A method, device and equipment for predicting springback of thin-walled aluminum alloy components

Abstract

Embodiments of the present invention provide a method, device, and apparatus for predicting the forming springback of thin-walled aluminum alloy components, relating to the technical field of aerospace load-bearing component processing. The method comprises: obtaining theoretical springback radius data and stress-strain relationship information through calculation using a theoretical springback prediction model; substituting forming parameters, theoretical springback radius data, and stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data; if the springback prediction error between the theoretical springback radius data and the simulated springback radius data is greater than a preset error threshold, the theoretical springback prediction model is corrected and the springback prediction error is recalculated; conversely, a forming springback dataset of thin-walled aluminum alloy components is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback dataset to obtain a trained forming springback prediction model. The present invention can improve the accuracy of prediction results for forming springback data of thin-walled aluminum alloy components.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of aerospace load-bearing component processing. More specifically, embodiments of the present invention relate to a forming springback prediction method, device, and equipment for aluminum alloy thin-walled components. Background Art

[0002] In recent years, high-strength aluminum alloys have been increasingly used in rail transportation and aerospace, and these fields also have very high precision requirements for the forming quality of aluminum alloys. The high-strength aluminum alloys used in aerospace bearing components have the characteristics of high material strength, significant work hardening, and high deformation resistance. The corresponding springback amount after forming is large, which will seriously affect the dimensional accuracy of the formed components. Aluminum alloy thin-walled parts are mainly produced by stamping, stretch bending and other methods. Sufficient forming accuracy must be ensured to meet the requirements of use. The existing forming process controls springback by measuring the springback amount after forming, modifying the mold and then forming again. This method is inefficient and costly.

[0003] The invention with patent application number "202211249843.6" and invention name "A method for predicting the springback of aluminum alloy profile roll bending considering anisotropy" discloses a method for predicting the springback of aluminum alloy profile roll bending considering anisotropy. The invention only uses the simulation results of the finite element model as experimental values ​​for theoretical calculations, resulting in inaccurate springback prediction results.

[0004] The invention with patent application number "202210570027.9" and title "A method and system for predicting and controlling springback in the forming of high-temperature alloy thin-walled parts" uses finite element analysis simulation software to simulate the stamping process of thin-walled sheet metal parts, predicting the springback of the sheet metal under different stamping process parameters. By studying the influence of process parameters such as stamping speed, stamping stroke, forming time, amplitude, and frequency on the springback of the sheet metal, a mathematical relationship model between each parameter and the springback is derived, realizing the prediction and control of the springback of high-temperature alloy thin-walled complex structural parts. Although this patent adopts finite element simulation and machine learning methods, it does not combine theoretical calculations. It only uses finite element simulation results instead of actual production and experimental results as the source of springback data, which is insufficiently reliable.

[0005] It can be seen that the existing technology has low accuracy in predicting the springback data of aluminum alloy thin-walled components. Summary of the Invention

[0006] In this context, embodiments of the present invention are intended to provide a method, device, and apparatus for predicting springback of thin-walled aluminum alloy components.

[0007] In a first aspect of an embodiment of the present invention, a method for predicting springback during forming of an aluminum alloy thin-walled component is provided, comprising:

[0008] Inputting the stretch-bending forming process parameters into the forming springback prediction model to obtain the forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model;

[0009] The forming springback prediction model is constructed through the following steps:

[0010] The forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component;

[0011] Substituting the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component;

[0012] Based on the theoretical rebound radius data and the simulated rebound radius data, a rebound prediction error is calculated. When the rebound prediction error is greater than a preset error threshold, the following steps are repeatedly performed:

[0013] The theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; forming parameters of the aluminum alloy thin-walled component are calculated using the corrected theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; and a springback prediction error is calculated based on the theoretical springback radius data and the simulated springback radius data;

[0014] Until the springback prediction error is less than or equal to the preset error threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model.

[0015] In one embodiment of this embodiment, the forming parameters of the aluminum alloy thin-walled component include at least mold size parameters, component initial size parameters, and material property parameters;

[0016] The mold size parameters include at least the mold radius;

[0017] The initial dimension parameters of the component include at least the cross-sectional area, the stretch-bending radius, the component length, the strain value, the moment of inertia, the neutral layer radius, the innermost radius and the outermost radius of the aluminum alloy thin-walled component formed by stretch bending;

[0018] The material property parameters include at least the elastic modulus, plastic modulus, yield strength, tensile strength, yield stress, plane shear stress and strength coefficient of the aluminum alloy thin-walled component.

[0019] In one embodiment of this embodiment, the theoretical springback prediction model includes a power exponential hardening model and a springback radius prediction model. The forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated using the theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component, including:

[0020] Calculating the strain value, the yield stress, the elastic modulus, and the strength coefficient in the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using the power exponential hardening model to obtain stress-strain relationship information of the aluminum alloy thin-walled component;

[0021] The forming parameters are calculated using the springback radius prediction model to obtain theoretical springback radius data of the aluminum alloy thin-walled component.

[0022] In one example of this embodiment, the stress-strain relationship information of the aluminum alloy thin-walled component is specifically expressed as:

[0023]

[0024] σ s =Eε s ;

[0025] Wherein, σ is the stress of the aluminum alloy thin-walled component, ε is the strain value, σ s is the yield stress, E is the elastic modulus, K is the strength coefficient, and n is the strain hardening exponent.

[0026] In one embodiment of this embodiment, the forming parameters are calculated using the springback radius prediction model to obtain theoretical springback radius data of the aluminum alloy thin-walled component, including:

[0027] constructing a yield stress equation based on a plurality of anisotropy constants, a tangential stress, a thickness stress, and the plane shear stress and the yield stress among the forming parameters;

[0028] Constructing a tangential stress equation based on the elastic modulus, the neutral layer radius, the tangential stress, and the target distance; wherein the target distance is the distance from the elastic and plastic transition layer to the neutral layer;

[0029] constructing a through-thickness stress equation based on the neutral layer radius, the innermost radius, the outermost radius, the target distance, the tangential stress, and the through-thickness stress;

[0030] Solve the yield stress equation, the tangential stress equation, and the thickness stress equation simultaneously to obtain the target distance;

[0031] Calculating a neutral layer bending moment based on the cross-sectional area, the target distance, and the stress of the aluminum alloy thin-walled member;

[0032] Based on the neutral layer bending moment, the moment of inertia, the elastic modulus and the stretch-bending forming radius, theoretical springback radius data of the aluminum alloy thin-walled component is calculated.

[0033] In one embodiment of this embodiment, until the springback prediction error is less than or equal to the preset error threshold, a forming springback dataset of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback prediction dataset to obtain a trained forming springback prediction model, including:

[0034] Until the rebound prediction error is less than or equal to the preset error threshold, the percentage of the rebound prediction error to the simulated rebound radius data is determined as the rebound prediction error percentage. When the rebound prediction error percentage is greater than the preset percentage threshold, the following steps are repeated:

[0035] The theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; forming parameters of the aluminum alloy thin-walled component are calculated using the corrected theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; and a springback prediction error is calculated based on the theoretical springback radius data and the simulated springback radius data;

[0036] Until the rebound prediction error percentage is less than or equal to the preset percentage threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model.

[0037] In one embodiment of this embodiment, generating the forming springback dataset of the aluminum alloy thin-walled component based on the theoretical springback prediction model includes:

[0038] Acquire multiple sets of stretch-bending process parameters for the aluminum alloy thin-walled component; wherein each set of stretch-bending process parameters includes target process parameters, die size parameters, component initial size parameters, and material property parameters;

[0039] Inputting each set of stretch-bending forming process parameters into the theoretical springback prediction model to obtain forming springback data for each set of stretch-bending forming process parameters;

[0040] Each set of stretch-bending forming process parameters and the forming springback data of each set of stretch-bending forming process parameters are combined to obtain a forming springback data set of the aluminum alloy thin-walled component.

[0041] In one embodiment of this embodiment, the input of the forming springback prediction model is the multiple sets of stretch-bending forming process parameters, and the output of the forming springback prediction model is the forming springback data of each set of stretch-bending forming process parameters;

[0042] Furthermore, after inputting the stretch-bending process parameters into the forming springback prediction model and obtaining the forming springback data of the stretch-bending process parameters output by the forming springback prediction model, the method further includes:

[0043] The forming springback prediction model is converted to obtain a forming springback control model; wherein the input of the forming springback control model is the expected forming springback data, the initial dimension parameters of the component and the material property parameters, and the output of the forming springback control model is the target process parameters and the mold dimension parameters.

[0044] In a second aspect of an embodiment of the present invention, a forming springback prediction device for an aluminum alloy thin-walled component is provided, the device being configured to input stretch-bending forming process parameters into a forming springback prediction model, and obtain forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model;

[0045] The forming springback prediction model is constructed by a forming springback prediction model construction device, and the forming springback prediction model construction device includes:

[0046] A first calculation unit is used to calculate the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component;

[0047] a simulation unit, configured to substitute the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component;

[0048] a second calculation unit, configured to calculate a rebound prediction error based on the theoretical rebound radius data and the simulated rebound radius data;

[0049] a correction unit, configured to correct the theoretical rebound prediction model to obtain a corrected theoretical rebound prediction model when the rebound prediction error is greater than a preset error threshold; and execute functions of the first calculation unit to the second calculation unit;

[0050] A training unit is used to generate a forming springback data set of the aluminum alloy thin-walled component based on the theoretical springback prediction model when the springback prediction error is less than or equal to the preset error threshold; and to train a pre-constructed forming springback prediction model based on the forming springback data set to obtain a trained forming springback prediction model.

[0051] In a third aspect of an embodiment of the present invention, a computing device is provided, comprising: at least one processor, a memory, and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0052] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, causes the computer to execute any one of the methods according to the first aspect.

[0053] In a fifth aspect of the embodiments of the present invention, a computer program product is provided, comprising a computer program, which implements the method according to any one of the first aspects when executed by a processor.

[0054] According to the forming springback prediction method, device and equipment of aluminum alloy thin-walled components according to the embodiment of the present invention, the theoretical springback prediction model can be corrected based on the combination of the theoretical springback prediction model and the finite element model constructed based on the formed aluminum alloy thin-walled component, so as to improve the accuracy of the theoretical springback radius data output by the theoretical springback prediction model; and when the theoretical springback prediction model is trained, the theoretical springback prediction model is used to generate a forming springback data set of the aluminum alloy thin-walled component, and then the forming springback prediction model is trained based on the forming springback data set of the aluminum alloy thin-walled component to obtain a trained forming springback prediction model, and then more accurate prediction results of the forming springback data of the aluminum alloy thin-walled component can be obtained based on the forming springback prediction model, thereby improving the accuracy of the prediction results of the forming springback data of the aluminum alloy thin-walled component. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0056] Figure 1 A schematic flow chart of a method for constructing a springback prediction model for thin-walled aluminum alloy components according to an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of a thin-walled aluminum alloy component formed by stretch bending according to an embodiment of the present invention;

[0058] Figure 3 A schematic structural diagram of a device for constructing a forming springback prediction model provided by one embodiment of the present invention;

[0059] Figure 4 The structure diagram of a medium according to an embodiment of the present invention is schematically shown;

[0060] Figure 5 The figure schematically shows a structural diagram of a computing device according to an embodiment of the present invention.

[0061] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts. DETAILED DESCRIPTION

[0062] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0063] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0064] According to an embodiment of the present invention, a forming springback prediction method, device and equipment for aluminum alloy thin-walled components are proposed.

[0065] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0066] The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0067] Exemplary Methods

[0068] In an embodiment of the present invention, a forming springback prediction method for aluminum alloy thin-walled components can be implemented using a pre-trained forming springback prediction model, specifically:

[0069] The stretch-bending forming process parameters are input into the forming springback prediction model to obtain the forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model.

[0070] The forming springback prediction model is constructed through the following steps. Figure 1 , Figure 1 This is a flow chart of a method for constructing a springback prediction model for thin-walled aluminum alloy components according to an embodiment of the present invention. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.

[0071] Figure 1 The process of the method for constructing a forming springback prediction model for aluminum alloy thin-walled components provided by one embodiment of the present invention includes:

[0072] Step S101 : calculating forming parameters of a thin-walled aluminum alloy component formed by stretch bending using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the thin-walled aluminum alloy component.

[0073] In the embodiment of the present invention, the aluminum alloy thin-walled component can be a profile, a plate, etc., and the forming methods include stamping, stretch bending, etc., which are specifically used in the stamping forming of the bottom of the rocket fuel tank and the stretch bending forming rebound prediction and control of the rocket body reinforcement frame.

[0074] Please also refer to Figure 2 , Figure 2 Schematic diagram of a thin-walled aluminum alloy member formed by stretch bending according to an embodiment of the present invention. Taking the stretch bending forming of a launch vehicle reinforcement frame member as an example, the stretch bending forming analysis of an L-shaped cross-section profile is performed. The profile length is 6000mm, and the cross-sectional dimensions and corresponding coordinate system are as follows: Figure 2 As shown, the X direction is the length direction of the profile, the negative Y direction is the bending direction of the profile, and the XOY plane is the bending plane;

[0075] According to the cross-sectional dimensions of the profile, it can be calculated that the cross-sectional area of ​​the profile is 475mm 2 , the distance from the center of mass to the Y-axis is 14.34 mm, and then the moment of inertia I about the Y-axis is calculated; the profile material is 7A09 aluminum alloy, with an elastic modulus of 71 GPa, a plastic modulus of 21 GPa, a yield strength of 440 MPa, and a tensile strength of 590 MPa.

[0076] In the embodiment of the present invention, the forming parameters of the aluminum alloy thin-walled component include at least mold size parameters, component initial size parameters and material property parameters; the mold size parameters include at least mold radius; the component initial size parameters include at least the cross-sectional area A of the aluminum alloy thin-walled component to be stretched and bent, the stretch bending forming radius R T , component length, strain value ε, moment of inertia I, neutral layer radius r m , innermost radius R min and the outermost radius r msx The material property parameters include at least the elastic modulus E, plastic modulus, yield strength, tensile strength, yield stress, plane shear stress τ of the aluminum alloy thin-walled component 12 And the strength coefficient K. The theoretical rebound prediction model includes the power exponential hardening model and the rebound radius prediction model.

[0077] As an optional embodiment, step S101 calculates the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using a theoretical springback prediction model, and the method of obtaining the theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component may include:

[0078] Calculating the strain value, the yield stress, the elastic modulus, and the strength coefficient in the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using the power exponential hardening model to obtain stress-strain relationship information of the aluminum alloy thin-walled component;

[0079] The forming parameters are calculated using the springback radius prediction model to obtain theoretical springback radius data of the aluminum alloy thin-walled component.

[0080] In the embodiment of the present invention, during the pre-stretching stage, the aluminum alloy thin-walled member is subjected to uniaxial stretching under the action of the clamp. The deformation of the aluminum alloy thin-walled member mainly occurs in the elastic stage, and the stress-strain relationship satisfies Hooke's law, which is specifically expressed as follows:

[0081] σ=Eε

[0082] Where σ is stress, ε is strain, and E is elastic modulus.

[0083] Among them, the power exponential hardening model expression in the entire deformation stage, that is, the stress-strain relationship information of aluminum alloy thin-walled components, is specifically expressed as:

[0084]

[0085] σ s =Eε s ;

[0086] Wherein, σ is the stress of the aluminum alloy thin-walled component, ε is the strain value, σs is the yield stress, E is the elastic modulus, K is the strength coefficient, and n is the strain hardening exponent.

[0087] As an optional embodiment, the method of calculating the forming parameters by using the springback radius prediction model to obtain the theoretical springback radius data of the aluminum alloy thin-walled component may include:

[0088] constructing a yield stress equation based on a plurality of anisotropy constants, a tangential stress, a thickness stress, and the plane shear stress and the yield stress among the forming parameters;

[0089] Constructing a tangential stress equation based on the elastic modulus, the neutral layer radius, the tangential stress, and the target distance; wherein the target distance is the distance from the elastic and plastic transition layer to the neutral layer;

[0090] constructing a through-thickness stress equation based on the neutral layer radius, the innermost radius, the outermost radius, the target distance, the tangential stress, and the through-thickness stress;

[0091] Solve the yield stress equation, the tangential stress equation, and the thickness stress equation simultaneously to obtain the target distance;

[0092] Calculating a neutral layer bending moment based on the cross-sectional area, the target distance, and the stress of the aluminum alloy thin-walled member;

[0093] Based on the neutral layer bending moment, the moment of inertia, the elastic modulus and the stretch-bending forming radius, theoretical springback radius data of the aluminum alloy thin-walled component is calculated.

[0094] In the embodiment of the present invention, the yield stress equation can be obtained based on the Hill'48 yield criterion under plane stress state, specifically:

[0095] (G+H)σ1 2 -2Hσ1σ2+(H+F)σ2 2 +2Nτ 12 2 =σ s 2

[0096] Among them, F, G, H, N are anisotropic constants, σ1 and σ2 are tangential stress and thickness stress respectively, τ 12 is the plane shear stress.

[0097] The calculation formulas for anisotropy constants F, G, H, and N are:

[0098]

[0099] Among them, r 11 =r 13 =r 23 =1, r 12 、r 22 、r 33 R obtained from 0°, 45°, and 90° tensile tests θ (R θ represents the anisotropy coefficient, θ represents the angle) calculation:

[0100]

[0101] In the embodiment of the present invention, the tangential stress equation may be:

[0102]

[0103] Among them, σ1 is the tangential stress, r m is the radius of the neutral layer, and h is the target distance from the elastic and plastic transition layer to the neutral layer.

[0104] In the embodiment of the present invention, the through-thickness stress equation may be:

[0105]

[0106] Among them, σ2 is the thickness stress, r min 、r max are the innermost radius and the outermost radius, r ε is the radius of any position.

[0107] For example, the radius of the stretch-bending die is 1650mm, and the neutral layer radius is 1640.66mm. Based on the elastic modulus and yield strength, the yield strain is calculated to be 0.006, and the distance y from the elastic-plastic transition layer to the neutral layer is calculated to be 9.86mm. Combined with the cross-sectional dimensions, the cross-sectional deformation distribution shows plastic tension in the outer layer and plastic compression in the inner layer.

[0108] In the embodiment of the present invention, the yield stress equation, the tangential stress equation, and the thickness stress equation are solved simultaneously to calculate the target distance.

[0109] Furthermore, the neutral layer bending moment can be calculated. The calculation formula of the neutral layer bending moment M can be:

[0110] M=∫ A hσdA

[0111] Where A is the cross-sectional area and σ is the stress of the aluminum alloy thin-walled component.

[0112] At this time, the neutral layer bending moment M, moment of inertia I, elastic modulus E and stretch bending radius R can be used to calculate the bending moment M, moment of inertia I, elastic modulus E and stretch bending radius R. T, calculate the theoretical rebound radius data R of aluminum alloy thin-walled components b , theoretical rebound radius data R b The calculation formula can be:

[0113]

[0114] Step S102 , substituting the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component.

[0115] In an embodiment of the present invention, the finite element model is constructed based on the formed aluminum alloy thin-walled component.

[0116] Step S103 : calculating a springback prediction error based on the theoretical springback radius data and the simulated springback radius data.

[0117] Step S104 , when the rebound prediction error is greater than a preset error threshold, repeatedly correcting the theoretical rebound prediction model to obtain a corrected theoretical rebound prediction model; and the product of steps S101 to S103 .

[0118] Step S105, until the rebound prediction error is less than or equal to the preset error threshold, a forming springback dataset of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback dataset to obtain a trained forming springback prediction model.

[0119] As an optional implementation manner, in step S105, until the springback prediction error is less than or equal to the preset error threshold, a forming springback dataset of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback prediction dataset. A method for obtaining the trained forming springback prediction model may include:

[0120] Until the rebound prediction error is less than or equal to the preset error threshold, the percentage of the rebound prediction error to the simulated rebound radius data is determined as the rebound prediction error percentage. When the rebound prediction error percentage is greater than the preset percentage threshold, the following steps are repeated:

[0121] The theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; forming parameters of the aluminum alloy thin-walled component are calculated using the corrected theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; and a springback prediction error is calculated based on the theoretical springback radius data and the simulated springback radius data;

[0122] Until the rebound prediction error percentage is less than or equal to the preset percentage threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model.

[0123] In an embodiment of the present invention, 90% of the forming springback data set can be used as training samples to train the forming springback prediction model to obtain the trained forming springback prediction model, and the remaining 10% can be used as a test set to verify the accuracy of the trained forming springback prediction model.

[0124] For example, by repeating the above steps using dies with different bending radii, simulated data for bending springback radius at 1650mm, 1700mm, 1750mm, and 1800mm dies were obtained. The accuracy and error results of the theoretical springback prediction model are shown in Table 1:

[0125] Table 1

[0126] Mold radius / mm 1650 1700 1750 1800 Simulation rebound radius data / mm 1659.3 1714.5 1766.2 1820.4 Simulated springback amount / mm 9.3 14.5 16.2 20.4 Theoretical rebound radius data / mm 1663.1 1722.3 1776.8 1835.5 Theoretical rebound amount / mm 13.1 22.3 26.8 35.5 Rebound prediction error percentage / % 0.229 0.455 0.600 0.829 Springback prediction error / mm 3.8 7.8 10.6 15.1

[0127] As an optional implementation, a method of generating the forming springback dataset of the aluminum alloy thin-walled component based on the theoretical springback prediction model may include:

[0128] Acquire multiple sets of stretch-bending process parameters for the aluminum alloy thin-walled component; wherein each set of stretch-bending process parameters includes target process parameters, die size parameters, component initial size parameters, and material property parameters;

[0129] Inputting each set of stretch-bending forming process parameters into the theoretical springback prediction model to obtain forming springback data for each set of stretch-bending forming process parameters;

[0130] Each set of stretch-bending forming process parameters and the forming springback data of each set of stretch-bending forming process parameters are combined to obtain a forming springback data set of the aluminum alloy thin-walled component.

[0131] In the embodiment of the present invention, different target process parameters may include heat treatment process parameters of the component and equipment parameters for component forming.

[0132] In an embodiment of the present invention, the input of the forming springback prediction model is the multiple sets of stretch-bending forming process parameters, and the output of the forming springback prediction model is the forming springback data of each set of stretch-bending forming process parameters.

[0133] As an optional embodiment, after inputting the stretch bending forming process parameters into the forming springback prediction model and obtaining the forming springback data of the stretch bending forming process parameters output by the forming springback prediction model, the method may further include:

[0134] The forming springback prediction model is converted to obtain a forming springback control model; wherein the input of the forming springback control model is the expected forming springback data, the initial dimension parameters of the component and the material property parameters, and the output of the forming springback control model is the target process parameters and the mold dimension parameters.

[0135] For example, the prediction and control of springback during the stretch-bending of a rocket body reinforcement frame specifically includes the following steps:

[0136] 1. Theoretical calculations were used to predict the springback of the rocket body reinforcement frame after stretch-bending. Based on the stretch-bending die dimensions, the initial dimensions of the reinforcement frame profile, and the material properties, the springback of different parts of the reinforcement frame after stretch-bending was calculated using the Hill'48 yield criterion and the power exponential hardening model. The relationship between the stretch-bending parameters, springback, and stress-strain was obtained.

[0137] 2. Establish a finite element model for the stretch-bending forming of the rocket body reinforcement frame. Substitute the theoretically calculated stretch-bending forming process parameters, springback amount, and stress-strain relationship into the finite element simulation model to calculate the theoretically corrected springback data of the stretch-bending forming of the rocket body reinforcement frame.

[0138] 3. Compare the springback results obtained from the simulation calculation with the theoretical calculation results. Substitute the springback error into the theoretical calculation formula for feedback correction. Substitute the corrected stretch-bending forming process parameters, springback amount, and stress-strain relationship into the finite element simulation model to calculate the feedback-corrected springback data of the rocket body reinforcement frame stretch-bending forming. Repeat the above process until the difference between the simulated springback result and the theoretical springback calculation result is within the allowable error range, and output the final simulated springback data.

[0139] 4. Summarize the springback data of the rocket body reinforcement frame stretch bending under different process parameters to obtain the reinforcement frame stretch bending springback dataset. Use machine learning methods to train and obtain the rocket body reinforcement frame stretch bending springback prediction model.

[0140] 5. Taking the expected springback amount, reinforcement frame profile size and stretch-bending die parameters as input, and the reinforcement frame stretch-bending process parameters and equipment parameters as output, the springback prediction model is transformed to obtain the rocket body reinforcement frame stretch-bending springback control model, and finally realize the accurate springback prediction and control of the rocket body reinforcement frame stretch-bending.

[0141] The present invention can correct the theoretical springback prediction model based on a combination of the theoretical springback prediction model and a finite element model constructed based on the formed aluminum alloy thin-walled component, so as to improve the accuracy of the theoretical springback radius data output by the theoretical springback prediction model; and when the theoretical springback prediction model is trained, the theoretical springback prediction model is used to generate a forming springback data set of the aluminum alloy thin-walled component, and then the forming springback prediction model is trained based on the forming springback data set of the aluminum alloy thin-walled component to obtain a trained forming springback prediction model, and then a more accurate prediction result of the forming springback data of the aluminum alloy thin-walled component can be obtained based on the forming springback prediction model, thereby improving the accuracy of the prediction result of the forming springback data of the aluminum alloy thin-walled component.

[0142] Exemplary devices

[0143] After introducing the method according to an exemplary embodiment of the present invention, a forming springback prediction device for an aluminum alloy thin-walled component according to an exemplary embodiment of the present invention is described below. The device is used to input stretch-bending forming process parameters into a forming springback prediction model and obtain forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model.

[0144] The forming springback prediction model is constructed by a forming springback prediction model construction device, referring to Figure 3 A device for constructing a forming springback prediction model according to an exemplary embodiment of the present invention is described. The device for constructing a forming springback prediction model includes:

[0145] The first calculation unit 301 is used to calculate the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component;

[0146] A simulation unit 302 is configured to substitute the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component;

[0147] A second calculation unit 303 is configured to calculate a rebound prediction error based on the theoretical rebound radius data and the simulated rebound radius data;

[0148] a correction unit 304 configured to correct the theoretical rebound prediction model to obtain a corrected theoretical rebound prediction model when the rebound prediction error is greater than a preset error threshold; and execute the functions of the first calculation unit 301 to the second calculation unit 303;

[0149] The training unit 305 is used to generate a forming springback data set of the aluminum alloy thin-walled component based on the theoretical springback prediction model when the springback prediction error is less than or equal to the preset error threshold; and train the pre-constructed forming springback prediction model based on the forming springback data set to obtain a trained forming springback prediction model.

[0150] The present invention can correct the theoretical springback prediction model based on a combination of the theoretical springback prediction model and a finite element model constructed based on the formed aluminum alloy thin-walled component, so as to improve the accuracy of the theoretical springback radius data output by the theoretical springback prediction model; and when the theoretical springback prediction model is trained, the theoretical springback prediction model is used to generate a forming springback data set of the aluminum alloy thin-walled component, and then the forming springback prediction model is trained based on the forming springback data set of the aluminum alloy thin-walled component to obtain a trained forming springback prediction model, and then a more accurate prediction result of the forming springback data of the aluminum alloy thin-walled component can be obtained based on the forming springback prediction model, thereby improving the accuracy of the prediction result of the forming springback data of the aluminum alloy thin-walled component.

[0151] Exemplary media

[0152] After introducing the method and apparatus of the exemplary embodiment of the present invention, the following is a reference to Figure 4 For a description of a computer-readable storage medium according to an exemplary embodiment of the present invention, please refer to Figure 4, the computer-readable storage medium shown is a CD-ROM 40, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, the steps described in the above method implementation are implemented, for example, the forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated by a theoretical springback prediction model to obtain the theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain the simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component; based on the theoretical springback radius data and the simulated springback radius data, the calculated Springback prediction error; if the springback prediction error is greater than a preset error threshold, the theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; and the forming parameters of the aluminum alloy thin-walled component are calculated by the theoretical springback prediction model to obtain the theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component, to the step of calculating the springback prediction error; if the springback prediction error is less than or equal to the preset error threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model; the specific implementation method of each step will not be repeated here.

[0153] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0154] Exemplary Computing Devices

[0155] After introducing the method, apparatus and medium of the exemplary embodiment of the present invention, the following is a reference to Figure 5 A computing device for predicting forming springback of aluminum alloy thin-walled components according to an exemplary embodiment of the present invention.

[0156] Figure 5 A block diagram is shown of an exemplary computing device 50 , which may be a computer system or server, suitable for implementing embodiments of the present invention. Figure 5 The computing device 50 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention.

[0157] like Figure 5 As shown, the components of computing device 50 may include, but are not limited to, one or more processors or processing units 501 , a system memory 502 , and a bus 503 connecting various system components (including system memory 502 and processing unit 501 ).

[0158] The computing device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 50, including volatile and non-volatile media, removable and non-removable media.

[0159] The system memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022. The computing device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the ROM 5023 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 is not shown in the , usually referred to as "hard drive"). Although not in Figure 5 As shown in FIG5 , a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 503 via one or more data media interfaces. System memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0160] A program / utility 5025 having a set (at least one) of program modules 5024 may be stored, for example, in system memory 502. Such program modules 5024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 5024 generally implement the functions and / or methods of the embodiments described herein.

[0161] The computing device 50 may also communicate with one or more external devices 504 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 505. Furthermore, the computing device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 506. Figure 5As shown, the network adapter 506 communicates with other modules (such as the processing unit 501, etc.) of the computing device 50 via the bus 503. Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with computing device 50 .

[0162] The processing unit 501 executes various functional applications and data processing by running the program stored in the system memory 502. For example, the forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated by a theoretical springback prediction model to obtain the theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data and the stress-strain relationship information are substituted into a finite element model for simulation to obtain the simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component; based on the theoretical springback radius data and the simulated springback radius data, the springback prediction error is calculated. If the springback prediction error is greater than a preset error threshold, the theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; and the forming parameters of the aluminum alloy thin-walled component are calculated using the theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component, up to the step of calculating the springback prediction error; if the springback prediction error is less than or equal to the preset error threshold, a forming springback dataset of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback dataset to obtain a trained forming springback prediction model. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the forming springback prediction device for aluminum alloy thin-walled components are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. On the contrary, the features and functions of one unit / module described above may be further divided into multiple units / modules to be embodied.

[0163] In the description of the present invention, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and should not be understood as indicating or implying relative importance.

[0164] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0165] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interface, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0166] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0167] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0168] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0169] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

[0170] Furthermore, although the operations of the method of the present invention are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0171] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

Claims

1. A method for predicting springback of thin-walled aluminum alloy components, characterized in that: The method comprises: Inputting the stretch-bending forming process parameters into the forming springback prediction model to obtain the forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model; The forming springback prediction model is constructed through the following steps: The forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; Substituting the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component; Based on the theoretical rebound radius data and the simulated rebound radius data, a rebound prediction error is calculated. When the rebound prediction error is greater than a preset error threshold, the following steps are repeatedly performed: The theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; forming parameters of the aluminum alloy thin-walled component are calculated using the corrected theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; and a springback prediction error is calculated based on the theoretical springback radius data and the simulated springback radius data; Until the springback prediction error is less than or equal to the preset error threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model.

2. The forming springback prediction method of aluminum alloy thin-walled components according to claim 1, characterized in that: The forming parameters of the aluminum alloy thin-walled component include at least mold size parameters, component initial size parameters and material property parameters; The mold size parameters include at least the mold radius; The initial dimension parameters of the component include at least the cross-sectional area, the stretch-bending radius, the component length, the strain value, the moment of inertia, the neutral layer radius, the innermost radius and the outermost radius of the aluminum alloy thin-walled component formed by stretch bending; The material property parameters include at least the elastic modulus, plastic modulus, yield strength, tensile strength, yield stress, plane shear stress and strength coefficient of the aluminum alloy thin-walled component.

3. The forming springback prediction method of aluminum alloy thin-walled components according to claim 2, characterized in that: The theoretical springback prediction model includes a power exponential hardening model and a springback radius prediction model. The forming parameters of the aluminum alloy thin-walled component formed by stretch bending are calculated using the theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component, including: Calculating the strain value, the yield stress, the elastic modulus, and the strength coefficient in the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using the power exponential hardening model to obtain stress-strain relationship information of the aluminum alloy thin-walled component; The forming parameters are calculated using the springback radius prediction model to obtain theoretical springback radius data of the aluminum alloy thin-walled component.

4. The forming springback prediction method of aluminum alloy thin-walled components according to claim 3, characterized in that: The stress-strain relationship information of the aluminum alloy thin-walled component is specifically expressed as: s s =Ee s ; Wherein, σ is the stress of the aluminum alloy thin-walled component, ε is the strain value, σ s is the yield stress, E is the elastic modulus, K is the strength coefficient, and n is the strain hardening exponent.

5. The forming springback prediction method of aluminum alloy thin-walled components according to claim 4, characterized in that: The forming parameters are calculated by the springback radius prediction model to obtain theoretical springback radius data of the aluminum alloy thin-walled component, including: constructing a yield stress equation based on a plurality of anisotropy constants, a tangential stress, a thickness stress, and the plane shear stress and the yield stress among the forming parameters; Constructing a tangential stress equation based on the elastic modulus, the neutral layer radius, the tangential stress, and the target distance; wherein the target distance is the distance from the elastic and plastic transition layer to the neutral layer; constructing a through-thickness stress equation based on the neutral layer radius, the innermost radius, the outermost radius, the target distance, the tangential stress, and the through-thickness stress; Solve the yield stress equation, the tangential stress equation, and the thickness stress equation simultaneously to obtain the target distance; Calculating a neutral layer bending moment based on the cross-sectional area, the target distance, and the stress of the aluminum alloy thin-walled member; Based on the neutral layer bending moment, the moment of inertia, the elastic modulus and the stretch-bending forming radius, theoretical springback radius data of the aluminum alloy thin-walled component is calculated.

6. The forming springback prediction method of aluminum alloy thin-walled components according to any one of claims 1 to 5, characterized in that: until the springback prediction error is less than or equal to the preset error threshold, generating a forming springback data set of the aluminum alloy thin-walled component based on the theoretical springback prediction model; The pre-built forming springback prediction model is trained based on the forming springback dataset to obtain a trained forming springback prediction model, including: Until the rebound prediction error is less than or equal to the preset error threshold, the percentage of the rebound prediction error to the simulated rebound radius data is determined as the rebound prediction error percentage. When the rebound prediction error percentage is greater than the preset percentage threshold, the following steps are repeated: The theoretical springback prediction model is corrected to obtain a corrected theoretical springback prediction model; forming parameters of the aluminum alloy thin-walled component are calculated using the corrected theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; the forming parameters, the theoretical springback radius data, and the stress-strain relationship information are substituted into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; and a springback prediction error is calculated based on the theoretical springback radius data and the simulated springback radius data; Until the rebound prediction error percentage is less than or equal to the preset percentage threshold, a forming springback data set of the aluminum alloy thin-walled component is generated based on the theoretical springback prediction model; and a pre-constructed forming springback prediction model is trained based on the forming springback data set to obtain a trained forming springback prediction model.

7. The forming springback prediction method of aluminum alloy thin-walled components according to claim 6, characterized in that: The generating of the forming springback data set of the aluminum alloy thin-walled component based on the theoretical springback prediction model comprises: Acquire multiple sets of stretch-bending process parameters for the aluminum alloy thin-walled component; wherein each set of stretch-bending process parameters includes target process parameters, die size parameters, component initial size parameters, and material property parameters; Inputting each set of stretch-bending forming process parameters into the theoretical springback prediction model to obtain forming springback data for each set of stretch-bending forming process parameters; Each set of stretch-bending forming process parameters and the forming springback data of each set of stretch-bending forming process parameters are combined to obtain a forming springback data set of the aluminum alloy thin-walled component.

8. The forming springback prediction method of aluminum alloy thin-walled components according to claim 7, characterized in that: The input of the forming springback prediction model is the multiple sets of stretch-bending forming process parameters, and the output of the forming springback prediction model is the forming springback data of each set of stretch-bending forming process parameters; Furthermore, after inputting the stretch-bending process parameters into the forming springback prediction model and obtaining the forming springback data of the stretch-bending process parameters output by the forming springback prediction model, the method further includes: The forming springback prediction model is converted to obtain a forming springback control model; wherein the input of the forming springback control model is the expected forming springback data, the initial dimension parameters of the component and the material property parameters, and the output of the forming springback control model is the target process parameters and the mold dimension parameters.

9. A forming springback prediction device for aluminum alloy thin-walled components, characterized in that: The device is used to input the stretch-bending forming process parameters into the forming springback prediction model to obtain the forming springback data of the stretch-bending forming process parameters output by the forming springback prediction model; The forming springback prediction model is constructed by a forming springback prediction model construction device, and the forming springback prediction model construction device includes: A first calculation unit is used to calculate the forming parameters of the aluminum alloy thin-walled component formed by stretch bending using a theoretical springback prediction model to obtain theoretical springback radius data and stress-strain relationship information of the aluminum alloy thin-walled component; a simulation unit, configured to substitute the forming parameters, the theoretical springback radius data, and the stress-strain relationship information into a finite element model for simulation to obtain simulated springback radius data of the aluminum alloy thin-walled component; wherein the finite element model is constructed based on the formed aluminum alloy thin-walled component; a second calculation unit, configured to calculate a rebound prediction error based on the theoretical rebound radius data and the simulated rebound radius data; a correction unit, configured to correct the theoretical rebound prediction model to obtain a corrected theoretical rebound prediction model when the rebound prediction error is greater than a preset error threshold; and execute functions of the first calculation unit to the second calculation unit; A training unit is used to generate a forming springback data set of the aluminum alloy thin-walled component based on the theoretical springback prediction model when the springback prediction error is less than or equal to the preset error threshold; and to train a pre-constructed forming springback prediction model based on the forming springback data set to obtain a trained forming springback prediction model.

10. A computing device, characterized in that The computing device comprises: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the method according to any one of claims 1 to 8.

Images