A method and system for predicting deformation of architectural curved curtain wall components based on GAN

Abstract

The present invention belongs to the field of structural deformation prediction and specifically discloses a method and system for predicting the deformation of curved building curtain wall components based on a generative adversarial network (GAN). The method comprises: establishing a database: collecting samples of data related to the deformation of curved building curtain wall components after processing to form a database, wherein the collected samples include measured samples and simulated samples; building a sample generation model: generating new samples of the deformation of various components after processing based on a generative adversarial network (GAN) and incorporating the generated samples into the database; building a deformation prediction model: building a component deformation prediction model after processing based on a generative adversarial network (CGAN), wherein the samples include collected samples and generated samples; and predicting deformation: using the model to predict the deformation of the component after processing and determining whether the predicted deformation meets acceptance criteria. By generating sample-enhanced data, the present invention effectively improves the prediction efficiency of the deformation of curtain wall components after processing, thereby reducing the rework costs caused by improper deformation control during the bending process of curtain wall components.

Description

Technical Field

[0001] The present invention belongs to the field of structural deformation prediction, and more specifically, relates to a method and system for predicting deformation of architectural curved curtain wall components based on GAN. Background Art

[0002] As demand for building quality and functionality increases, architectural forms are becoming more diverse and nonlinear. Curtain wall systems, the embodiment of a building's exterior, comprise a variety of components, including panels, keels, and decorative moldings. To meet the nonlinear appearance requirements of different architectural forms, curtain wall components must be bent through rolling, stretching, and stamping. However, due to their high aspect ratios and large dimensions, curtain wall components are prone to defects such as springback deformation during the bending process, which in turn affects the quality of the building's exterior and results in wasted resources due to rework. Therefore, predicting and controlling the post-processing deformation of curtain wall components is crucial.

[0003] Currently, the bending and forming processes of various complex components involve complex nonlinear deformation, which can be predicted using artificial intelligence algorithms. Researchers in fields such as shipbuilding and automotive manufacturing often use algorithms such as backpropagation and support vector machines to predict the springback deformation of simple components such as single-curved circular tubes and stamped plates, or determine component deformation through finite element simulation. However, due to the large size, complex and varied shapes, and high slenderness ratios of curtain wall components, factors such as twisting, deadweight, and material properties can affect component deformation after processing. Furthermore, unlike the mass production of shipbuilding and automotive manufacturing, a single curved curtain wall project may involve thousands of individual components with varying shapes and cross-sections. Existing deformation prediction methods designed for mass production and single-use scenarios cannot meet the deformation prediction needs of complex and variable building curtain wall components. Furthermore, existing finite element simulation methods require significant modeling resources and are unable to adapt to the large number and variety of building curtain wall components. Therefore, a new deformation prediction method and system is essential for curtain wall component processing quality control. Summary of the Invention

[0004] In response to the above-mentioned defects or improvement needs of the existing technology, the present invention provides a method and system for predicting the deformation of building curved curtain wall components based on GAN, which aims to achieve accurate prediction of the deformation of building curved curtain wall components after bending.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for predicting deformation of architectural curved curtain wall components based on GAN is proposed, comprising the following steps:

[0006] Model training phase:

[0007] Based on the initial database, the GAN is trained and the number of samples in the database is expanded through the trained GAN. The initial database includes several samples, each of which includes the material parameters M, process parameters A, geometric parameters Ge, bending parameters B and deformation parameters De of the building curved curtain wall components.

[0008] Based on the expanded database, CGAN is trained, including:

[0009] CGAN consists of a generator G2 and a discriminator D2. The generator G2 outputs a generated sample G2(C, Z2) based on a condition C and a noise vector Z2 that follows a Gaussian distribution. The condition C includes material parameters M, process parameters A, geometric parameters Ge, and bending parameters B. The discriminator D2 scores the authenticity of the real samples (C, De) in the database and the generated sample G2(C, Z2). During training, the generator G2 aims to make the generated sample G2(C, Z2) more similar to the real sample (C, De), while the discriminator D1 aims to better distinguish between the real sample (C, De) and the generated sample G2(C, Z2).

[0010] The generator G2 in the trained CGAN is used as the deformation prediction model;

[0011] Model application phase:

[0012] The material parameters M, process parameters A, geometric parameters Ge, and bending parameters B of the building curved curtain wall components to be predicted are input into the deformation prediction model to obtain the corresponding deformation parameters De, thereby realizing the deformation prediction of the building curved curtain wall components.

[0013] As a further preferred method, a GAN is trained based on the initial database, and the number of samples in the database is expanded by the trained GAN, including:

[0014] GAN consists of a generator G1 and a discriminator D1. The generator G1 outputs a generated sample G1(Z1) based on a noise vector Z1 that follows a Gaussian distribution. The discriminator D1 scores the authenticity of the real samples X in the initial database and the generated samples G1(Z1). During training, the generator G1 aims to make the generated samples G1(Z1) more similar to the real samples X, while the discriminator D1 aims to better distinguish between the real samples X and the generated samples G1(Z1).

[0015] The trained generator G1 is used as the sample generation model, and multiple samples are generated by the sample generation model and added to the initial database, thereby expanding the database.

[0016] As a further preferred method, when training GAN:

[0017] Loss function of discriminator D1 as follows:

[0018]

[0019] Loss function of generator G1 as follows:

[0020]

[0021] Wherein, the superscript i represents the corresponding data of the i-th sample in the training set, m represents the total number of training set samples randomly selected after the initial database sample mixture generator generates data samples; D1(X (i) )、D1(G1(Z1 (i) )) represent the scores of the discriminator D1 on the input X and G1(Z1) respectively.

[0022] As a further preferred embodiment, when the generator G1 and the discriminator D1 satisfy the expected formula, the training is terminated to obtain a trained GAN; the expected formula is as follows:

[0023]

[0024] in, The goal of the generator G1 is to minimize the above formula, and the goal of the discriminator D1 is to maximize the above formula; Indicates that for the real data X, the discriminator D1 gives the probability that it is the real data, It means that for the fake data G1(Z) generated by the generator G1, the discriminator D1 gives the probability that it is fake data.

[0025] As a further preferred method, when training CGAN:

[0026] Loss function of discriminator D2 as follows:

[0027]

[0028] Among them, the superscript i represents the corresponding data of the i-th sample in the training set, and n represents the total number of training set samples randomly selected from the expanded database; Represents the same as C (i) Any De that does not match (i) ;D2(C (i) ,De (i) )、D2(C (i) ,G2(C (i) ,Z2 (i) ))、 Respectively represent the discriminator D2 input (C, De), G2 (C, Z2), Rating of θ d represents the discriminator D2 parameter, η represents the learning rate, Represents theta d Perform gradient updates;

[0029] Loss function of generator G2 as follows:

[0030]

[0031] Among them, θ g represents the generator G2 parameter, η represents the learning rate, Represents theta g Perform gradient update.

[0032] As a further preferred embodiment, when the scores of the discriminator D2 for the real samples (C, De) and the generated samples G2 (C, Z2) in the database are consistent, the training is terminated to obtain a trained CGAN.

[0033] As a further preference, the material parameter M refers to the elastic modulus and yield strength of the component material; the process parameter A refers to the tensile bending forming force of the component; the geometric parameter Ge refers to the component cross-sectional size, cavity area ratio and material thickness; the bending parameter B refers to the bending angle, bending radius, arc length and chord length parameters of the bending line before the component is deformed; the deformation parameter De refers to the absolute value of the chord length difference of the bending line before and after the component is deformed.

[0034] As a further preferred method, the curved connection line is determined by: determining all endpoints of the component, and for any two endpoints, making a shortest distance connection line for the two endpoints on the component surface; and selecting a curved connection line from all the lines as the curved connection line.

[0035] As a further preference, the samples in the initial database are obtained through bending tests and / or simulation using Abaqus finite element analysis software.

[0036] According to another aspect of the present invention, a GAN-based building curved curtain wall component deformation prediction system is provided, comprising a processor configured to execute the GAN-based building curved curtain wall component deformation prediction method.

[0037] In general, the above technical solutions conceived by the present invention have the following technical advantages compared with the existing technology:

[0038] The present invention uses GAN (generative adversarial network) to generate deformation samples of curved curtain wall components. After expanding the database, CGAN (conditional generative adversarial network) is used to build a curved curtain wall component deformation prediction model. By generating sample enhancement data, the efficiency and accuracy of predicting the deformation of curtain wall components after processing can be effectively improved, thereby improving the one-time qualified quality of processing and reducing the rework cost caused by improper deformation control during the bending processing of curtain wall components. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the bending connection line and chord length of the aluminum profile according to an embodiment of the present invention;

[0040] Figure 2 A flowchart for building an initial database for an embodiment of the present invention;

[0041] Figure 3 Generate a model flow chart for the sample embodiment of the present invention;

[0042] Figure 4 This is a flow chart of a deformation prediction model according to an embodiment of the present invention;

[0043] Figure 5 This is a flow chart of deformation prediction of building curved curtain wall components according to an embodiment of the present invention;

[0044] Figure 6 This is a flowchart of deformation prediction of architectural curved curtain wall components based on GAN in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0046] The embodiment of the present invention provides a method for predicting deformation of building curved curtain wall components based on GAN. Figure 6 As shown, the following steps are included:

[0047] S1. Establish an Initial Database: Samples of deformation-related data from curved curtain wall components before and after fabrication are collected to form an initial database. Each sample includes the component's material parameters M, process parameters A, geometric parameters Ge, bending parameters B, and deformation parameters De. The samples include measured samples and / or simulated samples. Simulated samples are post-fabrication deformation data obtained using Abaqus finite element analysis software, while measured samples are post-fabrication deformation data obtained through on-site measurements following field bending tests.

[0048] like Figure 2 As shown, the details are as follows:

[0049] S11. Obtain basic component information, including component material parameters M, process parameters A, and geometric parameters Ge. Material parameters M refer to parameters related to material plastic deformation, such as elastic modulus and yield strength; process parameters A refer to stretch-bending forming forces, namely pre-force, forming force, and post-force, which are related to component processing and forming; and geometric parameters Ge refer to parameters related to component geometry, such as component cross-sectional dimensions, cavity area ratio, and material thickness.

[0050] S12. Determine the endpoint bending line. There are a number of endpoints on a component. Draw the shortest distance line between any two endpoints on the surface where the component is located. Root bending lines, where b is the number of straight lines connecting the endpoints of the component. Obtain the bending parameter B of each bending line, which refers to the bending angle, bending radius, arc length, chord length and other parameters related to the bending properties in the horizontal or vertical direction. Figure 1 The aluminum profile component shown in the figure has 14 endpoints. If you take any two endpoints and connect them by the shortest distance on the surface of the component, you can get Root curved line, where The number of straight lines connecting the endpoints of the component.

[0051] S13. Simulation and Testing. Components are simulated or tested to determine their deformation after bending. Simulations are performed using Abaqus finite element analysis software, using Latin hypercube sampling to create an orthogonal experimental table for common curtain wall component material parameters M, process parameters A, and geometric parameters Ge. Testing is performed using on-site bending. Based on component deformation, the deformation parameter De is obtained. De refers to the absolute value of the difference in chord length between the bending line and the component before and after deformation.

[0052] S14. Data preprocessing: Match and clean the data, match the material parameters M, process parameters A, geometric parameters Ge, bending parameters B, and deformation parameters De corresponding to each bending line, and remove redundant, repeated, inconsistent, missing, and other invalid data.

[0053] S15. Establish an initial database. Give the data corresponding labels in the database for easy access, form an initial data sample, and establish an initial database.

[0054] S2. Based on the initial database, GAN (generative adversarial network) is trained to obtain a sample generation model. Samples are generated through the sample generation model to expand the number of samples in the database.

[0055] like Figure 3 As shown, the details are as follows:

[0056] S21. Data normalization. Since the dimensions of each parameter vary greatly, all data need to be normalized to facilitate comparison and analysis, i.e.:

[0057]

[0058] where x max and x min Represent the maximum and minimum values ​​of parameter x, respectively. Represents the result after normalization operation.

[0059] S22. Divide the training set and test set. Randomly extract samples from the initial database in a ratio of 8:2 to generate the training set and test set of the model.

[0060] S23. Create generator G1. Introduce a noise vector Z1 that obeys a Gaussian distribution as the input of generator G1, and let generator G1 generate a data sample G1(Z1). The sample should contain material parameters M, process parameters A, geometric parameters Ge, bending parameters B, deformation parameters De and their corresponding labels. There should also be correlation between the data.

[0061] S24. Create discriminator D1. The real samples X and G1(Z1) obtained from the experiment and simulation are used as the input of D1. Discriminator D1 judges the sample quality respectively and outputs the judgment results D1(X) and D1(G1(Z1)). The discriminator D1 is trained to make the real sample X get a high score and generate sample G1.

[0062] (Z1) gets a low score. The training formula is:

[0063]

[0064] S25. Train the generator G1. The goal is to train the generator G1 with the generated sample G1(Z1) obtaining a high score in the discriminator D1. The training formula is:

[0065]

[0066] Wherein, the superscript i represents the corresponding data of the i-th sample in the training set, m represents the total number of training set samples randomly selected after the initial database sample mixture generator generates data samples; D1(X (i) )、D1(G1(Z1 (i) )) represent the scores of the discriminator D1 on the input X and G1(Z1) respectively.

[0067] S26, loop S24 and S25, when the generator G1 and the discriminator D1 meet the following expected formula, the training is ended and the trained generator G1 is used as the sample generation model.

[0068]

[0069] in, is the objective function, where the goal of the generator G1 is to minimize the entire formula, make the generated data as close to the real data as possible, let D1 judge the generated data as real data, and the goal of the discriminator D1 is to maximize the entire formula and improve the ability to distinguish between real and generated data. Indicates that for the real data X, the discriminator gives the probability that it is the real data, It means that for the fake data G1(Z) generated by the generator, the discriminator gives the probability that it is fake data.

[0070] S27. Use the test set to verify the accuracy of the sample generation model. Compare the generated samples based on the test set with the test set, and calculate the evaluation metrics RMSE and MAE. Once verified, the samples generated by the sample generation model can be included in the database and assigned corresponding labels, thereby expanding the sample base in the database.

[0071] S3. Based on the expanded database, CGAN (conditional generative adversarial network) is trained to obtain a deformation prediction model.

[0072] like Figure 4 As shown, the details are as follows:

[0073] S31. Data normalization Since the dimensions of various parameters vary greatly, all data need to be normalized to facilitate comparison and analysis, i.e.:

[0074]

[0075] where x max and x min Represent the maximum and minimum values ​​of parameter x, respectively. Represents the result after normalization operation.

[0076] S32. Divide the training set and the test set. Randomly extract samples from the database in a ratio of 8:2 to generate the training set and the test set of the model.

[0077] S33. Create generator G2. List material parameter M, process parameter A, geometric parameter Ge, and bending parameter B as condition C. Introduce a noise vector Z2 that follows a Gaussian distribution. Use both C and Z2 as inputs to generator G2. Under the constraints of condition C, generate data G2(C, Z2), which is the predicted deformation parameter.

[0078] S34. Create a discriminator D2. The (C, De) in the database and the data G2(C, Z2) generated by G2 are used as inputs of D2. Discriminator D2 makes data quality judgments respectively and outputs judgment results D2(C, De) and D2(G2(C, Z2)). Discriminator D2 is trained to make (C, De) get a high score and the generated data G2(C, Z2) get a low score. Data with mismatched C and De samples also get a low score. The training formula is:

[0079]

[0080] Among them, the superscript i represents the corresponding data of the i-th sample in the training set, and n represents the total number of training set samples randomly selected from the expanded database; Represents the same as C (i) Any De that does not match (i) ;D2(C (i) ,De (i) )、D2(C (i) ,G2(C (i) ,Z2 (i) ))、 Respectively represent the discriminator D2 input (C, De), G2 (C, Z2), Rating of θ d represents the discriminator D2 parameter, η represents the learning rate, Represents theta d Perform gradient update. S35, train generator G2. With the goal of generating data G2(C, Z2) to obtain a high score in discriminator D2, train generator G2. The training formula is:

[0081]

[0082] Among them, θ g represents the generator G2 parameter, η represents the learning rate, Represents theta g Perform gradient update.

[0083] S36, loop S34 and S35 until the deformation parameters predicted by the generator G2 are consistent with the score De of the deformation parameters in the database, then stop training, and the trained generator G2 can be regarded as a deformation prediction model with reliable accuracy.

[0084] S37. Use the test set to test the accuracy of the deformation prediction model. Compare the deformation prediction based on the test set with the deformation of the test set, and calculate the values ​​of the evaluation indicators RMSE and MAE.

[0085] S4. Deformation prediction: Input the new component parameters to be predicted and the allowable error value of the curtain wall component into the basic parameter input module. The deformation prediction module predicts the deformation of the component after processing. The comparison and analysis module determines whether the deformation of the component after processing is within the allowable error range.

[0086] like Figure 5 As shown, the details are as follows:

[0087] S41: Input new component material parameters M, process parameters A, geometric parameters Ge, bending parameters B, and curtain wall component error allowable values ​​through the basic parameter input module.

[0088] S42: The deformation of the curtain wall components after processing is predicted through the deformation prediction module to obtain the deformation parameter De and realize the deformation value prediction.

[0089] S43: The predicted deformation value and the curtain wall component error allowable value are compared through the comparison analysis module to evaluate whether the component size deformation is within the error range.

[0090] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A GAN-based deformation prediction method for building curved curtain wall components, characterized in that: The steps include: Model training phase: Based on the initial database, the GAN is trained and the number of samples in the database is expanded through the trained GAN. The initial database includes several samples, each of which includes the material parameters M, process parameters A, geometric parameters Ge, bending parameters B and deformation parameters De of the building curved curtain wall components. Based on the expanded database, CGAN is trained, including: CGAN consists of a generator G2 and a discriminator D2. The generator G2 outputs a generated sample G2(C, Z2) based on a condition C and a noise vector Z2 that follows a Gaussian distribution. The condition C includes material parameters M, process parameters A, geometric parameters Ge, and bending parameters B. The discriminator D2 scores the authenticity of the real samples (C, De) in the database and the generated sample G2(C, Z2). During training, the generator G2 aims to make the generated sample G2(C, Z2) more similar to the real sample (C, De), while the discriminator D1 aims to better distinguish between the real sample (C, De) and the generated sample G2(C, Z2). The generator G2 in the trained CGAN is used as the deformation prediction model; Model application phase: The material parameters M, process parameters A, geometric parameters Ge, and bending parameters B of the building curved curtain wall components to be predicted are input into the deformation prediction model to obtain the corresponding deformation parameters De, thereby realizing the deformation prediction of the building curved curtain wall components.

2. The GAN-based architectural curved curtain wall component deformation prediction method according to claim 1, characterized in that: Based on the initial database, the GAN is trained and the number of samples in the database is expanded through the trained GAN, including: GAN consists of a generator G1 and a discriminator D1. The generator G1 outputs a generated sample G1(Z1) based on a noise vector Z1 that follows a Gaussian distribution. The discriminator D1 scores the authenticity of the real samples X in the initial database and the generated samples G1(Z1). During training, the generator G1 aims to make the generated samples G1(Z1) more similar to the real samples X, while the discriminator D1 aims to better distinguish between the real samples X and the generated samples G1(Z1). The trained generator G1 is used as the sample generation model, and multiple samples are generated by the sample generation model and added to the initial database, thereby expanding the database.

3. The GAN-based architectural curved curtain wall component deformation prediction method according to claim 2, characterized in that: When training a GAN: Loss function of discriminator D1 as follows: Loss function of generator G1 as follows: Wherein, the superscript i represents the corresponding data of the i-th sample in the training set, m represents the total number of training set samples randomly selected after the initial database sample mixture generator generates data samples; D1(X (i) )、D1(G1(Z1 (i) )) represent the scores of the discriminator D1 on the input X and G1(Z1) respectively.

4. The GAN-based architectural curved curtain wall component deformation prediction method according to claim 3, characterized in that: When the generator G1 and the discriminator D1 satisfy the expected formula, the training is terminated and the trained GAN is obtained; the expected formula is as follows: in, The goal of the generator G1 is to minimize the above formula, and the goal of the discriminator D1 is to maximize the above formula; Indicates that for the real data X, the discriminator D1 gives the probability that it is the real data, It means that for the fake data G1(Z1) generated by the generator G1, the discriminator D1 gives the probability that it is fake data.

5. The GAN-based architectural curved curtain wall component deformation prediction method according to claim 1, characterized in that: When training CGAN: Loss function of discriminator D2 as follows: Among them, the superscript i represents the corresponding data of the i-th sample in the training set, and n represents the total number of training set samples randomly selected from the expanded database; Represents the same as C (i) Any De that does not match (i) ;D2(C (i) ,De (i) )、D2(C (i) ,G2(C (i) ,Z2 (i) ))、 They represent the discriminator D2's response to the input (C, De), (C, G2 (C, Z2)), Rating of θ d represents the discriminator D2 parameter, η represents the learning rate, Represents theta d Perform gradient updates; Loss function of generator G2 as follows: Among them, θ g represents the generator G2 parameter, η represents the learning rate, Represents theta g Perform gradient update.

6. The method for predicting deformation of curved curtain wall components based on GAN according to claim 5, characterized in that: When the scores of the discriminator D2 for the real samples (C, De) in the database and the generated samples G2 (C, Z2) are consistent, the training is terminated and the trained CGAN is obtained.

7. The GAN-based architectural curved curtain wall component deformation prediction method according to claim 1, characterized in that: Material parameter M refers to the elastic modulus and yield strength of the component material; process parameter A refers to the bending force of the component; geometric parameter Ge refers to the component cross-sectional size, cavity area ratio and material thickness; Bending parameter B refers to the bending angle, bending radius, arc length and chord length parameters of the bending line before the component is deformed; The deformation parameter De refers to the absolute value of the difference in chord length of the bending line before and after the component is deformed.

8. The method for predicting deformation of curved curtain wall components based on GAN according to claim 7, characterized in that: The method for determining the curved connection line is: determine all endpoints of the component, and for any two endpoints, draw a shortest distance connection line between the two endpoints on the component surface; and select a curved connection line from all the connection lines as the curved connection line.

9. The method for predicting deformation of curved curtain wall components based on GAN according to any one of claims 1 to 8, wherein: The samples in the initial database are obtained through bending tests and / or Abaqus finite element analysis software simulations.

10. A GAN-based building curved curtain wall component deformation prediction system, characterized in that: The method comprises a processor configured to execute the GAN-based architectural curved curtain wall component deformation prediction method according to any one of claims 1 to 9.

Images