Design method, device and equipment for aerodynamic surface structure of aircraft wing and medium

Abstract

The invention relates to a structural design method and device for an aerodynamic surface of an aircraft wing, electronic equipment and a computer readable medium. The method comprises the following steps: determining a design interval according to flight parameters of an aircraft and aircraft wing design parameters; determining sample points in the design interval through a Latin super method; establishing a fluid-solid coupling model of the aircraft wing; performing dynamic simulation at the sample points based on the fluid-solid coupling model to generate deformation parameters and aerodynamic loads of the aircraft wing; establishing a neural network agent model through the flight parameters, the deformation parameters and the aerodynamic load; and designing the aerodynamic surface structure of the aircraft wing based on the neural network agent model. According to the method, under the condition that the aerodynamic surface structure of the aircraft wing does not need to be subjected to experience checking and correction, aerodynamic surface structure design considering aeroelastic load redistribution is achieved, and the design and development efficiency is obviously improved.

Description

Technical Field

[0001] This application relates to the field of computer information processing. Specifically, it relates to a method, device, electronic device, and computer-readable medium for the aerodynamic surface structure design of an aircraft wing. Background Art

[0002] With the development of material technology and structural design methods, the degree of lightweight of aircraft has been increasingly improved, and the static aeroelasticity problem of the wing structure has become prominent. Under the action of aerodynamic forces, complex wing surface structures may form large bending and torsional deformations, which may lead to the deviation of the wing geometry from the optimal solution given by the aerodynamic design, resulting in the loss of aerodynamic performance and affecting flight efficiency. Therefore, when carrying out structural design, considering the static aeroelastic deformation of the wing is crucial for improving the aerodynamic and flight performance of modern fixed-wing aircraft.

[0003] Currently, the research method for aeroelasticity problems in aircraft structural design is mainly based on the fluid-structure interaction numerical simulation technology of computational fluid dynamics and computational structural dynamics, and the response law of the structure over time is obtained by alternately calculating the structural motion equation and the unsteady flow field. Although the fluid-structure interaction numerical simulation technology based on CFD / CSD can well solve the multi-field coupling problems of nonlinearity and large deformation, there are problems of high computational cost and long design cycle when analyzing large and complex wing surface structures, which seriously affect the design cycle of aircraft wings.

[0004] Therefore, a new method, device, electronic device, and computer-readable medium for the aerodynamic surface structure design of an aircraft wing are needed.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of this application. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] In view of this, this application provides a method, device, electronic device, and computer-readable medium for the aerodynamic surface structure design of an aircraft wing, which realizes the aerodynamic surface structure design considering the redistribution of aeroelastic loads without the need for empirical verification and correction of the aerodynamic surface structure of the aircraft wing, and significantly improves the design and development efficiency.

[0007] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of this application.

[0008] According to one aspect of the present application, a method for designing the aerodynamic surface structure of an aircraft wing is proposed. The method includes: determining a design range according to the flight parameters of the aircraft and the design parameters of the aircraft wing, where the flight parameters include flight speed, flight altitude, and angle of attack, and the design parameters of the aircraft wing include: wingspan and chord length; determining sample points within the design range by the Latin hypercube method; establishing a fluid-structure interaction model of the aircraft wing; performing dynamic simulation at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; establishing a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads; and performing the aerodynamic surface structure design of the aircraft wing based on the neural network surrogate model, where the aerodynamic surface structure design parameters include: the dihedral angle and the twist angle of the aircraft wing.

[0009] In an exemplary embodiment of the present application, determining the design range according to the flight parameters of the aircraft and the design parameters of the aircraft wing includes: determining the design range according to the flight speed, flight altitude, angle of attack of the aircraft and the design parameters of the aircraft wing.

[0010] In an exemplary embodiment of the present application, establishing the fluid-structure interaction model of the aircraft wing includes: establishing the geometric model of the aircraft wing and parameterizing it; establishing the flow field geometric model of the aircraft wing and parameterizing it.

[0011] In an exemplary embodiment of the present application, performing dynamic simulation at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing includes: obtaining the flow field distribution and the motion equilibrium equation at the sample points based on the fluid-structure interaction model; generating the deformation parameters and aerodynamic loads of the aircraft wing according to the calculation results of the flow field distribution and the motion equilibrium equation.

[0012] In an exemplary embodiment of the present application, establishing a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads includes: establishing a neural network surrogate model with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output.

[0013] In an exemplary embodiment of the present application, establishing a neural network surrogate model with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output includes: constructing a data loss function and a motion equilibrium equation loss function of the neural network surrogate model; aiming at minimizing the data loss function and the motion equilibrium equation loss function; and updating the network weights through a genetic algorithm to establish the neural network surrogate model.

[0014] In an exemplary embodiment of the present application, a neural network surrogate model is established with the flight parameters as the input and the deformation parameters and aerodynamic loads as the outputs, and it further includes: verifying the neural network surrogate model; generating the neural network surrogate model when the accuracy of the neural network surrogate model meets the accuracy requirement; and reconstructing the neural network surrogate model when the accuracy of the neural network surrogate model does not meet the accuracy requirement.

[0015] In an exemplary embodiment of the present application, reconstructing the neural network surrogate model includes: adjusting the number of sample points to reconstruct the neural network surrogate model; and / or adjusting the sample point selection strategy to reconstruct the neural network surrogate model.

[0016] In an exemplary embodiment of the present application, based on the neural network surrogate model, the aerodynamic surface structure design of the aircraft wing is carried out, including: obtaining the actual design interval and actual design scheme of the aircraft wing; generating the deformation parameters of the aircraft wing according to the actual design interval, the actual design scheme and the neural network surrogate model; and adjusting the deformation parameters to meet the actual design requirements.

[0017] In an exemplary embodiment of the present application, generating the deformation parameters of the aircraft wing according to the actual design interval, the actual design scheme and the neural network surrogate model includes: obtaining the working condition design interval and design scheme of the aircraft wing; determining the prediction parameters according to the actual design interval and the actual design scheme; and inputting the prediction parameters into the neural network surrogate model to generate the deformation parameters of the aircraft wing.

[0018] According to one aspect of the present application, an aerodynamic surface structure design device for an aircraft wing is provided, and the device includes: an interval determination module for determining a design interval according to the flight parameters and design parameters of the aircraft wing; a sample selection module for determining sample points within the design interval by the Latin hypercube method; a model module for establishing a fluid-structure interaction model of the aircraft wing; a simulation module for performing dynamic simulation at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; a surrogate model construction module for establishing a neural network surrogate model through the flight parameters, the deformation parameters and the aerodynamic loads; and a design module for performing the aerodynamic surface structure design of the aircraft wing based on the neural network surrogate model.

[0019] According to one aspect of the present application, an electronic device is provided, and the electronic device includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0020] According to one aspect of the present application, there is provided a computer-readable medium storing a computer program which, when executed by a processor, implements the method as described above.

[0021] According to the method, device, electronic device and computer-readable medium for the aerodynamic surface structure design of an aircraft wing of the present application, a design interval is determined according to the flight parameters of the aircraft and the design parameters of the aircraft wing; sample points are determined by the Latin hypercube method within the design interval; a fluid-structure interaction model of the aircraft wing is established; dynamic simulations are performed at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; a neural network surrogate model is established through the flight parameters, the deformation parameters and the aerodynamic loads; and the aerodynamic surface structure design of the aircraft wing is carried out based on the neural network surrogate model. In this way, without the need for empirical verification and correction of the aerodynamic surface structure of the aircraft wing, the aerodynamic surface structure design considering the redistribution of aerodynamic elastic loads is realized, and the design and development efficiency is significantly improved.

[0022] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By referring to the drawings and describing its exemplary embodiments in detail, the above and other objects, features and advantages of the present application will become more apparent. The following described drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 FIG. is a flowchart of a method for the aerodynamic surface structure design of an aircraft wing according to an exemplary embodiment.

[0025] Figure 2 FIG. is a flowchart of a method for the aerodynamic surface structure design of an aircraft wing according to another exemplary embodiment.

[0026] Figures 3 to 6 FIG. is a schematic diagram of a method for the aerodynamic surface structure design of an aircraft wing according to another exemplary embodiment.

[0027] Figures 7 to 10 FIG. is a schematic diagram of a method for the aerodynamic surface structure design of an aircraft wing according to another exemplary embodiment.

[0028] Figure 11 FIG. is a block diagram of a device for the aerodynamic surface structure design of an aircraft wing according to another exemplary embodiment.

[0029] Figure 12It is a block diagram of an electronic device shown according to an exemplary embodiment.

[0030] Figure 13 It is a block diagram of a computer-readable medium shown according to an exemplary embodiment. Detailed implementation manners

[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0032] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of this application. However, those skilled in the art will realize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of this application.

[0033] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the contents and operations / steps, nor do they necessarily have to be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0035] It should be understood that although terms such as first, second, and third may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concept of this application. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more of them.

[0036] Those skilled in the art can understand that the drawings are only schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily essential for implementing the present application, so they cannot be used to limit the protection scope of the present application.

[0037] Figure 1

[0038] Figure 1 As shown, in S102, a design interval is determined according to the flight parameters of the aircraft and the design parameters of the aircraft wing. The design interval can be determined according to the flight speed, flight altitude, angle of attack of the aircraft and the design parameters of the aircraft wing.

[0039] In S104, sample points are determined within the design interval by the Latin hypercube method. The Latin hypercube sampling method (LHS) is a random stratified sampling method, that is, the values within the range of 0-1 are divided into multiple layers for random sampling. LHS can better reflect the distribution range of variables under the condition of fewer samples.

[0040] In S106, a fluid-structure interaction model of the aircraft wing is established. The geometric model of the aircraft wing can be established and parameterized; the flow field geometric model of the aircraft wing can also be established and parameterized. Parameterization means expressing various types of information using parameters. For example, the fluid velocity and pressure are represented by v and P respectively.

[0041] More specifically, a fluid-structure interaction model of the wing deployment mechanism can be established at the selected sample points. For example, the aerodynamic load, deployment speed, deployment angle of the wing of the aircraft wing, and the total deformation of the wing along the z-axis, the displacement of the leading edge and trailing edge, and the torsion angle can be obtained by solving through Ansys Workbench simulation software for a period of time.

[0042] In S108, dynamic simulation is performed at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing. For example, based on the fluid-structure interaction model, the flow field distribution and the motion equilibrium equation at the sample points are obtained; the deformation parameters and aerodynamic loads of the aircraft wing are generated according to the calculation results of the flow field distribution and the motion equilibrium equation.

[0043] In the present application, the compressible Navier-Stokes equations are used as the control equations for solving the flow field. In the rectangular coordinate system, its integral form is:

[0044]

[0045] ​In the formula: is the flow field conservation term; Ω is the control volume; is the convective flux term; is the dissipation flux term.

[0046] The motion balance equation of the structure under aerodynamic load is:

[0047]

[0048] In the formula: x is the displacement vector; f is the external load vector; M is the mass matrix; C is the damping matrix; K is the stiffness matrix.

[0049] Calculate the deformation parameters and aerodynamic loads at each sample point through the control equation and the motion balance equation.

[0050] In S110, establish a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads. More specifically, a neural network surrogate model can be established with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output.

[0051] In one embodiment, a data loss function and a motion balance equation loss function can be constructed; with the minimization of the data loss function and the motion balance equation loss function as the goal; update the network weights through a genetic algorithm to establish a neural network surrogate model.

[0052] In a specific embodiment, the data obtained by wing structure simulation calculation can be used to construct a neural network surrogate model with the flight parameters of the aircraft, flight speed, flight altitude, and angle of attack as the input and the aerodynamic load of the wing, the twist angle of the structure, and the leading and trailing edge displacements as the output.

[0053] More specifically, in the present application, the data obtained by wing structure simulation calculation can be used to construct a neural network surrogate model with the flight parameters of the aircraft, flight speed, flight altitude, and angle of attack as the input and the aerodynamic load of the wing, the twist angle of the structure, and the leading and trailing edge displacements as the output. The data of fluid-structure interaction calculation is used as the training data for this model to construct a data loss function

[0054]

[0055] where y (i) is the output value of the current step of the model, is the true value, and m is the number of output parameters. Considering that the aerodynamic load and the wing tip displacement must satisfy the motion balance equation (2), a motion balance equation loss function is established between the displacement and the load at the wing tip to describe the compliance degree of the neural network model with respect to the differential equation.

[0056]

[0057] With L 1 ,L 2 Taking minimization of L as the goal, a genetic algorithm is used as an optimizer to update the network weights. After the model is constructed, the twist angle and load distribution during the wing deployment process can be predicted according to the input flight parameters. After the neural network surrogate model is constructed, the twist angle and load distribution during the wing deployment process can be predicted according to the input flight parameters.

[0058] In one embodiment, the neural network surrogate model can also be verified; when the accuracy of the neural network surrogate model meets the accuracy requirement, the neural network surrogate model is generated; when the accuracy of the neural network surrogate model does not meet the accuracy requirement, the neural network surrogate model is reconstructed.

[0059] More specifically, an accuracy evaluation result can be set. The situation where the deviation between the prediction result of the neural network surrogate model and the fluid-structure interaction simulation result is more than 10% can be set as insufficient calculation accuracy. When the calculation accuracy is insufficient, it can be considered that the neural network surrogate model generated this time cannot accurately reflect the deformation parameters and aerodynamic loads of the aircraft wing and other related data, and calculation needs to be performed again.

[0060] More specifically, when the accuracy of the neural network surrogate model does not meet the accuracy requirement, the number of sample points can be adjusted to reconstruct the neural network surrogate model; when the accuracy of the neural network surrogate model does not meet the accuracy requirement, the selection strategy of the sample points can also be adjusted to reconstruct the neural network surrogate model.

[0061] In S112, the aerodynamic surface structure design of the aircraft wing is carried out based on the neural network surrogate model. For example, the actual design interval and actual design scheme of the aircraft wing can be obtained; the deformation parameters of the aircraft wing are generated according to the actual design interval, the actual design scheme and the neural network surrogate model; the deformation parameters are adjusted to meet the actual design requirements.

[0062] More specifically, the working condition design interval and design scheme of the aircraft wing can be obtained; the prediction parameters are determined according to the actual design interval and the actual design scheme; the prediction parameters are input into the neural network surrogate model to generate the deformation parameters of the aircraft wing.

[0063] In actual applications, when designing the wing, the twist angle can be selected as the design variable. Under the condition that the given flight overload, that is, the total lift, is constant, the wing twist angle and the load distribution on the wing surface are determined.

[0064] Design parameters can be input into the neural network surrogate model, and the calculation results of the neural network surrogate model can be analyzed. According to the additional aerodynamic load caused by the elastic torsional deformation obtained from the model solution and the total elastic torsional angle of the structure, the design interval of the wing condition and the design scheme of the aerodynamic surface structure can be evaluated and adjusted through the aerodynamic load and the total elastic torsional angle of the structure. The dihedral angle and torsional angle of the wing in the reverse preset scheme can be set to achieve the aerodynamic surface structure design considering the redistribution of aeroelastic loads.

[0065] More specifically, when the load distribution of the wing torsional angle is greater than the threshold, it can be considered that the wing with this design parameter does not meet the safety requirements and needs to be redesigned. For another example, when the elastic torsional angle is greater than the deformation interval threshold, it can be considered that the wing with this design parameter does not meet the safety requirements and needs to be redesigned.

[0066] When the design parameters do not meet the safety requirements, the angle of attack and the design parameters of the aircraft wing can be adjusted to recalculate the aerodynamic load and the total elastic torsional angle of the structure until the design requirements are met.

[0067] According to the aerodynamic surface structure design method of the aircraft wing of the present application, the design interval is determined according to the flight parameters of the aircraft and the design parameters of the aircraft wing; sample points are determined by the Latin hypercube method within the design interval; a fluid-structure interaction model of the aircraft wing is established; dynamic simulations are performed at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; a neural network surrogate model is established through the flight parameters, the deformation parameters, and the aerodynamic loads; and the aerodynamic surface structure design of the aircraft wing is carried out based on the neural network surrogate model. In this way, without the need for empirical verification and correction of the aerodynamic surface structure of the aircraft wing, the aerodynamic surface structure design considering the redistribution of aeroelastic loads is achieved, significantly improving the design and development efficiency.

[0068] The aerodynamic surface structure design method of the aircraft wing of the present application is different from the traditional analysis method of empirical verification and correction after the design of the aerodynamic surface structure. By constructing a neural network surrogate model, the redistribution of aeroelastic loads on the aircraft wing surface structure is considered in advance, avoiding the increase in computing costs and shortening the design cycle.

[0069] Figure 2 It is a flowchart of an aerodynamic surface structure design method of an aircraft wing shown according to an exemplary embodiment. Figure 2 The shown process 20 is for Figure 1 The detailed description in the shown process.

[0070] As Figure 2As shown, in S202, determine the initial scheme design interval. The selection space of sample points can be determined according to the flight speed, altitude, angle of attack during the wing deployment process of the unmanned aerial vehicle, and the span and chord length of the wing.

[0071] In S204, select sample points. Select sample points through the Latin hypercube sampling method.

[0072] In S206, establish a finite element model of the wing. Establish a fluid-structure interaction model of the wing deployment mechanism at the selected sample points, and solve through Ansys Workbench simulation software to obtain the aerodynamic load, deployment speed, deployment angle of the wing during a period of time, as well as the total deformation of the wing along the z-axis, the displacement of the leading and trailing edges, and the twist angle.

[0073] In S208, solve to obtain a database. Solve the finite element model of the wing to obtain calculation results such as the twist angle and the displacement of the leading and trailing edges of the structure of the fluid-structure interaction model.

[0074] In S210, construct a neural network surrogate model. Using the data obtained from the wing structure simulation calculation, with the flight parameters of the aircraft, namely flight speed, flight altitude, and angle of attack, as inputs, and the aerodynamic load of the wing, the twist angle of the structure, and the displacement of the leading and trailing edges as outputs, construct a neural network surrogate model.

[0075] In S212, check if the model accuracy meets the requirements. A new set of test sample points can be obtained within the selection space of the sample points, and the wing structure load distribution parameters at the test sample points can be calculated using the fluid-structure interaction method and compared with the prediction results of the neural network surrogate model for accuracy evaluation. If the accuracy is insufficient, increase the number of sample points or change the sample point selection strategy to reconstruct the neural network surrogate model.

[0076] In S214, analyze the calculation results. When the accuracy meets the requirements, it can be considered that this neural network surrogate model can be applied in practice.

[0077] In S216, reverse design the dihedral angle and twist angle of the wing. In practical applications, certain parameters can be selected as design variables. Given a certain flight overload, that is, a certain total lift, determine the twist angle of the wing and the load distribution on the wing surface. Analyze the calculation results of the neural network surrogate model, and evaluate and adjust the design interval of the wing working conditions and the design scheme of the aerodynamic surface structure according to the additional aerodynamic load and the total elastic twist angle of the structure caused by the elastic twist deformation obtained from the model solution.

[0078] In S218, solve to meet the constraint conditions. Judge whether each index in the calculation results meets the range of the design threshold.

[0079] In S220, achieve the design goal. When all calculation indicators meet the design requirements, it can be considered that this design meets the design goal.

[0080] The aerodynamic surface structure design method for the aircraft wing of the present application avoids the empirical checking and correction of the aerodynamic surface structure by constructing a neural network surrogate model, realizes the aerodynamic surface structure design considering the redistribution of aerodynamic elastic loads, significantly improves the design and development efficiency, and has significant positive significance for the design of high-performance aircraft wing structures.

[0081] The aerodynamic surface structure design method for the aircraft wing of the present application is oriented to the wing structure. By establishing a data-driven neural network surrogate model, the aerodynamic surface structure design method under the premise of considering the redistribution of aerodynamic elastic loads is realized. Compared with the traditional method, rapid modeling and analysis are achieved, the calculation cost is greatly reduced, and it has positive significance for quickly and accurately analyzing the redistribution of wing surface loads and structural deformations and the design of high-performance aircraft wing structures.

[0082] It should be clearly understood that the present application describes how to form and use specific examples, but the principles of the present application are not limited to any details of these examples. On the contrary, based on the teachings disclosed in the present application, these principles can be applied to many other embodiments.

[0083] The following is an embodiment of applying the aerodynamic surface structure design method for the aircraft wing of the present application. Taking the deployable wing structure as an example, the actual application steps of the present application are described in detail:

[0084] First, determine the design interval for wing deployment. The specific flight parameters can be: flight speed from 0.5 to 0.8 Ma, flight altitude from 800 to 1200 m, and angle of attack from 0 to 10°. Then, use the Latin hypercube method to select 100 sample points within this design interval.

[0085] A wing geometric model can be established and parameterized according to the design parameters of the wing. The geometric model of the deployable wing is as Figure 3 shown. A flow field geometric model of the wing can also be established and parameterized according to the design parameters of the wing. The flow field geometric model of the deployable wing is as Figure 4 shown.

[0086] It is worth mentioning that since the wing is symmetrically designed, 1 / 2 of the wing geometric model is established for calculation.

[0087] Conduct mechanism deployment dynamics simulation for the working conditions at all sample points to obtain the deployment speed, deployment angle of the wing, and the total deformation of the wing along the z-axis, the displacement and twist angle of the leading edge and trailing edge within a certain period of time. The results calculated under the working conditions of flight speed 0.7 Ma, flight altitude 1000 m, and angle of attack 50° are shown in Table 1. The deformation during the deployment of the wing structure is as Figure 5 shown.

[0088] Table 1

[0089] Deployment speed Deployment angle Total deformation Leading edge displacement Trailing edge displacement Wing tip twist angle 9.2 m / s 61° 0.166m 0.142m 0.166m -4.76°

[0090] Taking the flight parameters (flight speed, flight altitude, angle of attack) of the aircraft as inputs and the twist angle, leading and trailing edge displacements, and aerodynamic loads of the wing structure as outputs, a neural network surrogate model in this application is constructed.

[0091] To verify the results, one or more sample points can also be randomly selected from the design interval for verification. The deviation between the prediction result of the neural network surrogate model and the fluid-structure interaction simulation result is within 6.4%, and the neural network surrogate model meets the accuracy standard.

[0092] After the neural network surrogate model is accurately verified, the operating condition altitude, speed, and angle of attack to be predicted can be input into the neural network surrogate model. The neural network surrogate model generates calculation results, and then the aerodynamic load and twist angle of the wing under this operating condition can be quickly predicted to determine the additional load generated by the elastic torsional deformation.

[0093] Analyze the calculation results of the neural network surrogate model. According to the additional aerodynamic load caused by the elastic torsional deformation obtained by model solving and the total elastic twist angle of the structure, evaluate and adjust the design interval of the wing operating condition and the design scheme of the aerodynamic surface structure. Reverse preset the dihedral angle and twist angle of the wing in the scheme, correct the design interval of the angle of attack to 0 to 6°, and the calculated wing tip twist angle is as Figure 6 shown, meeting the design goal that the maximum wing tip twist angle is less than -5°. This design scheme can meet the aerodynamic surface structure design considering the redistribution of aerodynamic elastic loads.

[0094] The following is an embodiment of applying the aerodynamic surface structure design method of the aircraft wing in this application. Taking a fixed-wing unmanned aircraft as an example, the actual application steps of this application are described in detail:

[0095] First, the design interval of the fixed-wing unmanned aircraft can be determined. The design interval can be, for example: flight speed 0.6 to 1 Ma, flight altitude 900 to 1500 m, angle of attack 0 to 8°. 100 sample points are selected within this design interval using the Latin hypercube method.

[0096] Establish and parameterize the geometric model of the fixed-wing unmanned aircraft wing. The geometric model of the fixed-wing unmanned aircraft wing is as Figure 7 shown. Establish and parameterize the flow field geometric model of the fixed-wing unmanned aircraft wing. The flow field geometric model of the fixed-wing is as Figure 8 shown.

[0097] Perform fluid-structure interaction dynamics simulations on the operating conditions at all sample points to obtain the deformation and load conditions of the fixed-wing UAV wing structure over a period of time. The results calculated under the conditions of a flight speed of 0.8 Ma, a flight altitude of 1200 m, and an angle of attack of 4° are shown in Table 2, and the deformation of the wing is as Figure 9 shown.

[0098] Table 2

[0099] Total deformation Leading edge displacement Trailing edge displacement Wing tip twist angle 0.183m 0.157m 0.183m -4.91°

[0100] Taking the flight parameters (flight speed, flight altitude, angle of attack) of the aircraft as inputs and the twist angle, leading and trailing edge displacements, and wing aerodynamic loads of the fixed-wing UAV wing structure as outputs, a neural network surrogate model is constructed.

[0101] Input the operating condition altitude, speed, and angle of attack that need to be predicted into the neural network surrogate model, and the wing aerodynamic load and twist angle of the fixed-wing UAV under this operating condition can be quickly predicted, and then the additional load generated by the elastic torsional deformation can be determined. Randomly select 1 sample point from the design interval for verification. The deviation between the prediction result of the neural network surrogate model and the fluid-structure interaction simulation result is within 8.2%, meeting the accuracy requirements.

[0102] Analyze the calculation results of the neural network surrogate model. According to the additional aerodynamic load and the total elastic twist angle of the structure caused by the elastic torsional deformation obtained by the model solution, evaluate and adjust the design interval of the wing operating conditions and the design scheme of the aerodynamic surface structure. Reverse preset the dihedral angle and twist angle of the fixed-wing UAV wing in the preset scheme, and correct the design interval of the angle of attack to 0 to 4°. The wing tip twist angle calculated is as Figure 10 shown, meeting the design goal that the maximum wing tip twist angle is less than -5°, and realizing the aerodynamic surface structure design considering the redistribution of aerodynamic elastic loads.

[0103] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided in this application are executed. The program can be stored in a computer-readable storage medium, and the storage medium can be a read-only memory, a disk, or an optical disc, etc.

[0104] In addition, it should be noted that the above drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of this application, rather than for limiting purposes. It is easy to understand that the processes shown in the above drawings do not indicate or limit the time sequence of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0105] The following is an embodiment of the apparatus of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the method embodiment of the present application.

[0106] Figure 11 It is a block diagram of an aerodynamic surface structure design device for an aircraft wing shown according to an exemplary embodiment. As Figure 11 shown, the aerodynamic surface structure design device 110 of the aircraft wing includes: an interval determination module 1102, a sample selection module 1104, a model module 1106, a simulation module 1108, a surrogate model construction module 1110, and a design module 1112.

[0107] The interval determination module 1102 is configured to determine a design interval according to the flight parameters and design parameters of the aircraft wing; the interval determination module 1102 is further configured to determine the design interval according to the flight speed, flight altitude, angle of attack of the aircraft and the design parameters of the aircraft wing.

[0108] The sample selection module 1104 is configured to determine sample points within the design interval by the Latin hypercube method;

[0109] The model module 1106 is configured to establish a fluid-structure interaction model of the aircraft wing; the model module 1106 is further configured to establish a geometric model of the aircraft wing and perform parametric processing on it; establish a flow field geometric model of the aircraft wing and perform parametric processing on it.

[0110] The simulation module 1108 is configured to perform dynamic simulation at the sample points based on the fluid-structure interaction model to generate deformation parameters and aerodynamic loads of the aircraft wing; the simulation module 1108 is further configured to obtain the flow field distribution and motion equilibrium equation at the sample points based on the fluid-structure interaction model; generate deformation parameters and aerodynamic loads of the aircraft wing according to the calculation results of the flow field distribution and the motion equilibrium equation.

[0111] The surrogate model construction module 1110 is configured to establish a neural network surrogate model through the flight parameters, the deformation parameters and the aerodynamic loads; the surrogate model construction module 1110 is further configured to establish a neural network surrogate model with the flight parameters as inputs and the deformation parameters and aerodynamic loads as outputs.

[0112] The design module 1112 is configured to perform aerodynamic surface structure design of the aircraft wing based on the neural network surrogate model. The design module 1112 is further configured to obtain the actual design interval and actual design scheme of the aircraft wing; generate deformation parameters of the aircraft wing according to the actual design interval, the actual design scheme and the neural network surrogate model; adjust the deformation parameters to meet the actual design requirements.

[0113] The aerodynamic surface structure design device for an aircraft wing according to the present application determines a design interval based on the flight parameters of the aircraft and the aircraft wing design parameters; determines sample points within the design interval by the Latin hypercube method; establishes a fluid-structure interaction model of the aircraft wing; performs dynamic simulations at the sample points based on the fluid-structure interaction model to generate deformation parameters and aerodynamic loads of the aircraft wing; establishes a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads; and designs the aerodynamic surface structure of the aircraft wing based on the neural network surrogate model. In this way, without the need for empirical verification and correction of the aerodynamic surface structure of the aircraft wing, the aerodynamic surface structure design considering the redistribution of aerodynamic elastic loads is achieved, and the design and development efficiency is significantly improved.

[0114] Figure 12 is a block diagram of an electronic device shown according to an exemplary embodiment.

[0115] Reference will be made below Figure 12 to describe the electronic device 1200 according to this embodiment of the present application. Figure 12 The electronic device 1200 shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0116] As Figure 12 shown, the electronic device 1200 is presented in the form of a general-purpose computing device. The components of the electronic device 1200 may include, but are not limited to: at least one processing unit 1210, at least one storage unit 1220, a bus 1230 connecting different system components (including the storage unit 1220 and the processing unit 1210), a display unit 1240, etc.

[0117] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 1210, so that the processing unit 1210 executes the steps according to various exemplary embodiments of the present application described in this specification. For example, the processing unit 1210 can execute as Figure 1 , Figure 2 shown in the steps.

[0118] The storage unit 1220 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 12201 and / or a cache storage unit 12202, and may further include a read-only storage unit (ROM) 12203.

[0119] The storage unit 1220 may further include a program / utility 12204 having a set (at least one) of program modules 12205. Such program modules 12205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0120] The bus 1230 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0121] The electronic device 1200 may also communicate with one or more external devices 1200' (such as a keyboard, a pointing device, a Bluetooth device, etc.), enabling communication with devices that allow a user to interact with the electronic device 1200, and / or any device with which the electronic device 1200 can communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be through the input / output (I / O) interface 1250. Further, the electronic device 1200 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 1260. The network adapter 1260 may communicate with other modules of the electronic device 1200 through the bus 1230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0122] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, as Figure 13 shown, the technical solution according to the embodiments of the present application can be embodied in the form of a software product. The software product may be stored in a non-volatile storage medium (which may be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present application.

[0123] The software product may employ any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0125] The program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0126] The above computer-readable medium carries one or more programs, which, when executed by the device, cause the computer-readable medium to implement the following functions: determining a design interval according to the flight parameters of the aircraft and the aircraft wing design parameters; determining sample points within the design interval by the Latin hypercube method; establishing a fluid-structure interaction model of the aircraft wing; performing dynamic simulation at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; establishing a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads; and performing aerodynamic surface structure design of the aircraft wing based on the neural network surrogate model.

[0127] Those skilled in the art can understand that the above-mentioned modules can be distributed in the device according to the description of the embodiments, or can be correspondingly changed and distributed in one or more devices that are different from the embodiments. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0128] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (such as a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0129] The above specifically shows and describes the exemplary embodiments of the present application. It should be understood that the present application is not limited to the detailed structures, settings, or implementation methods described herein; on the contrary, the present application is intended to cover various modifications and equivalent settings included in the spirit and scope of the appended claims.

Claims

1. A method for designing the aerodynamic surface structure of an aircraft wing, characterized in that, it includes: Determine the design interval according to the flight parameters of the aircraft and the design parameters of the aircraft wing. Among them, the flight parameters include flight speed, flight altitude, and angle of attack, and the design parameters of the aircraft wing include: wingspan and chord length; Determine sample points within the design interval by the Latin Hypercube method; Establish a fluid-structure interaction model of the aircraft wing; Based on the fluid-structure interaction model, perform dynamic simulation at the sample points to generate the deformation parameters and aerodynamic loads of the aircraft wing; Establish a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads; Based on the neural network surrogate model, perform the aerodynamic surface structure design of the aircraft wing, where the aerodynamic surface structure design parameters include: the dihedral angle and twist angle of the aircraft wing.

2. The method according to claim 1, characterized in that, Establishing the fluid-structure interaction model of the aircraft wing includes: Establish a geometric model of the aircraft wing and parameterize it; Establish a flow field geometric model of the aircraft wing and parameterize it.

3. The method according to claim 1, characterized in that, Based on the fluid-structure interaction model, perform dynamic simulation at the sample points to generate the deformation parameters and aerodynamic loads of the aircraft wing, including: Based on the fluid-structure interaction model, obtain the flow field distribution and the equation of motion balance at the sample points; Generate the deformation parameters and aerodynamic loads of the aircraft wing according to the calculation results of the flow field distribution and the equation of motion balance.

4. The method according to claim 1, characterized in that, Establishing a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads includes: Establish a neural network surrogate model with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output.

5. The method according to claim 4, characterized in that, Establishing a neural network surrogate model with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output includes: Construct a data loss function and a loss function for the equation of motion balance; Aim at minimizing the data loss function and the loss function for the equation of motion balance; Update the network weights through a genetic algorithm to establish a neural network surrogate model.

6. The method according to claim 5, characterized in that, Establishing a neural network surrogate model with the flight parameters as the input and the deformation parameters and aerodynamic loads as the output further includes: Verify the neural network surrogate model; When the accuracy of the neural network surrogate model meets the accuracy requirements, generate the neural network surrogate model; When the accuracy of the neural network surrogate model does not meet the accuracy requirements, reconstruct the neural network surrogate model.

7. The method according to claim 6, characterized in that, Reconstructing the neural network surrogate model includes: Adjust the number of sample points to reconstruct the neural network surrogate model; and / or Adjust the selection strategy of the sample points to reconstruct the neural network surrogate model.

8. The method according to claim 1, characterized in that, Based on the neural network surrogate model, perform the aerodynamic surface structure design of the aircraft wing, including: Obtain the actual design range and actual design scheme of the aircraft wing; Generate the deformation parameters of the aircraft wing according to the actual design range, the actual design scheme, and the neural network surrogate model; Adjust the deformation parameters to meet the actual design requirements.

9. The method according to claim 8, wherein, generating the deformation parameters of the aircraft wing according to the actual design range, the actual design scheme, and the neural network surrogate model includes: Obtain the working condition design range and design scheme of the aircraft wing; Determine the prediction parameters according to the actual design range and the actual design scheme; Input the prediction parameters into the neural network surrogate model to generate the deformation parameters of the aircraft wing.

10. An aerodynamic surface structure design device for an aircraft wing, wherein, it includes: An interval determination module, configured to determine the design interval according to the flight parameters and design parameters of the aircraft wing, where the flight parameters include flight speed, flight altitude, and angle of attack, and the aircraft wing design parameters include: wingspan and chord length; A sample selection module, configured to determine sample points within the design interval by the Latin hypercube method; A model module, configured to establish a fluid-structure interaction model of the aircraft wing; A simulation module, configured to perform dynamic simulation at the sample points based on the fluid-structure interaction model to generate the deformation parameters and aerodynamic loads of the aircraft wing; A surrogate model construction module, configured to establish a neural network surrogate model through the flight parameters, the deformation parameters, and the aerodynamic loads; A design module, configured to perform the aerodynamic surface structure design of the aircraft wing based on the neural network surrogate model, where the aerodynamic surface structure design parameters include: the dihedral angle and twist angle of the aircraft wing.

11. An electronic device, wherein, it includes: One or more processors; A storage device, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer-readable medium, on which a computer program is stored, wherein, when the program is executed by a processor, it implements the method according to any one of claims 1 to 9.

Images