Deformation-based control surface distributed load prediction method in flow field

Abstract

The invention provides a deformation-based control surface distributed load prediction method in a flow field, relates to the technical field of aircraft design, and solves the problem that the control torque and the distributed load of a thin control surface cannot be measured and obtained by adopting the traditional force measurement balance technology and the like. The method comprises the steps of calculating a control surface aerodynamic load field of an aircraft based on a wing-rudder fusion model, and establishing a typical control surface aerodynamic load database; determining a corresponding relation between a deformation displacement field and an aerodynamic load field of the control surface by adopting a thin plate control equation or a finite element method, and establishing a control surface load-displacement database; a deep convolutional neural network is obtained, corresponding training is completed, and a control surface displacement-load solver is constructed; during engineering application, a control surface displacement cloud picture obtained through actual measurement is input into the control surface displacement-load solver, the solver correspondingly outputs a control surface load cloud picture, and load prediction is achieved. According to the method, fine load measurement of the thin-walled control surface becomes possible, and key data support is provided for structural strength analysis and pneumatic optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft design, and is applied to the process of acquiring aircraft control surface loads, and in particular to a method for predicting control surface distributed loads in a deformation-based flow field. Background Art

[0002] In modern aircraft design, the load characteristics of the control surface directly affect the reliability of the flight control system. Accurately measuring the hinge torque of the control surface under different flight conditions and adapting it to the appropriate servo is one of the core links in aircraft design. With the improvement of stealth performance and maneuverability requirements, the fusion design trend of wing surfaces and control surfaces is obvious, and the structural thickness of the control surface and its installation area continues to decrease, which poses a severe challenge to the traditional hinge torque test method based on physical experiments.

[0003] At present, three technical means are mainly used in the engineering field to obtain the rudder load data. The first is the computational fluid dynamics method, which obtains the flow field and surface load information by establishing a full-scale model of the aircraft and discretizing and solving the flow control equations. This method has achieved high accuracy in lift calculation under simple shapes and high Mach number conditions, and the relative error can be controlled within 3%. However, when faced with complex flow phenomena in the rudder area, including physical processes such as shock wave boundary layer interference, gap flow, and unsteady flow separation, the prediction deviation of the local load on the rudder increases significantly due to the accuracy of the turbulence model and the resolution of the grid. In particular, the dynamic separation flow and shock wave oscillation phenomena in the leeward area of ​​the rudder are difficult to accurately capture with existing computational models, resulting in insufficient credibility in load assessment in key areas.

[0004] The second pressure measurement integration technology arranges discrete pressure sensors on the rudder surface and combines it with a reconstruction algorithm to invert the surface pressure distribution. This method has a certain adaptability in the testing of special-shaped rudder surfaces, but due to the spatial limitations of thin-walled structures, there are technical difficulties in optimizing the layout density and position of pressure measurement points. Engineering practice has shown that reconstruction algorithms based on area weighting or radial basis functions have obvious errors in complex flow areas, and the systematic deviation from the actual measured data of the strain balance is on the order of 10%. In addition, the internal piping of thin rudder surfaces is difficult to lay out, which further limits the applicable scenarios of this technology.

[0005] The third method, strain balance force measurement, is a traditional method that relies on the principle of elastic mechanics to infer load parameters by measuring structural strain. Its theoretical system is complete and widely used in conventional structural tests, but it faces inherent defects such as long balance design cycle and high test cost. When applied to ultra-thin rudder surfaces, the contradiction between structural deformation control and balance installation space is particularly prominent: on the one hand, the too-thin structural stiffness is difficult to meet the mechanical requirements of balance installation; on the other hand, the reduction in rudder surface thickness leads to an increase in the additional torque of the balance, which directly affects the measurement accuracy. For ultra-thin rudder surfaces with a thickness below the critical value, the existing force balance can no longer perform effective measurements due to physical size limitations.

[0006] Based on the existing technical means, computational fluid dynamics methods have the defect of insufficient accuracy in complex flow simulation, pressure measurement integration technology is limited by the sensor layout and reconstruction algorithm errors of thin-walled structures, and traditional strain balances face the problem of spatial adaptation under ultra-thin structures. These technical bottlenecks seriously restrict the ability of modern aircraft to evaluate the control surface loads in the process of stealth and high maneuverability development, and it is urgent to develop new measurement methods to break through the limitations of existing technologies. Summary of the invention

[0007] The purpose of the present invention is to solve the problem that some aircrafts cannot use traditional force measuring balance and other technologies to measure their control torque and distributed load due to their thin control surfaces. Therefore, a method for predicting the distributed load of the control surface in a flow field based on deformation is proposed. The present invention measures the deformation of the control surface after being loaded in real time by binocular vision, and reconstructs the distributed load of the control surface based on the displacement measurement of key points. In this way, the present invention will not have the difficulty of installing the measuring equipment due to limited space, and can accurately obtain the distributed load of the control surface, filling the gap in the effective acquisition of distributed load in the prior art.

[0008] The present invention adopts the following technical solutions to achieve the purpose: A method for predicting distributed loads on a control surface in a deformation-based flow field comprises the following steps: S1. Based on the wing-rudder fusion model, calculate the aerodynamic load field of the aircraft's rudder surface under different flight conditions and establish a typical rudder surface aerodynamic load database; S2. Using the thin plate control equation or the finite element method, determine the corresponding relationship between the deformation displacement field of the control surface and the aerodynamic load field, establish a control surface load-displacement database and obtain a training data set from it; S3, obtaining a deep convolutional neural network, using the training data set to complete the training of the deep convolutional neural network, and constructing a rudder displacement-load solver; S4. In engineering applications, the measured displacement cloud map of the rudder surface is input into the rudder surface displacement-load solver, and the rudder surface displacement-load solver outputs the rudder surface load cloud map to realize the prediction of the rudder surface distributed load.

[0009] Specifically, in step S1, the wing-rudder fusion model consists of a wing surface of preset area, shape and size and a rudder surface hinged on the wing surface; when calculating the aerodynamic load field of the rudder surface, the corresponding calculation conditions are designed according to the flight envelope parameters of the aircraft, and CFD calculation is performed to obtain the aerodynamic load distribution of the rudder surface in the flight envelope, which serves as the basis for establishing a typical rudder surface aerodynamic load database.

[0010] Preferably, when performing CFD calculations, a second-order method based on finite volume method discretization is used to solve the Reynolds-averaged Navier-Stokes equations under the calculation conditions, and the k-ω SST turbulence model is used to achieve the closure of the equation; the grid type used in the calculation is a polyhedral unstructured grid, free far-field conditions are used all around the calculation domain, and adiabatic wall conditions are used for the wing and rudder surfaces.

[0011] Specifically, in the wing-rudder fusion model, the aerodynamic force acting on the rudder surface includes the pressure perpendicular to any surface of the rudder surface and the friction parallel to any surface of the rudder surface. After performing CFD calculations for different flight conditions of the aircraft, the CFD calculation results are extracted to obtain the upper surface pressure distribution acting on the rudder surface. and the pressure distribution on the lower surface , forming a control surface pressure matrix corresponding to each flight condition; by traversing the control surface pressure matrix corresponding to each flight condition, a typical control surface aerodynamic load database can be formed.

[0012] Furthermore, in step S2, thin plate control equations or finite element method are used to process the two forms of the control surface; The first form is that the upper and lower surfaces of the rudder surface are both symmetric planes, and the thickness change rate between the symmetric planes is less than the preset thickness threshold. This form is processed using the thin plate control equation; The second form is that the thickness change rate between the upper and lower surfaces of the rudder surface is greater than or equal to a preset thickness threshold, or the curvature of the upper / lower surface of the rudder surface is greater than or equal to a preset curvature threshold. This form is processed using the finite element method.

[0013] Specifically, for the first type of rudder surface, based on Kirchhoff thin plate theory, the thin plate control equation is established with deflection as the unknown quantity, as follows:

[0014] In the formula, is the bending stiffness of the rudder surface, is the distributed load on the rudder surface, is the deflection distribution of the rudder surface, coordinate Indicates the horizontal and vertical coordinates in the plane coordinate system established based on the plane where the upper / lower surface of the rudder is located. is the gradient operator; The expression is as follows:

[0015] In the formula, is the elastic modulus of the rudder surface, is the thickness of the rudder surface, is Poisson's ratio; when the above thin plate control equation is applied to the rudder surface, when there is a distributed load in the rudder surface , then the rudder surface will have a deflection distribution at the same time , so for each flight condition, there is ; By distributing the load After expressing the net load acting on the rudder surface, the control equation of the thin plate is solved to obtain the deflection distribution corresponding to the rudder surface , forming the deformation displacement field of the rudder surface, that is, determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

[0016] Specifically, for the second type of rudder, the finite element method is directly used to solve it. The deformation displacement field of the rudder and the aerodynamic load field are related through a set of partial differential equations that control the elastic deformation of the solid, forming the Lame-Navier equation shown below:

[0017] In the equation, is the elastic modulus of the rudder surface, is the gradient operator, is Poisson's ratio; , , are the corresponding coordinates in the three-dimensional coordinate system; , , Respectively represent the , , The displacement in the direction; , , Respectively represent , , Directional body forces; is the volume strain of the rudder surface, and its value is equal to the first invariant of the strain tensor, as shown in the following formula:

[0018] The above partial differential equations are a linear system. For any distributed load on the rudder surface By giving boundary conditions and load conditions, the deformation displacement field of the linear system can be obtained, thereby determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

[0019] Preferably, in step S3, the training data set includes a rudder surface displacement cloud map as a training input, and a rudder surface load cloud map corresponding to the rudder surface displacement cloud map obtained based on a rudder surface load-displacement database; the deep convolutional neural network includes multiple branch paths, each branch path includes multiple convolutional layers, multiple activation function layers and a fully connected layer; the input of some convolutional layers in a preset number of branch paths comes from the output of the activation function layer in any other branch path; the output of each branch path is used as the output of the deep convolutional neural network after an output fusion operation.

[0020] Specifically, the constructed rudder displacement-load solver is expressed as follows:

[0021] In the formula, is the parameter set of the deep convolutional neural network; is the displacement cloud map of the rudder surface, which is used as the input of the solver; It is the rudder surface load cloud map, which is the output of the solver and is used to characterize the distributed load of the rudder surface; In a deep convolutional neural network, the convolution layer and activation function layer of each branch path make the input features undergo convolution operation and nonlinear transformation, and the output is as follows:

[0022] In the formula, is the input feature map of the convolutional layer, is the convolution operator, is a trainable convolution kernel, is the bias parameter, is a nonlinear activation function, is the output feature map of the activation function layer; the nonlinear activation function in the activation function layer The ReLU activation function is used, and its operation is as follows:

[0023] In the formula, Represents the input value of the activation function layer, Represents the input value and 0, select the larger value; Loss Function for Deep Convolutional Neural Networks As follows:

[0024] In the formula, represents the distributed load on the rudder surface obtained by CFD calculation, represents the distributed load on the rudder surface predicted by the deep convolutional neural network, Represents the total number of feature points; , represents a trainable convolution kernel and its corresponding weight A collection of; L2 regularization coefficient to prevent overfitting of deep convolutional neural networks; Represents the system of differential equations that govern the displacement stresses of the control surface.

[0025] Specifically, in step S4, a high-definition camera is used to photograph and monitor the aircraft rudder surface, and the deformation of the rudder surface after being loaded is measured in real time through binocular vision to form a rudder surface displacement cloud map; the rudder surface displacement-load solver outputs the corresponding rudder surface load cloud map based on the measured rudder surface displacement cloud map, thereby realizing the prediction of the rudder surface distributed load.

[0026] In summary, due to the adoption of this technical solution, the beneficial effects of the present invention are as follows: The method of the present invention takes the structural deformation characteristics as the key point and innovatively realizes the non-contact measurement of the distributed load on the rudder surface. Different from the limitation of the traditional pressure measurement integration method that relies on the reconstruction of discrete pressure points, this method can directly obtain the continuous load distribution on the rudder surface by combining high-precision displacement field measurement with the mechanical constitutive equation, providing key data support for structural strength analysis and aerodynamic optimization. This method also solves the industry problem that the force balance or pressure measurement pipeline cannot be laid due to insufficient installation space on ultra-thin rudder surfaces, making it possible to measure the refined load of thin-walled rudder surfaces.

[0027] In terms of engineering applications, the method of the present invention also demonstrates good technical transferability. In addition to being effectively applied in the field of aircraft design, its core principle can also be extended to the health monitoring process in the fields of building cantilever structures, large-span bridge components, etc. For example, in order to solve the problem of direct measurement of stress distribution of large-area cantilever panels in buildings, the structural displacement field can be obtained through a machine vision system, and then the method of the present invention can be combined to achieve non-contact load reconstruction, thereby significantly improving the ability to assess the safety of hidden structural parts. Compared with the discrete point pressure interpolation mode of the traditional pressure measurement integration method and the inherent defects of the strain balance that can only obtain concentrated forces, the method of the present invention has the dual advantages of global load distribution measurement and non-contact measurement.

[0028] Through numerical simulation and comparison with typical working conditions, the load prediction accuracy of the method of the present invention has met the actual engineering needs. The magnitude characteristics and spatial distribution laws of the distributed load are highly consistent with the true value, and the deviation of the rudder concentrated force and hinge moment parameters obtained by integral calculation from the reference value is stably controlled within 5%. This method not only effectively overcomes the calculation distortion problem of traditional measurement methods in complex flow areas, but also provides reliable technical guarantee for the refined design of thin-walled rudders of the new generation of aircraft. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The schematic diagram briefly describes the overall process of the method of the present invention; Figure 2 A schematic diagram of the wing-rudder fusion model used in the method of the present invention; Figure 3 is an overall schematic diagram of the computational domain grid used in the method of the present invention; Figure 4 A schematic diagram of the calculation grid and its boundary layer of the wing-rudder fusion model in the method of the present invention; Figure 5 This is an example diagram of the pressure cloud diagram of the control surface in the method of the present invention; Figure 6 Schematic diagram of a thin plate model based on Kirchhoff thin plate theory in the method of the present invention; Figure 7 The aerodynamic load distribution diagram of the windward surface of the second type of rudder surface in the method of the present invention; Figure 8 The aerodynamic load distribution diagram of the leeward side of the second type of rudder surface in the method of the present invention; Fig. 9 Schematic diagram of the deformation displacement of the steel rudder surface in the method of the present invention; Fig.10 Schematic diagram of the deformation displacement of the aluminum alloy rudder surface in the method of the present invention; Fig.11 A schematic diagram of the structure of a deep convolutional neural network used in the method of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0031] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Example A method for predicting distributed loads on control surfaces in a deformation-based flow field. Figure 1 The overall process of the method is briefly described in FIG. 1 , which can be viewed here simultaneously; the various steps of the method are summarized as follows: S1. Based on the wing-rudder fusion model, calculate the aerodynamic load field of the aircraft's rudder surface under different flight conditions and establish a typical rudder surface aerodynamic load database; S2. Using the thin plate control equation or the finite element method, determine the corresponding relationship between the deformation displacement field of the control surface and the aerodynamic load field, establish a control surface load-displacement database and obtain a training data set from it; S3, obtaining a deep convolutional neural network, using the training data set to complete the training of the deep convolutional neural network, and constructing a rudder displacement-load solver; S4. In engineering applications, the measured displacement cloud map of the rudder surface is input into the rudder surface displacement-load solver, and the rudder surface displacement-load solver outputs the rudder surface load cloud map to realize the prediction of the rudder surface distributed load.

[0033] This embodiment will introduce the details or preferred contents of each step in detail according to the above step sequence.

[0034] In step S1, according to the characteristics of the thin rudder surface, the following can be established: Figure 2 The wing-rudder fusion model shown, Figure 2 The dimension marking of the example is given in the figure, which can be used as a reference for modeling; the wing-rudder fusion model consists of a wing surface with a preset area, shape and size, and a rudder surface hinged on the wing surface.

[0035] For common aircraft flight conditions, the outflow Mach number, inflow static pressure, inflow static temperature, flight angle of attack and flight sideslip angle can be determined based on its flight envelope parameters, and then the corresponding calculation conditions can be designed. Through CFD calculation, the aerodynamic load distribution of the rudder surface in the flight envelope can be obtained as the basis for establishing a typical rudder surface aerodynamic load database. Since the wing-rudder fusion model in this embodiment is a simplified model, it can avoid the requirements for the calculation amount of the complex shape of the real aircraft. At the same time, through this typical wing-rudder combination, the pressure distribution law of the rudder surface can be reflected as much as possible.

[0036] In this embodiment, when performing CFD calculations, a second-order method based on the finite volume method (FVM) discretization is used to solve the Reynolds-averaged Navier-Stokes (RANS) equations under the calculation conditions, and the k-ω SST turbulence model is used to achieve the closure of the equation. The k-ω SST turbulence model has been verified by a large number of engineering calculations and is more suitable for simulations with adverse pressure gradients and separation zones. Therefore, it is suitable for the flow characteristics of the wing-rudder fusion model of this embodiment in the leeward area of ​​the large rudder.

[0037] The mesh type used in the calculation of this embodiment is a polyhedral unstructured mesh. The mesh used in the calculation domain can be found in Figure 3 The computational grid and boundary layer after the wing-rudder fusion model is shown in Figure 4The recommended number of mesh elements is about 2 million. Free far-field conditions are used around the computational domain, and adiabatic wall conditions are used on the wing and rudder surfaces.

[0038] In the wing-rudder fusion model of this embodiment, the aerodynamic force acting on the rudder surface includes the pressure perpendicular to any surface of the rudder surface and the friction parallel to any surface of the rudder surface. Compared with the surface pressure, the surface friction is a small quantity, and this embodiment will use magnitude analysis to determine it. First, the surface friction coefficient of the plate is It can be determined as follows:

[0039] In the formula, Represents the Reynolds number; during flight, the Reynolds number at high altitude is generally taken as 10 7 Up to 10 8 In this embodiment, the rudder surface area is 0.2m 2 For example, using the atmospheric parameters at an altitude of 10 km to calculate the surface friction of an aircraft with a flight Mach number of 0.6, the following is the result:

[0040] The direction of the surface friction force is parallel to the rudder surface. If it is assumed that the thickness of the rudder surface is 10 mm, the torque on the rudder axis will be less than 0.04 Nm. This torque value is small compared to the hinge torque generated by the surface pressure (generally 100 Nm), so it can be ignored in this embodiment.

[0041] In this embodiment, CFD calculations are performed for different flight conditions of the aircraft, and corresponding CFD calculation results are extracted to obtain the pressure distribution on the control surface, for example: Figure 5 An example of display; when the rudder action is offset, Figure 5 The left side of the figure shows the pressure cloud diagram of the windward side of the rudder, and the right side shows the pressure cloud diagram of the leeward side of the rudder. In this way, the pressure distribution on the upper surface of the rudder can be obtained. and the pressure distribution on the lower surface , forming a pressure matrix of the control surface corresponding to each flight condition. In addition, in actual engineering applications, since there are many grid cells on the control surface, it is not necessary to extract pressure for each grid point. Instead, a series of feature points can be pre-designed for sampling. These feature points can be obtained through the local coordinate system corresponding to the control surface, such as the standard three-axis coordinate system. In this way, by traversing the control surface pressure matrix corresponding to each flight condition, a typical control surface aerodynamic load database can be formed.

[0042] In step S2, for each flight state of the aircraft, there is a corresponding rudder surface distributed load based on the typical rudder surface aerodynamic load database. , which can be based on the upper surface pressure distribution of the rudder and the pressure distribution on the lower surface In this embodiment, the deformation displacement simulation process of the rudder surface is processed by using the thin plate control equation or the finite element method according to the two forms of the rudder surface.

[0043] The first form is that the upper and lower surfaces of the rudder are both symmetrical planes, and the thickness change rate between the symmetrical planes is less than the preset thickness threshold. This form is processed using the thin plate control equation. Because the symmetrical plane size of the rudder of a modern aircraft is usually much larger than its thickness dimension, that is, the ratio of thickness to width is between 1 / 80 and 1 / 5, which meets the assumptions of Kirchhoff's thin plate theory, this embodiment simplifies the rudder of the first form into a thin plate form, and its deformation displacement is mainly concentrated in the symmetrical plane, thereby ignoring the deformation in the other two directions. According to Kirchhoff's thin plate theory, the thin plate control equation is established with the deflection as the unknown quantity, as shown in the following formula:

[0044] In the formula, is the bending stiffness of the rudder surface, is the distributed load on the rudder surface, is the deflection distribution of the rudder surface, coordinate Indicates the plane coordinate system established based on the plane where the upper / lower surface of the rudder is located The horizontal and vertical coordinates in is the gradient operator; The expression is as follows:

[0045] In the formula, is the elastic modulus of the rudder surface, is the thickness of the rudder surface, is Poisson's ratio; when the above thin plate control equation is applied to the rudder surface, when there is a distributed load in the rudder surface , then the rudder surface will have a deflection distribution at the same time , so for each flight condition, there is ; By distributing the load After expressing the net load acting on the rudder surface, the control equation of the thin plate is solved (the solution of this equation can also be achieved by the finite element method) to obtain the deflection distribution corresponding to the rudder surface , forming the deformation displacement field of the rudder surface, that is, determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

[0046] The thin plate model under Kirchhoff thin plate theory can be found in Figure 6In this embodiment, a rectangular plate is used to represent the shape of the rudder surface. Coordinate system, the length of the rudder surface is , the width is , thickness is ; There is a rudder axis at the center line in the width direction ( Figure 6 In this established rudder coordinate system, the rudder shape function can be expressed as , the pressure is distributed on its upper surface , the pressure is distributed on the lower surface .

[0047] After the above simplification, the force on the first type of control surface in the air can be simplified to have a distributed load A rectangular thin plate that acts and rotates around a fixed axis. , which represents the net load acting on the rudder surface. After solving the thin plate control equation under Kirchhoff theory, the deformation displacement field of the first form of the rudder surface is obtained.

[0048] The second form is that the thickness change rate between the upper and lower surfaces of the rudder surface is greater than or equal to a preset thickness threshold, or the curvature of the upper / lower surface of the rudder surface is greater than or equal to a preset curvature threshold; this form is usually seen at the trailing edge rudder surface or V-tail rudder surface of the aircraft. Since this type of rudder surface does not meet the thin plate theory assumption, this embodiment will directly use the finite element method for processing.

[0049] When the finite element method is used for solution, the deformation displacement field of the rudder surface of the shape is associated with the aerodynamic load field through a set of partial differential equations that control the elastic deformation of the solid, forming the Lame-Navier equation as shown below:

[0050] In the equation, is the elastic modulus of the rudder surface, is the gradient operator, is Poisson's ratio; , , are the corresponding coordinates in the three-dimensional coordinate system; , , Respectively represent the , , The displacement in the direction; , , Respectively represent , , Directional body forces; is the volume strain of the rudder surface, and its value is equal to the first invariant of the strain tensor, as shown in the following formula:

[0051] The above partial differential equations are a linear system. For any distributed load on the rudder surface By giving boundary conditions and load conditions, the deformation displacement field of the linear system can be obtained, thereby determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

[0052] In this embodiment, the characteristic point representation method of the rudder surface can be a standard three-axis stereo coordinate system. ; Combined with the measured distributed loads in the typical rudder aerodynamic load database , that is, the aerodynamic load field, can be combined with the deformation displacement field obtained by solving the above partial differential equations Take the rudder with this morphological feature as an example, after the aerodynamic load distribution is applied to the rudder surface, its distribution can be seen in Figure 7 and Figure 8 Indications, among which Figure 7 This is the pressure diagram of the windward side. The load is larger overall. Figure 8 This is an illustration of the pressure on the leeward side, and the overall load is small.

[0053] After solving with the finite element method, the displacement changes of the rudder surfaces of different materials under the above aerodynamic loads can be found in Fig. 9 The steel types shown and Fig.10 Therefore, after sampling processing through characteristic points (in actual application, the sampling characteristic points for deformation displacement and the sampling characteristic points for aerodynamic load may be inconsistently distributed, but if a consistent characteristic point distribution is adopted for sampling, the calculation process can be relatively simplified and the processing is convenient), the deformation displacement field of the rudder surface is integrated with the typical rudder surface aerodynamic load database to obtain the rudder surface load-displacement database.

[0054] In step S3, the training data set includes a rudder displacement cloud map as a training input, and a rudder load cloud map corresponding to the rudder displacement cloud map obtained based on the rudder load-displacement database. In this embodiment, a deep convolutional neural network is used to construct a rudder displacement-load solver, wherein the rudder displacement cloud map and the rudder load cloud map can be regarded as two-dimensional single-channel photos, which are input into the deep convolutional neural network for training after uniform scaling, translation and other pre-processing operations.

[0055] Considering that the deep convolutional neural network needs to have the ability of input coordinate translation invariance and accurate spatial capture, this embodiment integrates full connection technology and convolution technology, etc., to form the deep convolutional neural network to realize the construction of the rudder surface displacement-load solver.

[0056] In this embodiment, a structure example of a deep convolutional neural network is as follows: Fig.11 As shown in the figure, "InPut" represents the input layer, "Conv" represents the convolution layer, ReLU represents the activation function layer, "Pooling" represents the maximum pooling layer, "FC" represents the fully connected layer, "CONCAT" represents the fusion layer, and "OutPut" represents the output layer. This deep convolutional neural network has three branch paths, which are introduced as follows: Branch path 1 receives external input from the input layer, including: convolution layer 1_1 → activation function layer 1_1 → maximum pooling layer 1_1 → convolution layer 1_2 → activation function layer 1_2 → fully connected layer 1_2; The input of branch path 2 is the output of activation function layer 1_1 in branch path 1, including: convolution layer 2_1→activation function layer 2_1→max pooling layer 2_1→convolution layer 2_2→activation function layer 2_2→fully connected layer 2_2; The input of branch path 3 is the output of activation function layer 2_1 in branch path 2, including: convolution layer 3_1→activation function layer 3_1→fully connected layer 3_1.

[0057] Subsequently, the fusion layer fuses the outputs of the fully connected layer 1_2, the fully connected layer 2_2, and the fully connected layer 3_1, and after passing through the activation function layer 4 and the fully connected layer 4 in turn, the output layer outputs them to the outside.

[0058] Based on the deep convolutional neural network, the constructed rudder displacement-load solver in this embodiment is expressed as the following formula:

[0059] In the formula, is the parameter set of the deep convolutional neural network; is the displacement cloud map of the rudder surface, which is used as the input of the solver; It is the rudder surface load cloud map, which is the output of the solver and is used to characterize the distributed load of the rudder surface; In a deep convolutional neural network, the convolution layer and activation function layer of each branch path make the input features undergo convolution operation and nonlinear transformation, and the output is as follows:

[0060] In the formula, is the input feature map of the convolutional layer, is the convolution operator, is a trainable convolution kernel, is the bias parameter, is a nonlinear activation function, is the output feature map of the activation function layer; the nonlinear activation function in the activation function layer The ReLU activation function is used as follows:

[0061] In the formula, Represents the input value of the activation function layer; Represents the input value and 0, select the larger value.

[0062] Loss Function for Deep Convolutional Neural Networks As follows:

[0063] In the formula, represents the distributed load on the rudder surface obtained by CFD calculation, represents the distributed load on the rudder surface predicted by the deep convolutional neural network, Represents the total number of feature points; , represents a trainable convolution kernel and its corresponding weight A collection of; L2 regularization coefficient to prevent overfitting of deep convolutional neural networks; Represents the system of differential equations that govern the displacement stresses of the control surface.

[0064] Finally, in step S4, this embodiment uses a high-definition camera to photograph and monitor the aircraft rudder surface, and measures the deformation of the rudder surface after being loaded in real time through binocular vision to form a rudder surface displacement cloud map; the rudder surface displacement-load solver outputs the corresponding rudder surface load cloud map based on the measured rudder surface displacement cloud map, thereby realizing the prediction of the rudder surface distributed load.

Claims

1. A method for predicting distributed loads on control surfaces in a deformation-based flow field, characterized in that: The steps include: S1. Based on the wing-rudder fusion model, calculate the aerodynamic load field of the aircraft's rudder surface under different flight conditions and establish a typical rudder surface aerodynamic load database; S2. Using the thin plate control equation or the finite element method, determine the corresponding relationship between the deformation displacement field of the control surface and the aerodynamic load field, establish a control surface load-displacement database and obtain a training data set from it; S3, obtaining a deep convolutional neural network, using the training data set to complete the training of the deep convolutional neural network, and constructing a rudder displacement-load solver; S4. In engineering applications, the measured displacement cloud map of the rudder surface is input into the rudder surface displacement-load solver, and the rudder surface displacement-load solver outputs the rudder surface load cloud map to realize the prediction of the rudder surface distributed load.

2. The method for predicting the distributed load on the control surface in the flow field according to claim 1, characterized in that: In step S1, the wing-rudder fusion model consists of a wing surface of preset area, shape and size and a rudder surface hinged on the wing surface; when calculating the aerodynamic load field of the rudder surface, the corresponding calculation conditions are designed according to the flight envelope parameters of the aircraft, and CFD calculation is performed to obtain the aerodynamic load distribution of the rudder surface in the flight envelope, which serves as the basis for establishing a typical rudder surface aerodynamic load database.

3. The method for predicting the distributed load on the control surface in the flow field according to claim 2, characterized in that: When performing CFD calculations, the second-order method based on the finite volume method is used to solve the Reynolds-averaged Navier-Stokes equations under the calculation conditions, and the k-ω SST turbulence model is used to achieve the closure of the equation; the mesh type used in the calculation is a polyhedral unstructured mesh, free far-field conditions are used all around the calculation domain, and adiabatic wall conditions are used for the wing and rudder surfaces.

4. The method for predicting the distributed load on the control surface in the flow field according to claim 2, characterized in that: In the wing-rudder fusion model, the aerodynamic force acting on the rudder surface includes the pressure perpendicular to any surface of the rudder surface and the friction parallel to any surface of the rudder surface. After performing CFD calculations for different flight conditions of the aircraft, the CFD calculation results are extracted to obtain the upper surface pressure distribution acting on the rudder surface. and the pressure distribution on the lower surface , forming a control surface pressure matrix corresponding to each flight condition; by traversing the control surface pressure matrix corresponding to each flight condition, a typical control surface aerodynamic load database can be formed.

5. The method for predicting the distributed load on the control surface in the flow field according to claim 1, characterized in that: In step S2, according to the two forms of the control surface, the thin plate control equation or the finite element method is used for processing; The first form is that the upper and lower surfaces of the rudder surface are both symmetric planes, and the thickness change rate between the symmetric planes is less than the preset thickness threshold. This form is processed using the thin plate control equation; The second form is that the thickness change rate between the upper and lower surfaces of the rudder surface is greater than or equal to a preset thickness threshold, or the curvature of the upper / lower surface of the rudder surface is greater than or equal to a preset curvature threshold. This form is processed using the finite element method.

6. The method for predicting the distributed load on the control surface in the flow field according to claim 5, characterized in that: For the first type of rudder surface, based on Kirchhoff thin plate theory, the thin plate control equation is established with deflection as the unknown quantity, as follows: In the formula, is the bending stiffness of the rudder surface, is the distributed load on the rudder surface, is the deflection distribution of the rudder surface, coordinate Indicates the horizontal and vertical coordinates in the plane coordinate system established based on the plane where the upper / lower surface of the rudder is located. is the gradient operator; The expression is as follows: In the formula, is the elastic modulus of the rudder surface, is the thickness of the rudder surface, is Poisson's ratio; when the above thin plate control equation is applied to the rudder surface, when there is a distributed load in the rudder surface , then the rudder surface will have a deflection distribution at the same time , so for each flight condition, there is ; By distributing the load After expressing the net load acting on the rudder surface, the control equation of the thin plate is solved to obtain the deflection distribution corresponding to the rudder surface , forming the deformation displacement field of the rudder surface, that is, determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

7. The method for predicting the distributed load on the control surface in the flow field according to claim 5, characterized in that: For the second type of rudder, the finite element method is directly used to solve it. The deformation displacement field of the rudder and the aerodynamic load field are related through a set of partial differential equations that control the elastic deformation of the solid, forming the Lame-Navier equation as shown below: In the equation, is the elastic modulus of the rudder surface, is the gradient operator, is Poisson’s ratio; , , are the corresponding coordinates in the three-dimensional coordinate system; , , Respectively represent the , , The displacement in the direction; , , Respectively represent , , Directional body forces; is the volume strain of the rudder surface, and its value is equal to the first invariant of the strain tensor, as shown below: The above partial differential equations are a linear system. For any distributed load on the rudder surface By giving boundary conditions and load conditions, the deformation displacement field of the linear system can be obtained, thereby determining the corresponding relationship between the deformation displacement field of the rudder surface and the aerodynamic load field.

8. The method for predicting the distributed load on the control surface in the flow field according to claim 1, characterized in that: In step S3, the training data set includes a rudder surface displacement cloud map as a training input, and a rudder surface load cloud map corresponding to the rudder surface displacement cloud map obtained based on the rudder surface load-displacement database; the deep convolutional neural network includes multiple branch paths, each branch path includes multiple convolutional layers, multiple activation function layers and a fully connected layer; the input of some convolutional layers in a preset number of branch paths comes from the output of the activation function layer in any other branch path; the output of each branch path is used as the output of the deep convolutional neural network after the output fusion operation.

9. The method for predicting the distributed load on the control surface in the flow field according to claim 8, characterized in that: The constructed rudder displacement-load solver is expressed as follows: In the formula, is the parameter set of the deep convolutional neural network; is the displacement cloud map of the rudder surface, which is used as the input of the solver; It is the rudder surface load cloud map, which is the output of the solver and is used to characterize the distributed load of the rudder surface; In a deep convolutional neural network, the convolution layer and activation function layer of each branch path make the input features undergo convolution operation and nonlinear transformation, and the output is as follows: In the formula, is the input feature map of the convolutional layer, is the convolution operator, is a trainable convolution kernel, is the bias parameter, is a nonlinear activation function, is the output feature map of the activation function layer; Non-linear activation function in activation function layer The ReLU activation function is used, and its operation is as follows: In the formula, Represents the input value of the activation function layer, Represents the input value and 0, select the larger value; Loss Function for Deep Convolutional Neural Networks As follows: In the formula, represents the distributed load on the rudder surface obtained by CFD calculation, represents the distributed load on the rudder surface predicted by the deep convolutional neural network, Represents the total number of feature points; , represents the trainable convolution kernel and its corresponding weight A collection of; L2 regularization coefficient to prevent overfitting of deep convolutional neural networks; Represents the system of differential equations that govern the displacement stresses of the control surface.

10. The method for predicting the distributed load on the control surface in the flow field according to claim 1, characterized in that: In step S4, a high-definition camera is used to photograph and monitor the aircraft rudder surface, and the deformation of the rudder surface after being loaded is measured in real time through binocular vision to form a rudder surface displacement cloud map; the rudder surface displacement-load solver outputs the corresponding rudder surface load cloud map based on the measured rudder surface displacement cloud map to realize the prediction of the rudder surface distributed load.

Images