber in a liquid rocket engine.

[0028] The second obtaining module is configured to obtain a second type of three-dimensional simulation result under a second target number of working condition points. The first type of three-dimensional simulation result represents a first actual grid number used in simulation calculation, which is less than or equal to a first preset grid number, and the second type of three-dimensional simulation result represents a second actual grid number used in simulation calculation, which is greater than or equal to a second preset grid number. The first preset grid number is a grid number in the order of one hundred thousand, and the second preset grid number is a grid number in the order of ten million. The first target number of working condition points is at least ten times the second target number of working condition points.

[0029] a fusion module configured to fuse the first type of three-dimensional simulation result at the first target number of working points and the second type of three-dimensional simulation result at the second target number of working points to obtain a three-dimensional simulation sample of the thrust chamber at the first target number of working points.

[0030] Optionally, the first obtaining module is specifically configured to obtain historical three-dimensional simulation data of the thrust chamber, and obtain the first type of three-dimensional simulation result at the first number of working points from the historical three-dimensional simulation data of the thrust chamber.

[0031] If the first number is less than the first target number, a first difference between the first target number and the first number is determined.

[0032] Based on the first actual number of grids, three-dimensional simulation is performed on the thrust chamber at the first difference number of working points to obtain the first type of three-dimensional simulation result at the first difference number of working points.

[0033] The first type of three-dimensional simulation result at the first difference number of working points is added to the first type of three-dimensional simulation result at the first number of working points to obtain the first type of three-dimensional simulation result at the first target number of working points.

[0034] Optionally, the second obtaining module is specifically configured to obtain the second type of three-dimensional simulation result at the second number of working points from the historical three-dimensional simulation data of the thrust chamber.

[0035] If the second number is less than the second target number, a second difference between the second target number and the second number is determined.

[0036] Based on the second actual number of grids, three-dimensional simulation is performed on the thrust chamber at the second difference number of working points to obtain the second type of three-dimensional simulation result at the second difference number of working points.

[0037] The second type of three-dimensional simulation result at the second difference number of working points is added to the second type of three-dimensional simulation result at the second number of working points to obtain the second type of three-dimensional simulation result at the second target number of working points.

[0038] In a third aspect, the present application provides an electronic device, comprising a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate through the communication bus; the memory stores a computer program which can be run by the processor; when the processor runs the computer program, the method for obtaining a three-dimensional simulation sample of a thrust chamber is executed.

[0039] In a fourth aspect, the present application provides a computer storage medium, wherein the computer storage medium stores instructions, and the instructions, when executed, implement the method for obtaining the three-dimensional simulation sample of the thrust chamber. BRIEF DESCRIPTION OF DRAWINGS

[0040] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0041] Figure 1 A flowchart of the method for obtaining the three-dimensional simulation sample of the thrust chamber according to an embodiment of the present application is shown in the figure;

[0042] Figure 2 A structural diagram of the device for obtaining the three-dimensional simulation sample of the thrust chamber according to an embodiment of the present application is shown in the figure;

[0043] Figure 3 A structural diagram of the electronic device according to an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0044] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using the words “first”, “second”, etc. For example, the first threshold value and the second threshold value are only used to distinguish different threshold values, and do not limit the order. Those skilled in the art can understand that the words “first”, “second”, etc. do not limit the number and execution order, and the words “first”, “second”, etc. also do not necessarily mean different.

[0045] It should be noted that in the present application, the words “exemplary” or “for example” are used to represent an example, illustration or description. Any embodiment or design scheme described as “exemplary” or “for example” in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words “exemplary” or “for example” are intended to present the relevant concept in a specific manner.

[0046] In the present application, “at least one” means one or more, and “multiple” means two or more. “And / or” describes the association between the associated objects, indicating that there can be three relationships.

[0047] As Figure 1 shown, the embodiment of the present application provides a method for obtaining a three-dimensional simulation sample of a thrust chamber, which can include:

[0048] Step 110: For the thrust chamber in the liquid rocket engine, obtain the first type of three-dimensional simulation result under the first target number of working condition points;

[0049] Before performing the simulation calculation, first, a three-dimensional geometric model of the thrust chamber needs to be constructed, and three simulation models of the thrust chamber are constructed. Model construction can be performed using any of a plurality of simulation software such as ANSYS ICEM, UG, CATIA, etc. After the model is successfully constructed, the simulation software is used to divide the three-dimensional simulation model of the thrust chamber into grids. One is to use a low-quality grid, that is, to divide the three-dimensional simulation model of the thrust chamber into a grid number of 100,000. Two is to use a high-quality grid, that is, to divide the three-dimensional simulation model of the thrust chamber into a grid number of 10,000,000. After the grid division, some simulation conditions and other parameters are set, and finally, the simulation calculation of the thrust chamber under different numbers of working conditions is performed to obtain three-dimensional simulation results under different numbers of working conditions. The three-dimensional simulation results under each working condition include a large amount of simulation result data. The simulation results can be three-dimensional simulation results of the thrust chamber pressure or three-dimensional simulation results of the thrust chamber Mach number.

[0050] Step 120: Obtain second-type three-dimensional simulation results under a second target number of working condition points; wherein the first-type three-dimensional simulation results represent that the first actual grid number used in the simulation calculation is less than or equal to the first preset grid number, and the second-type three-dimensional simulation results represent that the second actual grid number used in the simulation calculation is greater than or equal to the second preset grid number; the first preset grid number is a grid number of 100,000, and the second preset grid number is a grid number of 10,000,000; the first target number of working condition points is at least ten times the second target number of working condition points.

[0051] For example, the second target number can be 10.

[0052] For example, the first target number is 200.

[0053] It can be understood that the simulation calculation process corresponding to the first-type three-dimensional simulation results uses a grid number of 100,000, and the simulation calculation process corresponding to the second-type three-dimensional simulation results uses a grid number of 10,000,000.

[0054] For example, the first preset grid number is 900,000 grids, and the first actual grid number used in the simulation calculation is 200,000 grids.

[0055] For example, the second preset grid number is 90,000,000 grids, and the second actual grid number used in the simulation calculation is 20,000,000 grids.

[0056] Step 130: Data fusion is performed on the first-type three-dimensional simulation results under the first target number of working condition points and the second-type three-dimensional simulation results under the second target number of working condition points to obtain a three-dimensional simulation sample of the thrust chamber under the first target number of working condition points.

[0057] From the above, in order to obtain the first target number of (for example, 200) working condition points of the thruster three-dimensional simulation sample, the first type of three-dimensional simulation results of the same number of working condition points as the first target number are fused with the second type of three-dimensional simulation results of the second target number of working condition points less than the first target number, so that more three-dimensional simulation calculation time can be reduced, and the acquisition rate and acquisition efficiency of the thruster three-dimensional simulation sample can be improved. Because the first target number of working condition points is at least ten times the second target number of working condition points, if the first type of three-dimensional simulation results and the second type of three-dimensional simulation results are the same number, the calculation time is too long due to the too many grid numbers used by the second type of three-dimensional simulation results. In the embodiment, a small amount of second type of three-dimensional simulation results is obtained, and then a small amount of three-dimensional simulation results is fused with the first target number of first type of three-dimensional simulation results, so that the calculation time can be greatly reduced, and the acquisition efficiency of the thruster three-dimensional simulation sample can be improved.

[0058] In an optional embodiment, step 110 can include:

[0059] 1) Obtain historical thruster three-dimensional simulation data, and obtain the first type of three-dimensional simulation results under the first number of working condition points from the historical thruster three-dimensional simulation data;

[0060] In a specific implementation, the database saves data obtained by performing simulation multiple times, that is, historical thruster three-dimensional simulation data, which contains simulation result data corresponding to a certain number of first type of three-dimensional simulation results and simulation result data corresponding to a certain number of second type of three-dimensional simulation results.

[0061] For example, the first number is 80.

[0062] 2) If the first number is less than the first target number, determine a first difference value between the first target number and the first number;

[0063] For example, the first target number is 200, and the first number is 80, so the first difference value is 120.

[0064] 3) Based on the first actual grid number, perform three-dimensional simulation on the thruster under the first difference value number of working condition points to obtain the first type of three-dimensional simulation results under the first difference value number of working condition points;

[0065] For example, the first actual grid number is 200,000, so the thruster three-dimensional simulation model mentioned above is divided according to the grid number of 200,000, and then 120 simulation calculations are performed to obtain the first type of three-dimensional simulation results under 120 working condition points.

[0066] 4) adding the first type of three-dimensional simulation results at the first difference number of working points to the first type of three-dimensional simulation results at the first number of working points to obtain the first type of three-dimensional simulation results at the first target number of working points.

[0067] For example, the first type of three-dimensional simulation results at 120 working points are added to the first type of three-dimensional simulation results at 80 working points obtained from the historical thruster three-dimensional simulation data to obtain the first type of three-dimensional simulation results at 200 working points.

[0068] In an optional embodiment, step 120 can include, similar to step 110:

[0069] obtaining the second type of three-dimensional simulation results at the second number of working points from the historical thruster three-dimensional simulation data;

[0070] if the second number is less than the second target number, determining a second difference between the second target number and the second number;

[0071] performing three-dimensional simulation on the thruster at the second difference number of working points based on the second actual grid number to obtain the second type of three-dimensional simulation results at the second difference number of working points;

[0072] adding the second type of three-dimensional simulation results at the second difference number of working points to the second type of three-dimensional simulation results at the second number of working points to obtain the second type of three-dimensional simulation results at the second target number of working points.

[0073] For example, the second type of three-dimensional simulation results at 10 working points are needed, and 4 second type of three-dimensional simulation results are obtained from the historical thruster three-dimensional simulation data, then the thruster three-dimensional simulation model needs to be meshed according to the second actual grid number (for example, 20 million) and simulated for 6 times to obtain the second type of three-dimensional simulation results at 6 working points; the second type of three-dimensional simulation results at 6 working points are added to the second type of three-dimensional simulation results at 4 working points obtained from the historical thruster three-dimensional simulation data to obtain the second type of three-dimensional simulation results at 10 working points.

[0074] In an optional embodiment, step 130 can include:

[0075] fusing the first type of three-dimensional simulation results at the first target number of working points and the second type of three-dimensional simulation results at the second target number of working points by using a multi-source data fusion algorithm based on transfer learning.

[0076] Specifically, the core of transfer learning lies in the mechanism of knowledge transfer.

[0077] In an alternative embodiment, transfer learning can employ feature transfer. Feature transfer includes feature transformation and feature selection.

[0078] Feature Transformation: Feature transformation involves converting the feature representation of the source domain into a form that is usable by the target domain. This can be achieved by learning a feature transformation function that maps the features of the source domain onto the feature space of the target domain. This transformation can be linear or non-linear, depending on the complexity between the source and target domains.

[0079] Feature Selection is another way of feature transfer. It is based on the assumption that only part of the features are shared between the source and target domains. Therefore, transfer can be done by selecting those features that are useful for the target task. Feature selection can be achieved through statistical methods, machine learning algorithms, or deep learning methods.

[0080] Pre-trained Feature Extractor: In deep learning, a common way of feature transfer is to use a pre-trained Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) as a feature extractor. These networks have been trained on large datasets and have learned to extract general features from images, text, or audio data. These features can be used for classification, regression, or generation tasks in the target task.

[0081] In an alternative embodiment, transfer learning can employ model transfer. Model transfer can further include fine-tuning and multi-task learning.

[0082] Fine-tuning involves transferring the model parameters trained in the source domain to the target domain and fine-tuning them on the data of the target domain. During fine-tuning, only part of the layer parameters are updated, while the rest of the layer parameters are frozen. This method utilizes the knowledge in the source domain model and adapts to the data distribution of the target domain through fine-tuning.

[0083] Multi-task Learning is to learn multiple related tasks simultaneously and utilize the correlation between tasks by sharing network layers or parameters. In multi-task learning, the source and target domains are treated as different tasks and share part of the network structure or parameters. This method improves the generalization ability of the model by optimizing multiple tasks simultaneously.

[0084] To implement transfer learning, we use a portion of the labeled training data with the same distribution as the test data to build a classification model. We call these training data as in-distribution training data. The amount of these in-distribution training data is often insufficient to train a good classifier. The distribution of the training data can be different from the test data, which can be because they are outdated, and these training data are called out-of-distribution training data. Suppose these data are very rich, but due to the difference in data distribution, the classifier learned from these data cannot well classify the test data. More formally, let X s be the in-distribution instance space, X a be the out-of-distribution instance space, and Y = {0, 1} be the set of class labels. The concept is a Boolean function c that maps from X to Y, where X = X s ∪ X d .

[0085] The test data set is denoted by S = {(x , y )}k, where k is the size of the unlabeled test set S. The training data set tc {X x Y} is divided into two labeled sets T a and T s . T a represents the out-of-distribution training data of S , where T s represents the in-distribution training data of S , where n and m are the sizes of T a and T s , respectively. c(x) returns the label of data instance x. The combined training set T = {(x i , c(x i ))} is defined as follows

[0086]

[0087] Here, T a corresponds to some labeled data from the old domain, and as much as possible, these data are reused; when it is unknown which part of T a is available, a small amount of data is labeled from the new domain, called t, and then these data are used to find the useful part of T a . The problem to be solved is: given a small amount of labeled in-distribution training data, a large amount of out-of-distribution training data T a , and some unlabeled test data S, the goal is to train a classifier e: X → Y that minimizes the prediction error on the unlabeled data set S.

[0088] The learning framework TrAdaBoost, which extends AdaBoost for transfer learning, is migrated. AdaBoost (Freund & Schapire, 1997) is a learning framework that aims to improve the accuracy of weak learners by carefully adjusting the weights of training instances and learning classifiers accordingly. However, similar to most traditional machine learning methods, AdaBoost assumes that the training data and test data are from the same distribution. In the extension of AdaBoost, AdaBoost is still applied to the same distribution of training data to build the basis of the model. However, for the different distribution training instances, when they are wrongly predicted due to the distribution change of the learned model, these instances are likely to be those that are least similar to the same distribution instances. Therefore, a mechanism can be added in the extension to reduce the weights of these instances to weaken their impact.

[0089]

[0090]

[0091] Algorithm 1 gives a formal description of the framework. As can be seen from the algorithm, in each iteration, if a different distribution training instance is wrongly predicted, it is likely to be in conflict with the same distribution training data. Then, by multiplying its weight by to reduce its training weight to reduce its effect, note that Therefore, in the next round, the different distribution training instances that are wrongly classified with the same distribution training instances will have less impact on the learning process than this round. After several iterations, the training weight of the different distribution training instances that fit well with the same distribution training instances is larger, and the training weight of the different distribution training instances that are not similar to the same distribution training instances is smaller. The poses with larger training weights will help the learning algorithm to train better classifiers.

[0092] The strength property will be discussed below and it will be explained why the framework can learn knowledge even when the domain distributions are not the same.

[0093] Let be the loss caused by hypothesis htto training instance x. The distribution d t is the training weight vector of T a at the n-th iteration, After N iterations, the training loss of TrAdaBoost with respect to T a is For the training loss of instance x i (i = 1,..., n), the loss suffered by TrAdaBoost through N iterations is

[0094] The data corresponding to the first type of three-dimensional simulation result can be regarded as low-fidelity data, and the data corresponding to the second type of three-dimensional simulation result can be regarded as high-fidelity data; therefore, when the first type of three-dimensional simulation result and the second type of three-dimensional simulation result are fused, the above multi-source data fusion algorithm based on transfer learning can be used to fuse multi-fidelity data.

[0095] In an optional embodiment, the method for obtaining the thruster three-dimensional simulation sample can further include:

[0096] The thruster three-dimensional simulation samples under the first target number of working condition points are reduced in order to obtain a required thruster three-dimensional simulation target model.

[0097] In a specific implementation, if a traditional technology is used, if three-dimensional simulation results under, for example, 200 different working condition points are to be obtained, 200 simulation calculations are required, each simulation calculation is performed according to 20 million grid quantities, and each simulation calculation requires about 6 hours, working condition preparation, starting simulation calculation, and simulation result collection are performed once a day, and it takes about 200 days to complete 200 three-dimensional simulation calculations under different working condition points. This process requires too much time and manpower. However, by using the scheme in the embodiment of the present application, the original simulation calculation workload of 200 days can be shortened to 30 days, a large number of three-dimensional simulation calculation results can be quickly obtained, and a large amount of manpower and physical costs can be saved.

[0098] As shown in FIG. 10, the embodiment of the present application further provides a device for obtaining a thruster three-dimensional simulation sample, which can include: Figure 2 The first obtaining module 210 is configured to obtain, for a thruster in a liquid rocket engine, a first type of three-dimensional simulation result under a first target number of working condition points;

[0099] The second obtaining module 220 is configured to obtain a second type of three-dimensional simulation result under a second target number of working condition points; wherein the first type of three-dimensional simulation result represents that a first actual grid number used in simulation calculation is less than or equal to a first preset grid number, and the second type of three-dimensional simulation result represents that a second actual grid number used in simulation calculation is greater than or equal to a second preset grid number; the first preset grid number is a grid number of the order of 100,000, the second preset grid number is a grid number of the order of 10,000,000, and the first target number of working condition points is at least ten times the second target number of working condition points.

[0100]

[0101] ​The fusion module 230 is configured to fuse the first type of three-dimensional simulation result at the first target number of operating points and the second type of three-dimensional simulation result at the second target number of operating points to obtain the thruster chamber three-dimensional simulation sample at the first target number of operating points.

[0102] In an optional implementation, the first acquisition module 210 is specifically configured to:

[0103] acquire historical thruster chamber three-dimensional simulation data, and obtain the first type of three-dimensional simulation result at the first number of operating points from the historical thruster chamber three-dimensional simulation data;

[0104] if the first number is less than the first target number, determine a first difference value between the first target number and the first number;

[0105] perform three-dimensional simulation on the thruster chamber at the first difference value number of operating points based on the first actual grid number to obtain the first type of three-dimensional simulation result at the first difference value number of operating points;

[0106] add the first type of three-dimensional simulation result at the first difference value number of operating points and the first type of three-dimensional simulation result at the first number of operating points to obtain the first type of three-dimensional simulation result at the first target number of operating points.

[0107] In an optional implementation, the second acquisition module 220 is specifically configured to:

[0108] obtain the second type of three-dimensional simulation result at the second number of operating points from the historical thruster chamber three-dimensional simulation data, if the second number is less than the second target number, determine a second difference value between the second target number and the second number, perform three-dimensional simulation on the thruster chamber at the second difference value number of operating points based on the second actual grid number to obtain the second type of three-dimensional simulation result at the second difference value number of operating points, and add the second type of three-dimensional simulation result at the second difference value number of operating points and the second type of three-dimensional simulation result at the second number of operating points to obtain the second type of three-dimensional simulation result at the second target number of operating points.

[0109] In an optional implementation, the fusion module 230 is specifically configured to:

[0110] acquire a preconfigured co-Kriging model, and fuse the first type of three-dimensional simulation result at the first target number of operating points and the second type of three-dimensional simulation result at the second target number of operating points based on the co-Kriging model.

[0111] In an optional implementation, the device for obtaining the thruster chamber three-dimensional simulation sample further comprises a reduction module configured to reduce the thruster chamber three-dimensional simulation sample at the first target number of operating points.

[0112] As shown in Figure 3 The electronic device can comprise a processor 310, a communication interface 320, a memory 330 and a communication bus, wherein the processor 310, the communication interface 320 and the memory 330 complete the communication among each other through the communication bus. The memory 330 stores a computer program which can be run by the processor 310; the processor 310 can execute the obtaining method of the three-dimensional simulation sample of the thrust chamber in any of the above-mentioned embodiments when running the computer program. In addition, the logic instructions in the memory 330 mentioned above can be realized in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program codes that can store the medium.

[0113] In another aspect, the present application also provides a non-transitory computer readable storage medium, and the computer storage medium stores instructions, when the instructions are run, the obtaining method of the three-dimensional simulation sample of the thrust chamber in any of the above-mentioned embodiments is realized.

[0114] Although the present application has been described in connection with various embodiments thereof, it will be understood that the application is capable of further modifications and that this application is intended to cover any and all such variations, using the scope of the application, which is defined by the following claims, and their equivalents. In the claims, the term "including" does not exclude other components or steps. The indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit can fulfil the functions of several items recited in the claims. The terms "first", "second" and the like in the description do not necessarily imply that there are only two. The terms "including", "containing", "comprising" and similar terms are to be construed in an inclusive, not an exclusive, sense. The reference number of a described feature is intended to denote that feature and its functional equivalent throughout the description and claims. Accordingly, the description and figures are to be regarded in an illustrative, rather than a restrictive, sense. The application is intended to cover any and all modifications and variations of the application herein disclosed, together with their equivalents. It is therefore intended that this application be interpreted by the appended claims in their broadest reasonable manner, related to what is new and desirable, without restricting the scope of the application.

Claims

1. A method of obtaining a three-dimensional simulation sample of a thrust chamber, characterized in that, The method comprises the following steps: obtaining first three-dimensional simulation results of a first target number of working conditions for a thrust chamber in a liquid rocket engine; obtaining second three-dimensional simulation results of a second target number of working conditions; wherein the first three-dimensional simulation results represent that a first actual grid number used in simulation calculation is less than or equal to a first preset grid number, and the second three-dimensional simulation results represent that a second actual grid number used in simulation calculation is greater than or equal to a second preset grid number; the first preset grid number is a grid number of the order of 100,000, and the second preset grid number is a grid number of the order of 10,000,000; the first target number of working conditions is at least ten times the second target number of working conditions; performing data fusion on the first three-dimensional simulation results of the first target number of working conditions and the second three-dimensional simulation results of the second target number of working conditions to obtain thrust chamber three-dimensional simulation samples of the first target number of working conditions; the method comprises the following steps: obtaining historical thrust chamber three-dimensional simulation data, and obtaining first three-dimensional simulation results of a first number of working conditions from the historical thrust chamber three-dimensional simulation data; if the first number is less than the first target number, determining a first difference between the first target number and the first number; performing three-dimensional simulation on the thrust chamber under the first difference number of working conditions based on the first actual grid number to obtain first three-dimensional simulation results of the first difference number of working conditions; adding the first three-dimensional simulation results of the first difference number of working conditions to the first three-dimensional simulation results of the first number of working conditions to obtain the first three-dimensional simulation results of the first target number of working conditions; the method comprises the following steps: obtaining second three-dimensional simulation results of a second number of working conditions from the historical thrust chamber three-dimensional simulation data; if the second number is less than the second target number, determining a second difference between the second target number and the second number; performing three-dimensional simulation on the thrust chamber under the second difference number of working conditions based on the second actual grid number to obtain second three-dimensional simulation results of the second difference number of working conditions; adding the second three-dimensional simulation results of the second difference number of working conditions to the second three-dimensional simulation results of the second number of working conditions to obtain the second three-dimensional simulation results of the second target number of working conditions; the method comprises the following steps: adopting a multi-source data fusion algorithm based on transfer learning to fuse the first three-dimensional simulation results of the first target number of working conditions and the second three-dimensional simulation results of the second target number of working conditions; performing reduction on the thrust chamber three-dimensional simulation samples of the first target number of working conditions.

2. An apparatus for obtaining a three-dimensional simulation sample of a thrust chamber, characterized in that, The method comprises the following steps: The first obtaining module is configured to obtain first three-dimensional simulation results under a first target number of working conditions for a thrust chamber in a liquid rocket engine. The second obtaining module is configured to obtain second three-dimensional simulation results under a second target number of working conditions. The first three-dimensional simulation results are obtained by using a first actual number of grids that is less than or equal to a first preset number of grids, and the second three-dimensional simulation results are obtained by using a second actual number of grids that is greater than or equal to a second preset number of grids. The first preset number of grids is in the order of 100,000, and the second preset number of grids is in the order of 1,000,000. The first target number of working conditions is at least ten times the second target number of working conditions. The fusion module is configured to fuse the first three-dimensional simulation results under the first target number of working conditions and the second three-dimensional simulation results under the second target number of working conditions to obtain thrust chamber three-dimensional simulation samples under the first target number of working conditions. The first obtaining module is specifically configured to obtain historical thrust chamber three-dimensional simulation data, and obtain the first three-dimensional simulation results under the first number of working conditions from the historical thrust chamber three-dimensional simulation data. If the first number is less than the first target number, a first difference between the first target number and the first number is determined. The first three-dimensional simulation results under the first difference number of working conditions are obtained by performing three-dimensional simulation on the thrust chamber under the first difference number of working conditions based on the first actual number of grids. The first three-dimensional simulation results under the first difference number of working conditions are added to the first three-dimensional simulation results under the first number of working conditions to obtain the first three-dimensional simulation results under the first target number of working conditions. The second obtaining module is specifically configured to obtain the second three-dimensional simulation results under the second number of working conditions from the historical thrust chamber three-dimensional simulation data. If the second number is less than the second target number, a second difference between the second target number and the second number is determined.

3. An electronic device, comprising: The second three-dimensional simulation results under the second difference number of working conditions are obtained by performing three-dimensional simulation on the thrust chamber under the second difference number of working conditions based on the second actual number of grids. The second three-dimensional simulation results under the second difference number of working conditions are added to the second three-dimensional simulation results under the second number of working conditions to obtain the second three-dimensional simulation results under the second target number of working conditions. The obtaining device of the thrust chamber three-dimensional simulation sample further includes a reduction module configured to reduce the thrust chamber three-dimensional simulation samples under the first target number of working conditions. The device includes a processor, a communication interface, a memory, and a communication bus. The memory stores a computer program that can be executed by the processor. When the processor executes the computer program, the method for obtaining thrust chamber three-dimensional simulation samples is executed.

4. A computer storage medium, characterized in that, The computer storage medium stores instructions, and when the instructions are executed, the method for obtaining a three-dimensional simulation sample of a thrust chamber in claim 1 is implemented.

Images