CN114861569A - Pneumatic characteristic evaluation method, electronic device and storage medium - Google Patents
Pneumatic characteristic evaluation method, electronic device and storage medium Download PDFInfo
- Publication number
- CN114861569A CN114861569A CN202210579230.2A CN202210579230A CN114861569A CN 114861569 A CN114861569 A CN 114861569A CN 202210579230 A CN202210579230 A CN 202210579230A CN 114861569 A CN114861569 A CN 114861569A
- Authority
- CN
- China
- Prior art keywords
- data
- design
- low
- aerodynamic
- machine learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention provides a method for evaluating aerodynamic characteristics, electronic equipment and a storage medium, and belongs to the technical field of aircraft aerodynamic performance evaluation. The method comprises the following steps: s1, acquiring a low-order data source of the aerodynamic characteristics of a certain aircraft in the basic state, which change along with Mach number, an attack angle and a sideslip angle; s2, acquiring data inflection points among low-order data sources, data relations among data linearity and contribution degrees of variables to target pneumatic characteristics; s3, finding out state points or state point sets which have large influence on the target to form a test scheme design matrix; and S4, evaluating state points in the test scheme design matrix by a solver, constructing a machine learning model by combining the evaluation result and the low-order data source data, and predicting all the pneumatic characteristics of the basic state of a certain aircraft. The problems of low efficiency of the OFAT method and low precision of the MDOE method are solved, the wind tunnel test efficiency and the CFD evaluation efficiency are improved, and the obtained pneumatic characteristic data are ensured to meet the fine design requirements of modern aircrafts.
Description
Technical Field
The application relates to a pneumatic performance evaluation method, in particular to a pneumatic characteristic evaluation method, electronic equipment and a storage medium, and belongs to the technical field of aircraft pneumatic performance evaluation.
Background
Wind tunnel tests and Computational Fluid Dynamics (CFD) are currently important means for researching aerodynamic technical problems, evaluating and determining the aerodynamic performance of an aircraft, and play an important role in the design and development of the aircraft. The aerodynamic data obtained through wind tunnel tests and CFD evaluation are the main basis of aerodynamic shape shaping, aircraft structure design and flight control design of various aircraft models. The cycle time and aerodynamic performance of aircraft development depends largely on the efficiency and effectiveness of wind tunnel testing and CFD evaluation. Detailed test protocol (evaluation protocol) formulation is required before wind tunnel testing and CFD evaluation.
The current test scheme adopts a univariate design of experiment (OFAT) method, namely, a certain independent variable is continuously changed in a certain range, when the influence of the change rule is researched, all other variables are required to be kept unchanged, and for example, when the attack angle is independently changed, variables such as Mach number, Reynolds number and sideslip angle are kept as constants. The method does not consider the interaction effect among the variables, does not systematically consider the influence of the change of a plurality of independent variables, and cannot reflect the influence relationship among the variables.
In order to overcome the defects, research institutions at home and abroad develop modern design of experiments (MDOE) method research to improve the efficiency and effect of aircraft aerodynamic characteristic evaluation. The MDOE method is mainly based on a Latin hypercube method or a uniformity design method for experimental design, and is combined with a response surface model for aerodynamic characteristic result prediction to obtain aerodynamic data meeting aircraft design requirements. The MDOE method does not consider the relation among pneumatic data when performing test design, and the modeling precision is low by adopting a response surface model. With the development of aircraft design technology and processing technology, the aerodynamic characteristic data obtained by the MDOE method cannot meet the requirement of modern aircraft design on precision.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of the above, in order to solve the technical problems of low efficiency of using an OFAT method and low accuracy of an MDOE method in the prior art, the invention provides a pneumatic characteristic evaluation method, electronic equipment and a storage medium, so as to improve wind tunnel test and CFD evaluation efficiency and ensure that obtained pneumatic characteristic data meet the requirement of fine design of modern aircrafts.
The first scheme is as follows: a method of aerodynamic property assessment comprising the steps of:
s1, acquiring a low-order data source of the aerodynamic characteristics of a certain aircraft in the basic state, which change along with Mach number, an attack angle and a sideslip angle;
s2, acquiring data inflection points among low-order data sources, data relations among data linearity and contribution degrees of variables to target aerodynamic characteristics;
s3, finding out state points or state point sets which have large influence on the target to form a test scheme design matrix;
and S4, evaluating state points in the test scheme design matrix by a solver, constructing a machine learning model by combining the evaluation result and the low-order data source data, and predicting all the pneumatic characteristics of the basic state of a certain aircraft.
Preferably, the method for obtaining the data relation between the data inflection point and the data linearity between the low-order data sources is,
s21, determining a primary data inflection point and a linear interval attack angle range;
s22, circularly screening data with data inflection point properties, removing one data with the data inflection point properties each time, constructing a machine learning model by using residual data, predicting the removed data magnitude with the data inflection point properties, and evaluating the prediction accuracy of the data magnitude;
s23, circularly screening data with linear interval properties, removing one or more data with linear interval properties each time, constructing a machine learning model by using the residual data, predicting the removed data values with linear interval properties, and evaluating the prediction accuracy of the data values;
preferably, the degree of contribution of said variable to the target aerodynamic properties is determined by,
s24, constructing a machine learning model by using all data;
and S25, predicting the contribution degree of the variables to the target aerodynamic characteristics by using a Sobol' sensitivity analysis method on a machine learning model.
Preferably, the specific method for forming the design matrix of the test scheme comprises the following steps:
s31, constructing a machine learning model by using all data;
s32, taking the data number as a design variable, taking an optimization target as the pneumatic characteristic prediction precision, developing the genetic algorithm optimizing operation with the number of the design variables of 1, obtaining a data point set with large single variable influence, and sorting the results from large to small according to the influence;
s33, taking the data serial number as a design variable, taking an optimization target as the prediction precision of pneumatic characteristics, developing the optimization operation of the genetic algorithm with the design variable quantity of 2-4, obtaining a data point set with large multivariate interaction effect influence, and sequencing the results from large to small according to the influence;
s34, setting a threshold value by taking the number M of actual test design samples as a standard, wherein if the number M is larger than the threshold value, the design matrix of the test scheme is obtained.
Scheme II: an electronic device comprising a memory storing a computer program and a processor, said processor implementing the steps of the method for intelligent design of experiments for rapid assessment of aerodynamic properties according to the first aspect when executing said computer program.
The third scheme is as follows: a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out an intelligent test design method for rapid assessment of aerodynamic properties according to solution one.
The invention has the following beneficial effects: the method can formulate a reduced test scheme on the basis of considering influence relation among variables, and compared with an OFAT method, the method can construct a high-precision machine learning model so as to improve the efficiency and effect of aircraft aerodynamic characteristic evaluation.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a graphical illustration of data relationships illustrating a roll moment coefficient versus side slip angle for an aircraft;
FIG. 3 is a schematic diagram of data contribution for an example of a geometric control parameter of an aircraft;
fig. 4 is a flow chart of an implementation of the method proposed by the present invention.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1, this embodiment is described with reference to fig. 1 to 4, and a method for evaluating aerodynamic characteristics includes the steps of:
s1, acquiring a low-order data source of the aerodynamic characteristics of a certain aircraft in the basic state, which change along with Mach number, attack angle and sideslip angle;
the low-order data source is a relative concept, for example, CFD data is easier to obtain relative to experimental data, and the CFD data source is the low-order data source; and like all data of the existing data source A, all data of the data source B is expected to be obtained through prediction of the data source A, wherein the data source A is a low-order data source.
The method of the low-order data source is that a low-order data source of the basic state aerodynamic characteristics of the certain aircraft changing along with Mach number, attack angle and sideslip angle is obtained through an Euler equation solver.
S2, acquiring data inflection points among low-order data sources, data relations among data linearity and contribution degrees of variables to target pneumatic characteristics; the variables include Mach number, angle of attack, and sideslip angle, among others
The method for obtaining the data relation between the data inflection point and the data linearity between the low-order data sources is,
s21, determining a primary data inflection point and a linear interval attack angle range;
s22, circularly screening data with data inflection point properties, removing one data with the data inflection point properties each time, constructing a machine learning model by using residual data, predicting the removed data magnitude with the data inflection point properties, and evaluating the prediction accuracy of the data magnitude; the residual data refers to data with a data inflection point property.
S23, circularly screening data with linear interval properties, removing one or more data with linear interval properties each time, constructing a machine learning model by using the residual data, predicting the removed data values with linear interval properties, and evaluating the prediction accuracy of the data values;
constructing a machine learning model by using the residual data, and predicting the removed data quantity value by using the machine learning model, wherein, for example, a group of aircraft lift force data changing along with the angle of attack, the total number of the 12 angles of attack is 12, and each angle of attack corresponds to one lift force; removing the 9 th data, and constructing an approximate model by using the remaining 11 data, wherein the input of the model is an attack angle, the output of the model is a lift force, and the data magnitude is the lift force; inputting an attack angle of the 9 th data on the approximate model, and outputting a lift force predicted value of the 9 th data; the prediction error is the error between the true value and the predicted value, and the prediction precision is the difference between the true value and the predicted value.
The degree of contribution of the variable to the target aerodynamic characteristics is by,
s24, constructing a machine learning model by using all data; all data includes low order data and high order data.
And S25, predicting the contribution degree of the variables to the target aerodynamic characteristics by using a Sobol' sensitivity analysis method on a machine learning model.
S3, finding out state points or state point sets which have large influence on the target to form a test scheme design matrix, and comprising the following steps:
s31, constructing a machine learning model by using all data;
s32, taking the data number as a design variable, taking an optimization target as the pneumatic characteristic prediction precision, developing the genetic algorithm optimizing operation with the number of the design variables of 1, obtaining a data point set with large single variable influence, and sorting the results from large to small according to the influence;
s33, taking the data serial number as a design variable, taking an optimization target as the prediction precision of pneumatic characteristics, developing the optimization operation of the genetic algorithm with the design variable quantity of 2-4, obtaining a data point set with large multivariate interaction effect influence, and sequencing the results from large to small according to the influence;
s34, setting a threshold value by taking the number M of actual test design samples as a standard, wherein if the number M is larger than the threshold value, the design matrix of the test scheme is obtained.
And S4, evaluating state points in the test scheme design matrix by a solver, constructing a machine learning model by combining the evaluation result and the low-order data source data, and predicting all the pneumatic characteristics of the basic state of a certain aircraft.
The method for evaluating the state points in the test scheme design matrix by the solver is to solve by using an RANS equation.
In embodiment 2, the computer device of the present invention may be a device including a processor, a memory, and the like, for example, a single chip microcomputer including a central processing unit, and the like. And the processor is used for implementing the steps of the recommendation method capable of modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The computer readable storage medium of the present invention may be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., and the computer readable storage medium has stored thereon a computer program that, when the computer program stored in the memory is read and executed by the processor of the computer device, can implement the above-mentioned steps of the CREO-based software that can modify the modeling method of the relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.
Claims (6)
1. A method of aerodynamic property assessment, comprising the steps of:
s1, acquiring a low-order data source of the aerodynamic characteristics of the basic state of a certain aircraft, which changes along with the Mach number, the attack angle and the sideslip angle;
s2, acquiring data inflection points among low-order data sources, data relations among data linearity and contribution degrees of variables to target aerodynamic characteristics;
s3, finding out the state points or state point sets which have great influence on the target to form a design matrix of the test scheme;
and S4, evaluating state points in the design matrix of the test scheme by a solver, constructing a machine learning model by combining the evaluation result and the low-order data source data, and predicting all the aerodynamic characteristics of the basic state of an aircraft.
2. The intelligent experimental design method for the rapid assessment of aerodynamic characteristics as claimed in claim 1, wherein the method for obtaining the data relationship between the data inflection point and the data linearity between the low-order data sources is,
s21, determining a primary data inflection point and a linear interval attack angle range;
s22, circularly screening data with data inflection point properties, removing one data with the data inflection point properties each time, constructing a machine learning model by using residual data, predicting the removed data magnitude with the data inflection point properties, and evaluating the prediction accuracy of the data magnitude;
and S23, circularly screening the data with the linear interval property, removing one or more data with the linear interval property each time, constructing a machine learning model by using the residual data, predicting the removed data value with the linear interval property, and evaluating the prediction accuracy of the data value.
3. An intelligent test design method for rapid evaluation of aerodynamic characteristics according to claim 2, wherein the contribution degree of the variable to the target aerodynamic characteristics is determined by,
s24, constructing a machine learning model by using all data;
and S25, predicting the contribution degree of the variables to the target aerodynamic characteristics by using a Sobol' sensitivity analysis method on a machine learning model.
4. The intelligent test design method for the rapid evaluation of aerodynamic characteristics according to claim 3, wherein the specific method for forming the test scheme design matrix comprises the following steps:
s31, constructing a machine learning model by using all data;
s32, taking the data number as a design variable, taking an optimization target as the pneumatic characteristic prediction precision, developing the genetic algorithm optimizing operation with the number of the design variables of 1, obtaining a data point set with large single variable influence, and sorting the results from large to small according to the influence;
s33, taking the data serial number as a design variable, taking an optimization target as the prediction precision of pneumatic characteristics, developing the optimization operation of the genetic algorithm with the design variable quantity of 2-4, obtaining a data point set with large multivariate interaction effect influence, and sequencing the results from large to small according to the influence;
s34, setting a threshold value by taking the number M of actual test design samples as a standard, wherein if the number M is larger than the threshold value, the design matrix of the test scheme is obtained.
5. An electronic device comprising a memory storing a computer program and a processor, wherein the processor when executing the computer program implements the steps of the intelligent test design method for rapid pneumatic characteristic assessment according to any one of claims 1-4.
6. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out an intelligent test design method for rapid assessment of aerodynamic properties according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210579230.2A CN114861569A (en) | 2022-05-26 | 2022-05-26 | Pneumatic characteristic evaluation method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210579230.2A CN114861569A (en) | 2022-05-26 | 2022-05-26 | Pneumatic characteristic evaluation method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114861569A true CN114861569A (en) | 2022-08-05 |
Family
ID=82640022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210579230.2A Pending CN114861569A (en) | 2022-05-26 | 2022-05-26 | Pneumatic characteristic evaluation method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114861569A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574115A (en) * | 2024-01-16 | 2024-02-20 | 中国空气动力研究与发展中心计算空气动力研究所 | Wind tunnel test research data acquisition, analysis and evaluation method, system and related equipment |
-
2022
- 2022-05-26 CN CN202210579230.2A patent/CN114861569A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574115A (en) * | 2024-01-16 | 2024-02-20 | 中国空气动力研究与发展中心计算空气动力研究所 | Wind tunnel test research data acquisition, analysis and evaluation method, system and related equipment |
| CN117574115B (en) * | 2024-01-16 | 2024-03-22 | 中国空气动力研究与发展中心计算空气动力研究所 | Wind tunnel test research data acquisition, analysis and evaluation method, system and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109783604B (en) | Information extraction method and device based on small amount of samples and computer equipment | |
| KR20210032140A (en) | Method and apparatus for performing pruning of neural network | |
| CN111401472B (en) | Infrared target classification method and device based on deep convolutional neural network | |
| CN102314533B (en) | Methods and systems for matching a computed curve to a target curve | |
| CN111144548A (en) | Method and device for identifying working condition of pumping well | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| CN114861569A (en) | Pneumatic characteristic evaluation method, electronic device and storage medium | |
| CN114444988A (en) | Service performance evaluation method and device for traffic infrastructure health monitoring system | |
| CN114943674A (en) | Defect detection method, electronic device and storage medium | |
| JP2016018230A (en) | Control parameter adaptation method and control parameter adaptation assist device | |
| CN111832610A (en) | 3D printing organization prediction method, system, medium and terminal equipment | |
| CN116205918A (en) | Multi-mode fusion semiconductor detection method, device and medium based on graph convolution | |
| CN109800508A (en) | The calculation method and terminal device of the empty top plate thickness at rock-socketed piles end | |
| CN115423159A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
| Tran et al. | Training-free hardware-aware neural architecture search with reinforcement learning | |
| CN112433952B (en) | Method, system, device and medium for testing fairness of deep neural network model | |
| CN106997462A (en) | A kind of quantum wire image-recognizing method | |
| CN115547058B (en) | Method for rapidly calibrating parameters of travel chain model based on gradient descent | |
| CN111815510A (en) | Image processing method based on improved convolutional neural network model and related equipment | |
| CN113051790B (en) | Steam load loading method, system, equipment and medium for finite element simulation | |
| WO2019209571A1 (en) | Proactive data modeling | |
| US11561654B2 (en) | Machine learning-based position determination | |
| JP2019160254A (en) | Learning discrimination device and method for learning discrimination | |
| CN113435058B (en) | Data dimension reduction method, system, terminal and medium for distribution network self-healing test model | |
| WO2024070170A1 (en) | Trial production condition proposal system and trial production condition proposal method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |