Error correction method and system for high-speed aerodynamic prediction

Abstract

The application discloses an error correction method and system for high-speed aerodynamic prediction, and relates to the field of data processing. The method comprises the following steps: determining aircraft structure design information of a target aircraft, a preset flight route and flight parameters; analyzing a flow region experienced by the target aircraft in the atmosphere based on the preset flight route and the flight parameters, and generating a multi-stage flow region; analyzing gas molecule collision characteristics of the multi-stage flow region, and combining the aircraft structure design information to perform aerodynamic prediction, and generating multi-stage aerodynamic prediction data; determining a transition region and transition region characteristics of the multi-stage flow region on the preset flight route; and training a transition correction layer based on the transition region characteristics, and performing error correction on the multi-stage aerodynamic prediction data. The technical problem of large prediction error in the existing high-speed aerodynamic prediction is solved, and the technical effect of improving the accuracy of aerodynamic prediction is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and particularly relates to an error correction method and system for high-speed aerodynamic prediction. BACKGROUND

[0002] Aerodynamic prediction of high-speed vehicles is crucial for the design and safe operation of the vehicles, especially when entering the atmosphere. Accurate aerodynamic prediction can help optimize flight trajectories, improve fuel efficiency, and ensure flight safety. Currently, the main methods to solve this problem are through computational fluid dynamics (CFD) simulation and empirical formulas to predict aerodynamic characteristics. These methods can provide estimates of aerodynamic parameters to some extent. However, existing methods have limitations in dealing with complex flow phenomena when high-speed vehicles enter the atmosphere, especially in the transition region between different flow regions, where the variation of aerodynamic parameters is complex, resulting in large prediction errors.

[0003] In the related art, there is a technical problem of large prediction error in high-speed aerodynamic prediction. SUMMARY

[0004] The present application provides an error correction method and system for high-speed aerodynamic prediction, which determines the structural design parameters of the aircraft, the preset flight route and the flight conditions, analyzes the different flow regions experienced by the aircraft when entering the atmosphere based on these input parameters, divides the multi-stage flow region, combines the collision characteristics of gas molecules in different flow regions and the aircraft configuration for aerodynamic prediction, generates aerodynamic data for each stage, further identifies the transition region where the flow state changes on the flight trajectory, extracts its flow characteristics, and uses these characteristic data to train a transition correction model to correct the error of the preliminary aerodynamic prediction result across the flow domain, and obtain the full flight trajectory aerodynamic characteristic prediction result. Technical means such as technical means solve the technical problem of large prediction error in existing high-speed aerodynamic prediction, and achieve the technical effect of improving the accuracy of aerodynamic prediction.

[0005] The present application provides an error correction method for high-speed aerodynamic prediction, comprising: determining the aircraft structural design information of a target aircraft, a preset flight route and flight parameters; analyzing the flow region experienced by the target aircraft when entering the atmosphere based on the preset flight route and the flight parameters, generating a multi-stage flow region; analyzing the collision characteristics of gas molecules in the multi-stage flow region, combining the aircraft structural design information for aerodynamic prediction, generating multi-stage aerodynamic prediction data; determining the transition region of the multi-stage flow region and the transition region characteristics on the preset flight route; training a transition correction layer based on the transition region characteristics, and correcting the error of the multi-stage aerodynamic prediction data.

[0006] In a possible implementation, based on the preset flight route and the flight parameter, a flow region experienced by a target aircraft entering the atmosphere is analyzed, and the following processing is performed: a Mach number and a Reynolds number of each flight position are calculated based on the preset flight route and the flight parameter respectively; a molecular flow division mechanism determined for a free molecular flow region, a rarefied transitional flow region and a continuous flow region is read; based on the molecular flow division mechanism, the continuous region is segmented according to the Mach number and the Reynolds number of each flight position, and a flow region map is generated; and the multi-stage flow region is generated based on the flow region map.

[0007] In a possible implementation, gas molecule collision characteristics of the multi-stage flow region are analyzed, aerodynamic prediction is performed in combination with the aircraft structure design information, multi-stage aerodynamic prediction data is generated, and the following processing is performed: a pre-constructed molecular collision database is connected, and collision frequencies between gas molecules corresponding to the free molecular flow region, the rarefied transitional flow region and the continuous flow region are read, to generate free molecular flow collision parameters, rarefied transitional flow molecular collision parameters and continuous flow molecular collision parameters; local flow field difference analysis is performed based on the aircraft structure design information, and aircraft local flow field difference characteristics are constructed; multi-stage aircraft local molecule collision parameter analysis is performed in combination with the aircraft local flow field difference characteristics, the free molecular flow collision parameters, the rarefied transitional flow molecular collision parameters and the continuous flow molecular collision parameters, to generate respective molecule collision parameters corresponding to each stage; and aerodynamic prediction is performed by calling an aerodynamic-molecule collision regression relationship trained based on a structure material in the aircraft structure design information, based on the respective molecule collision parameters corresponding to each stage, to generate the multi-stage aerodynamic prediction data.

[0008] In a possible implementation, the following processing is performed: the local flow field difference analysis includes flow field difference analysis of a wing, a tail and a fuselage part.

[0009] In a possible implementation, based on the aircraft structure design information, local flow field difference analysis is performed, and aircraft local flow field difference characteristics are constructed, and the following processing is performed: modeling is performed according to the aircraft structure design information, to generate a three-dimensional geometric model and flow field correlation parameters; based on the three-dimensional geometric model and the flow field correlation parameters, CFD simulation is performed, to analyze interaction between an aircraft surface and a flow field, to identify an influence of a wing, a tail and a fuselage part on the flow field, and to generate the aircraft local flow field difference characteristics.

[0010] In a possible implementation, the following processing is performed: the interaction analysis between the aircraft surface and the flow field includes local difference analysis of surface aerodynamic heating, aerodynamic load and flow field distribution.

[0011] In a possible implementation, the following processing is performed: the transition region includes a first type of transition region and a second type of transition region, wherein the first type of transition region is a transition region from a free molecular flow to a rarefied transitional flow, and the second type of transition region is a transition region from the rarefied transitional flow to a continuous flow; and the transition region features include first flow field change features corresponding to the first type of transition region and second flow field change features corresponding to the second type of transition region.

[0012] In a possible implementation, a transition correction layer is trained based on the transition region features, and error correction is performed on the multi-stage aerodynamic prediction data, and the following processing is performed: preset key features are extracted from the first flow field change features and the second flow field change features, including change trends of Mach number, Reynolds number, and molecular collision parameters, to generate first key features and second key features; a regression relationship between changes of Mach number, Reynolds number, and molecular collision parameters and aerodynamic parameters is constructed, and then a first transition correction layer is trained according to the first key features, and a second transition correction layer is trained according to the second key features; and the first transition correction layer and the second transition correction layer are used to perform error correction on the multi-stage aerodynamic prediction data.

[0013] In a possible implementation, the following processing is performed: the transition region further includes a third type of transition region, and the third type of transition region is an aerodynamic characteristic transition region; transition features of the third type of transition region are collected, including aerodynamic heat distribution and aerodynamic load change features of a surface of the aircraft, and a third transition correction layer is trained.

[0014] The application also provides an error correction system for high-speed aerodynamic prediction, including: a flight information determination module configured to determine aircraft structure design information of a target aircraft, a preset flight route, and flight parameters; a flow region analysis module configured to analyze flow regions experienced by the target aircraft in entering the atmosphere based on the preset flight route and the flight parameters, and generate multi-stage flow regions; an aerodynamic prediction module configured to analyze gas molecular collision features of the multi-stage flow regions, and perform aerodynamic prediction in combination with the aircraft structure design information, and generate multi-stage aerodynamic prediction data; a transition region feature determination module configured to determine transition regions and transition region features of the multi-stage flow regions in the preset flight route; and an error correction module configured to train a transition correction layer based on the transition region features, and perform error correction on the multi-stage aerodynamic prediction data.

[0015] The proposed error correction method and system for high-speed aerodynamic prediction, as described in this application, first determines the target aircraft's structural design information, preset flight path, and flight parameters. Then, based on the preset flight path and flight parameters, it analyzes the flow regions experienced by the target aircraft upon entering the atmosphere, generating multi-stage flow regions. Next, it analyzes the gas molecule collision characteristics of these multi-stage flow regions and, combined with the aircraft's structural design information, performs aerodynamic prediction to generate multi-stage aerodynamic prediction data. Then, it determines the transition regions and characteristics of these multi-stage flow regions along the preset flight path. Finally, it trains a transition correction layer based on these transition region characteristics to correct errors in the multi-stage aerodynamic prediction data. This achieves the technical effect of improving the accuracy of aerodynamic prediction. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a flowchart illustrating the error correction method for high-speed aerodynamic prediction provided in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of the structure of an error correction system for high-speed aerodynamic prediction provided in an embodiment of this application.

[0019] Explanation of reference numerals in the attached diagram: Flight information determination module 10, flow region analysis module 20, aerodynamic prediction module 30, transition region feature determination module 40, error correction module 50. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, "some embodiments" are referred, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict, the term "first\second" referred to only distinguishes similar objects, and does not represent a specific order for the objects. The terms "include" and "have" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide an error correction method for high-speed aerodynamic prediction, as shown in Figure 1 The method comprises the following steps:

[0024] In step S100, aircraft structure design information of a target aircraft, a preset flight route and flight parameters are determined.

[0025] Specifically, the aircraft structure design information includes the size of the aircraft shape, material properties, mass distribution, etc., which are used to describe the physical structure of the aircraft. The preset flight route refers to the flight path of the aircraft according to the predetermined task planning, which is expressed in latitude and longitude coordinates and height. The flight parameters refer to the parameters that need to be considered in the flight process, such as speed, attack angle, side slip angle, etc.

[0026] The three-dimensional model file (such as STL format) of the aircraft is exported from the aircraft design software (such as CATIA, SolidWorks, etc.), and the three-dimensional structure model data of the aircraft is obtained, including the size of the shape, the material properties, the mass distribution, etc. The preset flight route (such as latitude and longitude coordinate sequence, height change curve) and flight parameters (such as speed, attack angle, side slip angle, etc.) are extracted from the flight mission planning system. The above data is transmitted to the aerodynamic prediction system through the API interface.

[0027] In step S200, the flow region experienced by the target aircraft entering the atmosphere is analyzed based on the preset flight route and the flight parameters, and a multi-stage flow region is generated.

[0028] Specifically, the flow region refers to the region divided according to the flight state of the aircraft in the atmosphere, such as hypersonic, supersonic, subsonic, etc. The aircraft structure design information, the preset flight route and the flight parameters of the target aircraft are imported into the computational fluid dynamics (CFD) software (such as ANSYS Fluent, OpenFOAM), and the atmospheric environment parameters (such as the distribution of temperature and density changing with height) are set. Run the CFD simulation to generate flow field data of the target aircraft at different flight stages. Use the flow region division algorithm to divide the flow field into multiple stages according to parameters such as Mach number and Reynolds number.

[0029] For example, using ANSYS Fluent for flow field simulation, according to the speed and altitude of the target aircraft, the flow region is divided into three stages: hypersonic stage: Mach number > 5, corresponding to altitude > 80 km; supersonic stage: 1 < Mach number ≤ 5, corresponding to altitude 50 km-80 km; subsonic stage: Mach number ≤ 1, corresponding to altitude < 50 km.

[0030] In one possible implementation, based on the preset flight route and the flight parameters, the flow region experienced by the target aircraft entering the atmosphere is analyzed to generate a multi-stage flow region, and step S200 further includes step S210 of calculating the Mach number and Reynolds number of each flight position based on the preset flight route and the flight parameters. Specifically, the Mach number is the ratio of the flight speed to the local sound speed, which is used to describe the speed state of the aircraft. The Reynolds number is a dimensionless number representing the flow state of the fluid, which is used to distinguish the type of flow region. The height and speed of each flight position are extracted from the preset flight route and flight parameters. Using a standard atmospheric model (such as International Standard Atmosphere ISA) or a custom atmospheric model, the temperature, pressure and density at different altitudes are obtained. The Mach number is calculated according to the flight speed and local sound speed. The Reynolds number is calculated according to the flight speed, characteristic length (such as wing chord length) and fluid dynamic viscosity.

[0031] For example, for a certain flight position, the height is 50 km and the speed is 3000 m / s, using the International Standard Atmosphere model to calculate: the local temperature is 270 K, the local sound speed is 330 m / s, the local density is 0.001 kg / m 3 , the dynamic viscosity is 1.68×10 -5 Pa·s, and the characteristic length is 1 m (assuming a certain dimension of the aircraft, such as the wing chord length). The Mach number (Ma) is the ratio of the flight speed to the local sound speed: Ma=3000 / 330≈9.1. The Reynolds number (Re) is the ratio of inertial force to viscous force, and the calculation formula is: Re=fluid density×fluid velocity×characteristic length / fluid dynamic viscosity=0.001×3000×1 / 1.68×10 -5 ≈1.79×10 5 .

[0032] In step S220, the molecular flow division mechanism determined for the free molecular flow region, the rarefied transitional flow region, and the continuous flow region is read. Specifically, the free molecular flow region refers to a region where the gas molecule collision frequency is extremely low, and the molecular motion is close to free flight. The rarefied transitional flow region refers to a region where the gas molecule collision frequency is moderate, and the flow characteristics are between the free molecular flow and the continuous flow. The continuous flow region refers to a region where the gas molecule collision frequency is high, and the fluid behavior can be described using the continuous medium assumption. The division criteria for the free molecular flow region, the rarefied transitional flow region, and the continuous flow region are read from the database and loaded into the calculation module. For example, the division criteria are shown in Table 1.

[0033] Table 1: Example of molecular flow division mechanism

[0034] .

[0035] In step S230, based on the molecular flow division mechanism, the continuous region is divided according to the Mach number and Reynolds number of each flight position, and a flow region map is generated. Specifically, for each flight position, the Mach number and Reynolds number are combined with the division mechanism to determine the flow region to which it belongs. Using a drawing tool (such as MATLAB, Python's Matplotlib), the flow region information of all flight positions is integrated to generate a flow region map. The flow region map is used to display the distribution of different flow regions on the flight path in graphical form.

[0036] In step S240, the multi-stage flow region is generated based on the flow region map. Specifically, according to the flow region map, the flight path is divided into multiple stages, each stage corresponding to a different flow region type, and the flow region information of each stage is stored as a data file. For example, the generated multi-stage flow region is shown in Table 2.

[0037] Table 2: Example of multi-stage flow region

[0038] .

[0039] This implementation can accurately divide the flight path into free molecular flow region, rarefied transitional flow region, and continuous flow region by calculating the Mach number and Reynolds number and combining the molecular flow division mechanism. This accurate division helps to more accurately simulate the aerodynamic characteristics of the aircraft in different flow regions. By accurately dividing the flow region, more accurate input conditions can be provided for subsequent aerodynamic prediction, thereby improving the accuracy of aerodynamic prediction.

[0040] In step S300, the gas molecule collision characteristics of the multi-stage flow region are analyzed, and aerodynamic prediction is performed in combination with the aircraft structure design information to generate multi-stage aerodynamic prediction data.

[0041] Specifically, the gas molecule collision characteristics are analyzed using a direct simulation Monte Carlo method (DSMC) or a continuum model (such as the Navier-Stokes equation). The gas molecule collision characteristics are parameters describing the collision behavior of gas molecules in the flow region, such as collision frequency, collision cross section, etc. In combination with the aircraft structure design information, aerodynamic prediction data such as lift coefficient, drag coefficient are generated using aerodynamic prediction algorithms (such as CFD-based aerodynamic coefficient calculation). The aerodynamic prediction data are used to describe the aerodynamic performance of the target aircraft in different flow regions.

[0042] In one possible implementation, the gas molecule collision characteristics of the multi-stage flow region are analyzed, the aerodynamic prediction is performed in combination with the aircraft structure design information, and the multi-stage aerodynamic prediction data are generated. Step S300 further includes step S310 of connecting a pre-built molecular collision database, reading the collision frequency between gas molecules corresponding to the free molecular flow region, the rarefied transitional flow region and the continuous flow region respectively, and generating the free molecular flow collision parameters, the rarefied transitional flow molecular collision parameters and the continuous flow molecular collision parameters. Specifically, the molecular collision database is a pre-built database storing the collision frequency and other related parameters of gas molecules in different flow regions (free molecular flow, rarefied transitional flow, continuous flow). The pre-built molecular collision database is connected. According to the type of flow region, the corresponding gas molecule collision frequency and other related parameters are read, and the free molecular flow collision parameters, the rarefied transitional flow molecular collision parameters and the continuous flow molecular collision parameters are generated.

[0043] For example, it is assumed that the collision frequencies stored in the molecular collision database are as follows: free molecular flow region: collision frequency f free =10 3 s －1 , rarefied transitional flow region: collision frequency f trans =10 5 s －1 , continuous flow region: collision frequency f cont =10 7 s －1 . The generated collision parameters are shown in Table 3.

[0044] Table 3: Collision parameter example:

[0045] .

[0046] Step S320, based on the aircraft structure design information, a local flow field difference analysis is performed to construct the aircraft local flow field difference characteristics. Specifically, the three-dimensional structure model of the target aircraft is imported into the CFD software, the local flow field simulation is run, the flow field distribution around the aircraft surface is calculated, and the difference characteristics of the local flow field are extracted, such as velocity gradient, pressure gradient, temperature gradient, density gradient, etc. For example, the local flow field difference characteristics of the target aircraft are shown in Table 4.

[0047] Table 4: Local flow field difference characteristic examples:

[0048] .

[0049] Step S330, combining the aircraft local flow field difference characteristics, free molecular flow collision parameters, rarefied transitional flow molecular collision parameters and continuous flow molecular collision parameters, a multi-stage aircraft local molecular collision parameter analysis is performed to generate each corresponding molecular collision parameter. Specifically, the difference characteristics of the local flow field are extracted from the flow field simulation of the aircraft, wherein the velocity gradient represents the rate of change of velocity in the flow field, the larger the velocity gradient, the more violent the change of velocity in the flow field. The pressure gradient represents the rate of change of pressure in the flow field, the larger the pressure gradient, the more violent the change of pressure in the flow field. The temperature gradient represents the rate of change of temperature in the flow field, the larger the temperature gradient, the more violent the change of temperature in the flow field. The density gradient represents the rate of change of density in the flow field, the larger the density gradient, the more violent the change of density in the flow field. Analyze the influence of these local flow field difference characteristics on the gas molecular collision parameters, specifically: the velocity gradient will affect the relative velocity of the gas molecules, in the area with large velocity gradient, the relative velocity of the gas molecules will increase, thus leading to an increase in collision frequency. For example, in the nose or tail of the aircraft, etc. areas with large velocity change, the collision frequency will be higher than other areas. The pressure gradient will affect the density distribution of the gas molecules, in the area with large pressure gradient, the density of the gas molecules will be higher, thus leading to an increase in collision frequency and collision cross section. The temperature gradient will affect the thermal motion of the gas molecules, in the area with large temperature gradient, the thermal motion of the gas molecules is more violent, the collision frequency and collision cross section will also increase. For example, in the high temperature area of the aircraft (such as near the engine nozzle), the temperature gradient is large, and the collision parameters will change significantly. The density gradient will affect the distribution of the gas molecules, in the area with large density gradient, the distribution of the gas molecules is uneven, and the collision frequency will also change accordingly. For example, in the edge area of the aircraft, the density gradient is large, and the collision parameters will be different.

[0050] For each flow region stage, the molecular collision parameters are adjusted in combination with the local flow field characteristics. The specific steps are as follows: in the free molecular flow region, the gas molecule collision frequency is low, but the local flow field characteristics (such as velocity gradient, temperature gradient) will still affect the collision parameters. For example, in the area with large velocity gradient, the collision frequency will increase slightly. In the rarefied transition flow region, the gas molecule collision frequency is moderate, and the influence of local flow field characteristics on collision parameters is more significant. For example, in the area with large pressure gradient and temperature gradient, the collision frequency and collision cross section will increase significantly. In the continuous flow region, the gas molecule collision frequency is high, and the influence of local flow field characteristics on collision parameters is also large. For example, in the area with large density gradient and pressure gradient, the collision frequency and collision cross section will further increase. By comprehensively considering the influence of velocity gradient, pressure gradient, temperature gradient and density gradient, the original collision parameters of each flow region stage are adjusted to generate molecular collision parameters of each stage.

[0051] In step S340, the aerodynamic prediction is performed based on the aerodynamic-molecular collision regression relationship trained based on the structural materials in the aircraft structure design information, using the molecular collision parameters corresponding to each stage, to generate the multi-stage aerodynamic prediction data. Specifically, the regression relationship is a prediction model established based on machine learning or statistical methods using aircraft structural materials, which is used to predict aerodynamic characteristics according to input parameters. First, load the regression model trained based on the aircraft structural materials, and for each stage, input the corresponding molecular collision parameters, call the regression model, and predict the aerodynamic characteristics of the aircraft in different flow regions, such as lift coefficient, drag coefficient, etc., by calculation or model, to generate the aerodynamic prediction data of each stage.

[0052] The aerodynamic-molecular collision regression relationship is based on a three-layer fully connected neural network model. The model realizes accurate prediction through strong association between input multi-dimensional features and output aerodynamic parameters. The core logic is as follows: the input layer receives 6-dimensional fusion data, including molecular collision frequency, collision cross section, velocity gradient, pressure gradient, temperature gradient, and density gradient. These data directly correspond to the physical properties of different flow regions and the influence of the local structure of the aircraft on the flow field. The hidden layer extracts nonlinear correlation features through 32 neurons of the ReLU activation function, and then maps them through 16 neurons to convert the original features into high-order features that can reflect the aerodynamic law. The Dropout layer is used to avoid overfitting. The output layer directly outputs the lift coefficient and the drag coefficient. During model training, historical flight data and high-precision CFD simulation data corresponding to the target aircraft structure material are collected. The data is divided into training set, validation set, and test set in the ratio of 7:2:1. The Adam optimizer is used to minimize the mean square error loss. The model is trained for 100 rounds with a batch size of 32. When the validation set loss does not decrease for 10 consecutive rounds, the learning rate decay is started with a decay coefficient of 0.5. The optimal model with a test set accuracy of ≥95% is saved. In practical applications, the model automatically matches the molecular collision parameters and local flow field difference features of different regions such as free molecular flow, rarefied transitional flow, and continuous flow as input, and outputs aerodynamic parameters that adapt to the characteristics of the region.

[0053] This implementation can more accurately adjust the molecular collision parameters by considering the local flow field difference features, thereby improving the accuracy of aerodynamic prediction and providing more accurate basis for the structural design and material selection of aircraft, and helping to optimize the aerodynamic performance of aircraft.

[0054] In one possible implementation, step S320 further includes that the local flow field difference analysis includes flow field difference analysis of the wing, tail, and fuselage parts.

[0055] Specifically, the wing is the main part of the aircraft that generates lift, and its flow field characteristics are crucial to the performance of the aircraft. The main function of the tail is to provide directional stability and control moment. The fuselage is the main structural part of the aircraft, and its flow field characteristics will affect the drag and stability of the aircraft. This implementation can more accurately adjust the molecular collision parameters by refining the local flow field difference analysis, especially the detailed analysis of the wing, tail, and fuselage parts.

[0056] In a possible implementation, the local flow field difference analysis is performed based on the aircraft structure design information, and the aircraft local flow field difference features are constructed, and step S320 further includes step S321 of modeling according to the aircraft structure design information to generate a three-dimensional geometric model and flow field related parameters. Specifically, the aircraft structure design information includes the outer shape design of the aircraft, including the size and shape of the wings, tail and fuselage, and material properties such as density, thermal conductivity, etc., as well as flight parameters such as flight speed, altitude, angle of attack, etc. A three-dimensional geometric model is generated using computer-aided design (CAD) software (such as SolidWorks, CATIA) according to the aircraft structure design information. The aircraft surface and the surrounding space are divided into small grid cells for CFD simulation, and the boundary conditions of the aircraft surface and the surrounding environment are defined, such as velocity, pressure, temperature, etc., and the initial state of the flow field is defined, such as the initial velocity field, pressure field, etc., to generate flow field related parameters.

[0057] Step S322, based on the three-dimensional geometric model and the flow field correlation parameters, the interaction between the aircraft surface and the flow field is analyzed by CFD simulation, the influence of the wing, tail and fuselage parts on the flow field is identified, and the local flow field difference characteristics of the aircraft are generated. Specifically, the computational fluid dynamics (CFD) software (such as ANSYS Fluent, OpenFOAM) is used for flow field simulation, the three-dimensional geometric model and the flow field correlation parameters are input, the simulation is run, and the interaction between the aircraft surface and the surrounding flow field is calculated. Analyze the velocity distribution of the aircraft surface, especially the velocity gradient of the wing, tail and fuselage parts; analyze the pressure distribution of the aircraft surface, especially the pressure gradient of the wing, tail and fuselage parts; analyze the temperature distribution of the aircraft surface, especially the temperature gradient of the wing, tail and fuselage parts; analyze the density distribution of the aircraft surface, especially the density gradient of the wing, tail and fuselage parts. Extract the flow field difference characteristics of the wing, tail and fuselage parts, including velocity gradient, pressure gradient, temperature gradient and density gradient. Store these features as data files for later use. Among them, the flow field difference characteristics are extracted by a multi-scale feature fusion algorithm, which designs different extraction logic for the dominant characteristics of the flow field of different parts of the wing, tail and fuselage, ensuring that the features are highly consistent with the aerodynamic influence law. First, the original data of the velocity field, pressure field, temperature field and density field output by the CFD simulation are smoothed by Gaussian filtering to remove simulation noise. According to the three-dimensional geometric model of the aircraft, the grid regions of the wing, tail and fuselage are automatically segmented, 1mm fine-scale grid is used for the lift / moment dominant characteristics of the wing and tail, and 5mm medium-scale grid is used for the drag dominant characteristics of the fuselage, to improve the relevance of feature extraction through different grid resolutions. The central difference method is used to calculate the velocity gradient, pressure gradient, temperature gradient and density gradient of each local region grid point. Finally, the gradient values are normalized according to the region type, i.e. the wing region is divided by the maximum gradient value of the wing, and the fuselage region is divided by the maximum gradient value of the fuselage, and the standardized 4-dimensional feature vector is output. This feature vector can directly reflect the different effects of different local structures on the flow field. This implementation can accurately extract the difference characteristics of the aircraft surface and the surrounding flow field through CFD simulation, providing more accurate data support for subsequent molecular collision parameter analysis.

[0058] In one possible implementation, step S322 further includes that the interaction analysis between the aircraft surface and the flow field includes local difference analysis of surface aerodynamic heating, aerodynamic load and flow field distribution.

[0059] Specifically, the surface aerodynamic heating analysis refers to analyzing the aerodynamic heating effect on the surface of the aircraft. The aerodynamic load analysis refers to analyzing the aerodynamic load distribution on the surface of the aircraft. The local difference analysis of the flow field distribution refers to analyzing the local difference of the flow field around the surface of the aircraft. Among them, the surface aerodynamic heating analysis mainly focuses on the heat flux density and temperature distribution, the heat flux density refers to the heat flow per unit area, and the temperature distribution is used to reflect the concentrated area of the thermal load. These data directly affect the thermal motion of gas molecules, thereby affecting the molecular collision parameters. Aerodynamic load refers to the air force and moment acting on the surface of the aircraft, and the aerodynamic load analysis mainly focuses on the pressure distribution and load distribution, the pressure distribution can reflect the distribution of lift and drag, and the load distribution can help evaluate the aerodynamic performance and structural strength requirement of the aircraft. These data directly affect the density distribution of gas molecules, thereby affecting the molecular collision parameters. The local difference analysis of the flow field distribution mainly focuses on the velocity distribution, pressure distribution, temperature distribution and density distribution, the velocity distribution can reflect the flow characteristics of the flow field, the pressure distribution can reflect the pressure characteristics of the flow field, the temperature distribution can reflect the thermal characteristics of the flow field, and the density distribution can reflect the density characteristics of the flow field. These data directly affect the relative velocity and density distribution of gas molecules, thereby affecting the molecular collision parameters.

[0060] This implementation can more accurately adjust the molecular collision parameters by detailed analysis of the surface aerodynamic heating, aerodynamic load and local difference of the flow field distribution. This method not only improves the accuracy of aerodynamic prediction, but also provides important data support for the design and optimization of the aircraft.

[0061] Step S400, determining the transition region of the multi-stage flow region and the transition region characteristics in the preset flight route.

[0062] Specifically, the transition region is the transition part between the multi-stage flow regions, and the characteristic parameters change more complex. In the preset flight route, the transition region between the flow regions is determined by a numerical analysis method (such as interpolation, fitting), and the characteristic parameters of the transition region are extracted, such as the change rate of the aerodynamic coefficient, the temperature gradient, etc. The transition region and its characteristic parameters are stored as a data file.

[0063] In one possible implementation, step S400 further includes: the transition region includes a first type of transition region and a second type of transition region, wherein the first type of transition region is a transition region from free molecular flow to rarefied transitional flow, and the second type of transition region is a transition region from rarefied transitional flow to continuous flow; the transition region characteristics include first flow field change characteristics corresponding to the first type of transition region and second flow field change characteristics corresponding to the second type of transition region.

[0064] Specifically, the first type of transition region is the transition region from free molecular flow to rarefied transitional flow, in which the collision frequency of gas molecules gradually increases but is still at a low level. The main characteristics of the flow field change are: gradually increasing from a low collision frequency to a moderate collision frequency; the changes of velocity gradient, pressure gradient, temperature gradient and density gradient are relatively significant; the changes of aerodynamic coefficients (such as lift coefficient, drag coefficient) are relatively complex and need special attention. The first type of transition region may have a higher error in aerodynamic prediction due to the large changes in collision frequency and flow field gradient. By analyzing these characteristics in detail, the aerodynamic prediction model can be adjusted to reduce the error.

[0065] The second type of transition region is the transition region from rarefied transitional flow to continuous flow, in which the collision frequency of gas molecules further increases and the flow field gradually tends to the characteristics of continuous flow. The main characteristics of the flow field change are: increasing from a moderate collision frequency to a higher collision frequency; the changes of velocity gradient, pressure gradient, temperature gradient and density gradient gradually tend to be stable; the changes of aerodynamic coefficients gradually tend to be stable, but the influence of local flow field differences still needs to be considered. The second type of transition region has a relatively low error in aerodynamic prediction due to the gradual stabilization of collision frequency and flow field gradient, but the influence of local flow field differences still needs to be considered.

[0066] This implementation can more accurately identify the location and characteristics of these transition regions by refining the classification and characteristic analysis of the transition regions, providing a basis for subsequent error correction, thereby optimizing the aerodynamic prediction model and improving the accuracy and reliability of the prediction.

[0067] Step S500, based on the transition region characteristics, training a transition correction layer to correct the error of the multi-stage aerodynamic prediction data.

[0068] Specifically, the transition correction layer is used to correct the error of the aerodynamic prediction data to make it closer to the true value. Linear regression, polynomial regression or other regression methods are used to establish the relationship between the transition region characteristic parameters and the aerodynamic coefficient correction values. Historical flight data or high-precision CFD simulation data are used as training data sets. By training the transition correction layer, the regression model is used to calculate the aerodynamic coefficient correction value to correct the error of the multi-stage aerodynamic prediction data.

[0069] In a possible implementation, the transition correction layer is trained based on the transition region characteristics, and error correction is performed on the multi-stage aerodynamic prediction data, and step S500 further includes step S510 of extracting preset key characteristics in the first flow field change characteristics and the second flow field change characteristics, including the change trend of Mach number, Reynolds number, and molecular collision parameters, to generate first key characteristics and second key characteristics. Specifically, the change trend of the Mach number in the first type of transition region is analyzed, the change trend of the Reynolds number in the first type of transition region is analyzed, the change trend of the molecular collision parameters (such as collision frequency and collision cross section) in the first type of transition region is analyzed, and the change trends are integrated into the first key characteristics. The change trend of the Mach number in the second type of transition region is analyzed, the change trend of the Reynolds number in the second type of transition region is analyzed, the change trend of the molecular collision parameters in the second type of transition region is analyzed, and the change trends are integrated into the second key characteristics.

[0070] Step S520, the regression relationship between the changes of the Mach number, the Reynolds number, and the molecular collision parameters and the aerodynamic parameters is constructed, and then the first transition correction layer is trained according to the first key characteristics, and the second transition correction layer is trained according to the second key characteristics. Specifically, the changes of the Mach number, the Reynolds number, and the molecular collision parameters are used as independent variables, and the correction values of the aerodynamic parameters (such as the lift coefficient and the drag coefficient) are used as dependent variables, and the regression relationship between these variables is established by using historical flight data or high-precision CFD simulation data. The first transition correction layer is trained using the first key characteristics (the key characteristics of the first type of transition region), and the second transition correction layer is trained using the second key characteristics (the key characteristics of the second type of transition region).

[0071] Step S530, the first transition correction layer and the second transition correction layer are used to perform error correction on the multi-stage aerodynamic prediction data. Specifically, for the aerodynamic prediction data of the first type of transition region, the first transition correction layer is used to perform error correction, and the predicted value of the aerodynamic coefficient is adjusted according to the first key characteristics to reduce the error. For the aerodynamic prediction data of the second type of transition region, the second transition correction layer is used to perform error correction, and the predicted value of the aerodynamic coefficient is adjusted according to the second key characteristics to reduce the error.

[0072] This implementation can more accurately correct the multi-stage aerodynamic prediction data by extracting key characteristics, constructing a regression relationship, and training a transition correction layer, which not only improves the accuracy of aerodynamic prediction, but also provides important data support for the design and optimization of aircraft.

[0073] In a possible implementation, step S500 further includes step S540, the transition region further includes a third type of transition region, the third type of transition region is a transition region of aerodynamic characteristics; the transition characteristics of the third type of transition region are collected, including the aerodynamic heat distribution and the aerodynamic load variation characteristics of the aircraft surface, and a third transition correction layer is trained.

[0074] Specifically, the third type of transition region is a transition region of aerodynamic characteristics, and the change of aerodynamic characteristics (aerodynamic heat distribution and aerodynamic load) is concerned. This region covers the whole process from free molecular flow to continuous flow. The aerodynamic heat distribution of the aircraft surface is analyzed, including heat flux density and temperature distribution. The aerodynamic load variation of the aircraft surface is analyzed, including lift coefficient, drag coefficient and moment coefficient. The aerodynamic heat distribution and the aerodynamic load variation characteristics of each flow region are collected. Historical flight data or high-precision CFD simulation data are used as training data sets. A regression relationship is constructed, taking the aerodynamic heat distribution and the aerodynamic load variation characteristics as input and the aerodynamic coefficient correction value as output. The model is trained using the training data set, and the model parameters are adjusted to minimize the error between the predicted value and the true value. The trained model is the third transition correction layer, which is used to adjust the predicted value of the aerodynamic coefficient. For the aerodynamic prediction data of each flow region, the third transition correction layer is used for error correction. According to the aerodynamic heat distribution and the aerodynamic load variation characteristics, the predicted value of the aerodynamic coefficient is adjusted to reduce the error. This implementation can more accurately correct the aerodynamic prediction data, reduce the error and improve the prediction accuracy by introducing the third transition correction layer.

[0075] The first and second transition correction layers employ a gradient boosting regression tree (GBRT) model, while the third transition correction layer uses a convolutional neural network (CNN) model. Both models achieve error correction through precise matching of features with aerodynamic parameter correction requirements. The core logic is as follows: For the first and second transition correction layers, the model uses a decision tree of depth 5 as the base learner. A feature mapping module standardizes key features such as the rate of change of Mach number and Reynolds number. A gradient calculation module captures the residual gradient between the predicted and actual aerodynamic parameter values ​​in real time. A loss update module iteratively reduces the residual. During training, a learning rate of 0.01, a subsample ratio of 0.8, and a feature sampling ratio of 0.7 are set. Training stops when the validation set residual is less than 0.001. In application, the model inputs the key feature sequence corresponding to the transition region and outputs the correction amounts for the lift and drag coefficients. The multi-stage aerodynamic prediction data is directly corrected using the formula: predicted value + correction amount. For the third transition correction layer, the CNN model is designed based on the two-dimensional distribution features of the aerodynamic characteristic transition region. The input layer receives three-dimensional data H×W×C of the aerodynamic and thermal distribution and aerodynamic load distribution of the aircraft surface grid, where H and W are the number of rows and columns of the grid, and C=2. Spatial distribution features are extracted through two layers of convolution and pooling operations, and then the feature mapping is deepened through a fully connected layer, finally outputting the accurate correction amount. During training, the SGD optimizer and Huber loss function are used, combined with data augmentation techniques to improve generalization ability. After training, models with a correction error ≤3% on the validation set are saved. When applied, the two-dimensional distribution features of the transition region are directly input, and the correction amount is output to complete the final optimization of the aerodynamic parameters of the entire flight trajectory.

[0076] This application employs techniques such as determining the structural design parameters of the aircraft, the preset flight path, and flight conditions, analyzing the different flow regions experienced by the aircraft when entering the atmosphere based on these input parameters, dividing the flow regions into multiple stages, combining the collision characteristics of gas molecules in different flow regions and the aircraft configuration to perform aerodynamic prediction, generating aerodynamic data for each stage, further identifying transition regions where the flow state changes on the flight trajectory, extracting their flow characteristics, using these characteristic data to train a transition correction model, and performing cross-flow region error correction on the preliminary aerodynamic prediction results to obtain the full flight trajectory aerodynamic characteristic prediction results. These techniques solve the technical problem of large prediction errors in existing high-speed aerodynamic predictions and achieve the technical effect of improving the accuracy of aerodynamic predictions.

[0077] In the above text, refer to Figure 1 An error correction method for high-speed aerodynamic prediction according to an embodiment of the present invention is described in detail. Next, reference will be made to... Figure 2 An error correction system for high-speed aerodynamic prediction according to an embodiment of the present invention is described.

[0078] The error correction system for high-speed aerodynamic prediction according to the embodiment of the present application is used to solve the technical problem of large prediction error in the existing high-speed aerodynamic prediction, and achieves the technical effect of improving the accuracy of aerodynamic prediction. The error correction system for high-speed aerodynamic prediction comprises: a flight information determination module 10, a flow region analysis module 20, an aerodynamic prediction module 30, a transition region feature determination module 40, and an error correction module 50.

[0079] The flight information determination module 10 is configured to determine the aircraft structure design information of the target aircraft, the preset flight route, and the flight parameters. The flow region analysis module 20 is configured to analyze the flow region experienced by the target aircraft entering the atmosphere based on the preset flight route and the flight parameters, and generate a multi-stage flow region. The aerodynamic prediction module 30 is configured to analyze the gas molecule collision characteristics of the multi-stage flow region, and perform aerodynamic prediction in combination with the aircraft structure design information to generate multi-stage aerodynamic prediction data. The transition region feature determination module 40 is configured to determine the transition region and the transition region feature of the multi-stage flow region in the preset flight route. The error correction module 50 is configured to train a transition correction layer based on the transition region feature, and perform error correction on the multi-stage aerodynamic prediction data.

[0080] In the following, the specific configuration of the flow region analysis module 20 will be described in detail. As described above, the flow region analysis module 20 can further comprise: a Mach Reynolds number calculation unit configured to calculate the Mach number and the Reynolds number of each flight position based on the preset flight route and the flight parameters; a molecular flow division mechanism reading unit configured to read the molecular flow division mechanism determined for the free molecular flow region, the rarefied transition flow region, and the continuous flow region; a continuous region segmentation unit configured to segment the continuous region according to the Mach number and the Reynolds number of each flight position based on the molecular flow division mechanism, and generate a flow region map; and a multi-stage flow region generation unit configured to generate the multi-stage flow region based on the flow region map.

[0081] In the following, the specific configuration of the aerodynamic prediction module 30 will be described in detail. As described above, the aerodynamic prediction module 30 can further include a collision parameter generation unit for connecting a pre-constructed molecular collision database to read the collision frequency between gas molecules corresponding to the free molecular flow region, the rarefied transitional flow region and the continuous flow region respectively, to generate the free molecular flow collision parameter, the rarefied transitional flow molecular collision parameter and the continuous flow molecular collision parameter; a local flow field difference analysis unit for performing local flow field difference analysis based on the aircraft structure design information to construct the aircraft local flow field difference feature; a local molecular collision parameter analysis unit for performing multi-stage aircraft local molecular collision parameter analysis in combination with the aircraft local flow field difference feature, the free molecular flow collision parameter, the rarefied transitional flow molecular collision parameter and the continuous flow molecular collision parameter to generate each molecular collision parameter corresponding to each stage; and an aerodynamic prediction unit for performing aerodynamic prediction by calling the aerodynamic-molecular collision regression relationship trained based on the structure material in the aircraft structure design information with each molecular collision parameter corresponding to each stage to generate the multi-stage aerodynamic prediction data.

[0082] In the above, the local flow field difference analysis unit can further include a local flow field difference analysis including flow field difference analysis of the wing, the tail and the fuselage part.

[0083] In the above, the local flow field difference analysis unit can further include a modeling sub-unit for modeling according to the aircraft structure design information to generate a three-dimensional geometric model and a flow field correlation parameter; and a CFD simulation sub-unit for analyzing the interaction between the aircraft surface and the flow field by CFD simulation based on the three-dimensional geometric model and the flow field correlation parameter, identifying the influence of the wing, the tail and the fuselage part on the flow field, and generating the aircraft local flow field difference feature.

[0084] In the above, the CFD simulation sub-unit can further include that the interaction analysis between the aircraft surface and the flow field includes local difference analysis of the surface aerodynamic heating, the aerodynamic load and the flow field distribution.

[0085] Hereinafter, the specific configuration of the transition region feature determination module 40 will be described in detail. As described above, the transition region feature determination module 40 can further comprise: the transition region comprises a first type of transition region and a second type of transition region, wherein the first type of transition region is a transition region from a free molecular flow to a rarefied transitional flow, and the second type of transition region is a transition region from a rarefied transitional flow to a continuous flow; and the transition region feature comprises a first flow field change feature corresponding to the first type of transition region and a second flow field change feature corresponding to the second type of transition region.

[0086] Hereinafter, the specific configuration of the error correction module 50 will be described in detail. As described above, the transition correction layer is trained based on the transition region feature, and the error correction module 50 can further comprise: a preset key feature extraction unit for extracting preset key features in the first flow field change feature and the second flow field change feature, including the variation trend of Mach number, Reynolds number and molecular collision parameter, to generate first key features and second key features; a transition correction layer training unit for constructing the regression relationship between the variation of Mach number, Reynolds number and molecular collision parameter and the aerodynamic parameter, and then training a first transition correction layer according to the first key features and a second transition correction layer according to the second key features; and an error correction unit for performing error correction on the multi-stage aerodynamic prediction data by using the first transition correction layer and the second transition correction layer.

[0087] The error correction module 50 can further comprise: a third transition correction layer training unit for the transition region further comprising a third type of transition region, the third type of transition region being an aerodynamic characteristic transition region, collecting transition features of the third type of transition region, including aerodynamic heat distribution and aerodynamic load variation characteristics of the aircraft surface, and training a third transition correction layer.

[0088] The error correction system for high-speed aerodynamic prediction provided in the embodiments of the present application can execute the error correction method for high-speed aerodynamic prediction provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0089] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and each unit and module included is only divided according to the functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy mutual differentiation, and do not limit the protection scope of the present application.

[0090] The foregoing DETAILED DESCRIPTION, including the above section titled "Detailed Description," is not to be taken as limiting the scope of the application. Various modifications, combinations, and equivalents can be apparent to those skilled in the art and can be made once the nature of the application is understood. Any modification, combination, or equivalent, which falls within the principles and the scope of the present application, is intended to be included in the present application. In some instances, the actions or steps can be performed in different order from those described herein, and still achieve desirable results. Additionally, the process depicted in the figures can not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

Claims

1. Error correction method oriented to high-speed aerodynamic prediction, characterized in that, The method comprises the following steps: determining the aircraft structure design information of the target aircraft, the preset flight route and the flight parameters; analyzing the flow region experienced by the target aircraft entering the atmosphere based on the preset flight route and the flight parameters, and generating a multi-stage flow region; analyzing the gas molecule collision characteristics of the multi-stage flow region, combining the aircraft structure design information to perform aerodynamic prediction, and generating multi-stage aerodynamic prediction data; determining the transition region and the transition region characteristics of the multi-stage flow region in the preset flight route; training a transition correction layer based on the transition region characteristics to correct errors of the multi-stage aerodynamic prediction data; the transition region includes a first type of transition region and a second type of transition region, wherein the first type of transition region is a transition region from free molecular flow to rarefied transitional flow, and the second type of transition region is a transition region from rarefied transitional flow to continuous flow; the transition region characteristics include a first flow field change characteristic corresponding to the first type of transition region and a second flow field change characteristic corresponding to the second type of transition region; training a transition correction layer based on the transition region characteristics to correct errors of the multi-stage aerodynamic prediction data, comprising: extracting preset key characteristics in the first flow field change characteristic and the second flow field change characteristic, including the change trend of Mach number, Reynolds number and molecular collision parameters, to generate first key characteristics and second key characteristics; constructing the regression relationship between the changes of Mach number, Reynolds number and molecular collision parameters and aerodynamic parameters, and then training a first transition correction layer according to the first key characteristics and a second transition correction layer according to the second key characteristics; correcting errors of the multi-stage aerodynamic prediction data by using the first transition correction layer and the second transition correction layer.

2. The error correction method for high-speed aerodynamic prediction of claim 1, wherein, analyzing the flow region experienced by the target aircraft entering the atmosphere based on the preset flight route and the flight parameters, and generating a multi-stage flow region, comprising: calculating the Mach number and Reynolds number of each flight position based on the preset flight route and the flight parameters; reading the molecular flow division mechanism determined for the free molecular flow region, the rarefied transitional flow region and the continuous flow region; based on the molecular flow division mechanism, segmenting the continuous region according to the Mach number and Reynolds number of each flight position to generate a flow region map; generating the multi-stage flow region based on the flow region map.

3. The error correction method for high-speed aerodynamic prediction of claim 1, wherein, analyzing the gas molecule collision characteristics of the multi-stage flow region, combining the aircraft structure design information to perform aerodynamic prediction, and generating multi-stage aerodynamic prediction data, comprising: connecting a pre-constructed molecular collision database to read the collision frequency between gas molecules corresponding to the free molecular flow region, the rarefied transitional flow region and the continuous flow region, to generate free molecular flow collision parameters, rarefied transitional flow molecular collision parameters and continuous flow molecular collision parameters; performing local flow field difference analysis based on the aircraft structure design information to construct aircraft local flow field difference characteristics; The multi-stage aircraft local molecule collision parameter analysis is performed in combination with the aircraft local flow field difference characteristics, the free molecule flow collision parameters, the rarefied transitional flow molecule collision parameters and the continuous flow molecule collision parameters, to generate each molecule collision parameter corresponding to each stage; The aerodynamic prediction is performed by calling the aerodynamic-molecule collision regression relationship trained based on the structural material in the aircraft structure design information, based on each molecule collision parameter corresponding to each stage, to generate the multi-stage aerodynamic prediction data.

4. The error correction method for high-speed aerodynamic prediction of claim 3, wherein, The local flow field difference analysis includes the flow field difference analysis of the wing, the tail and the fuselage parts.

5. The error correction method for high-speed aerodynamic prediction of claim 3, wherein, The local flow field difference analysis is performed based on the aircraft structure design information, to construct the aircraft local flow field difference characteristics, including: The three-dimensional geometric model and the flow field correlation parameters are generated by modeling according to the aircraft structure design information; The interaction between the aircraft surface and the flow field is analyzed based on the three-dimensional geometric model and the flow field correlation parameters through the CFD simulation, to identify the influence of the wing, the tail and the fuselage parts on the flow field, and to generate the aircraft local flow field difference characteristics.

6. The error correction method for high-speed aerodynamic prediction of claim 5, wherein, Wherein, The interaction analysis between the aircraft surface and the flow field includes the local difference analysis of the surface aerodynamic heating, the aerodynamic load and the flow field distribution.

7. The error correction method for high-speed aerodynamic prediction of claim 1, wherein, The transition region further includes a third type of transition region, and the third type of transition region is an aerodynamic characteristic transition region. The transition characteristics of the third type of transition region are collected, including the aerodynamic heating distribution and the aerodynamic load change characteristics of the aircraft surface, and the third transition correction layer is trained.

8. An error correction system oriented towards high-speed aerodynamic prediction, characterized in that, The system is used to implement the error correction method for high-speed aerodynamic prediction according to any one of claims 1-7, and the system includes: A flight information determination module is configured to determine aircraft structure design information of a target aircraft, a preset flight route and flight parameters. A flow region analysis module is configured to analyze flow regions experienced by the target aircraft in the atmosphere based on the preset flight route and the flight parameters, to generate multi-stage flow regions. An aerodynamic prediction module is configured to analyze gas molecule collision characteristics of the multi-stage flow regions, to perform aerodynamic prediction in combination with the aircraft structure design information, to generate multi-stage aerodynamic prediction data. A transition region characteristic determination module is configured to determine transition regions and transition region characteristics of the multi-stage flow regions in the preset flight route. An error correction module is configured to train a transition correction layer based on the transition region characteristics, to perform error correction on the multi-stage aerodynamic prediction data.

Images