Flow field reconstruction method and system for aircraft design

Abstract

The invention provides a flow field reconstruction method and system for aircraft design, and the method comprises the steps: carrying out the simulation calculation of an aircraft under different working conditions, and constructing a full-field data reduced-order model and a sparse measurement point data reduced-order model based on a simulation result; establishing a coefficient correlation model between the full-field data reduced-order model and the sparse measuring point data reduced-order model; performing a wind tunnel test on the aircraft, and based on a test result, obtaining a coefficient of the full-field data reduced-order model through the sparse measurement point data reduced-order model and the coefficient correlation model; and substituting the coefficient of the full-field data reduced-order model into the full-field data reduced-order model to obtain a reconstructed flow field. According to the method, the value of the test result to the aircraft design process is improved, the test result is converted into a model-based field data form from a traditional text-based scalar data form by combining numerical simulation and test, and extension from a discrete working condition to a continuous working condition is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft design, and in particular to a flow field reconstruction method and system for aircraft design. Background Art

[0002] In the traditional aircraft design process, test results are usually delivered in the form of test reports, which contain a small amount of scalar data and data under discrete working conditions. This form of data makes it difficult to intuitively display the performance of the aircraft under different working conditions, limiting the application value of the test results. Summary of the invention

[0003] The purpose of the present invention is to provide a flow field reconstruction method and system for aircraft design, aiming to solve the above-mentioned problems in the prior art.

[0004] An embodiment of the present invention provides a flow field reconstruction method for aircraft design, comprising:

[0005] Simulate the aircraft under different working conditions, and build a full-field data reduction model and a sparse measurement point data reduction model based on the simulation results;

[0006] Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model;

[0007] Performing a wind tunnel test on the aircraft, and obtaining the coefficients of the full-field data reduced-order model based on the test results and through the sparse measurement point data reduced-order model and the coefficient association model; and

[0008] The coefficients of the full-field data reduction model are substituted into the full-field data reduction model to obtain a reconstructed flow field.

[0009] An embodiment of the present invention provides a flow field reconstruction system for aircraft design, comprising:

[0010] A construction module is used to simulate the aircraft under different working conditions and build a full-field data reduction model and a sparse measurement point data reduction model based on the simulation results;

[0011] An association module, used to establish a coefficient association model between the full-field data reduction model and the sparse measurement point data reduction model;

[0012] A test module, used for performing a wind tunnel test on the aircraft, and obtaining the coefficients of the full-field data reduced-order model based on the test results and through the sparse measurement point data reduced-order model and the coefficient association model; and

[0013] The reconstruction module is used to substitute the coefficients of the full-field data reduction model into the full-field data reduction model to obtain a reconstructed flow field.

[0014] An embodiment of the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the above-mentioned flow field reconstruction method for aircraft design when executed by the processor.

[0015] An embodiment of the present invention further provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of the flow field reconstruction method for aircraft design are implemented.

[0016] The following beneficial effects can be achieved by using the embodiments of the present invention: The embodiments of the present invention propose a flow field reconstruction method based on a simulation data reduced-order model to correct test data, aiming to enhance the value of test results to the aircraft design process. By combining numerical simulation with experiments, the test results are transformed from the traditional text-based scalar data form to the model-based field data form, and the expansion from discrete working conditions to continuous working conditions is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 is a flow chart of a flow field reconstruction method for aircraft design according to an embodiment of the present invention;

[0019] Figure 2 Schematic diagram of a flow field reconstruction system for aircraft design according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0021] Method Embodiment

[0022] According to an embodiment of the present invention, a flow field reconstruction method for aircraft design is provided. Figure 1 is a flow chart of a flow field reconstruction method for aircraft design according to an embodiment of the present invention. Figure 1 As shown, the flow field reconstruction method for aircraft design according to an embodiment of the present invention specifically includes:

[0023] Step S101, performing simulation calculations on the aircraft under different working conditions, and constructing a full-field data reduction model and a sparse measurement point data reduction model based on the simulation results, specifically including:

[0024] Select corresponding numerical simulation software to establish an aircraft simulation model according to the aircraft design requirements, use the aircraft simulation model to perform simulation calculations under different working conditions, convert and preprocess the obtained simulation results, and build a full-field data reduction model and a sparse measurement point data reduction model based on the processed simulation results;

[0025] The simulation results include full-field results and sparse measurement point results obtained through simulation;

[0026] The preprocessing includes coordinate point extraction and physical quantity extraction;

[0027] Step S102, establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model, specifically includes:

[0028] Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model through a machine learning algorithm;

[0029] Wherein, the machine learning algorithm is determined according to the type of the reduced-order model;

[0030] Step S103, performing a wind tunnel test on the aircraft, and obtaining the coefficients of the full-field data reduction model based on the test results and through the sparse measurement point data reduction model and the coefficient association model, specifically includes:

[0031] Performing a wind tunnel test on the aircraft to obtain sparse measurement point test data, replacing the simulation results with the sparse measurement point test data to obtain coefficients of the sparse measurement point data reduced-order model, and obtaining coefficients of the full-field data reduced-order model using the coefficient association model according to the coefficients of the sparse measurement point data reduced-order model;

[0032] The measurement points used in the sparse measurement point data reduction model are the same as the measurement points used in the wind tunnel test in terms of position, number and order;

[0033] Step S104, substituting the coefficients of the full-field data reduction model into the full-field data reduction model to obtain a reconstructed flow field.

[0034] The above technical solution of the embodiment of the present invention is described in detail below in combination with the specific situation of the flow field reconstruction method for aircraft design in the embodiment of the present invention.

[0035] The embodiments of the present invention aim to solve the problems existing in the prior art and provide a flow field reconstruction solution based on the simulation data reduced-order model to correct the test data, so as to realize the expansion of the test results from a small number of scalar data to field data and from discrete working conditions to continuous working conditions.

[0036] The embodiment of the present invention proposes a solution for flow field reconstruction based on simulation data reduction model correction test data, including the following steps:

[0037] 1. Simulation and data analysis: Before the test, the test piece is simulated multiple times to obtain simulation results under different working conditions;

[0038] 2. Construction of reduced-order models based on full-field and sparse measurement point results: The full-field results and sparse measurement point results obtained by simulation are used to construct reduced-order models that can generate full-field data and sparse measurement point data in real time;

[0039] 3. Machine learning of associated reduced-order models: Through machine learning, an associated relationship model is established between the reduced-order models of the full-field data and the sparse measurement point data, so that the coefficients of the reduced-order model of the full-field data can be predicted through the coefficients of the reduced-order model of the sparse measurement point;

[0040] 4. Test: Conduct the test according to the test outline and obtain sparse measurement point test data;

[0041] 5. Obtaining the coefficients of the reduced-order model of the test measurement points: Replace the simulation data with the test data of the measurement points to obtain the coefficients of the reduced-order model of the sparse measurement points;

[0042] 6. Prediction of full-field reduced-order model coefficients: Through the reduced-order model coefficient association model, the full-field reduced-order model coefficients are predicted from the reduced-order model coefficients of the test measurement points;

[0043] 7. Flow field reconstruction: Substitute the predicted full-field reduced-order model coefficients into the full-field data reduced-order model to obtain the reconstructed flow field.

[0044] Among them, the reduced-order model uses methods such as singular value decomposition (SVD) to decompose the physical field into several independent fields, and realizes real-time calculation through linear combination; the measurement points used in the sparse measurement point result reduced-order model are the same as the test measurement points in position, quantity and order; the association model uses the sparse measurement point reduced-order model coefficients as input and the full-field data reduced-order model coefficients as output; the internal mechanism of the reduced-order model includes eigenvector extraction and coefficient calculation steps.

[0045] Specifically, the embodiment of the present invention includes the following steps:

[0046] 1. Simulation and data analysis

[0047] Simulation software selection: According to the aircraft design requirements, select appropriate numerical simulation software, such as Fluent, Star-CCM+, etc.

[0048] Simulation model establishment: Establish an aircraft simulation model, including geometric model, mesh division, boundary condition setting, etc.

[0049] Simulation calculation: Perform simulation calculations under different working conditions to obtain the physical field distribution on the aircraft surface, such as pressure field, temperature field, etc.

[0050] Data format conversion: Convert simulation results into a dedicated training data format, such as CSV or TXT files.

[0051] 2. Model construction

[0052] (1) Data preprocessing: Preprocess the simulation data, including:

[0053] ① Coordinate point extraction: Extract the coordinate points of all grid nodes from the simulation results and ensure the consistency of the coordinate points under different working conditions.

[0054] ② Physical quantity extraction: Extract the physical quantity values ​​of all grid nodes from the simulation results, such as pressure, temperature, etc.

[0055] (2) Feature extraction:

[0056] ① Singular value decomposition (SVD): Use the SVD method to decompose the training data, extract the eigenvector with the largest contribution, and calculate the eigenvalue.

[0057] ② Eigenvector sorting: Sort the eigenvectors according to the size of the eigenvalues ​​and retain the first n eigenvectors, where n is the order of the reduced-order model.

[0058] ③Eigenvector matrix construction: Combine the retained eigenvectors into an eigenvector matrix V.

[0059] (3) Construction of reduced-order models based on full-field and sparse measurement point results: The full-field results and sparse measurement point results obtained by simulation are used to construct reduced-order models that can generate full-field data and sparse measurement point data in real time.

[0060] (4) Machine learning of correlation models: Through machine learning, a correlation model is established between the reduced-order models of the full-field data and the sparse measurement point data, so that the coefficients of the reduced-order model of the full-field data can be predicted from the coefficients of the reduced-order model of the sparse measurement point data.

[0061] ① Machine learning algorithm selection: Select an appropriate machine learning algorithm based on the type of reduced-order model, for example:

[0062] Linear regression: If the reduced-order model is a linear model, you can select the linear regression algorithm.

[0063] Support Vector Machine (SVM): If the reduced-order model is a nonlinear model, the support vector machine algorithm can be selected.

[0064] Neural Network: If the reduced-order model is a complex model, you can choose a neural network algorithm.

[0065] ②Model parameter setting: Set the parameters of the machine learning algorithm, such as learning rate, number of iterations, regularization coefficient, etc.

[0066] ③Model training: Use training data to train the machine learning model and continuously adjust the model parameters to obtain the best model performance.

[0067] 3. Experiment

[0068] (1) Preparation of test outline: Prepare the test outline, including the test purpose, test content, test equipment, test methods, etc.

[0069] (2) Test preparation: Prepare test equipment, such as wind tunnel, sensors, data acquisition system, etc.

[0070] (3) Test execution: Conduct tests according to the test outline to obtain physical values ​​of key locations on the aircraft surface, such as pressure and temperature.

[0071] (4) Data acquisition: Use the data acquisition system to collect test data and store it.

[0072] 4. Flow field reconstruction

[0073] Obtaining the coefficients of the reduced-order model of the test measurement points: Replace the simulation data with the test data of the measurement points to obtain the coefficients of the reduced-order model of the sparse measurement points;

[0074] Prediction of full-field reduced-order model coefficients: Through the reduced-order model coefficient association model, the full-field reduced-order model coefficients are predicted from the reduced-order model coefficients of the test measurement points;

[0075] Flow field reconstruction: Substitute the predicted full-field reduced-order model coefficients into the full-field data reduced-order model to obtain the reconstructed flow field.

[0076] The embodiments of the present invention are based on the following principles:

[0077] 1. Reduced-order model: Using methods such as singular value decomposition (SVD), complex physical fields are decomposed into several independent fields, and real-time calculations are achieved through linear combinations. The reduced-order model can retain the characteristics of the original physical field while significantly reducing the computational cost and improving computational efficiency.

[0078] 2. Machine learning: Use machine learning algorithms to train reduced-order models or modified models based on simulation results or experimental data so that they can accurately predict changes in the physical field.

[0079] 3. Experimental data correction: Use experimental data to correct the reduced-order model, eliminate simulation errors, and improve the prediction confidence of the reduced-order model.

[0080] In summary, the embodiments of the present invention propose machine learning based on simulation results: developing software tools to train machine learning models according to simulation results to generate reduced-order models that can generate field data in real time; and propose secondary machine learning based on measurement data: developing software tools to train correction models (i.e., correlation models) according to experimental data and reduced-order model calculation results to improve the prediction confidence of the reduced-order model.

[0081] System Example

[0082] According to an embodiment of the present invention, a flow field reconstruction system for aircraft design is provided. Figure 2 Schematic diagram of a flow field reconstruction system for aircraft design according to an embodiment of the present invention. Figure 2 As shown, the flow field reconstruction system for aircraft design according to an embodiment of the present invention specifically includes:

[0083] The construction module 20 is used to perform simulation calculations on the aircraft under different working conditions, and to construct a full-field data reduction model and a sparse measurement point data reduction model based on the simulation results, specifically for:

[0084] Select corresponding numerical simulation software to establish an aircraft simulation model according to the aircraft design requirements, use the aircraft simulation model to perform simulation calculations under different working conditions, convert and preprocess the obtained simulation results, and build a full-field data reduction model and a sparse measurement point data reduction model based on the processed simulation results;

[0085] The simulation results include full-field results and sparse measurement point results obtained through simulation;

[0086] The preprocessing includes coordinate point extraction and physical quantity extraction;

[0087] The correlation module 22 is used to establish a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model, specifically for:

[0088] Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model through a machine learning algorithm;

[0089] Wherein, the machine learning algorithm is determined according to the type of the reduced-order model;

[0090] The test module 24 is used to perform a wind tunnel test on the aircraft, and obtain the coefficients of the full-field data reduction model based on the test results and through the sparse measurement point data reduction model and the coefficient association model, specifically for:

[0091] Performing a wind tunnel test on the aircraft to obtain sparse measurement point test data, replacing the simulation results with the sparse measurement point test data to obtain coefficients of the sparse measurement point data reduced-order model, and obtaining coefficients of the full-field data reduced-order model using the coefficient association model according to the coefficients of the sparse measurement point data reduced-order model;

[0092] The measurement points used in the sparse measurement point data reduction model are the same as the measurement points used in the wind tunnel test in terms of position, number and order;

[0093] The reconstruction module 26 is used to substitute the coefficients of the full-field data reduction model into the full-field data reduction model to obtain a reconstructed flow field.

[0094] The embodiment of the present invention is a system embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0095] In summary, the embodiment of the present invention proposes a flow field reconstruction solution based on the simulation data reduction model to correct the test data. By combining numerical simulation and experiment, the test results are transformed from the traditional text-based scalar data form to the model-based field data form, and the expansion from discrete working conditions to continuous working conditions is achieved. The embodiment of the present invention can effectively improve the application value of the test results and provide more accurate and comprehensive reference data for aircraft design. The embodiment of the present invention specifically includes the following beneficial effects:

[0096] 1. Enhance the value of test results to the aircraft design process;

[0097] 2. Realize the expansion of test results from a few scalar data to field data, and from discrete working conditions to continuous working conditions;

[0098] 3. Reduce computing costs and improve computing efficiency;

[0099] 4. Improve the prediction confidence of the reduced-order model;

[0100] 5. Able to handle complex physical fields, such as fluid fields, temperature fields, etc.

[0101] Device Example 1

[0102] An embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps described in the method embodiment when executed by the processor.

[0103] Device Example 2

[0104] An embodiment of the present invention provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps described in the method embodiment are implemented.

[0105] The computer-readable storage medium in this embodiment includes, but is not limited to, ROM, RAM, magnetic disk or optical disk, etc.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A flow field reconstruction method for aircraft design, characterized in that include: Perform simulation calculations on aircraft under different working conditions, and build full-field data reduction model and sparse measurement point data reduction model based on the simulation results; Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model; Perform a wind tunnel test on the aircraft, and obtain the coefficients of the full-field data reduction model based on the test results and through the sparse measurement point data reduction model and the coefficient association model; as well as The coefficients of the full-field data reduction model are substituted into the full-field data reduction model to obtain a reconstructed flow field.

2. The method according to claim 1, characterized in that: The aircraft under different working conditions is simulated and calculated, and the full-field data reduction model and sparse measurement point data reduction model are constructed based on the simulation results. Specifically, the following are included: Select corresponding numerical simulation software to establish an aircraft simulation model according to the aircraft design requirements, use the aircraft simulation model to perform simulation calculations under different working conditions, convert and preprocess the obtained simulation results, and build a full-field data reduction model and a sparse measurement point data reduction model based on the processed simulation results; The simulation results include full-field results and sparse measurement point results obtained through simulation; The preprocessing includes coordinate point extraction and physical quantity extraction.

3. The method according to claim 1, characterized in that Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model specifically includes: Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model through a machine learning algorithm; Wherein, the machine learning algorithm is determined according to the type of reduced-order model.

4. The method according to claim 1, characterized in that Performing a wind tunnel test on an aircraft, and obtaining the coefficients of the full-field data reduction model based on the test results and through the sparse measurement point data reduction model and the coefficient association model specifically includes: Performing a wind tunnel test on the aircraft to obtain sparse measurement point test data, replacing the simulation results with the sparse measurement point test data to obtain coefficients of the sparse measurement point data reduced-order model, and obtaining coefficients of the full-field data reduced-order model using the coefficient association model according to the coefficients of the sparse measurement point data reduced-order model; The measurement points used in the sparse measurement point data reduction model are the same as those used in the wind tunnel test in terms of position, number and order.

5. A flow field reconstruction system for aircraft design, characterized in that include: A construction module is used to simulate the aircraft under different working conditions and build a full-field data reduction model and a sparse measurement point data reduction model based on the simulation results; An association module, used to establish a coefficient association model between the full-field data reduction model and the sparse measurement point data reduction model; A test module, used for performing a wind tunnel test on the aircraft, and obtaining the coefficients of the full-field data reduction model based on the test results and through the sparse measurement point data reduction model and the coefficient association model; as well as The reconstruction module is used to substitute the coefficients of the full-field data reduction model into the full-field data reduction model to obtain a reconstructed flow field.

6. The system according to claim 5, characterized in that The building blocks are specifically used for: Select corresponding numerical simulation software to establish an aircraft simulation model according to the aircraft design requirements, use the aircraft simulation model to perform simulation calculations under different working conditions, convert and preprocess the obtained simulation results, and build a full-field data reduction model and a sparse measurement point data reduction model based on the processed simulation results; The simulation results include full-field results and sparse measurement point results obtained through simulation; The preprocessing includes coordinate point extraction and physical quantity extraction.

7. The system according to claim 5, characterized in that The association module is specifically used for: Establishing a coefficient correlation model between the full-field data reduction model and the sparse measurement point data reduction model through a machine learning algorithm; Wherein, the machine learning algorithm is determined according to the type of reduced-order model.

8. The system according to claim 5, characterized in that The test module is specifically used for: Performing a wind tunnel test on the aircraft to obtain sparse measurement point test data, replacing the simulation results with the sparse measurement point test data to obtain coefficients of the sparse measurement point data reduced-order model, and obtaining coefficients of the full-field data reduced-order model using the coefficient association model according to the coefficients of the sparse measurement point data reduced-order model; The measurement points used in the sparse measurement point data reduction model are the same as those used in the wind tunnel test in terms of position, number and order.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the flow field reconstruction method for aircraft design according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the flow field reconstruction method for aircraft design according to any one of claims 1 to 4 are implemented.

Images