Method and device for predicting assembly deformation of aircraft composite material structure based on proxy model
Through a two-stage framework based on the agent model, using compressed convolutional automatic encoder and multi-layer perceptron, combined with genetic algorithms and Latin hypercube sampling, the problem of real-time accurate prediction of field displacement and stress fields in the assembly of composite material structures in the aircraft is solved, and the problem of real-time accurate prediction of the structure of aircraft composite materials is realized. Efficient data compression and precise reconstruction of complex systems.
Patent Information
- Application Number
- CN202410844832.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-27
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-06-27
AI Technical Summary
The assembly site of aircraft composite material structures lacks real-time and accurate displacement and stress field perception technology. Traditional numerical simulations are difficult to quickly respond to changes in assembly site operating conditions, and the prediction accuracy of agent models is insufficient.
Using a proxy model-based method, a two-stage proxy model is constructed, using a compressed convolutional automatic encoder and a multi-layer perceptron, combined with genetic algorithms and Latin hypercube sampling, a numerical simulation model of composite material structure is established to perform displacement and stress fields. nonlinear feature extraction and prediction.
Real-time accurate prediction of displacement and stress fields at the assembly site of the composite material structure of aircraft is achieved, and the problems of extended solution time and insufficient prediction accuracy of traditional numerical simulation are overcome, and more comprehensive deformation monitoring and evaluation indicators are provided for assembly process.
Smart Images

Figure CN119004940A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of aircraft automated assembly, and in particular relates to a method and a device for predicting aircraft composite material structure assembly deformation based on a proxy model. Background Art
[0002] Aircraft is a highly complex product, and its assembly process is crucial to improving the final quality and safety. Thousands of parts are assembled in multiple stages to form the main structure of the aircraft. The assembly process mainly involves steps such as positioning, hole making and connection. Different process stages also place strict requirements on the appearance of the aircraft structure. In addition, due to the widespread use of carbon fiber reinforced composite materials in aircraft, the manufacturing characteristics of their laminated laying place higher requirements on the assembly process. In addition to paying attention to the appearance accuracy of the composite structure, its stress distribution should also be included in the assembly quality evaluation criteria. However, there is still a lack of full-field stress sensing technology and means suitable for assembly sites.
[0003] Therefore, intelligent assembly technology based on data-driven methods has emerged. However, due to the characteristics of low production volume and long cycle in aircraft manufacturing, it is difficult to directly collect a large amount of data from the production process to build a data-driven model. Numerical simulation models have been increasingly widely used in actual production and manufacturing processes due to their accuracy and low cost. However, the numerical model of composite structure introduces higher nonlinearity, and the discrete dimension of field variables is greatly increased, resulting in longer solution time, making it difficult for traditional numerical simulation to quickly respond to changes in working conditions at the actual assembly site. These shortcomings of numerical models strictly limit their application in aircraft assembly processes. Surrogate models based on simulation data drive provide an effective solution for simulating and analyzing complex systems. Surrogate models establish a bridge between parameter space and model results without paying attention to the details of model construction. However, the construction of surrogate models is also prone to the problem of insufficient prediction accuracy. Generally, the higher the complexity of the problem, the more simulation samples are required. In summary, it is urgent to propose a method to construct an accurate surrogate model under limited data conditions to achieve comprehensive perception of displacement and stress fields of composite structures at assembly sites.
[0004] Patent document CN117973142A discloses a method for assembly control of composite thin-walled parts driven by numerical simulation. This method takes the construction of the stiffness distribution law of composite thin-walled parts and the prediction of assembly deformation of composite thin-walled parts under the action of continuous error accumulation as important supports for numerical simulation, and predicts and optimizes key assembly processes through shape control and compensation of composite thin-walled parts under multiple assembly conditions.
[0005] Patent document CN115630558A discloses a method for predicting the assembly deformation of a composite material component, which includes the following steps: S1, obtaining point cloud data of the composite material component to be predicted, and preprocessing the obtained point cloud data to obtain noise-free point cloud data N; S2, building a deep neural network prediction model based on a multivariate linear regression model and an RBF neural network; S3, training the deep neural network prediction model to obtain an optimal deep neural network prediction model; S4, using the optimal deep neural network prediction model to predict the deformation of the composite material component to be predicted. Summary of the invention
[0006] The purpose of the present invention is to provide a method and device for predicting deformation of aircraft composite material structure assembly based on a proxy model. The method can reconstruct the displacement and stress field according to the actual status of each digital tooling at the assembly site, so as to solve the problem of real-time and accurate prediction of displacement and stress field at the aircraft composite material structure assembly site.
[0007] In order to achieve the first object of the present invention, the following technical solution is provided: a method for predicting deformation of aircraft composite material structure assembly based on a proxy model, comprising the following steps:
[0008] Acquire aircraft assembly information, including specific positioning and connection methods of assembly structures, and determine the range of motion of each digital tooling based on the acquired aircraft assembly information;
[0009] Sampling is performed according to the motion range of each digital tooling to construct a uniform and discretely distributed input parameter sample set;
[0010] Constructing a numerical simulation reference model according to the material properties of the assembly structure and specific ply information, and meshing the numerical simulation reference model;
[0011] The boundary condition form of the numerical simulation reference model is set according to the acquired aircraft assembly information, and each sample point in the sample set is used as the boundary condition of the numerical simulation reference model to solve the stress and displacement distribution of the structure under different boundary conditions;
[0012] Each input parameter sample point and the corresponding stress and displacement distribution form a data set;
[0013] A two-stage proxy model is constructed. The first stage of the proxy model uses a compressed convolutional autoencoder, which includes an encoder for compressed data and a decoder for reconstructed data. Nonlinear feature extraction is performed on stress and displacement distribution through self-supervised learning to obtain a low-dimensional embedding of high-dimensional field variables in the latent variable space. In the second stage, a multi-layer perceptron is used to establish a mapping relationship between aircraft assembly information and the low-dimensional embedding.
[0014] During prediction, the aircraft assembly information is input into a multi-layer perceptron to obtain a low-dimensional embedding, which is then input into the decoder in the compressed convolutional autoencoder to obtain a high-dimensional stress and displacement field.
[0015] The proxy model is trained using the dataset to obtain an assembly deformation proxy model for predicting stress and displacement distribution.
[0016] The present invention establishes a numerical simulation model of a composite material structure, takes into account its intra-layer damage and inter-layer failure, adopts Latin hypercube sampling based on a genetic algorithm to design parameter space sample points, establishes a composite material structure assembly deformation data set through parametric modeling technology, and uses the composite material structure assembly deformation data set to train a proxy model of the target to obtain the optimal proxy model.
[0017] Specifically, the original Latin hypercube sampling is used as the initial value of the motion range sampling of the digital tooling, and the average distance from each design point to other design points is used as the optimization target to optimize it through the genetic algorithm to obtain a uniform and discretely distributed sample set.
[0018] Specifically, the numerical simulation reference model predicts the mechanical properties based on the material direction and thickness of each layer, the damage inside the single layer material, and the delamination damage between layers.
[0019] Specifically, the delamination damage is analyzed using the 3D Hashin criterion as the failure criterion, which specifically includes:
[0020] Fiber tensile failure:
[0021]
[0022] Fiber compression failure:
[0023]
[0024] Resin tensile failure
[0025]
[0026] Resin compression failure:
[0027]
[0028] Among them, X 11,t and X 22,t Indicates the tensile strength of the material in directions 1 and 2, X 11,c and X 22,c represent the compressive strength in directions 1 and 2 respectively, and X 12 and X 23 represents shear strength; σ11 , σ 22 , σ 33 Represents the stress components in the 1st, 2nd, and 3rd directions in the fiber-reinforced region; σ 12 , σ 13 , σ 23 represents the shear stress component in the fiber reinforced region; f f,t 、f f,c 、f m,t and f m,c It is the failure index of the fiber and matrix resin, where damage occurs when the index is greater than 1;
[0029] The cohesion unit based on the bilinear hybrid constitutive model is used to simulate the delamination behavior. The specific process is as follows:
[0030]
[0031] Where K i (i=n,st, represents the stiffness of the cohesion unit, t i (i=n,s,t) and δ i (i=n,s,t) are the nominal stress and displacement in the normal or shear direction, respectively;
[0032] The initial delamination of the delamination behavior is predicted according to the quadratic stress criterion, neglecting the effect of the normal stress:
[0033]
[0034] where N, S, and T are the strengths in the normal and in-plane shear directions, respectively, and the damage evolution of delamination is predicted by the energy-based Benzeggah-Kenane criterion:
[0035]
[0036] Among them G c is the total fracture energy, G iC (i=Ι,ΙΙ) are normal and shear fracture energies respectively, where G S and G T are the out-of-plane shear and total dissipated energy in three directions, respectively, and η is the BK ratio.
[0037] Specifically, the compressed convolutional autoencoder is constructed using a convolutional neural network combined with residual connections and an attention mechanism, and its expression is as follows:
[0038] φ:x→f
[0039] ψ:f→x
[0040]
[0041] Among them, φ represents the encoder, f represents the latent space representation, ψ represents the decoder, and x represents the field variable predicted by the proxy model.
[0042] Specifically, the attention mechanism enhances the feature extraction capability of the compressed convolutional autoencoder through three independent branches, including channel attention, spatial attention, and deep attention.
[0043] Specifically, during the training process, the mean square error is used as the training loss function of each neural network, and the determination coefficient, signal-to-noise ratio, and multi-scale structural similarity index are combined as indicators for optimizing and evaluating the proxy model.
[0044] In order to achieve the second object of the present invention, the following technical solution is provided: a device for predicting the assembly deformation of an aircraft composite material structure, which is implemented by the above-mentioned method for predicting the assembly deformation of an aircraft composite material structure based on a proxy model, and the specific implementation process is as follows:
[0045] The aircraft assembly information of the aircraft to be assembled is input into the assembly deformation proxy model to obtain the stress and displacement distribution of each structure of the aircraft to be assembled.
[0046] Compared with the prior art, the present invention has the following beneficial effects:
[0047] By establishing a numerical simulation model of aircraft structure, a data foundation is provided for data-driven perception algorithms. At the same time, a two-stage proxy model framework is proposed, which uses an attention-enhanced convolutional compression autoencoder to obtain nonlinear features, thereby achieving efficient compression and accurate reconstruction of high-dimensional field variable data, ensuring the final prediction accuracy of the proxy model.
[0048] In addition, the trained proxy model can predict the stress field and displacement field at the same time, providing a more comprehensive evaluation index for deformation monitoring in the aircraft assembly process, thus overcoming the difficulty of directly measuring the stress of complex aircraft structures at the assembly site. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 A flowchart of a method for predicting aircraft composite material structure assembly deformation based on a proxy model provided in this embodiment;
[0050] Figure 2 The projection of the Latin hypercube sampling result based on the genetic algorithm provided in this embodiment in two-dimensional space;
[0051] Figure 3 A schematic diagram of the specific positioning of the aircraft fuselage provided in this embodiment;
[0052] Figure 4A diagram of the attention-enhanced compressed autoencoder architecture provided for this embodiment. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme 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 only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0054] like Figure 1 As shown, a method for predicting aircraft composite material structure assembly deformation based on a proxy model is provided in this embodiment, and the specific steps are as follows:
[0055] Acquire aircraft assembly information, including specific positioning and connection methods of assembly structures, and determine the range of motion of each digital tooling based on the acquired aircraft assembly information.
[0056] like Figure 2 As shown, it is a flowchart of positioning a specific large aircraft fuselage provided in this embodiment, and the specific process is as follows: considering that the positioning process in aircraft assembly has a significant impact on the final manufacturing accuracy of the entire product, it is chosen to construct a positioning deformation proxy model of the fuselage structure. Since the position and shape of the aircraft fuselage are adjusted by the CNC positioner, the spatial coordinates of each CNC positioner are defined as the input variables of the proxy model, and each positioner has three degrees of freedom in three directions, so the input variables of the proxy model have 12 dimensions.
[0057] The Latin hypercube sampling method based on genetic algorithm optimization is used to sample the motion range of each digital tooling to construct a sample set with uniform and discrete distribution.
[0058] Furthermore, a set of original Latin hypercube sampling results is used as initial values, which are a set of n points in a d-dimensional space.
[0059] The Latin hypercube sampling scheme is then evaluated according to a fitness function that takes the pairwise Euclidean distance between sampling points as the fitness function, aiming to maximize the spatial coverage:
[0060]
[0061] Among them, xi and x j is a point in the Latin hypercube sampling design X, ||x i -x j || is the Euclidean distance between them, with the inverse square penalizing shorter distances.
[0062] Select individuals with better performance from the current group to generate a new generation. The present invention randomly selects a certain number of individuals in the group, and takes the individuals with the highest fitness value as the parent generation. The generation of offspring can be generated by combining two or more parent generation samples through a simple crossover operation:
[0063] Child k =α·Parent 1 +(1-α)·Parent 2
[0064] Among them, α is a random factor between 0 and 1, indicating that the generation of offspring mixes the characteristics of the two parents. In addition, random mutations can be introduced into the offspring to maintain genetic diversity and explore new areas of the solution space.
[0065] A certain degree of random mutation is introduced by randomly adjusting the position of samples within the sampling interval:
[0066] x i =x i +δ·(upper bound i -lower bound i )
[0067] Here, δ is a small random perturbation, and the above optimization process is repeated for a specified number of times or until the fitness is no longer significantly improved.
[0068] According to the material properties of the structure and the specific ply information, a numerical simulation reference model is constructed to mesh the mechanical properties in the assembly space. This embodiment is constructed using the general Abaqus software machine and developed using the finite element method. Consistent with its actual additive manufacturing process, the model is built layer by layer, using a single-layer solid element for each layer and zero-thickness cohesion units between layers for modeling. When establishing the simulation model, the damage inside the laminate and the possible delamination damage between layers are also considered.
[0070] Furthermore, the delamination damage is analyzed using the 3D Hashin criterion as failure, which specifically includes:
[0071] Fiber tensile failure:
[0072]
[0073] Fiber compression failure:
[0074]
[0075] Resin tensile failure
[0076]
[0077] Resin compression failure:
[0078]
[0079] Among them, X 11,t and X 22,t Indicates the tensile strength of the material in directions 1 and 2, X 11,c and X 22,c represent the compressive strength in directions 1 and 2 respectively, and X 12 and X 23 represents shear strength; σ 11 , σ 22 , σ 33 Represents the stress components in the 1st, 2nd, and 3rd directions in the fiber-reinforced region; σ 12 , σ 13 , σ 23 Represents the shear stress component in the fiber reinforced area. In this embodiment, direction 1 is the longitudinal direction, direction 2 is the transverse direction, and direction 3 is the vertical direction.
[0080] f f,t 、f f,c 、f m,t and f m,c It is the failure index of the fiber and matrix resin, where damage occurs when the index is greater than 1;
[0081] The cohesion unit based on the bilinear hybrid constitutive model is used to simulate the delamination behavior. The specific process is as follows:
[0082]
[0083] Where K i (i=n,st, represents the stiffness of the cohesion unit, t i (i=n,s,t) and δ i (i=n,s,t) are the nominal stress and displacement in the normal or shear direction, respectively;
[0084] The initial delamination of the delamination behavior is predicted according to the quadratic stress criterion, neglecting the effect of the normal stress:
[0085]
[0086] where N, S, and T are the strengths in the normal and in-plane shear directions, respectively, and the damage evolution of delamination is predicted by the energy-based Benzeggah-Kenane criterion:
[0087]
[0088] Among them G c is the total fracture energy, G iC (i=Ι,ΙΙ) are normal and shear fracture energies respectively, where G S and G T are the out-of-plane shear and total dissipated energy in three directions, respectively, and η is the BK ratio.
[0089] As shown in Table 1, the material properties provided for this embodiment.
[0090] Table 1
[0091]
[0092] The boundary condition form of the numerical simulation reference model is set according to the acquired aircraft assembly information, and each sample point in the sample set is used as the boundary condition of the numerical simulation reference model to solve the stress and displacement distribution under different boundary adjustments.
[0093] The displacements of all finite element nodes and the stresses at all element integration points are extracted, and all input sample points and displacement and stress field values are integrated to construct a data set.
[0094] A two-stage proxy model is constructed. The first stage of the proxy model uses a compressed convolutional autoencoder, and the second stage uses a multi-layer perceptron. During prediction, the aircraft assembly information is input into the multi-layer perceptron to obtain a low-dimensional embedding, and then the low-dimensional embedding is input into the decoder in the autoencoder to obtain a high-dimensional stress and displacement field. Furthermore, the proxy model in this embodiment uses an attention-enhanced compressed convolutional autoencoder to perform self-supervised training on the input stress and displacement distribution to obtain the corresponding low-dimensional representation. Due to the characteristics of the autoencoder, after the training is completed, an encoder for dimensionality reduction and a decoder for restoring data to a high-dimensional space can be obtained at the same time. The autoencoder is a self-supervised neural network used to learn effective encoding of data. It consists of two parts: the encoder φ is responsible for compressing the input data into a latent space representation f, and the decoder ψ attempts to reconstruct the original input data from this latent representation. The goal of the autoencoder is to minimize the reconstruction error so that the network can capture the most important features in the data. Its principle can be expressed by the following formula.
[0095] φ:x→f
[0096] ψ:f→x
[0097]
[0098] like Figure 4 As shown, the autoencoder in this embodiment adopts a convolutional neural network as the main structure. This autoencoder is also called a convolutional compression autoencoder. By using convolutional layers and pooling layers, feature extraction and downsampling are performed on the input data, thereby achieving effective encoding and reconstruction of high-dimensional data.
[0099] The residual block is integrated into the network to enhance its performance. The key to the residual block is to use skip connections to add the input of the hidden layer directly to the output. During training, these skip connections can promote the flow of gradients, thereby alleviating the problem of gradient disappearance and making it possible to build deeper networks.
[0100] The triplet attention mechanism is adopted, which aims to enhance the feature representation ability of convolutional neural networks by paying attention across spatial and channel dimensions. The triplet attention mechanism mainly consists of three branches, two of which are specifically used to capture the interaction between the channel dimension C and the spatial dimension W / H, and the remaining branch is responsible for the calculation of the traditional spatial attention weight.
[0101] The first branch builds attention between the height dimension and the channel dimension. Given an input tensor X∈R C×H×W , first rotate it 90° counterclockwise along the H axis, and the shape of the rotated tensor is (W×H×C), recorded as Substituting it into the following formula, we can obtain the feature map corrected by attention. Finally, rotate the feature 90° clockwise along the H axis to restore the data to the original input shape of X.
[0102]
[0103] Among them A hc is the feature modified by attention. w It includes the Z-pool module shown in the following formula and a standard convolution layer. σ is a nonlinear activation function Sigmoid. After the activation function, the channel attention weight is generated. ⊙ represents the Hadamard product between the attention weight and the input feature.
[0104]
[0105] Where 0d refers to the maximum and average pooling operations in the 0th dimension.
[0106] Similarly, in the second branch, the input feature is first rotated 90° counterclockwise along the W axis, and the resulting tensor is recorded as Substituting it into the following formula can obtain the attention-corrected feature, and finally the feature is also rotated clockwise along the W axis to restore the original shape.
[0107]
[0108] Among them A wc is the attention-corrected feature, f h There is w The same structure also consists of a Z-pool module and a standard convolutional layer.
[0109] For the last branch, the original input is directly substituted into the following without rotating the input features.
[0110] A wh (X) = σ(f c (X))⊙X
[0111] Finally, the features generated by each branch are aggregated through average pooling to complete the calculation of the entire attention module.
[0112] The proxy model uses a multi-layer perceptron to establish the relationship between input parameters and low-dimensional embedding to achieve accurate mapping of input parameters to high-dimensional stress and displacement fields. The specific principles are as follows:
[0113] After the data is compressed in the first stage, when building the proxy model in the low-dimensional space, a relatively simple multi-layer perceptron can be used to fit the mapping relationship between the input parameters and the latent variables. The multi-layer perceptron structure in the second stage of the proxy model is designed to have four hidden layers, with 64 neural nodes in each layer.
[0114] After the mapping between input parameters and latent variables is established, a proxy model of the displacement and stress field of the aircraft structure under the action of boundary conditions can be established. During the assembly process, the control parameters are input into the second-stage multi-layer perceptron to obtain the corresponding low-dimensional representation of the displacement and stress field. The low-dimensional representation is then input into the decoder of the attention-enhanced compressed autoencoder to achieve real-time perception of the entire displacement and stress field of the aircraft structure.
[0115] The proxy model is trained using the data set. The training process uses the mean square error as the training loss function of each neural network, and combines the coefficient of determination, signal-to-noise ratio and multi-scale structural similarity index as indicators for optimizing and evaluating the proxy model. Since the displacement of each node of the discrete field quantity and the principal stress at the integration point contain three components, after preprocessing, the high-dimensional field variable data can be converted into a three-dimensional array similar to an image. The mean square error is a commonly used indicator to quantify the difference between the original data and the compressed data. The calculation formula is:
[0116]
[0117] Among them, I orig (i, j) represents the displacement or stress value at the node or integration point (i, j) in the field quantity data. comp (i, j) is the value of the field quantity data at the same position after compression and reconstruction, and m and n are the number of rows and columns of the array after the field quantity data is transformed. The loss function reflects the degree of distortion or loss caused by data compression by measuring the mean square error of each node value. The lower the value of the loss function, the higher the accuracy of the reconstructed field quantity data, and the quality of the original data is effectively retained while compressing.
[0118] And R 2 Also known as the coefficient of determination, it is a common metric for evaluating the predictive accuracy of a single feature in regression analysis. In the case of multi-output regression tasks, it is often used to calculate the coefficient of determination. 2 The value of can be used to analyze the relative importance and value of different features. In addition, the R 2 Statistical analysis of the values can also be used to optimize the constructed regression model, which helps to refine and enhance the model.
[0119] For a given feature, is the predicted value of the i-th sample, y i is the corresponding label, R 2 The value is obtained by using the following formula in N s Calculated on samples:
[0120]
[0121] in R 2 The maximum value of R is 1.0, indicating that the model fits the data perfectly. 2 Negative values indicate poor performance of the model.
[0122] The structural similarity index is a widely used image quality assessment indicator that imitates the human visual system to extract structural information from images. Although it is designed to measure the similarity between two images, the high-dimensional field variable data studied in this invention can be converted into a three-dimensional array similar to an image, so the structural similarity index is also suitable for predictive evaluation of field quantity data reconstruction. The structural similarity index is obtained by multiplying the brightness, contrast and structural similarity between the calculated samples x and y.
[0123] SSIM(x,y)=[l(x,y) α c(x,y) β s(x,y) γ ]
[0124] Where l(x,y) is a brightness comparison, c(x,y) is a comparison based on contrast, and s(x,y) is a structure comparison.
[0125] Based on the structural similarity index, the multi-scale structural similarity index improves it. This method takes the integration of the reference image and the distorted image signal as input, and then iteratively applies a low-pass filter to downsample the image by a factor of 0.5. The resolution of the original image is denoted as Scale 1 , the resolution of the image after M-1 iterations is expressed as Scale M The contrast index c(x,y) and structure index s(x,y) are calculated at each scale, and the brightness index l(x,y) is calculated at the final scale. By integrating the results of different scale measurements, the comprehensive index MS-SSIM is obtained.
[0126]
[0127] where α M , β j , γ j is a coefficient used to adjust the relative importance of different components.
[0128] The signal-to-noise ratio is a key indicator used to quantify the quality of compressed and reconstructed data. It is obtained by calculating the ratio of signal power to the noise power that affects the fidelity of the reconstructed data. The calculation formula for the signal-to-noise ratio is as follows:
[0129]
[0130] Among them I orig (i, j) is the displacement or stress value at the node or integration point (i, j) in the field data. comp (i, j) is the value of the field quantity data at the same position after compression and reconstruction, and m and n are the number of rows and columns of the array after the field quantity data is transformed. The present invention uses logarithmic decibels to represent the signal-to-noise ratio, which more clearly characterizes the reconstruction quality. The higher the signal-to-noise ratio value, the lower the noise level, and the better the reconstruction quality.
[0131] This embodiment also provides an aircraft composite material structure assembly deformation prediction device, which is implemented by the aircraft composite material structure assembly deformation prediction method based on the proxy model provided in the above embodiment, and its specific implementation process is as follows:
[0132] The aircraft assembly information of the aircraft to be assembled is input into the assembly deformation proxy model to obtain the stress and displacement distribution of each structure of the aircraft to be assembled.
[0133] In addition, the terms "upper", "lower", "inner", "outer", "front", "rear" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. Unless otherwise specifically stated, the relative steps, numerical expressions and values of the components and steps described in these embodiments do not limit the scope of the present invention.
[0134] Of course, the above description is only a specific embodiment of the present invention and is not intended to limit the scope of implementation of the present invention. All equivalent changes or modifications made according to the structure, characteristics and principles described in the patent application scope of the present invention should be included in the patent application scope of the present invention.
[0135] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A method for predicting aircraft composite structure assembly deformation based on a proxy model, characterized in that: The following steps are involved: Acquire aircraft assembly information, including specific positioning and connection methods of assembly structures, and determine the range of motion of each digital tooling based on the acquired aircraft assembly information; Sampling is performed according to the motion range of each digital tooling to construct a uniform and discretely distributed input parameter sample set; Constructing a numerical simulation reference model according to the material properties of the assembly structure and specific ply information, and meshing the numerical simulation reference model; The boundary condition form of the numerical simulation reference model is set according to the acquired aircraft assembly information, and each sample point in the sample set is used as the boundary condition of the numerical simulation reference model to solve the stress and displacement distribution of the structure under different boundary conditions; Each input parameter sample point and the corresponding stress and displacement distribution form a data set; A two-stage proxy model is constructed. The first stage of the proxy model uses a compressed convolutional autoencoder, which includes an encoder for compressed data and a decoder for reconstructed data. Nonlinear feature extraction is performed on stress and displacement distribution through self-supervised learning to obtain a low-dimensional embedding of high-dimensional field variables in the latent variable space. In the second stage, a multi-layer perceptron is used to establish a mapping relationship between aircraft assembly information and the low-dimensional embedding. During prediction, the aircraft assembly information is input into a multi-layer perceptron to obtain a low-dimensional embedding, which is then input into the decoder in the compressed convolutional autoencoder to obtain a high-dimensional stress and displacement field. The proxy model is trained using the dataset to obtain an assembly deformation proxy model for predicting stress and displacement distribution.
2. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 1, characterized in that: The original Latin hypercube sampling was used as the initial value for sampling the motion range of the digital tooling, and the average distance from each design point to other design points was used as the optimization target to obtain a uniform and discretely distributed sample set through genetic algorithm.
3. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 1, characterized in that: The numerical simulation reference model predicts mechanical properties based on the material direction and thickness of each layer, the damage inside the single layer material, and the delamination damage between layers.
4. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 1, characterized in that: The delamination damage is analyzed using the 3D Hashin criterion as the failure criterion, which specifically includes: Fiber tensile failure: Fiber compression failure: Resin tensile failure Resin compression failure: Among them, X 11,t and X 22,t Indicates the tensile strength of the material in directions 1 and 2, X 11,c and X 22,c represent the compressive strength in directions 1 and 2 respectively, and X 12 and X 23 represents shear strength; σ 11 , σ 22 , σ 33 Represents the stress components in the 1st, 2nd, and 3rd directions in the fiber-reinforced region; σ 12 , σ 13 , σ 23 represents the shear stress component in the fiber reinforced region; f f,t 、f f,c 、f m,t and f m,c It is the failure index of the fiber and matrix resin. When the index is greater than 1, it is judged that damage will occur. The cohesion unit based on the bilinear hybrid constitutive model is used to simulate the delamination behavior. The specific process is as follows: Where K i (i=n,s,t) represents the stiffness of the cohesion unit, t i (i=n,s,t) and δ i (i=n,s,t) are the nominal stress and displacement in the normal or shear direction, respectively; The initial delamination of the delamination behavior is predicted according to the quadratic stress criterion, neglecting the effect of the normal stress: where N, S, and T are the strengths in the normal and in-plane shear directions, respectively, and the damage evolution of delamination is predicted by the energy-based Benzeggah-Kenane criterion: Among them G c is the total fracture energy, G iC (i=Ι,ΙΙ) are normal and shear fracture energies respectively, where G S and G T are the out-of-plane shear and total dissipated energy in three directions, respectively, and η is the BK ratio.
5. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 1, characterized in that: The compressed convolutional autoencoder is constructed using a convolutional neural network combined with residual connections and an attention mechanism, and its expression is as follows: φ:x→f ψ:f→x Among them, φ represents the encoder, f represents the latent space representation, ψ represents the decoder, and x represents the field variable predicted by the proxy model.
6. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 5, characterized in that: The attention mechanism enhances the feature extraction capability of the compressed convolutional autoencoder through three independent branches, including channel attention, spatial attention, and deep attention.
7. The method for predicting aircraft composite material structure assembly deformation based on a proxy model according to claim 1, characterized in that: During the training process, the mean square error was used as the training loss function of each neural network, and the coefficient of determination, signal-to-noise ratio, and multi-scale structural similarity index were combined as indicators for optimizing and evaluating the proxy model.
8. An aircraft composite material structure assembly deformation prediction device, characterized in that: This is achieved by the aircraft composite material structure assembly deformation prediction method based on the proxy model as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Assembly error prediction and tolerance optimization method for air separation integral cold box
CN116384257A
Fatigue crack propagation prediction method and system for fatigue damage key part of aircraft
CN117725859A
CSI feedback method based on automatic encoder structure
CN117856848A
Deep unsupervised learning approach , device and storage medium for airspace complexity evaluation
US20210174262A1
Predictive Model Data Stream Prioritization
US20230123322A1
Cited By
Coal mine tunnel deformation detection basic model based on self-supervised learning and detection method
CN120101674A
An intelligent analysis method for shape and position deviation of aircraft composite thin-walled components based on a double-branch network
CN122693499A
An intelligent analysis method for shape and position deviation of aircraft composite thin-walled components based on a double-branch network
CN122693499B
