Physical field prediction method and device based on deep learning, equipment and medium
Through deep learning and static data reconstruction technology, the sample three-dimensional physics of rocket engine components is reduced and restored, solving the problem of insufficient simulation accuracy in traditional methods and achieving efficient and accurate physics prediction.
Patent Information
- Application Number
- CN202510243180.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-03
- Publication Date
- 2025-08-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional methods are difficult to meet the demand for high-precision and high-efficiency physics simulation in the field of aerospace liquid rocket engines, especially in the precise prediction of rocket engine components.
Deep learning method is used to lower the sample three-dimensional physics of rocket engine components, obtain the low-dimensional physics characteristics of the sample, obtain the mapping relationship through machine learning model training, and restore the real-time three-dimensional physics using static data reconstruction technology.
The physics simulation accuracy of rocket engine components under different operating conditions is improved, and efficient and accurate physics prediction is achieved.
Smart Images
Figure CN120449620A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing and simulation technology, and in particular to a physical field prediction method, device, equipment and medium based on deep learning. Background Art
[0002] With the continuous advancement of science and technology, the study of multi-physics coupled systems has become increasingly complex. Traditional research methods based on observation and experimentation are no longer able to meet the high-precision, high-efficiency simulation requirements of modern engineering. In the field of aerospace liquid rocket engines, accurate and efficient prediction of the physical fields of rocket engine components is crucial for product design and optimization. Summary of the Invention
[0003] The purpose of the present invention is to provide a physical field prediction method, device, equipment and medium based on deep learning to accurately and efficiently predict the physical field of rocket engine components.
[0004] In order to achieve the above object, the present invention provides the following technical solutions:
[0005] A physical field prediction method based on deep learning, comprising:
[0006] The sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine components is reduced to obtain the sample low-dimensional physical field characteristics;
[0007] A pre-built machine learning model is trained based on the sample operating condition data and the sample low-dimensional physical field characteristics through a machine learning method to obtain a machine learning model for predicting the real-time low-dimensional physical field based on the mapping relationship between the operating condition data and the low-dimensional physical field characteristics;
[0008] Inputting the real-time operating condition data of the rocket engine component into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data;
[0009] The static data reconstruction technology is used to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0010] In an optional embodiment of the present application, reducing the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics includes:
[0011] Using a singular value decomposition method, the three-dimensional physical field of the sample is reduced to obtain a low-dimensional physical field characteristic of the sample;
[0012] Alternatively, an orthogonal decomposition method is used to reduce the order of the three-dimensional physical field of the sample to obtain the low-dimensional physical field characteristics of the sample.
[0013] In an optional embodiment of the present application, the machine learning method is used to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics to obtain a machine learning model for predicting the real-time low-dimensional physical field based on the mapping relationship between the sample operating condition data and the low-dimensional physical field characteristics, including:
[0014] The sample operating condition data and the sample low-dimensional physical field characteristics are used as training samples to train the pre-built machine learning model to obtain a trained machine learning model.
[0015] In an optional embodiment of the present application, the use of static data reconstruction technology to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data includes:
[0016] Using a singular value decomposition method, the three-dimensional physical field of the sample is reduced to obtain an orthogonal basis matrix;
[0017] The orthogonal basis matrix is multiplied by the low-dimensional physical field feature to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0018] In an optional embodiment of the present application, the present invention further includes:
[0019] obtaining sample operating condition data of the rocket engine component;
[0020] The sample operating condition data is input into a pre-built three-dimensional characteristic model of a rocket engine component to obtain a sample three-dimensional physical field output by the three-dimensional characteristic model.
[0021] Compared with the existing technology, the present application provides a deep learning-based physical field prediction method. This method reduces the order of the sample three-dimensional physical field corresponding to the sample operating condition data of rocket engine components to obtain the sample low-dimensional physical field characteristics. Then, the machine learning model is trained based on the mapping relationship between the sample low-dimensional physical field characteristics and the sample operating condition data. The trained machine learning model is then used to analyze the real-time operating condition data of the rocket engine components to obtain the real-time low-dimensional physical field characteristics corresponding to the real-time operating condition data. Finally, the real-time low-dimensional physical field is restored to obtain the real-time three-dimensional physical field. This method realizes the prediction of the physical field corresponding to the rocket engine components under different operating conditions, which is conducive to improving the accuracy of physical field simulation.
[0022] The present invention also provides a physical field prediction device based on deep learning, comprising:
[0023] A physical field order reduction unit is used to reduce the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics;
[0024] a model building unit, configured to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics through a machine learning method, to obtain a machine learning model for predicting the real-time low-dimensional physical field based on a mapping relationship between the operating condition data and the low-dimensional physical field characteristics;
[0025] A low-dimensional physical field prediction unit, configured to input the real-time operating condition data of the rocket engine component into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data;
[0026] The three-dimensional physical field reconstruction unit is used to restore the real-time low-dimensional physical field characteristics by using static data reconstruction technology to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0027] Compared with the prior art, the beneficial effects of the deep learning-based physical field prediction device provided by the present invention are the same as the beneficial effects of the deep learning-based physical field prediction method described in the above technical solution, and will not be repeated here.
[0028] The present invention further provides an electronic device, comprising:
[0029] processor;
[0030] a memory for storing instructions executable by the processor;
[0031] The processor is used to execute the above-mentioned deep learning-based physical field prediction method by running instructions in the memory.
[0032] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the field cloud map display method of the rocket engine described in the above technical solution, and will not be repeated here.
[0033] The present invention also provides a computer storage medium, which stores instructions. When the instructions are executed, the above-mentioned physical field prediction method based on deep learning is implemented.
[0034] Compared with the prior art, the beneficial effects of the computer storage medium provided by the present invention are the same as the beneficial effects of the physical field prediction method based on deep learning described in the above technical solution, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] 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:
[0036] Figure 1 A flow chart of a physical field prediction method based on deep learning provided in an embodiment of the present application;
[0037] Figure 2 A structural diagram of a physical field prediction device based on deep learning provided in an embodiment of the present application;
[0038] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0039] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the words "first" and "second" are used in the embodiments of the present invention to distinguish between identical or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are merely used to distinguish between different thresholds and do not limit their order. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or execution order, and the words "first" and "second" do not necessarily mean different.
[0040] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.
[0041] In the present invention, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.
[0042] With the continuous advancement of science and technology, the study of multi-physics coupled systems has become increasingly complex. Traditional research methods based on observation and experimentation are no longer able to meet the high-precision, high-efficiency simulation requirements of modern engineering. In the field of aerospace liquid rocket engines, accurate and efficient prediction of the physical fields of rocket engine components is crucial for product design and optimization.
[0043] The present application provides a physical field prediction method, device, equipment and medium based on deep learning to accurately and efficiently predict the physical field of rocket engine components, which are described in detail one by one in the following embodiments.
[0044] Please refer to Figure 1 , Figure 1 Flowchart of the deep learning-based physical field prediction method provided in an embodiment of the present application.
[0045] like Figure 1 As shown, the physical field prediction method based on deep learning includes the following S101 to S104:
[0046] S101, reducing the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics.
[0047] The sample three-dimensional physical field of the sample operating condition data of the rocket engine component can be understood as a three-dimensional physical field obtained by combining the three-dimensional characteristic model of the rocket engine component with the historical operating condition data.
[0048] In an optional embodiment of the present application, the three-dimensional characteristic model can be constructed based on the actual structure of the rocket engine components, using three-dimensional technology and combining with the physical equations of the engine components; wherein the engine components include: three-dimensional characteristic models of key components of the rocket engine such as flow regulator, thrust chamber, inducer, centrifugal pump, etc.; the physical equations include: combustion dynamics formulas, fluid mechanics formulas, structural mechanics formulas, etc.
[0049] In actual application, the sample operating condition data of the rocket engine components are input into the three-dimensional feature model, so that the three-dimensional feature model combines the sample operating condition data and the corresponding physical equations to obtain a sample three-dimensional physical field corresponding to the rocket engine operating condition data.
[0050] Considering that the traditional process of predicting the physical field of rocket engine components based on the three-dimensional feature model as mentioned above requires a large amount of calculations on the operating data of the rocket engine, this application adopts a machine learning method to construct a machine learning model that can predict the low-dimensional physical field characteristics of the rocket engine.
[0051] Specifically, before constructing the machine learning model, first, it is necessary to construct the training samples corresponding to the model, that is, the sample operating condition data and the sample low-dimensional physical field characteristics.
[0052] Specifically, as described in S101 above, the step of reducing the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component can be achieved by the singular value decomposition (SVD) method to reduce the amount of data in the sample three-dimensional physical field, retain the key physical characteristics of the key rocket engine components, and achieve the extraction of the main characteristics of the key components of the rocket engine components, thereby efficiently describing and compressing the sample three-dimensional physical field. In another optional embodiment of the present application, the order reduction of the sample physical field can also be achieved by orthogonal decomposition (POD), thereby extracting the key physical characteristics of the rocket engine components.
[0053] In another optional embodiment of the present application, it is considered that the process of reducing the order of the sample three-dimensional physical field will cause the reduced sample low-dimensional physical field to lose part of the data, which in turn leads to low prediction accuracy of the physical field by the subsequent machine learning model obtained by training based on the sample low-dimensional physical field.
[0054] To solve this problem, the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component is reduced to obtain the sample low-dimensional physical field characteristics, including:
[0055] Using a singular value decomposition method, the three-dimensional physical field of the sample is degraded to obtain a first low-dimensional physical field feature;
[0056] Inputting the sample three-dimensional physical field into a feature extraction network to obtain extraction features of the sample three-dimensional physical field;
[0057] The first low-dimensional physical field feature and the extracted feature are subjected to feature fusion to obtain the sample low-dimensional physical field feature.
[0058] The feature extraction network may be a convolutional neural network (CNN) or a recurrent neural network (RNN), and this application does not impose any restrictions on this.
[0059] The extracted features can be understood as the key features in the sample three-dimensional physical field used to describe the operating laws of rocket engine components. In actual application, these features can be combined with the first low-dimensional physical field features, and then these features can be used to make up for the missing operating law information in the first low-dimensional physical field features, thereby improving the training accuracy of subsequent machine learning models.
[0060] S102, through a machine learning method, a pre-built machine learning model is trained based on the sample operating condition data and the sample low-dimensional physical field characteristics to obtain a machine learning model for predicting the real-time low-dimensional physical field according to the mapping relationship between the operating condition data and the low-dimensional physical field characteristics.
[0061] In an embodiment of the present application, in order to achieve accurate and efficient prediction of the physical field, the sample low-dimensional physical field characteristics obtained in S101 and the sample operating condition data corresponding to the sample physical field characteristics are used as training samples to train a pre-constructed machine learning model so that the machine learning model learns the mapping relationship between the physical field characteristics and the operating condition data.
[0062] In actual application, the machine learning model includes but is not limited to a multi-layer feedforward neural network model, a deep learning model, etc.
[0063] During the training process, the sample operating condition data may be input into the machine learning model to obtain a first physical field feature output by the machine learning model;
[0064] Thereafter, the machine learning model is trained based on the difference between the first physical field characteristics and the sample physical field characteristics.
[0065] In another optional embodiment of the present application,
[0066] S103, inputting the real-time operating condition data of the rocket engine components into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data.
[0067] After obtaining the trained machine learning model, the machine learning model can be used to predict the low-dimensional physical field characteristics of the rocket engine system under different working conditions, and the corresponding real-time physical field characteristics can be obtained by inputting the real-time working condition data of the rocket engine components.
[0068] S104 , using static data reconstruction technology to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0069] The static data reconstruction technology can be understood as a technology that remaps low-dimensional data after dimensionality reduction back to high-dimensional space. Through the static data reconstruction technology, while maintaining key information, the requirements for computing and storage can be reduced, and high-dimensional data can be restored when needed for detailed analysis or visualization.
[0070] The use of static data reconstruction technology to restore the real-time low-dimensional physical field features refers to remapping the reduced-order low-dimensional physical field features back to the high-dimensional space. This method is based on the order reduction process of the sample three-dimensional physical field in S101. The process of reducing the order of the sample three-dimensional physical field can be expressed by the following formula (1):
[0071]
[0072] Wherein, Y represents the low-dimensional physical field characteristics; X represents the three-dimensional physical field of the sample; is an orthogonal basis matrix.
[0073] In the process of reducing the order of the sample three-dimensional physical field using the singular value decomposition method, the orthogonal basis matrix is determined. In the process of restoring the real-time low-dimensional physical field characteristics, it is only necessary to combine the low-dimensional physical field characteristics with the orthogonal basis matrix to obtain the real-time three-dimensional physical field corresponding to the real-time working condition data.
[0074] In summary, the present application provides a physical field prediction method based on deep learning. This method reduces the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics. Afterwards, the machine learning model is trained based on the mapping relationship between the sample low-dimensional physical field characteristics and the sample operating condition data. The real-time operating condition data of the rocket engine component is analyzed by the trained machine learning model to obtain the real-time low-dimensional physical field characteristics corresponding to the real-time operating condition data. Finally, the real-time low-dimensional physical field is restored to obtain the real-time three-dimensional physical field. This method realizes the prediction of the physical field corresponding to the rocket engine component under different operating conditions, which is conducive to improving the accuracy of physical field simulation.
[0075] The present application also provides a physical field prediction device based on deep learning. Figure 2 , Figure 2 This is a structural diagram of the deep learning-based physical field prediction device provided in an embodiment of the present application.
[0076] like Figure 2 As shown, the physical field prediction device based on deep learning includes:
[0077] The physical field order reduction unit 201 is used to reduce the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics;
[0078] A model building unit 202 is configured to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics using a machine learning method to obtain a machine learning model for predicting the real-time low-dimensional physical field based on a mapping relationship between the operating condition data and the low-dimensional physical field characteristics;
[0079] A low-dimensional physical field prediction unit 203 is configured to input the real-time operating condition data of the rocket engine component into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data;
[0080] The three-dimensional physical field reconstruction unit 204 is used to restore the real-time low-dimensional physical field characteristics by using static data reconstruction technology to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0081] In an optional embodiment of the present application, reducing the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics includes:
[0082] Using a singular value decomposition method to reduce the order of the sample's three-dimensional physical field to obtain the sample's low-dimensional physical field characteristics;
[0083] Alternatively, an orthogonal decomposition method is used to reduce the order of the three-dimensional physical field of the sample to obtain the low-dimensional physical field characteristics of the sample.
[0084] In an optional embodiment of the present application, the machine learning method is used to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics to obtain a machine learning model for predicting the real-time low-dimensional physical field based on the mapping relationship between the sample operating condition data and the low-dimensional physical field characteristics, including:
[0085] The sample operating condition data and the sample low-dimensional physical field characteristics are used as training samples to train the pre-built machine learning model to obtain a trained machine learning model.
[0086] In an optional embodiment of the present application, the use of static data reconstruction technology to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data includes:
[0087] Using a singular value decomposition method, the three-dimensional physical field of the sample is reduced to obtain an orthogonal basis matrix;
[0088] The orthogonal basis matrix is multiplied by the low-dimensional physical field feature to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
[0089] In an optional embodiment of the present application, the device is further used for:
[0090] obtaining sample operating condition data of the rocket engine component;
[0091] The sample operating condition data is input into a pre-built three-dimensional characteristic model of a rocket engine component to obtain a sample three-dimensional physical field output by the three-dimensional characteristic model.
[0092] The above-mentioned device embodiment provided in this embodiment and the method embodiment of this application belong to the same application concept, and can execute the physical field prediction method based on deep learning provided in any of the above-mentioned embodiments of this application, and have the corresponding functional modules and beneficial effects of executing the physical field prediction method based on deep learning. For technical details not fully described in this embodiment, please refer to the specific processing content of the physical field prediction method based on deep learning provided in the above-mentioned embodiments of this application, and will not be repeated here.
[0093] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device. The processor can be a general-purpose processor, such as a CPU or a microprocessor, and the memory can be a memory within the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits. The functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units can be realized by designing the logical relationships between the components within the circuit. For another example, in another implementation, the hardware circuit can be implemented by a PLD. For example, an FPGA can include a large number of logic gate circuits. The connection relationships between the logic gate circuits are configured through a configuration file to realize the functions of some or all of the above units. All units of the above devices can be implemented entirely in the form of a processor calling software, or entirely in the form of hardware circuits, or partially in the form of a processor calling software, with the remaining parts implemented in the form of hardware circuits.
[0094] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.
[0095] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
[0096] In addition, the various units in the above apparatus may be fully or partially integrated together, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the apparatus. The at least one processor may be of different types, such as a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.
[0097] The present application also provides an electronic device, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0098] like Figure 3 As shown, the electronic device includes:
[0099] Processor 210;
[0100] a memory 200 for storing instructions executable by the processor 210;
[0101] The processor 210 is configured to execute the field cloud display method for a rocket engine disclosed in any of the above embodiments by running instructions in the memory 200 .
[0102] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are interconnected via a bus.
[0103] A bus may include a pathway that transfers information between components of a computer system.
[0104] Processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, or the like, or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention. Alternatively, it can be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.
[0105] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.
[0106] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include program code, which may include computer operating instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, etc.
[0107] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a touch screen, etc.
[0108] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speakers, etc.
[0109] The communication interface 220 may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.
[0110] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of the field cloud map display method of any rocket engine provided in the above embodiments of the present application.
[0111] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the deep learning-based physical field prediction method of various embodiments of the present application.
[0112] The computer program product may be written in any combination of one or more programming languages to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0113] In addition, an embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the deep learning-based physical field prediction method in various embodiments of the present application.
[0114] For the sake of simplicity, the aforementioned method embodiments are described as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.
[0115] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.
[0116] The steps in the methods of each embodiment of the present application can be adjusted in sequence, merged, and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.
[0117] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be merged, divided, and deleted according to actual needs.
[0118] In the several embodiments provided in this application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or submodules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.
[0119] The modules or submodules described as separate components may or may not be physically separate, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules may be selected to achieve the purpose of this embodiment according to actual needs.
[0120] In addition, each functional module or submodule in each embodiment of the present application may be integrated into a processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into a single module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or software functional modules or submodules.
[0121] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0122] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software units executed by a processor, or a combination of the two. The software units may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0123] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.
[0124] The above description of the disclosed embodiments will enable those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is to be construed in the widest manner consistent with the principles and novel features disclosed herein.
Claims
1. A physical field prediction method based on deep learning, characterized in that: include: The sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine components is reduced to obtain the sample low-dimensional physical field characteristics; A pre-built machine learning model is trained based on the sample operating condition data and the sample low-dimensional physical field characteristics through a machine learning method to obtain a machine learning model for predicting the real-time low-dimensional physical field based on the mapping relationship between the operating condition data and the low-dimensional physical field characteristics; Inputting the real-time operating condition data of the rocket engine component into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data; The static data reconstruction technology is used to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
2. The method according to claim 1, characterized in that The sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component is reduced to obtain the sample low-dimensional physical field characteristics, including: Using a singular value decomposition method to reduce the order of the sample's three-dimensional physical field to obtain the sample's low-dimensional physical field characteristics; Alternatively, an orthogonal decomposition method is used to reduce the order of the three-dimensional physical field of the sample to obtain the low-dimensional physical field characteristics of the sample.
3. The method according to claim 1, characterized in that The machine learning method is used to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics to obtain a machine learning model for predicting the real-time low-dimensional physical field based on the mapping relationship between the sample operating condition data and the low-dimensional physical field characteristics, including: The sample operating condition data and the sample low-dimensional physical field characteristics are used as training samples to train the pre-built machine learning model to obtain a trained machine learning model.
4. The method according to claim 1, wherein The method of using static data reconstruction technology to restore the real-time low-dimensional physical field characteristics to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data includes: Using a singular value decomposition method, the three-dimensional physical field of the sample is reduced to obtain an orthogonal basis matrix; The orthogonal basis matrix is multiplied by the low-dimensional physical field feature to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
5. The method according to claim 1, wherein Also includes: obtaining sample operating condition data of the rocket engine component; The sample operating condition data is input into a pre-built three-dimensional characteristic model of a rocket engine component to obtain a sample three-dimensional physical field output by the three-dimensional characteristic model.
6. A physical field prediction device based on deep learning, characterized in that: include: A physical field order reduction unit is used to reduce the order of the sample three-dimensional physical field corresponding to the sample operating condition data of the rocket engine component to obtain the sample low-dimensional physical field characteristics; a model building unit, configured to train a pre-built machine learning model based on the sample operating condition data and the sample low-dimensional physical field characteristics through a machine learning method, to obtain a machine learning model for predicting the real-time low-dimensional physical field based on a mapping relationship between the operating condition data and the low-dimensional physical field characteristics; A low-dimensional physical field prediction unit, configured to input the real-time operating condition data of the rocket engine component into the machine learning model to obtain real-time low-dimensional physical field features corresponding to the real-time operating condition data; The three-dimensional physical field reconstruction unit is used to restore the real-time low-dimensional physical field characteristics by using static data reconstruction technology to obtain a real-time three-dimensional physical field corresponding to the real-time working condition data.
7. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the deep learning-based physical field prediction method described in any one of claims 1 to 5 by running instructions in the memory.
8. A computer storage medium, characterized in that The computer storage medium stores instructions, and when the instructions are executed, the physical field prediction method based on deep learning described in any one of claims 1 to 5 is implemented.