Aircraft surface peak heat flow prediction method, device, equipment and medium

Abstract

The invention provides a surface peak heat flow prediction method and device of an aircraft, equipment and a medium, and relates to the technical field of aircraft design, and the method comprises the steps: obtaining a parameter value of a first target parameter used for predicting the surface peak heat flow in a target application scene and a parameter range of all second target parameters; determining a target parameter combination according to the parameter range of the second target parameter, and matching a corresponding target prediction model; inputting the target parameter combination, the parameter range of the second target parameters except the third target parameter in the second target parameters and the parameter value of the first target parameter into a target prediction model to obtain a surface peak heat flux prediction value corresponding to the target parameter combination; and determining a surface peak heat flow prediction result based on each target parameter combination and the corresponding surface peak heat flow prediction value. According to the method, the calculation time is greatly shortened, the use of calculation resources is reduced, the calculation efficiency is improved, and efficient and accurate aircraft surface peak heat flow prediction is realized.

Description

Technical Field

[0001] The present application relates to the technical field of aircraft design, and in particular to a method, device, equipment and medium for predicting the surface peak heat flux of an aircraft. Background Art

[0002] In recent years, the aerodynamic heating of hypersonic vehicles has become a research hotspot. The stagnation point often has a heat flux concentration area under the action of the shock wave formed by the hypersonic flow. At the same time, the shoulder and corner of the vehicle also have a heat flux concentration area due to flow separation. Therefore, the location of the peak heat flux on the entire vehicle surface has become one of the issues that researchers need to consider, and the location of the peak heat flux and the heat flux change with the shape parameters and operating parameters. Efficient and accurate prediction of the peak heat flux on the vehicle surface is of great significance to improving the aerodynamic performance of the vehicle.

[0003] The prior art (a method for determining the flight angle of attack of an aircraft that optimizes the thermal environment) discloses a method for determining the flight angle of attack of an aircraft that optimizes the thermal environment. The method improves the thermal environment of the surfaces of key parts of the aircraft by changing the flight angle of attack of the aircraft, so that the thermal environment of the surfaces of key parts of the aircraft is in the optimal state, that is, the heat flux in the thermal environment is the smallest, and belongs to the field of flight control technology of aircraft. However, the method does not clearly define the location and problem of the peak heat flux on the surface of the aircraft, and cannot solve the initial configuration design.

[0004] At the same time, current prediction methods for the peak value of heat flux density on the aircraft surface mostly focus on predicting the heat flux density at the stagnation point on the aircraft head, and do not consider the heat flux density at the flow separation points such as the aircraft shoulder, resulting in the predicted value being far less than the actual value; and the current method of calculating the heat flux density on the aircraft surface through numerical simulation, but the computing resources consumed by a single numerical simulation are too large, the time is long, and it is inconvenient to call during the aerodynamic shape optimization process. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, equipment and medium for predicting the surface peak heat flux of an aircraft, so as to solve the above-mentioned problems existing in the prior art and to accurately and efficiently predict the surface peak heat flux of an aircraft.

[0006] In a first aspect, a method for predicting peak surface heat flux of an aircraft is provided, and the method may include:

[0007] Obtaining a parameter value of a first target parameter and a parameter range of all second target parameters for predicting a surface peak heat flux in a target application scenario;

[0008] Extracting at least one third target parameter from all second target parameters;

[0009] For any third target parameter, taking a value within a parameter range of the third target parameter to obtain multiple parameter values ​​of the third target parameter;

[0010] Combining different parameter values ​​of each third target parameter to obtain a plurality of target parameter combinations;

[0011] For any target parameter combination, a target prediction model corresponding to the target parameter combination is matched from a pre-built comparison table of different parameter combinations and corresponding prediction models;

[0012] Inputting the target parameter combination, the parameter range of the second target parameters of each second target parameter except the third target parameter, and the parameter value of the first target parameter into the target prediction model to obtain the surface peak heat flux prediction value corresponding to the target parameter combination;

[0013] Based on each target parameter combination and the corresponding surface peak heat flux prediction value, the surface peak heat flux prediction result is determined.

[0014] In an optional implementation, extracting at least one third target parameter from all second target parameters includes:

[0015] Acquire the parameter category to which the second target parameter belongs, and key parameters under the parameter category; wherein the key parameters are obtained by analyzing data in a pre-constructed aircraft heat flux density distribution database;

[0016] For any second target parameter, if the second target parameter is the key parameter, the second target parameter is used as the third target parameter.

[0017] In an optional implementation, the method for constructing the aircraft heat flux density distribution database includes:

[0018] Respectively obtaining the historical parameter range and the parameter category of the first target parameter and the second target parameter; wherein the parameter categories of the first target parameter and the second target parameter are different; the parameter categories include working condition category and appearance category;

[0019] For any target parameter, taking a value within the historical parameter range of the target parameter to obtain multiple historical parameter values ​​of the target parameter;

[0020] For any parameter category, combining different historical parameter values ​​of each target parameter included in the parameter category to obtain multiple historical parameter combinations;

[0021] Combining different historical parameter combinations under each parameter category to obtain multiple historical parameter vectors;

[0022] For any historical parameter vector, based on the combination of historical parameters of the shape class in the historical parameter vector, construct a three-dimensional model of the aircraft corresponding to the historical parameter vector;

[0023] Using the three-dimensional model to perform simulation under the historical parameter combination of the operating condition class, obtaining heat flux density distribution data of the aircraft corresponding to the historical parameter vector;

[0024] Based on different historical parameter vectors and the corresponding heat flux density distribution data of the aircraft, an aircraft heat flux density distribution database is constructed.

[0025] In an optional implementation, the method for determining the key parameters includes:

[0026] Analyze different historical parameter vectors and the corresponding heat flux density distribution data of the aircraft to obtain the importance scores of different target parameters;

[0027] For any parameter category, sort the target parameters contained in the parameter category from large to small according to the corresponding importance scores;

[0028] From the sorted target parameters, a preset number of target parameters that are sorted first are extracted to obtain key parameters of the parameter category.

[0029] In an optional implementation, after constructing the aircraft heat flux density distribution database, the method further includes:

[0030] For any historical parameter vector in the aircraft heat flux density distribution database, based on the three-dimensional model of the aircraft corresponding to the historical parameter vector, determine the stationary point coordinates and shoulder coordinates of the aircraft;

[0031] Extracting the stagnation point heat flux density and the shoulder heat flux density corresponding to the stagnation point coordinates and the shoulder coordinates respectively from the heat flux density distribution data of the aircraft corresponding to the historical parameter vector;

[0032] If the stagnation point heat flux density is greater than the shoulder heat flux density, storing the heat flux density distribution data of the aircraft corresponding to the historical parameter vector in the configured first data set;

[0033] If the stagnation point heat flux density is not greater than the shoulder heat flux density, the heat flux density distribution data of the aircraft corresponding to the historical parameter vector is stored in the configured second data set.

[0034] In an optional implementation, the prediction model includes a first prediction model and a second prediction model;

[0035] The first prediction model is obtained by training a pre-built first initial prediction model using the first data set;

[0036] The second prediction model is obtained by training a pre-constructed second initial prediction model using a second data set.

[0037] In an optional implementation, the target application scenarios include: aircraft design scenarios and aircraft surface peak heat flux analysis scenarios;

[0038] When the target application scenario is an aircraft design scenario, the surface peak heat flux prediction result is determined based on each target parameter combination and the corresponding surface peak heat flux prediction value, including:

[0039] From each target parameter combination, extract the target parameter combination with the smallest corresponding surface peak heat flux prediction value and the corresponding surface peak heat flux prediction value to obtain the surface peak heat flux prediction result;

[0040] When the target application scenario is an aircraft surface peak heat flux analysis scenario, each target parameter combination and the corresponding surface peak heat flux prediction value are used as the surface peak heat flux prediction result of the aircraft.

[0041] In a second aspect, a device for predicting peak surface heat flux of an aircraft is provided, which may include:

[0042] An acquisition unit, used to acquire a parameter value of a first target parameter for predicting a surface peak heat flux and a parameter range of all second target parameters in a target application scenario;

[0043] an extraction unit, configured to extract at least one third target parameter from all the second target parameters;

[0044] A combining unit, configured to take a value within a parameter range of any third target parameter to obtain a plurality of parameter values ​​of the third target parameter; and to combine different parameter values ​​of each third target parameter to obtain a plurality of target parameter combinations;

[0045] A matching unit, for matching a target parameter combination to a target prediction model corresponding to the target parameter combination from a pre-built comparison table of different parameter combinations and corresponding prediction models;

[0046] A prediction unit, used for inputting the target parameter combination, the parameter range of the second target parameters of each second target parameter except the third target parameter, and the parameter value of the first target parameter into the target prediction model to obtain a surface peak heat flux prediction value corresponding to the target parameter combination;

[0047] The determination unit is used to determine the surface peak heat flux prediction result based on each target parameter combination and the corresponding surface peak heat flux prediction value.

[0048] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0049] Memory, used to store computer programs;

[0050] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0051] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0052] The present application solves the problem that the position of the peak heat flux density on the aircraft surface is difficult to predict. Data is classified according to the different positions where the peak heat flux density appears, and different prediction models are trained using the classified data. When the target parameter combination to be predicted appears, the corresponding prediction model is selected according to the distribution range of the classified data, and the peak heat flux density of the aircraft surface under the corresponding shape and working condition is quickly obtained. It can be used for optimizing the aerodynamic shape under fixed working conditions with the minimum peak heat flux density of the aircraft as the optimization goal, and can also be used for outputting and predicting the curve of the change of the peak heat flux of the aircraft with the ballistic working condition under a fixed shape.

[0053] This application innovatively compares and classifies the stagnation point heat flux and the shoulder heat flux, quickly locates the location where the peak heat flux density occurs, and only calculates the heat flux density once during the prediction model generation process, reducing the amount of calculation.

[0054] In the face of multi-dimensional parameters, this application selects at least one key parameter that has the greatest impact on the output result for each parameter category through orthogonal experimental design and sensitivity analysis to perform parameter inversion, thereby providing a judgment basis for the target parameter combination and providing support for classification prediction.

[0055] The present application has a wide range of uses. It can be combined with an optimization algorithm to find the optimal aerodynamic shape with the minimum peak heat flux under fixed working conditions, and it can also obtain the variation law of the peak heat flux under different working conditions of the fixed shape according to the ballistic working conditions.

[0056] Compared with numerical simulation calculations, the introduction of the prediction model in this application directly constructs the relationship between input parameters and output performance parameters. Compared with CFD simulation calculations, it greatly reduces the calculation time, reduces the use of computing resources, and improves the calculation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A flow chart of a method for predicting peak surface heat flux of an aircraft provided in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of a method for predicting peak surface heat flux of an aircraft provided in an embodiment of the present application;

[0060] Figure 3 A flow chart for optimizing the minimum aerodynamic shape with peak heat flux under fixed working conditions provided in an embodiment of the present application;

[0061] Figure 4 A schematic diagram of analyzing the variation law of peak heat flux under different working conditions of a fixed shape provided in an embodiment of the present application;

[0062] Figure 5 A schematic diagram of the structure of a device for predicting peak surface heat flux of an aircraft provided in an embodiment of the present application;

[0063] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] The surface peak heat flux prediction method of the aircraft provided in the embodiment of the present application can be applied in a server or in a terminal with strong computing power. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a user equipment (User Equipment, UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing equipment connected to a wireless modem, a mobile station (Mobile Station, MS), a mobile terminal (Mobile Terminal), etc. The terminal and the server can be directly or indirectly connected by a wired or wireless communication method, and this application is not limited here.

[0066] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0067] Figure 1 The present invention provides a flow chart of a method for predicting the peak heat flux on the surface of an aircraft. Figure 1 As shown, the method may include:

[0068] Step S110, obtaining the parameter value of the first target parameter for predicting the surface peak heat flux in the target application scenario and the parameter range of all second target parameters; extracting at least one third target parameter from all the second target parameters.

[0069] In the embodiments of the present application, there are two target application scenarios, one is an aircraft aerodynamic shape optimization scenario, and the other is an aircraft surface peak heat flux analysis scenario; no matter which application scenario is used to predict the surface peak heat flux, two types of parameters, namely, first target parameters and second target parameters, need to be input, among which the first target parameter requires input of a specific parameter value, while the second target parameter requires input of a parameter range; the first target parameters and the second target parameters in the two application scenarios are different.

[0070] In an embodiment of the present application, the first target parameter and the second target parameter each correspond to a parameter category, and the parameter categories of the first target parameter and the second target parameter are different; when the target application scenario is an aircraft aerodynamic shape optimization scenario, the parameter category to which the first target parameter belongs is an operating condition parameter category, and the parameter category to which the second target parameter belongs is an appearance category; when the target application scenario is an aircraft surface peak thermal flux analysis scenario, the parameter category to which the first target parameter belongs is an appearance category, and the parameter category to which the second target parameter belongs is an operating condition parameter category.

[0071] In the embodiment of the present application, the operating parameters include: flight altitude, flight Mach number and angle of attack, etc.; the appearance parameters include: head radius, shoulder radius and total length, etc.

[0072] In practical applications, the purpose of the aircraft aerodynamic shape optimization scenario is to find the optimal shape parameters of the aircraft under certain working conditions; the purpose of the aircraft surface peak heat flux analysis scenario is to analyze the corresponding surface peak heat flux distribution law for an aircraft with a certain shape.

[0073] In the embodiment of the present application, the parameter value of the first target parameter and the parameter ranges of all second target parameters are user-defined input or configuration.

[0074] In practical applications, since there are multiple second target parameters, and the amount of calculation required in the early stage to match the corresponding prediction model after taking values ​​from multiple second target parameters is large, the present application performs dimensionality reduction processing on the multiple second target parameters, extracts at least one third target parameter from them, and only uses the third target parameter to match the prediction model, thereby reducing the amount of data and improving overall efficiency.

[0075] In the embodiment of the present application, at least one third target parameter is extracted from all the second target parameters, including:

[0076] The parameter category to which the second target parameter belongs and the key parameters under the parameter category are obtained; for any second target parameter, if the second target parameter is a key parameter, the second target parameter is used as the third target parameter.

[0077] In an embodiment of the present application, the parameter categories to which the first target parameter and the second target parameter belong both contain at least one key parameter; for example, the second target parameter is the flight altitude, the flight Mach number and the angle of attack, and the parameter category to which the second target parameter belongs is the operating condition category; the key parameters under the operating condition category are the flight altitude and the angle of attack, and the flight altitude and the angle of attack are extracted from the second target parameter as the third target parameter.

[0078] In the embodiment of the present application, the key parameters of each parameter category are obtained by analyzing the data in a pre-built aircraft heat flux density distribution database, and the specific steps include:

[0079] Different historical parameter vectors stored in the aircraft heat flux density distribution database and the corresponding aircraft heat flux density distribution data are analyzed to obtain the importance scores of different target parameters; for any parameter category, the target parameters contained in the parameter category are sorted from large to small according to the corresponding importance scores; from the sorted target parameters, a preset number of target parameters ranked first are extracted to obtain the key parameters of the parameter category.

[0080] For example, assuming that the preset number is 2, the data stored in the aircraft thermal flux density distribution database is analyzed, and the importance scores of different target parameters such as flight altitude, flight Mach number, angle of attack, head radius, shoulder radius and total length are 9, 5, 6, 4, 2, and 1 respectively; for the working condition category, the flight altitude, flight Mach number, and angle of attack are sorted from large to small according to the corresponding importance scores, and the top two parameters are extracted to obtain the key parameters of the working condition category, which are flight altitude and angle of attack; for the shape category, the head radius, shoulder radius and total length are sorted from large to small according to the corresponding importance scores, and the top two parameters are extracted to obtain the key parameters of the shape category, which are head radius and shoulder radius.

[0081] In an embodiment of the present application, the data stored in the aircraft heat flux density distribution database is analyzed by using a variety of methods such as correlation analysis, regression analysis, feature importance assessment, partial derivative dependency graph, Shapley value and / or sensitivity analysis.

[0082] In the embodiment of the present application, the key parameter of each parameter category is actually the parameter in the parameter category that has the greatest impact on the final heat flux density distribution on the aircraft surface.

[0083] In an embodiment of the present application, a method for constructing an aircraft heat flux density distribution database includes:

[0084] Respectively obtain the historical parameter range and the parameter category to which the first target parameter and the second target parameter belong; for any target parameter, take a value within the historical parameter range of the target parameter to obtain multiple historical parameter values ​​of the target parameter; for any parameter category, combine different historical parameter values ​​of each target parameter included in the parameter category to obtain multiple historical parameter combinations; combine different historical parameter combinations under each parameter category to obtain multiple historical parameter vectors;

[0085] For any historical parameter vector, a three-dimensional model of the aircraft corresponding to the historical parameter vector is constructed based on the historical parameter combination of the appearance class in the historical parameter vector; the three-dimensional model is used to perform simulation under the historical parameter combination of the working condition class to obtain the heat flux density distribution data of the aircraft corresponding to the historical parameter vector; based on different historical parameter vectors and the corresponding heat flux density distribution data of the aircraft, an aircraft heat flux density distribution database is constructed.

[0086] In the embodiment of the present application, the historical parameter values ​​or parameter values ​​are combined, and an orthogonal experimental design method can be used to reduce the amount of data and balance the different parameter values ​​or different historical parameter values ​​of each target parameter.

[0087] In an embodiment of the present application, historical parameter ranges of all operating condition parameters and appearance parameters are obtained in advance, and each parameter is selected within its parameter range by an orthogonal experimental design method, so as to obtain a plurality of parameter vectors composed of historical parameter values ​​corresponding to different parameters; for example, the value ranges of flight altitude, flight Mach number, angle of attack, head radius, shoulder radius and total length are 3000-5000, 100-200, 30-50, 20-30, 60-80 and 10-15 respectively; assuming that each parameter takes two values, namely 3500, 4000; 150, 160; 30, 40; 22, 23; 70, 75; 12, 13, then an orthogonal experimental design is adopted to obtain 8 historical parameter vectors (3500, 150, 30, 22, 70, 12), (3500, 150, 40, 23,75,13), (3500,160,30,23,70,13), (3500,160,40,22,75,12), (4000,150,30,23,75,12), (4000,150,40,22,70,13), (4000,160,30,22,75,13) and (4000,160,40,23,70,12); in the above history vectors, the parameter combination composed of the first three parameter values ​​is the parameter combination of the working condition class, and the parameter combination composed of the last three parameter values ​​is the parameter combination of the appearance class. The three-dimensional model of the aircraft is constructed according to the parameter combination of the appearance class, and the CFD numerical simulation is carried out according to the parameter combination of the working condition class and the three-dimensional model, so as to obtain the corresponding aircraft heat flux density distribution data, and construct the aircraft heat flux density distribution database.

[0088] In an embodiment of the present application, the historical parameter ranges of all operating condition parameters and appearance parameters may be determined according to aircraft design specifications or other design specifications, or may be customized by the user.

[0089] In the embodiment of the present application, the aircraft heat flux density distribution data is the heat flux density distribution of the aircraft along the symmetry axis corresponding to each historical parameter vector.

[0090] In an embodiment of the present application, the stagnation point coordinates and shoulder coordinates of the corresponding aircraft can be determined according to the three-dimensional model corresponding to each historical parameter vector, and the corresponding stagnation point heat flux density and shoulder heat flux density can be extracted from the heat flux density distribution of the aircraft along the axis of symmetry based on the determined coordinates.

[0091] In an embodiment of the present application, for each piece of data stored in the aircraft heat flux density distribution database, the sizes of the extracted stagnation point heat flux density and shoulder heat flux density are compared. If the stagnation point heat flux density is greater than the shoulder heat flux density, the heat flux density distribution data of the aircraft corresponding to the historical parameter vector is stored in the configured first data set; if the stagnation point heat flux density is not greater than the shoulder heat flux density, the heat flux density distribution data of the aircraft corresponding to the historical parameter vector is stored in the configured second data set, thereby obtaining two data sets containing different data.

[0092] In an embodiment of the present application, after obtaining two different data sets, it is necessary to determine the distribution range of the key parameters of each parameter category in each data set; taking the database composed of the 8 historical parameter vectors obtained above as an example, assuming that the key parameter of the working condition category is flight altitude, the first 4 groups of data are the first data set, and the last 4 groups of data are the second data set; then for flight altitude, its distribution range in the first data set is a value of 3500, and its distribution range in the second data set is also a value of 400; the key parameters of the shape category are shoulder radius and total length, the distribution range of shoulder radius in the second data set is (70,75), and the distribution range of total length in the second data set is (12,13), and for the parameter combination of the key parameters of the shape category, its distribution range is (75,12), (75,13), (70,12) and (70,13); based on this, the distribution range of the key parameters of each parameter category in the corresponding data set is determined.

[0093] In practical applications, if the peak heat fluxes of the head and shoulders are compared and screened each time, and the larger one is selected, the amount of calculation will be greatly increased. Therefore, this application performs classification in the early stage of building the prediction model, and directly outputs the peak heat flux of the aircraft according to the previous classification in actual use, thereby improving the calculation and optimization efficiency.

[0094] In an embodiment of the present application, the prediction model includes a first prediction model and a second prediction model; the two prediction models may be the same model or different models, preferably, the same model; specifically, the prediction model may be selected from radial basis, Kriging or BP neural network models, etc.

[0095] Step S120: for any third target parameter, take a value within the parameter range of the third target parameter to obtain multiple parameter values ​​of the third target parameter; and combine different parameter values ​​of each third target parameter to obtain multiple target parameter combinations.

[0096] In the embodiment of the present application, the third target parameter is actually a key parameter of the parameter category to which the second target parameter belongs; and the number of key parameters of the parameter category may be one or more. If it is multiple, the third target parameter needs to be combined after taking values ​​to obtain the corresponding target parameter combination; the method of taking values ​​and combining them may adopt the orthogonal experimental design method.

[0097] Step S130: For any target parameter combination, a target prediction model corresponding to the target parameter combination is matched from a pre-constructed comparison table of different parameter combinations and corresponding prediction models.

[0098] In an embodiment of the present application, a method for constructing a comparison table of different parameter combinations and corresponding prediction models includes: for any parameter category in any data set, extracting historical parameter values ​​of each key parameter of the parameter category from the data set; based on the extracted historical parameter values, determining the historical parameter combination of each key parameter of the parameter category in the data set; using the determined historical parameter combination as the parameter combination, and using the prediction model obtained by training the data set as the prediction model corresponding to the parameter combination, to obtain a comparison table of different parameter combinations and corresponding prediction models.

[0099] In an embodiment of the present application, two data sets are used to train two models respectively, the first data set is used to train the first prediction model, and the second data set is used to train the second prediction model; and the distribution range of key parameters of each parameter category in the two data sets is different, so an association relationship can be established based on the distribution range of the parameter combination of each parameter category in the data set and the training objective of the data set.

[0100] For example, the distribution range of parameter combinations of key parameters of the appearance type in the second data set is (75, 12), (75, 13), (70, 12) and (70, 13); and the second data set is used to train the second prediction model, so the parameter combinations of shoulder radius and total length (75, 12), (75, 13), (70, 12) and (70, 13) are associated with the second prediction model. Similarly, the distribution range of the flight altitude of the working condition type parameters of the second data set is associated with the second prediction model, and the parameter combinations of the working condition type parameters and the appearance type parameters of the first data set are associated with the first prediction model, thereby obtaining a comparison table of different parameter combinations and corresponding prediction models.

[0101] In an embodiment of the present application, for any target parameter combination of the third target parameter, it is possible to determine whether its value is within the distribution range of the key parameters of the corresponding parameter category in the first data set; for example, the parameter category of the third target parameter is the operating condition category, and the target parameter combination is (60, 12), then it can be determined that the target parameter combination does not belong to the distribution range of the key parameters of the operating condition category in the second data set, and therefore, it should be within the distribution range in the first data set, that is, the first prediction model is the target model.

[0102] In the embodiment of the present application, it is sufficient to determine the distribution range of the key parameters of the working condition category and the appearance category in the first data set. As long as the target parameter combination does not conform to the distribution range of the key parameters of the corresponding parameter category in the first data set, it is directly judged as conforming to the distribution range of the key parameters of the corresponding parameter category in the second data set; that is, as long as the range corresponding to the first prediction model does not match, the second prediction model is directly used as the target model.

[0103] Step S140, input the target parameter combination, the parameter range of the second target parameters of each second target parameter except the third target parameter, and the parameter value of the first target parameter into the target prediction model to obtain the surface peak heat flux prediction value corresponding to the target parameter combination.

[0104] In an embodiment of the present application, during the prediction process, the parameter value of the first target parameter, the target parameter combination, and the parameter range of the second target parameter in the second target parameter except the third target parameter are all taken as input to obtain the surface peak heat flux prediction value of the corresponding target parameter combination.

[0105] Step S150: Determine the surface peak heat flux prediction result based on each target parameter combination and the corresponding surface peak heat flux prediction value.

[0106] In an embodiment of the present application, when the target application scenario is an aircraft design scenario, the target parameter combination with the smallest corresponding surface peak heat flux prediction value and the corresponding surface peak heat flux prediction value are extracted from each target parameter combination to obtain a surface peak heat flux prediction result.

[0107] In an embodiment of the present application, when the target application scenario is an aircraft design scenario, the parameter category to which the second target parameter belongs is the appearance category, and the first target parameter is the operating condition category. The core is to select a corresponding aircraft configuration with the smallest surface peak heat flux prediction value under fixed operating conditions from a plurality of appearance category target parameter combinations, and output the corresponding target parameter combination and the corresponding surface peak heat flux prediction value.

[0108] In an embodiment of the present application, when the target application scenario is an aircraft surface peak heat flux analysis scenario, each target parameter combination and the corresponding surface peak heat flux prediction value are used as the aircraft surface peak heat flux prediction result.

[0109] In an embodiment of the present application, in the aircraft surface peak heat flux analysis scenario, the aircraft's shape parameters are fixed, and its core is to analyze the aircraft determined by certain shape parameters and its surface peak heat flux distribution under different operating parameters.

[0110] In another embodiment of the present application, Figure 2 As shown, the method for predicting the peak surface heat flux of the aircraft includes:

[0111] 1. Build a prediction model:

[0112] Step 1: Determine the parameter range: The parameters that affect the aerodynamic simulation and heat flux density calculation of the aircraft are mainly divided into two categories, one is the structural shape parameters, such as the head radius, shoulder radius, total length, etc., and the other is the working condition parameters, such as flight altitude, flight Mach number, angle of attack, etc. Determine the range of each parameter to facilitate sampling and test design.

[0113] Step 2: Orthogonal experimental design: Sampling is performed within the parameter range through the experimental design method of orthogonal experimental design to obtain calculation sample points, which is convenient for the next step of simulation calculation.

[0114] Step 3: CFD numerical simulation: Perform CFD numerical simulation on each sample point of the above-mentioned determined shape and working conditions to form a database.

[0115] Step 4: Obtain heat flux density distribution: After the calculation is completed, the heat flux density distribution of the aircraft at each sample point along the symmetry axis is output to facilitate classification, comparison and screening.

[0116] Step 5: Heat flux classification prediction: Classify each sample point according to its different heat flux density distribution. When the stagnation point heat flux density Qo>shoulder heat flux density Qr, put the sample point into the training sample set of the first prediction model; when the stagnation point heat flux density Qo≤shoulder heat flux density Qr, put the sample point into the training sample set of the second prediction model.

[0117] Step 6: Establish prediction model: The first prediction model constructs a prediction model with stagnation heat flux density Qoa as output and shape and working condition parameters as input. The second prediction model constructs a prediction model with shoulder heat flux density Qrb as output and shape and working condition parameters as input. The prediction model can choose radial basis, Kriging, BP neural network and other prediction models, and generate the final prediction model after training and testing.

[0118] Step 7: Parameter sensitivity analysis: For the first prediction model and the second prediction model, perform parameter sensitivity analysis on their input variables to obtain the shape parameters x1, x2 and operating parameters y1, y2 that have the greatest impact on the heat flux density of their respective outputs, and determine the intervals of the above parameters based on the classification.

[0119] 2. Use the prediction model to make predictions

[0120] After the prediction model is established, it can be applied in two aspects.

[0121] (1) Optimization of aerodynamic shape with minimum peak heat flux under fixed working conditions

[0122] like Figure 3 As shown in the figure, when optimizing the aerodynamic shape of an aircraft, optimization is often performed at a single operating point, that is, fixed operating parameters, determined by the input variable Y. At this time, according to the parameter range of the new sample point (x1, x2), it can be determined whether the sample point belongs to the first prediction model or the second prediction model. If it belongs to the first prediction model, the peak heat flux Qoa at this time is calculated according to the prediction model, otherwise the peak heat flux Qrb is calculated, and the peak heat flux position and value of this sample point can be quickly determined. After the calculation is completed, a judgment is made. When this heat flux is not the minimum heat flux among all sample points, the shape parameters are re-entered, and a new sample point is constructed to start the cyclic calculation. If it is the minimum heat flux, the result is directly output. At this time, the configuration and heat flux value of the aircraft corresponding to the minimum peak heat flux under fixed conditions are obtained.

[0123] (2) Variation of peak heat flux under different working conditions with fixed shape

[0124] like Figure 4 As shown in the figure, during the trajectory simulation of the aircraft, it is necessary to simulate the peak heat flux variation law under different working conditions of the aircraft with a certain configuration. Therefore, the input variable X is determined, and the range of the working condition parameters (y1, y2) of the new sample point is determined. The corresponding peak heat flux calculation is also performed according to the previous classification. After the calculation is completed, the corresponding working condition parameters and peak heat flux are output. After that, the cyclic calculation is performed. After the calculation is completed, the peak heat flux variation law along the ballistic working condition point can be obtained, which provides a reference for the design of heat protection materials.

[0125] Corresponding to the above method, the embodiment of the present application also provides a device for predicting the peak heat flux on the surface of an aircraft, such as Figure 5 As shown, the surface peak heat flux prediction device of the aircraft includes:

[0126] An acquisition unit 510 is used to acquire a parameter value of a first target parameter for predicting a surface peak heat flux and a parameter range of all second target parameters in a target application scenario;

[0127] An extraction unit 520, configured to extract at least one third target parameter from all second target parameters;

[0128] The combining unit 530 is used to take a value within the parameter range of the third target parameter for any third target parameter to obtain multiple parameter values ​​of the third target parameter; and combine different parameter values ​​of each third target parameter to obtain multiple target parameter combinations;

[0129] A matching unit 540 is used to match a target prediction model corresponding to the target parameter combination from a pre-built comparison table of different parameter combinations and corresponding prediction models for any target parameter combination;

[0130] The prediction unit 550 is used to input the target parameter combination, the parameter range of the second target parameter except the third target parameter in each second target parameter, and the parameter value of the first target parameter into the target prediction model to obtain the surface peak heat flux prediction value corresponding to the target parameter combination;

[0131] The determination unit 560 is used to determine the surface peak heat flux prediction result based on each target parameter combination and the corresponding surface peak heat flux prediction value.

[0132] The functions of the various functional units of the surface peak heat flux prediction device for an aircraft provided in the above-mentioned embodiments of the present application can be achieved through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the surface peak heat flux prediction device for an aircraft provided in the embodiments of the present application will not be repeated here.

[0133] The present application also provides an electronic device, such as Figure 6 As shown, it includes a processor 610 , a communication interface 620 , a memory 630 and a communication bus 640 , wherein the processor 610 , the communication interface 620 , and the memory 630 communicate with each other via the communication bus 640 .

[0134] Memory 630, for storing computer programs;

[0135] The processor 610 is used to implement the following steps when executing the program stored in the memory 630:

[0136] Obtaining a parameter value of a first target parameter and a parameter range of all second target parameters for predicting a surface peak heat flux in a target application scenario;

[0137] Extracting at least one third target parameter from all second target parameters;

[0138] For any third target parameter, a value is taken within the parameter range of the third target parameter to obtain multiple parameter values ​​of the third target parameter; different parameter values ​​of each third target parameter are combined to obtain multiple target parameter combinations;

[0139] For any target parameter combination, match the target prediction model corresponding to the target parameter combination from the pre-built comparison table of different parameter combinations and corresponding prediction models;

[0140] Inputting the target parameter combination, the parameter range of the second target parameter except the third target parameter in each second target parameter, and the parameter value of the first target parameter into the target prediction model to obtain the surface peak heat flux prediction value corresponding to the target parameter combination;

[0141] Based on each target parameter combination and the corresponding surface peak heat flux prediction value, the surface peak heat flux prediction result is determined.

[0142] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] The communication interface is used for communication between the above electronic device and other devices.

[0144] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0145] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0146] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 1 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0147] In another embodiment provided in the present application, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the surface peak heat flux prediction method of the aircraft in any of the above embodiments.

[0148] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the method for predicting the surface peak heat flux of an aircraft in any of the above embodiments.

[0149] Those skilled in the art will appreciate that the embodiments in the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt a complete hardware embodiment, a complete software embodiment, or a form of an embodiment combining software and hardware. Moreover, the present application may adopt a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0153] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0154] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application fall within the scope of the claims and their equivalents in the embodiments of the present application, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A method for predicting peak surface heat flux of an aircraft, characterized in that: The method comprises: Obtaining a parameter value of a first target parameter and a parameter range of all second target parameters for predicting a surface peak heat flux in a target application scenario; Extracting at least one third target parameter from all second target parameters; For any third target parameter, taking a value within a parameter range of the third target parameter to obtain multiple parameter values ​​of the third target parameter; Combining different parameter values ​​of each third target parameter to obtain a plurality of target parameter combinations; For any target parameter combination, a target prediction model corresponding to the target parameter combination is matched from a pre-built comparison table of different parameter combinations and corresponding prediction models; Inputting the target parameter combination, the parameter range of the second target parameters of each second target parameter except the third target parameter, and the parameter value of the first target parameter into the target prediction model to obtain the surface peak heat flux prediction value corresponding to the target parameter combination; Based on each target parameter combination and the corresponding surface peak heat flux prediction value, the surface peak heat flux prediction result is determined.

2. The method according to claim 1, characterized in that Extracting at least one third target parameter from all the second target parameters includes: Acquire the parameter category to which the second target parameter belongs, and key parameters under the parameter category; wherein the key parameters are obtained by analyzing data in a pre-constructed aircraft heat flux density distribution database; For any second target parameter, if the second target parameter is the key parameter, the second target parameter is used as the third target parameter.

3. The method according to claim 2, characterized in that The method for constructing the aircraft heat flux density distribution database comprises: Respectively obtaining the historical parameter range and the parameter category of the first target parameter and the second target parameter; wherein the parameter categories of the first target parameter and the second target parameter are different; the parameter categories include working condition category and appearance category; For any target parameter, taking a value within the historical parameter range of the target parameter to obtain multiple historical parameter values ​​of the target parameter; For any parameter category, combining different historical parameter values ​​of each target parameter included in the parameter category to obtain multiple historical parameter combinations; Combining different historical parameter combinations under each parameter category to obtain multiple historical parameter vectors; For any historical parameter vector, based on the combination of historical parameters of the shape class in the historical parameter vector, construct a three-dimensional model of the aircraft corresponding to the historical parameter vector; Using the three-dimensional model to perform simulation under the historical parameter combination of the operating condition class, obtaining heat flux density distribution data of the aircraft corresponding to the historical parameter vector; Based on different historical parameter vectors and the corresponding heat flux density distribution data of the aircraft, an aircraft heat flux density distribution database is constructed.

4. The method according to claim 3, characterized in that The method for determining the key parameters comprises: Analyze different historical parameter vectors and the corresponding heat flux density distribution data of the aircraft to obtain the importance scores of different target parameters; For any parameter category, sort the target parameters contained in the parameter category from large to small according to the corresponding importance scores; From the sorted target parameters, a preset number of target parameters that are sorted first are extracted to obtain key parameters of the parameter category.

5. The method according to claim 3, characterized in that After constructing the aircraft heat flux density distribution database, the method further includes: For any historical parameter vector in the aircraft heat flux density distribution database, based on the three-dimensional model of the aircraft corresponding to the historical parameter vector, determine the stationary point coordinates and shoulder coordinates of the aircraft; Extracting the stagnation point heat flux density and the shoulder heat flux density corresponding to the stagnation point coordinates and the shoulder coordinates respectively from the heat flux density distribution data of the aircraft corresponding to the historical parameter vector; If the stagnation point heat flux density is greater than the shoulder heat flux density, storing the heat flux density distribution data of the aircraft corresponding to the historical parameter vector in the configured first data set; If the stagnation point heat flux density is not greater than the shoulder heat flux density, the heat flux density distribution data of the aircraft corresponding to the historical parameter vector is stored in the configured second data set.

6. The method according to claim 5, characterized in that The prediction model includes a first prediction model and a second prediction model; The first prediction model is obtained by training a pre-built first initial prediction model using the first data set; The second prediction model is obtained by training a pre-constructed second initial prediction model using a second data set.

7. The method according to claim 6, characterized in that The target application scenarios include: aircraft design scenarios and aircraft surface peak heat flux analysis scenarios; When the target application scenario is an aircraft design scenario, the surface peak heat flux prediction result is determined based on each target parameter combination and the corresponding surface peak heat flux prediction value, including: From each target parameter combination, extract the target parameter combination with the smallest corresponding surface peak heat flux prediction value and the corresponding surface peak heat flux prediction value to obtain the surface peak heat flux prediction result; When the target application scenario is an aircraft surface peak heat flux analysis scenario, each target parameter combination and the corresponding surface peak heat flux prediction value are used as the surface peak heat flux prediction result of the aircraft.

8. A device for predicting peak heat flux on the surface of an aircraft, characterized in that: The device comprises: An acquisition unit, used to acquire a parameter value of a first target parameter for predicting a surface peak heat flux and a parameter range of all second target parameters in a target application scenario; an extraction unit, configured to extract at least one third target parameter from all the second target parameters; A combining unit, configured to take a value within a parameter range of any third target parameter to obtain a plurality of parameter values ​​of the third target parameter; and to combine different parameter values ​​of each third target parameter to obtain a plurality of target parameter combinations; A matching unit, for matching a target parameter combination to a target prediction model corresponding to the target parameter combination from a pre-built comparison table of different parameter combinations and corresponding prediction models; A prediction unit, used for inputting the target parameter combination, the parameter range of the second target parameters of each second target parameter except the third target parameter, and the parameter value of the first target parameter into the target prediction model to obtain a surface peak heat flux prediction value corresponding to the target parameter combination; The determination unit is used to determine the surface peak heat flux prediction result based on each target parameter combination and the corresponding surface peak heat flux prediction value.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 1-7 when executing a program stored in a memory.

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

Images