An aircraft dynamic aerodynamic modeling sample point distribution optimization method and system

Abstract

The application provides a kind of aircraft dynamic aerodynamic modeling sample point distribution optimization method and system, the method includes determining the motion form of aircraft under single working condition, according to the simulation accuracy of aerodynamic modeling, set the number of aircraft working condition and the sampling point number under each working condition;Genetic algorithm is used to adjust the amplitude, frequency and balance angle of attack under each working condition, to determine the uniformity value of all sample points in the study range;Based on the uniformity value and the set iteration number, iteration is carried out, and the minimum uniformity value is used as the best sample distribution scheme of aircraft dynamic aerodynamic modeling. The application uses sinusoidal simple harmonic oscillation motion under different amplitude, frequency and balance angle of attack to obtain dynamic aerodynamic force, and uses genetic algorithm to optimize the amplitude, frequency and balance angle of attack to obtain the best working condition combination. The sample is distributed by this method, and a more accurate aerodynamic model can be obtained.

Description

Technical Field

[0001] This invention relates to the field of aircraft aerodynamic design technology, and in particular to a method and system for optimizing the layout of sample points in dynamic aerodynamic modeling of aircraft. Background Technology

[0002] In the development of future new fighter jets in my country, maneuverability is one of our key concerns. Accurate and rapid aerodynamic characteristic prediction is a crucial step in aircraft control design. In the past, aerodynamic modeling has been a commonly used engineering method for rapid aerodynamic prediction. Among these methods, neural network-based dynamic aerodynamic modeling is also a feasible prediction approach.

[0003] In the process of neural network-based dynamic aerodynamic modeling of aircraft, it is necessary to obtain the relationship between aircraft attitude, velocity and aerodynamic force / torque. Existing technologies have not considered how to effectively obtain their relationship and build an optimized dynamic model to describe this relationship, so as to obtain a highly accurate aerodynamic model. Summary of the Invention

[0004] This specification provides one or more embodiments of a method for optimizing the placement of sample points in dynamic aerodynamic modeling of an aircraft, including the following steps:

[0005] S1. Determine the motion pattern of the aircraft under a single working condition. Based on the aerodynamic modeling and simulation accuracy, set the number of aircraft working conditions and the number of sampling points under each working condition.

[0006] S2. A genetic algorithm is used to adjust the amplitude, frequency, and equilibrium angle of attack for each working condition to determine the uniformity of all sample points within the study range.

[0007] S3. Based on the uniformity value and the set number of iterations, perform iterative operation step S2 to find the optimal point layout scheme for the aircraft dynamic aerodynamic modeling sample with the minimum uniformity value.

[0008] This specification provides one or more embodiments of a sample point placement optimization system for dynamic aerodynamic modeling of an aircraft, including:

[0009] Parameter setting module: Used to set the motion pattern of the aircraft under a single working condition. Based on the aerodynamic modeling and simulation accuracy, the number of aircraft working conditions and the number of sampling points under each working condition are set.

[0010] Calculation module: Used to adjust the amplitude, frequency, and equilibrium angle of attack for each working condition using a genetic algorithm, and to determine the uniformity value of all sample points within the study range;

[0011] The point placement scheme iteration module: Based on the uniformity value calculated by the calculation module and the set number of iterations, the calculation module is called to perform iterative calculations, and the optimal point placement scheme for the aircraft dynamic aerodynamic modeling sample with the minimum uniformity value is selected.

[0012] This specification provides one or more embodiments of a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aircraft dynamic aerodynamic modeling sample point placement optimization method as described above.

[0013] This specification provides one or more embodiments of a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for optimizing the placement of sample points in dynamic aerodynamic modeling of aircraft.

[0014] This invention first uses the motion of sinusoidal simple harmonic oscillations under different amplitudes, frequencies, and equilibrium angles of attack to obtain dynamic aerodynamic forces. Then, a genetic algorithm is used to optimize the amplitude, frequency, and equilibrium angle of attack to obtain the best combination of working conditions. By using this method to place samples, a more accurate aerodynamic model can be obtained, providing an important reference for sample planning of dynamic aerodynamic modeling methods based on neural networks. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of a method for optimizing the layout of sample points for dynamic aerodynamic modeling of an aircraft, provided for one or more embodiments of this specification;

[0017] Figure 2 A flowchart illustrating a method for optimizing the placement of sample points in dynamic aerodynamic modeling of an aircraft, provided as a specific example in this specification.

[0018] Figure 3 This is a distribution map of sample points obtained using the equal-interval selection method in the examples of this specification;

[0019] Figure 4 This is the sample point distribution map obtained using a genetic algorithm in the case study of this manual;

[0020] Figure 5A schematic diagram of a sample point layout optimization system for dynamic aerodynamic modeling of an aircraft, provided for one or more embodiments of this specification;

[0021] Figure 6 This is a schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0023] The present invention will now be described in detail with reference to specific embodiments and accompanying drawings.

[0024] Method Implementation Examples

[0025] According to embodiments of the present invention, a method for optimizing the placement of sample points in dynamic aerodynamic modeling of aircraft is provided, such as... Figure 1 The diagram shown is a flowchart of a method for optimizing the placement of sample points in dynamic aerodynamic modeling of an aircraft according to this embodiment. The method for optimizing the placement of sample points in dynamic aerodynamic modeling of an aircraft according to this embodiment includes:

[0026] S1. Determine the motion pattern of the aircraft under a single working condition. Based on the aerodynamic modeling and simulation accuracy, set the number of aircraft working conditions and the number of sampling points under each working condition.

[0027] S2. A genetic algorithm is used to adjust the amplitude, frequency, and equilibrium angle of attack for each working condition to determine the uniformity of all sample points within the study range.

[0028] S3. Based on the uniformity value and the set number of iterations, perform iterative operation step S2 to find the optimal point layout scheme for the aircraft dynamic aerodynamic modeling sample with the minimum uniformity value.

[0029] The method in this embodiment first uses the motion of sinusoidal simple harmonic oscillation under different amplitudes, frequencies, and equilibrium angles of attack to obtain dynamic aerodynamic forces. Then, a genetic algorithm is used to optimize the amplitude, frequency, and equilibrium angle of attack to obtain the best combination of working conditions. By using this method to place the samples, a more accurate aerodynamic model can be obtained, providing an important reference for sample planning of dynamic aerodynamic modeling methods based on neural networks.

[0030] In one specific embodiment, the method for optimizing the placement of sample points in dynamic aerodynamic modeling of an aircraft includes the following steps:

[0031] Step A1: Determine the motion mode of a single working condition as sinusoidal simple harmonic oscillation. This embodiment is not limited to the application of sinusoidal simple harmonic oscillation; other motions such as uniform motion and various variable speed motions can also be optimized using similar methods.

[0032] Step A2: Determine the three characterization parameters for the left and right working conditions: frequency, amplitude, and equilibrium angle of attack.

[0033] Step A3: Based on the effective range of the aerodynamic model, such as the attitude and velocity that the aerodynamic model can simulate, determine the simulation range of frequency, amplitude, and equilibrium angle of attack. The purpose of this embodiment is to establish a more accurate aerodynamic model. The established aerodynamic model cannot be applicable to all situations, so the simulation range must be defined in advance; for example, if the flight angle of attack range of an aircraft is 0-20, then the effective angle of attack range of the established aerodynamic model is set to 0-20. Therefore, when determining the simulation range of equilibrium angle of attack in this embodiment, the simulation range will also be set to around 0-20. The same applies to amplitude and frequency.

[0034] Step A4: Based on the simulation accuracy required for aerodynamic modeling, plan the number of aircraft operating conditions and the number of sampling points for each operating condition.

[0035] Step A5: Summarize the amplitude, frequency, and equilibrium angle of attack for each operating condition to form a DNA.

[0036] Step A6: Form an initial population from 200 DNA samples.

[0037] Step A7: Select any two DNAs from the population and perform crossover operations.

[0038] Step A8: Perform mutation operations on the DNA to generate new DNA.

[0039] Step A9: Based on the amplitude, frequency, and equilibrium angle of attack represented by the new DNA, form a sample.

[0040] Step A10: Based on the formed samples, a sample evaluation plane is created. The uniformity of the sample points within the evaluation plane is used as a standard to evaluate the applicability of the sample distribution. In this embodiment, a smaller sample uniformity value indicates greater uniformity, thereby evaluating the applicability of the sample distribution.

[0041] Step A11: Based on the evaluation results of step A10, repeat steps A7 to A10 to finally obtain the optimal sample point distribution.

[0042] The practicality and advantages of the method in this embodiment are illustrated below through specific examples.

[0043] This case study uses the dynamic aerodynamic modeling sample layout of a flying wing configuration as an example. The detailed process is as follows: Figure 2 .

[0044] First, the motion pattern of a single operating condition is determined to be the pitch motion process of a flying wing standard model under different frequencies, amplitudes, and equilibrium angles of attack. The simple harmonic oscillation form is (pitch angle, pitch angular velocity):

[0045] θ=θ0+θ m sin(2πft) (1)

[0046]

[0047] In the formula, θ is the pitch angle, θ m f is the amplitude, and f is the oscillation frequency;

[0048] Next, determine the research range for the equilibrium angle of attack, amplitude, and frequency; the equilibrium angle of attack is selected within the range of θ = -10° to 10°, and the amplitude range is θ m =0°~5°, frequency range f=2Hz~8Hz, how to select the above three variables will be the key to obtaining samples.

[0049] The third step is to determine the number of operating conditions and the preliminary sample distribution. For example, using the equal-interval selection method, the equilibrium angle of attack θ is set to -10°, -5°, 0°, 5°, and 10°, and the amplitude is selected as θ... m For angles of 2.5° and 5°, frequencies f were selected at 2Hz, 4Hz, 6Hz, and 8Hz, resulting in 40 calculation cases. The distribution of the obtained sample points is as follows: Figure 3 As shown in the figure, the sample point distribution is relatively regular, but near the pitch angular velocity of 0° / s, the sample distribution is basically blank. Furthermore, the sample distribution is relatively sparse in the pitch angular velocity ranges of 100° / s to 200° / s and -100° / s to -200° / s. Most samples are distributed in the ranges of 20° / s to 100° / s and -20° / s to -100° / s. The sample distribution is not uniform throughout the entire study area, and manually adjusting the sample distribution would undoubtedly result in a huge workload.

[0050] To address the aforementioned issues, a genetic algorithm is proposed for planning the sample distribution. The approach involves randomly selecting 40 different equilibrium angles of attack, amplitudes, and frequencies within the study area to form a sample set. The optimization objective is to determine the uniformity of the sample point distribution within the study area. Through continuous optimization, the optimal sample distribution is obtained. The optimization process is as follows: Figure 4 The specific calculation process of the genetic algorithm is as follows:

[0051] (1) Initialization

[0052] Within the scope of the study, 40 sets of equilibrium angle of attack, amplitude, and frequency were randomly selected to form a one-dimensional array (120 numbers in total), and the one-dimensional array was converted into binary form, with a population size of 200.

[0053] (2) Cross operation

[0054] Two DNA sequences are randomly selected from the population for crossover, with a crossover probability of 80%.

[0055] (3) Variation Budget

[0056] After the crossover operation is completed, the new DNA is subjected to mutation operation with a mutation probability of 0.5%, and a new population is obtained.

[0057] (4) Evaluate the adaptability parameters

[0058] The fitness parameters of each DNA in the new population are calculated. In this case, the fitness parameter is the uniformity of the distribution of sample points within the study area. The fitness parameter is also the optimization objective in the genetic algorithm.

[0059] (5) Filtering

[0060] The size of each DNA fitness parameter in the population is sorted, and only the top 200 are selected as the new population.

[0061] (6) Iterative optimization

[0062] Repeat steps (1) to (5). In this case, the number of iterations is 100. Continue until the fitness parameters of the population no longer change. This means that the population is already optimal, thus completing the optimization process.

[0063] The fifth step is to evaluate and confirm the final sample point distribution. Since the sample distribution is random at the beginning of the calculation, each calculation will yield different sample distribution results. A single calculation can lead to a local optimum. To mitigate this issue, this case study will perform 50 calculations, selecting the condition with the most uniform sample distribution from among these 50 for modeling. Figure 3 The sample distribution obtained through the genetic algorithm is shown in the figure. As can be seen from the figure, the problem of sample distribution has been improved to a certain extent. The samples can be distributed more evenly in the study area, which can be used as the sample distribution for dynamic aerodynamic modeling. Table 1 below shows the calculation conditions obtained through the genetic algorithm.

[0064] Table 1. Values ​​of the three characterization parameters obtained by the genetic algorithm

[0065]

[0066] System Implementation Examples

[0067] According to embodiments of the present invention, a system for optimizing the placement of sample points in dynamic aerodynamic modeling of aircraft is provided, such as... Figure 5 The diagram shown is a structural schematic of a sample point optimization system for dynamic aerodynamic modeling of an aircraft provided in this embodiment. According to an embodiment of the present invention, a sample point optimization system for dynamic aerodynamic modeling of an aircraft includes:

[0068] Parameter setting module: Used to set the motion pattern of the aircraft under a single working condition. Based on the aerodynamic modeling and simulation accuracy, the number of aircraft working conditions and the number of sampling points under each working condition are set.

[0069] Calculation module: Used to adjust the amplitude, frequency, and equilibrium angle of attack for each working condition using a genetic algorithm, and to determine the uniformity value of all sample points within the study range;

[0070] The point layout scheme determination module: Based on the uniformity value calculated by the calculation module and the set number of iterations, the calculation module is called iteratively to calculate the optimal point layout scheme for the aircraft dynamic aerodynamic modeling sample with the minimum uniformity value.

[0071] In this embodiment, the system first obtains dynamic aerodynamic forces by setting the motion of sinusoidal simple harmonic oscillations under different amplitudes, frequencies, and equilibrium angles of attack through a parameter setting module. The calculation module then uses a genetic algorithm to optimize the amplitude, frequency, and equilibrium angle of attack. Finally, an iterative optimization module through a point placement scheme module obtains the optimal combination of working conditions. Using this method to place points for the samples enables the acquisition of a more accurate aerodynamic model. This provides an important reference for sample planning in dynamic aerodynamic modeling methods based on neural networks.

[0072] In this preferred embodiment, the motion mode under a single working condition is set as sinusoidal simple harmonic oscillation based on the parameter setting module, and three characterizing parameters of frequency, amplitude, and equilibrium angle of attack are set for the working condition. The simulation range of frequency, amplitude, and equilibrium angle of attack is determined according to the attitude and velocity range simulated by the aerodynamic model of the aircraft.

[0073] In one specific embodiment, the calculation module uses a genetic algorithm to adjust the amplitude, frequency, and equilibrium angle of attack for each operating condition. The specific steps are as follows:

[0074] Step A31: Summarize the amplitude, frequency, and equilibrium angle of attack for each operating condition to form a DNA;

[0075] Step A32: Form an initial population from 200 DNA samples;

[0076] Step A33: Select any two DNA sequences from the population and perform a crossover operation;

[0077] Step A34: Perform mutation operations on the DNA to generate new DNA;

[0078] Step A35: Form a sample based on the amplitude, frequency, and equilibrium angle of attack represented by the new DNA.

[0079] The embodiments of the present invention are system embodiments corresponding to the above method embodiments. The specific operations of each module processing step can be understood by referring to the description of the method embodiments, and will not be repeated here.

[0080] like Figure 6 As shown, the present invention also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steps of the aircraft dynamic aerodynamic modeling sample point layout optimization method in the above embodiments, or when the computer program is executed by a processor, it implements the steps of the aircraft dynamic aerodynamic modeling sample point layout optimization method in the above embodiments. When the computer program is executed by the processor, it implements the following method steps:

[0081] S1. Determine the motion pattern of the aircraft under a single working condition. Based on the aerodynamic modeling and simulation accuracy, set the number of aircraft working conditions and the number of sampling points under each working condition.

[0082] S2. A genetic algorithm is used to adjust the amplitude, frequency, and equilibrium angle of attack for each working condition to determine the uniformity of all sample points within the study range.

[0083] S3. Based on the uniformity value and the set number of iterations, perform iterative operation step S2 to find the optimal point layout scheme for the aircraft dynamic aerodynamic modeling sample with the minimum uniformity value.

[0084] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0085] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or system embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The apparatus and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions 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. An aircraft dynamic aerodynamic modeling sample point placement optimization method, characterized in that, The method comprises the following steps: S1, determining the motion form of the aircraft under a single working condition, setting the number of aircraft working conditions and the number of sampling points under each working condition according to the simulation accuracy of aerodynamic modeling; S2, adjusting the amplitude, frequency and balance attack angle under each working condition by using a genetic algorithm to determine the uniformity value of all sample points within the research range; S3, performing iterative operation step S2 based on the uniformity value and the set number of iterations, and taking the minimum uniformity value as the optimal sample point arrangement scheme for the aircraft dynamic aerodynamic modeling.

2. The method of claim 1, wherein, The motion form under the single working condition is sinusoidal simple harmonic oscillation, and three characteristic parameters of frequency, amplitude and balance attack angle are used under this working condition; According to the attitude and speed range simulated by the aircraft aerodynamic model, the simulation range of frequency, amplitude and balance attack angle is determined.

3. The method of claim 1, wherein, The specific steps of adjusting the amplitude, frequency and balance attack angle under each working condition by using the genetic algorithm are as follows: Step S31, the amplitude, frequency and balance attack angle under each working condition are summarized to form a DNA; Step S32, 200 DNAs form an initial population; Step S33, any two DNAs in the population are selected for cross operation; Step S34, DNA mutation operation is performed to generate new DNA; Step S35, according to the amplitude, frequency and balance attack angle represented by the new DNA, a sample is formed.

4. An aircraft dynamic aerodynamic modeling sample point placement optimization system, comprising: It comprises: A parameter setting module is used to set the motion form of the aircraft under a single working condition, and set the number of aircraft working conditions and the number of sampling points under each working condition according to the simulation accuracy of aerodynamic modeling; A calculation module is used to adjust the amplitude, frequency and balance attack angle under each working condition by using a genetic algorithm to determine the uniformity value of all sample points within the research range; A point arrangement scheme iteration module is used to iteratively call the calculation module for calculation based on the uniformity value calculated by the calculation module and the set number of iterations, and take the minimum uniformity value as the optimal sample point arrangement scheme for the aircraft dynamic aerodynamic modeling.

5. A system according to claim 4, wherein, The parameter setting module is used to set the motion form under the single working condition as sinusoidal simple harmonic oscillation, and set three characteristic parameters of frequency, amplitude and balance attack angle under this working condition, and determine the simulation range of frequency, amplitude and balance attack angle according to the attitude and speed range simulated by the aircraft aerodynamic model.

6. A system for flight vehicle dynamic aerodynamic modeling sample point placement optimization as in claim 4, wherein, The calculation module is used to adjust the amplitude, frequency and balance attack angle under each working condition by using a genetic algorithm, and the specific steps are as follows: Step A31, the amplitude, frequency and balance attack angle under each working condition are summarized to form a DNA; Step A32, 200 DNAs form an initial population; Step A33, any two DNAs in the population are selected for cross operation; Step A34, DNA mutation operation is performed to generate new DNA; Step A35, according to the amplitude, frequency and balance attack angle represented by the new DNA, a sample is formed.

7. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the aircraft dynamic aerodynamic modeling sample point arrangement optimization method according to any one of claims 1 to 3.

8. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by the processor to realize the steps of the aircraft dynamic aerodynamic modeling sample point arrangement optimization method according to any one of claims 1 to 3.

Images