High-precision aluminum alloy stamping process and die design method

Abstract

The embodiment of the present application relates to the field of precision machining technology, and discloses a high-precision aluminum alloy stamping process and die design method, which comprises the following steps: predicting material data of aluminum alloy to be processed according to experimental data of the aluminum alloy; the material data comprises material flow, springback and stress distribution data; simulating and predicting a die surface for compensating springback according to the material data of the aluminum alloy to be processed, so as to manufacture a stamping die; determining the spraying thickness of a lubricant according to the composition of the lubricant, the inner surface structure of the stamping die and the material data of the aluminum alloy to be processed; spraying the lubricant on the surface of the aluminum alloy to be processed according to the spraying thickness; step-by-step stamping the aluminum alloy to be processed; springback calibration is performed on the stamped aluminum alloy, so as to obtain calibrated aluminum alloy; after trimming the calibrated aluminum alloy, a formed aluminum alloy is obtained. The embodiment of the present application effectively reduces the springback problem in the machining process and reduces the trial and error cost.

Description

High-precision aluminum alloy stamping process and mold design method Technical Field

[0001] The embodiments of the present invention relate to the field of precision machining technology, specifically to a high-precision aluminum alloy stamping process and mold design method. Background Technology

[0002] Currently, aluminum alloys are among the most widely used metallic materials in industries such as aerospace, with extensive applications in aircraft structural components (skin, stringers, bulkheads, etc.), engine parts, landing gear, and airborne equipment housings. Aluminum alloy parts are lightweight, have good specific stiffness, and are corrosion-resistant, but they also exhibit poor ductility and resilience. Therefore, to improve the production efficiency and product quality of aluminum alloy parts, it is necessary to research aluminum alloy stamping processes, especially high-precision aluminum alloy stamping processes.

[0003] The prior art discloses a method for preparing high-density aluminum-lithium alloy plates based on a fully compounded extrusion process and its application. This method utilizes a multi-roll mill to cold roll the slab, reducing the energy consumption of subsequent processes. However, this method does not consider the characteristics of aluminum alloy materials and cannot guarantee the forming accuracy of the aluminum alloy.

[0004] The inventors of this application have discovered that existing aluminum alloy stamping processes do not fully consider the characteristics of aluminum alloy materials and potential problems during processing, resulting in aluminum alloy stamping products having problems such as large springback and unstable precision, which cannot meet the requirements of the aerospace field. Summary of the Invention

[0005] In view of the above problems, embodiments of the present invention provide a high-precision aluminum alloy stamping process and mold design method to solve the problems of large springback and unstable precision in aluminum alloy stamping products in the prior art.

[0006] According to one aspect of the present invention, a high-precision aluminum alloy stamping process is provided, the process comprising:

[0007] Based on the experimental data of the aluminum alloy to be processed, predict the material data of the aluminum alloy to be processed; the material data includes material flow, springback and stress distribution data;

[0008] Based on the material data of the aluminum alloy to be processed, the die profile for compensating springback is simulated and predicted in order to manufacture the stamping die.

[0009] The coating thickness of the lubricant is determined based on the composition of the lubricant, the internal surface structure of the stamping die, and the material data of the aluminum alloy to be processed.

[0010] According to the specified coating thickness, the coating is applied to the surface of the aluminum alloy to be processed;

[0011] The aluminum alloy to be processed is stamped in steps to obtain the stamped aluminum alloy;

[0012] The stamped aluminum alloy is spring-loaded for calibration to obtain a calibrated aluminum alloy.

[0013] After the calibrated aluminum alloy is punched and trimmed, a shaped aluminum alloy is obtained.

[0014] Optionally,

[0015] The prediction of material data for the aluminum alloy to be processed based on experimental data includes:

[0016] Based on the basic information of the selected aluminum alloy to be processed, the experimental data of the aluminum alloy to be processed are obtained by querying the pre-established aluminum alloy material database; wherein, the aluminum alloy material database includes basic information, physicochemical property information, mechanical property information, processing performance information, surface treatment performance information, and corrosion resistance performance information of aluminum alloy materials.

[0017] The experimental data of the aluminum alloy to be processed is input into a nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed. The nonlinear elastoplastic model is obtained by training a deep learning algorithm based on training data. The training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data for the experimental aluminum alloy. The simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data corresponding to the experimental aluminum alloy.

[0018] Optionally, the step of simulating and predicting the die profile for compensating springback based on the material data of the aluminum alloy to be processed, in order to manufacture the stamping die, includes:

[0019] Based on the material data of the aluminum alloy to be processed, finite element analysis software is used to perform three-dimensional modeling of the mold and the aluminum alloy to be processed, and simulation prediction is performed to obtain the first compensation data of the first mold surface for compensating springback.

[0020] The material data of the aluminum alloy to be processed and the initial modeling mold are input into the springback compensation model to obtain the second compensation data of the second mold surface for springback compensation; wherein, the springback compensation model is trained based on the experimental data of the experimental aluminum alloy, the modeling mold corresponding to the experimental aluminum alloy, and the simulated material data corresponding to the experimental data;

[0021] The target compensation data is obtained by weighted fusion of the first compensation data and the second compensation data.

[0022] Based on the target compensation data, springback compensation design is performed on the initial modeling mold, and a stamping mold is manufactured.

[0023] Optionally, before performing weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data, the process further includes:

[0024] Calculate the difference between the first compensation data and the second compensation data;

[0025] If the difference is within a preset difference threshold, then the step of weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data is performed.

[0026] If the difference is greater than a preset difference threshold, the cause of the difference is analyzed according to the preset analysis steps, and the first compensation data and / or the second compensation data are recalculated based on the cause of the difference.

[0027] Optionally, the lubricant comprises water-based synthetic esters, nano-graphite, and sulfurized isobutylene.

[0028] Optionally, determining the coating thickness of the lubricant based on the composition of the lubricant, the inner surface structure of the stamping die, and the material data of the aluminum alloy to be processed includes:

[0029] The frictional force between the aluminum alloy to be processed and the stamping die is determined when the lubricant is sprayed to different thicknesses on the aluminum alloy to be processed.

[0030] The effect of different frictional forces on the springback of the aluminum alloy to be processed was determined;

[0031] Based on the rebound effect, the target friction force and the corresponding lubricant coating thickness are determined.

[0032] Optionally, after the calibrated aluminum alloy is punched and trimmed to obtain the shaped aluminum alloy, the process further includes:

[0033] The formed aluminum alloy is subjected to quality inspection to determine its dimensional accuracy, surface defects, grain size, and heat treatment effect.

[0034] Another embodiment of the present invention provides a method for designing aluminum alloy molds, the method comprising:

[0035] Simulation software is used to simulate and predict the material data of the aluminum alloy to be processed; the material data includes material flow, springback, and stress distribution data;

[0036] Based on the material data of the aluminum alloy to be processed, the die profile for compensating springback is simulated and predicted in order to manufacture the stamping die.

[0037] Optionally, the step of using simulation software to simulate and predict the material data of the aluminum alloy to be processed includes:

[0038] A tensile test is performed on the aluminum alloy to be processed to obtain the mechanical property parameters of the aluminum alloy to be processed; the mechanical property parameters include elastic modulus, yield strength, and hardening index;

[0039] The deformation data of the aluminum alloy to be processed during the actual stamping process were obtained using a strain measurement system.

[0040] The mechanical property parameters and the deformation data are used as experimental data for the aluminum alloy to be processed.

[0041] The experimental data of the aluminum alloy to be processed is input into a nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed. The nonlinear elastoplastic model is obtained by training a deep learning algorithm based on training data. The training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data of the experimental aluminum alloy. The simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data of the experimental aluminum alloy.

[0042] Optionally, the step of simulating and predicting the die profile for compensating springback based on the material data of the aluminum alloy to be processed, in order to manufacture the stamping die, includes:

[0043] Based on the material data of the aluminum alloy to be processed, finite element analysis software is used to perform three-dimensional modeling of the mold and the aluminum alloy to be processed, and simulation prediction is performed to obtain the first compensation data of the first mold surface for compensating springback.

[0044] The material data of the aluminum alloy to be processed and the initial modeling mold are input into the springback compensation model to obtain the second compensation data of the second mold surface for springback compensation; wherein, the springback compensation model is trained based on the experimental data of the experimental aluminum alloy, the modeling mold corresponding to the experimental aluminum alloy, and the simulated material data corresponding to the experimental data;

[0045] The target compensation data is obtained by weighted fusion of the first compensation data and the second compensation data.

[0046] Based on the target compensation data, springback compensation design is performed on the initial modeling mold, and a stamping mold is manufactured.

[0047] This invention improves the accuracy and efficiency of predicting the material data of the aluminum alloy to be processed by using a pre-established database and a nonlinear elastoplastic model. Furthermore, in springback compensation design, computer-aided engineering (CAE) and artificial intelligence (AI) technologies are fully utilized to achieve digital design of the aluminum alloy material, reducing trial-and-error costs and enabling rapid and accurate acquisition of information on the physical and mechanical properties and processing performance of the aluminum alloy material, providing strong support for the development of aluminum alloy stamping products. Moreover, springback can be further reduced by designing suitable lubricants. In addition, this invention can analyze the microstructure of the aluminum alloy material to understand the variation law of its mechanical properties, thereby optimizing the design scheme of aluminum alloy stamping products, reducing manufacturing costs, and improving production efficiency.

[0048] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0049] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0050] Figure 1 shows a schematic flowchart of the high-precision aluminum alloy stamping process provided in an embodiment of the present invention;

[0051] Figure 2 shows a schematic flowchart of a mold design method provided in another embodiment of the present invention. Detailed Implementation

[0052] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0053] Figure 1 shows a flowchart of the high-precision aluminum alloy stamping process provided by an embodiment of the present invention. As shown in Figure 1, the process includes the following steps:

[0054] Step 110: Based on the experimental data of the aluminum alloy to be processed, predict the material data of the aluminum alloy to be processed; the material data includes material flow, springback and stress distribution data.

[0055] In this embodiment of the invention, experimental data on the aluminum alloy to be processed are first obtained, specifically including the following steps:

[0056] Step 1101: Based on the basic information of the selected aluminum alloy to be processed, retrieve the experimental data of the aluminum alloy to be processed from the pre-established aluminum alloy material database.

[0057] In this embodiment of the invention, the experimental data of the aluminum alloy to be processed are obtained by querying a pre-established aluminum alloy material database based on the basic information of the selected aluminum alloy to be processed.

[0058] Specifically, this embodiment of the invention pre-establishes an aluminum alloy material database, which mainly includes the following parts: basic information, physicochemical properties, mechanical properties, processing performance, surface treatment performance, and corrosion resistance information of the aluminum alloy material. The basic information includes grade, composition, and state; the physicochemical properties include density, melting point, electrical conductivity, and coefficient of thermal expansion; the mechanical properties include tensile strength, yield strength, elongation, and hardness; the processing performance includes weldability, machinability, and casting performance; the surface treatment performance includes anodizing, coating, and electroplating; and the corrosion resistance includes salt spray testing and acid / alkali solution immersion testing. By establishing this aluminum alloy material database, this embodiment of the invention allows for convenient querying and management of information on various aluminum alloy materials, providing convenient support for the development and production of aluminum alloy stamping products.

[0059] The information in the aluminum alloy material database is obtained through prior experiments on various aluminum alloy materials. For example, a tensile test is performed on the aluminum alloy to be processed to obtain its mechanical property parameters; these mechanical property parameters include elastic modulus, yield strength, and hardening index. In this embodiment of the invention, a tensile test can be performed on the aluminum alloy to be processed according to a preset standard (such as a national standard) to obtain its mechanical property parameters. A strain measurement system is used to obtain the deformation data of the aluminum alloy to be processed during the actual stamping process; this strain measurement system can be an existing strain measurement device, etc., and this embodiment of the invention does not impose specific limitations.

[0060] Step 1102: Input the experimental data of the aluminum alloy to be processed into the nonlinear elastic-plastic model to obtain the predicted material data of the aluminum alloy to be processed.

[0061] The nonlinear elastoplastic model is obtained by training a deep learning algorithm using training data. The training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data for the experimental aluminum alloy. The simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data.

[0062] In this embodiment of the invention, a deep learning algorithm is trained in advance to obtain the nonlinear elastoplastic model.

[0063] Specifically, it includes the following steps:

[0064] 1. Obtain training data. This training data includes historical experimental data of aluminum alloys for training samples and corresponding historical material data, as well as sample labels: experimental data and corresponding simulated material data for the experimental aluminum alloys.

[0065] 2. Input the training data into a deep learning neural network for training to obtain predicted material data;

[0066] 3. Based on the predicted material data and sample labels, calculate the loss of the deep learning neural network using a preset loss function.

[0067] 4. Adjust the parameters of the deep learning neural network according to the loss, and continue iterative training until the preset number of iterations is reached to obtain the nonlinear elastoplastic model.

[0068] Step 001: Acquiring Training Data: 1. Collect historical experimental data of aluminum alloys and corresponding historical material data of the aluminum alloys, including parameters such as elastic modulus, yield strength, and hardening index, as well as stress-strain curves and springback data. 2. Acquiring Simulated Material Data: Use finite element simulation software (such as ABAQUS or LS-DYNA) to simulate the stamping process of historical aluminum alloys. Input the aluminum alloy simulation experimental data (such as material parameters, boundary conditions, loads, etc.) to generate simulated material data (such as stress distribution, strain distribution, springback, etc.). Ensure the consistency between the simulated data and the experimental data, and verify the accuracy of the model through comparison. 3. Data Processing: Organize the experimental and simulated data into a structured dataset, including input features (such as strain, load, and material parameters) and output features (such as stress, springback, and material flow path). The dataset contains historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and simulated material data corresponding to new experimental aluminum alloys.

[0069] Step 002: Nonlinear Elastoplastic Model Construction: 1. Select a suitable nonlinear elastoplastic material model for the aluminum alloy, such as the Tresca criterion, Hill criterion, or a model based on the strain energy density function (e.g., the Neo-Hookean model). Define material parameters (e.g., elastic modulus, yield strength, hardening exponent, etc.) and calibrate them based on experimental data. 2. Deep Learning Model Training: Select a suitable deep learning algorithm (e.g., Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), etc.) to model and predict the nonlinear behavior of the material. Train the deep learning model using prepared training data. Input features are experimental and simulated data, and output features are predicted material data (e.g., stress, strain, springback, etc.). Improve the model's prediction accuracy through cross-validation and hyperparameter optimization techniques (e.g., grid search, random search).

[0070] Step 003: Model Validation and Optimization: Evaluate the model's predictive ability using the validation set, and calculate the root mean square error (RMSE) or coefficient of determination (R²). 2 Indicators such as [list of indicators]. Adjust the model structure or parameters based on the validation results to optimize model performance.

[0071] After training the nonlinear elastoplastic model, the experimental data of the aluminum alloy to be processed are input into the nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed.

[0072] Step 120: Based on the material data of the aluminum alloy to be processed, simulate and predict the die surface for compensating for springback in order to manufacture the stamping die.

[0073] In this embodiment of the invention, if the mold parameters are not accurately determined during mold production, the generated experimental mold will not meet the requirements, leading to repeated modifications of the experimental mold to obtain the final mold, thus wasting time and materials. This embodiment of the invention combines model prediction with finite element software analysis to improve the accuracy of mold springback compensation, reduce the number of repeated modifications to the experimental mold, effectively reduce trial-and-error costs, and improve work efficiency. Specifically, based on the material data of the aluminum alloy to be processed, the mold profile for springback compensation is simulated and predicted to manufacture the stamping die, specifically including:

[0074] Step 1201: Based on the material data of the aluminum alloy to be processed, use finite element analysis software to perform three-dimensional modeling of the mold and the aluminum alloy to be processed, and perform simulation prediction to obtain the first compensation data of the first mold surface for compensating springback.

[0075] First, based on parameters such as elastic modulus, yield strength, and hardening index from the material data of the aluminum alloy to be processed, finite element simulation software (such as ABAQUS or LS-DYNA) is used to simulate the stamping process of the aluminum alloy, generating simulated material data (such as stress distribution, strain distribution, and springback). Then, 3D models of the aluminum alloy sheet and the initial mold are created using CAD software (such as SolidWorks or CATIA). These models are then imported into the finite element analysis software for mesh generation, ensuring that the mesh accuracy meets the requirements.

[0076] Then, the initial mold surface modeling is performed. In the finite element software, the geometric model of the initial modeling mold and the aluminum alloy sheet corresponding to the aluminum alloy to be processed is set, and the material parameters (such as elastic modulus, yield strength, hardening index) and process parameters (such as blank holder force, friction coefficient) are input.

[0077] Finally, stamping and springback simulations were performed, the surface data after stamping was recorded, the springback process was simulated after unloading, the magnitude and distribution of springback were extracted, and the first compensation data of the first mold surface was obtained.

[0078] Step 1202: Input the material data of the aluminum alloy to be processed and the initial modeling mold into the springback compensation model to obtain the second compensation data of the second mold surface for springback compensation; wherein, the springback compensation model is trained based on the experimental data of the experimental aluminum alloy, the modeling mold corresponding to the experimental aluminum alloy, and the simulated material data corresponding to the experimental data. The initial modeling mold is obtained based on the software modeling in step 1201.

[0079] Before using artificial intelligence technology to predict the springback behavior of aluminum alloy materials, the equipment is trained in the following way:

[0080] First, training data is acquired by collecting experimental data, including a large amount of experimental data on aluminum alloy materials from the laboratory, covering mechanical properties, chemical composition, and microstructure. Then, the data is preprocessed: the collected data is cleaned and standardized to facilitate subsequent use by machine learning algorithms. The experimental data of the aluminum alloys, the corresponding modeling mold data, and the simulated material data corresponding to the experimental data are organized into a training dataset. The dataset should include input features (such as strain, load, and material parameters) and output features (such as stress, springback, and material flow path). The deep learning model is trained using the training dataset, and the model parameters are optimized to obtain a trained springback compensation model. After obtaining the trained springback compensation model, it is validated using an independent test set to evaluate its predictive accuracy. The validated model is then deployed to a production environment for real-time prediction of the springback behavior of aluminum alloy materials.

[0081] After obtaining the trained springback compensation model, the material data of the aluminum alloy to be processed and the initial modeling mold are input into the springback compensation model to obtain the second compensation data of the second mold surface for compensating springback.

[0082] Step 1203: Perform weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data.

[0083] The target compensation data is obtained by weighted fusion of the first and second compensation data. The weighted fusion formula is as follows:

[0084] S traget =α·S first +(1-α)S second

[0085] Where α is the weighting coefficient, typically ranging from 0.5 to 1, and S first This is the first compensation data, S second This is the second compensation data. In this embodiment of the invention, the relative importance of the two models is controlled by adjusting the weighting coefficients, making the final target compensation data more accurate and reliable. Furthermore, if a significant difference is found between the prediction results of the two models, other measures can be taken for correction, such as introducing expert experience or manual intervention. Specifically, this embodiment of the invention uses a difference setting to mutually verify the prediction results of the two models. Therefore, before the weighted fusion of the first compensation data and the second compensation data to obtain the target compensation data, the process further includes:

[0086] Calculate the difference between the first compensation data and the second compensation data;

[0087] If the difference is within a preset difference threshold, then the step of weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data is performed.

[0088] If the difference exceeds a preset difference threshold, the cause of the difference is analyzed according to preset analysis steps, and the first compensation data and / or the second compensation data are recalculated based on the cause of the difference. The cause of the deviation in the first compensation data may be an incorrect selection of the numerical calculation method or insufficient mesh generation precision. Therefore, the numerical calculation method or mesh generation can be reselected for simulation calculation to update the first compensation data.

[0089] Step 1204: Perform springback compensation design on the initial modeling mold based on the target compensation data, and manufacture the stamping mold.

[0090] The process involves importing the target compensation data into CAD software to adjust the initial mold surface. Using the CAD software's surface editing functions (such as offset, deformation, and fitting), the geometry of the mold surface is adjusted based on the compensation data. Specifically, for areas with significant springback, the curvature of the surface is appropriately increased; for areas with less springback, fine-tuning is performed. Finite element analysis software (such as ABAQUS or Dynaform) is used to re-simulate the compensated mold surface to verify the compensation effect. After completing the compensation design in the CAD software, a machining file (such as NC code) for the mold surface is generated, ensuring that the accuracy and format of the machining file meet the requirements of the CNC machining center. The machining file is then imported into the CNC machining center for machining the mold surface to obtain the stamping die.

[0091] In this embodiment of the invention, after obtaining the stamping die, it can be subjected to actual stamping tests and verifications to verify the compensation effect.

[0092] Step 130: Determine the coating thickness of the lubricant based on the composition of the lubricant, the internal surface structure of the stamping die, and the material data of the aluminum alloy to be processed.

[0093] In this embodiment of the invention, the lubricant comprises water-based synthetic ester, nano-graphite, and sulfurized isobutylene. Specifically, considering the springback problem of the aluminum alloy to be processed, the stability of the lubricant during heating, and the ease of cleaning, this embodiment of the invention adjusts the friction of the aluminum alloy material by changing the composition, composition ratio, and spray thickness of the lubricant, thereby effectively reducing springback during the stamping process. Nano-graphite is added to ensure stability. Since graphite is prone to agglomeration, surface modification (such as treatment with silane coupling agents) or the addition of dispersants (such as polyethers) are necessary to ensure its uniform suspension in the lubricant. Furthermore, the extreme pressure additive must be compatible with the base carrier (oil-based / water-based) to avoid stratification or precipitation. The layered structure of graphite forms a physical lubricating film during friction, reducing the coefficient of friction. Nano-graphite is a solid lubricant; its layered structure forms a physical lubricating film at the friction interface, reducing the dynamic coefficient of friction (by 30%-40%). It maintains lubrication performance even at high temperatures (above 400℃), making it suitable for high-speed stamping or warm stamping processes. Graphite promotes uniform material flow, reducing areas of insufficient local plastic deformation (such as stamping corners), thereby reducing springback. By reducing friction between the die and the sheet metal, it releases residual stress within the material, reducing elastic recovery energy. Secondly, considering the combination of graphite and sulfurized isobutylene, this embodiment uses a water-based synthetic ester as the base carrier. On the one hand, it provides a uniform lubricating medium, ensuring that nano-graphite and sulfurized isobutylene form a continuous lubricating film on the aluminum alloy surface. On the other hand, it has rapid evaporation / cleaning properties, avoiding residue interference with subsequent processes (such as welding and anodizing). By stabilizing the lubricating film thickness, it reduces local flow resistance differences caused by uneven lubrication, thereby reducing the asymmetry of residual stress distribution (one of the main causes of springback). To suppress non-uniform stress concentration caused by local adhesion, it makes the overall material deformation closer to the ideal state. To reduce the uncertainty of springback caused by friction fluctuations during stamping, this embodiment adds sulfur-based extreme pressure additive sulfurized isobutylene to the lubricant.

[0094] The thickness of the lubricant coating can be determined in the following ways:

[0095] The frictional force between the aluminum alloy to be processed and the stamping die is determined when the lubricant is sprayed to different thicknesses on the aluminum alloy to be processed; the effect of different frictional forces on the springback of the aluminum alloy to be processed is determined; based on the springback effect, the target frictional force and the corresponding lubricant spraying thickness are determined.

[0096] Specifically, this invention can determine the slip behavior of aluminum alloy materials under different conditions through experimental testing or numerical simulation, thereby determining the coating thickness of the lubricant. In this embodiment, by setting the coating thickness of the lubricant components, the following effects can be achieved: Optimized friction coefficient: By setting this lubricant, the friction coefficient can be reduced to 0.05-0.08 (approximately 0.2-0.3 without lubrication), significantly reducing material flow resistance. Experimental data: In the deep drawing test of 6061-T6 aluminum alloy, using this formula can reduce the springback from ±0.25mm to ±0.12mm (a reduction of approximately 50%). CAE simulation shows that after reducing the friction coefficient, the standard deviation of the springback distribution is reduced by 60%, significantly improving consistency. Material flow and stress balance: Nano-graphite ensures low global friction, while sulfurized isobutylene supplements lubrication in the high-pressure area; the two work together to achieve uniform plastic deformation, avoiding insufficient deformation (springback source) in localized areas due to excessive friction. Symmetrical residual stress distribution: Reduces warping caused by stress imbalance after demolding. Enhanced process stability: Rapid film formation of water-based synthetic esters reduces batch variations caused by uneven lubricant spraying. Durable extreme pressure film: Maintains stable lubrication performance during continuous stamping, preventing lubrication failure due to mold temperature rise (reduced risk of springback fluctuations).

[0097] Step 140: Spray the coating onto the surface of the aluminum alloy to be processed according to the specified coating thickness.

[0098] Different parts may correspond to different coating thicknesses, which are applied to the aluminum alloy surface to be processed according to the coating thickness.

[0099] Step 150: Perform step-by-step stamping on the aluminum alloy to be processed to obtain the stamped aluminum alloy.

[0100] To prevent excessive deformation and cracking during stamping, a step-by-step stamping process is employed using a servo motor. Each stamping process can include drawing, shaping, and flanging. Simultaneously, localized heating is used through temperature control to improve material recovery, and constant mold temperature control reduces thermal deformation.

[0101] Step 160: Perform springback calibration on the stamped aluminum alloy to obtain the calibrated aluminum alloy.

[0102] In this embodiment of the invention, after obtaining the stamped aluminum alloy, it can be shaped with the assistance of a precision straightening mold or a robotic arm, or the residual stress can be locally adjusted by laser shock strengthening, thereby obtaining a calibrated aluminum alloy.

[0103] Step 170: After punching and trimming the calibrated aluminum alloy, a shaped aluminum alloy is obtained.

[0104] The process involves employing negative clearance punching (punch and die clearance < 5% of material thickness) to improve cross-sectional quality; using a precision punching die with a V-shaped ring pressure plate to achieve a bright band ratio of over 90%. For complex contours, fiber laser cutting (accuracy ±0.05mm) is used to avoid burrs. After punching and trimming, a finished aluminum alloy is obtained.

[0105] In some possible implementations, after the calibrated aluminum alloy is punched and trimmed to obtain the shaped aluminum alloy, the process further includes:

[0106] The formed aluminum alloy is subjected to quality inspection to determine its dimensional accuracy, surface defects, grain size, and heat treatment effect. Specifically, this invention can employ various testing methods to ensure the quality and reliability of aluminum alloy stamping products, including non-destructive testing, metallographic inspection, and mechanical property testing. These testing methods can promptly detect and correct quality problems in the production process, thereby preventing defective products from entering the market and causing losses.

[0107] This invention improves the accuracy and efficiency of predicting the material data of the aluminum alloy to be processed by using a pre-established database and a nonlinear elastoplastic model. Furthermore, in springback compensation design, computer-aided engineering (CAE) and artificial intelligence (AI) technologies are fully utilized to achieve digital design of the aluminum alloy material, reducing trial-and-error costs and enabling rapid and accurate acquisition of information on the physical and mechanical properties and processing performance of the aluminum alloy material, providing strong support for the development of aluminum alloy stamping products. Moreover, springback can be further reduced by designing suitable lubricants. In addition, this invention can analyze the microstructure of the aluminum alloy material to understand the variation law of its mechanical properties, thereby optimizing the design scheme of aluminum alloy stamping products, reducing manufacturing costs, and improving production efficiency.

[0108] Referring to Figure 2, another embodiment of the present invention also provides an aluminum alloy mold design method, including the following steps:

[0109] Step 210: Use simulation software to simulate and predict the material data of the aluminum alloy to be processed; the material data includes material flow, springback and stress distribution data;

[0110] In some possible implementations, predicting the material data of the aluminum alloy to be processed based on experimental data includes:

[0111] Based on the basic information of the selected aluminum alloy to be processed, the experimental data of the aluminum alloy to be processed are obtained by querying the pre-established aluminum alloy material database; wherein, the aluminum alloy material database includes basic information, physicochemical property information, mechanical property information, processing performance information, surface treatment performance information, and corrosion resistance performance information of aluminum alloy materials.

[0112] The experimental data of the aluminum alloy to be processed is input into a nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed. The nonlinear elastoplastic model is obtained by training a deep learning algorithm based on training data. The training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data for the experimental aluminum alloy. The simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data corresponding to the experimental aluminum alloy.

[0113] Step 220: Based on the material data of the aluminum alloy to be processed, simulate and predict the die surface for compensating springback in order to manufacture the stamping die.

[0114] Specifically, this invention allows for the selection of different simulation software and algorithms based on the varying properties of aluminum alloy materials, enabling accurate simulation and prediction of their stamping processes. For instance, high-strength aluminum alloys can be simulated using CAE software based on the finite element method, while low-strength aluminum alloys can be simulated using CAE software based on the boundary element method.

[0115] In some possible implementations, the step of simulating and predicting the die profile to compensate for springback based on the material data of the aluminum alloy to be processed, in order to manufacture the stamping die, includes:

[0116] Based on the material data of the aluminum alloy to be processed, finite element analysis software is used to perform three-dimensional modeling of the mold and the aluminum alloy to be processed, and simulation prediction is performed to obtain the first compensation data of the first mold surface for compensating springback.

[0117] The material data of the aluminum alloy to be processed and the initial modeling mold are input into the springback compensation model to obtain the second compensation data of the second mold surface for springback compensation; wherein, the springback compensation model is trained based on the experimental data of the experimental aluminum alloy, the modeling mold corresponding to the experimental aluminum alloy, and the simulated material data corresponding to the experimental data;

[0118] The target compensation data is obtained by weighted fusion of the first compensation data and the second compensation data.

[0119] Based on the target compensation data, springback compensation design is performed on the initial modeling mold, and a stamping mold is manufactured.

[0120] The aluminum alloy mold design method is largely consistent with the specific implementation steps of steps 110-120 of the aforementioned high-precision aluminum alloy stamping process, and will not be repeated here.

[0121] This invention improves the accuracy and efficiency of predicting the material data of the aluminum alloy to be processed by using a pre-established database and a nonlinear elastoplastic model. Furthermore, in springback compensation design, computer-aided engineering (CAE) and artificial intelligence (AI) technologies are fully utilized to achieve digital design of the aluminum alloy material, reducing trial-and-error costs and enabling rapid and accurate acquisition of information on the physical and mechanical properties and processing performance of the aluminum alloy material, providing strong support for the development of aluminum alloy stamping products. Moreover, springback can be further reduced by designing suitable lubricants. In addition, this invention can analyze the microstructure of the aluminum alloy material to understand the variation law of its mechanical properties, thereby optimizing the design scheme of aluminum alloy stamping products, reducing manufacturing costs, and improving production efficiency.

[0122] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0123] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0124] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0125] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0126] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A high-precision aluminum alloy stamping process, characterized in that, The process includes: predicting the material data of the aluminum alloy to be processed based on experimental data of the aluminum alloy to be processed; the material data includes material flow, springback, and stress distribution data; simulating and predicting the mold surface for springback compensation based on the material data of the aluminum alloy to be processed, in order to manufacture a stamping die, including: using finite element analysis software to perform three-dimensional modeling of the die and the aluminum alloy to be processed based on the material data of the aluminum alloy to be processed, and performing simulation and prediction to obtain the first compensation data of the first mold surface for springback compensation; inputting the material data of the aluminum alloy to be processed and the initially modeled die into the springback compensation model to obtain the second compensation data of the second mold surface for springback compensation; wherein, the springback compensation model is based on the experimental data of the experimental aluminum alloy, the experimental aluminum alloy... The modeling mold and the simulated material data corresponding to the experimental data are trained together; the first compensation data and the second compensation data are weighted and fused to obtain the target compensation data; the initial modeling mold is designed for springback compensation based on the target compensation data, and a stamping mold is manufactured; the coating thickness of the lubricant is determined based on the composition of the lubricant, the inner surface structure of the stamping mold, and the material data of the aluminum alloy to be processed; the lubricant is sprayed onto the surface of the aluminum alloy to be processed according to the coating thickness; the aluminum alloy to be processed is stamped in steps to obtain the stamped aluminum alloy; the stamped aluminum alloy is spring-loaded and calibrated to obtain the calibrated aluminum alloy; the calibrated aluminum alloy is punched and trimmed to obtain the formed aluminum alloy.

2. The process according to claim 1, characterized in that, The step of predicting the material data of the aluminum alloy to be processed based on the experimental data of the aluminum alloy to be processed includes: querying the experimental data of the aluminum alloy to be processed in a pre-established aluminum alloy material database based on the basic information of the selected aluminum alloy to be processed; wherein, the aluminum alloy material database includes basic information, physicochemical properties, mechanical properties, processing performance, surface treatment performance, and corrosion resistance information of the aluminum alloy material; inputting the experimental data of the aluminum alloy to be processed into a nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed; wherein, the nonlinear elastoplastic model is obtained by training a deep learning algorithm based on training data; the training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data of the experimental aluminum alloy; the simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data corresponding to the experimental aluminum alloy.

3. The process according to claim 1, characterized in that, Before performing weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data, the process further includes: calculating the difference between the first compensation data and the second compensation data; if the difference is within a preset difference threshold, then performing weighted fusion based on the first compensation data and the second compensation data to obtain the target compensation data; if the difference is greater than the preset difference threshold, then analyzing the cause of the difference according to preset analysis steps, and recalculating the first compensation data and / or the second compensation data based on the cause of the difference.

4. The process according to any one of claims 1-3, characterized in that, The lubricant comprises water-based synthetic ester, nano-graphite, and sulfurized isobutylene.

5. The process according to claim 4, characterized in that, The step of determining the coating thickness of the lubricant based on the composition of the lubricant, the inner surface structure of the stamping die, and the material data of the aluminum alloy to be processed includes: determining the frictional force between the aluminum alloy to be processed and the stamping die when the lubricant is coated with different thicknesses; determining the springback effect of different frictional forces on the aluminum alloy to be processed; and determining the target frictional force and the corresponding coating thickness of the lubricant based on the springback effect.

6. The process according to any one of claims 1-3, characterized in that, After the calibrated aluminum alloy is punched and trimmed to obtain the shaped aluminum alloy, the process further includes: performing a quality inspection on the shaped aluminum alloy to determine the dimensional accuracy, surface defects, grain size, and heat treatment effect of the shaped aluminum alloy.

7. A method for designing aluminum alloy molds, characterized in that, The method includes: using simulation software to simulate and predict the material data of the aluminum alloy to be processed; the material data includes material flow, springback, and stress distribution data; based on the material data of the aluminum alloy to be processed, simulating and predicting the mold surface for springback compensation to manufacture a stamping die, including: using finite element analysis software to create a three-dimensional model of the mold and the aluminum alloy to be processed based on the material data of the aluminum alloy to be processed, and performing simulation and prediction to obtain first compensation data for the first mold surface for springback compensation; inputting the material data of the aluminum alloy to be processed and the initial modeled mold into the springback compensation model to obtain second compensation data for the second mold surface for springback compensation; wherein, the springback compensation model is trained based on experimental data of the experimental aluminum alloy, the modeled mold corresponding to the experimental aluminum alloy, and the simulated material data corresponding to the experimental data; performing weighted fusion of the first compensation data and the second compensation data to obtain target compensation data; designing springback compensation for the initial modeled mold based on the target compensation data, and manufacturing a stamping die.

8. The method according to claim 7, characterized in that, The method of using simulation software to predict the material data of the aluminum alloy to be processed includes: conducting tensile tests on the aluminum alloy to be processed to obtain its mechanical property parameters, including elastic modulus, yield strength, and hardening index; using a strain measurement system to obtain deformation data of the aluminum alloy to be processed during the actual stamping process; using the mechanical property parameters and the deformation data as experimental data of the aluminum alloy to be processed; inputting the experimental data of the aluminum alloy to be processed into a nonlinear elastoplastic model to obtain the predicted material data of the aluminum alloy to be processed; wherein, the nonlinear elastoplastic model is obtained by training a deep learning algorithm based on training data; the training data includes historical aluminum alloy experimental data and corresponding historical material data, as well as experimental data and corresponding simulated material data of the experimental aluminum alloy; the simulated material data is obtained by simulating the stamping process of the experimental aluminum alloy using finite element simulation software based on the experimental data corresponding to the experimental aluminum alloy.

Images