Neutral layer position positioning method during metal plate bending and unfolding calculation

Abstract

The invention relates to a method for positioning the position of a neutral layer during metal plate bending and unfolding calculation, and belongs to the technical field of metal plate bending processes. The method for positioning the position of the neutral layer during bending and unfolding calculation of the metal plate comprises the steps of performing a metal plate bending simulation test, establishing a metal plate bending simulation database and training a neutral layer position coefficient model. According to the method, through a metal plate bending simulation test, the bending process under various machining conditions is accurately simulated, and the reliability of neutral layer position data is improved; by constructing a database containing various materials and process conditions, rich data is provided for subsequent model training; through model analysis, the position of the neutral layer can be accurately predicted, and the practicability and adaptability of the neutral layer positioning method are enhanced. In conclusion, the problem that the position randomness of the neutral layer is large in the metal plate bending process can be effectively solved, and the positioning precision and reliability of the neutral layer are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of metal sheet bending technology, and in particular relates to a method for locating a neutral layer position during metal sheet bending and expansion calculation. Background Art

[0002] During the bending process of metal sheets, there is a layer that is neither stretched nor compressed, which is called the neutral layer of the metal. The neutral layer is the basis for the calculation of the bending and unfolding of metal sheets. A large number of studies have shown that during the bending process of metal sheets, the neutral layer migration problem will occur due to the thinning of the sheet thickness.

[0003] In the prior art, some scholars have proposed a formula for calculating the neutral layer. By calculating the neutral layer position coefficient, it is believed that the neutral layer position is related to the thinning coefficient of the metal material, the inner diameter of the bend, and the thickness of the plate before bending, which reveals the law of neutral layer migration to a certain extent. However, the data of the neutral layer position located by this method is relatively random, and the influencing factors considered are relatively simple. It is unknown whether this theoretical formula can still be used as a production guide for plates with different material properties under different processing conditions.

[0004] Therefore, how to provide a method for locating the neutral layer during the bending and unfolding calculation of metal sheets is a technical problem that urgently needs to be solved. Summary of the invention

[0005] In view of the shortcomings in the prior art, the present invention provides a method for locating the neutral layer during the bending and unfolding calculation of metal plates, which can effectively solve the problem of high randomness of the neutral layer position during the bending process of metal plates and improve the accuracy and reliability of neutral layer positioning.

[0006] The present invention provides a method for locating the neutral layer position during bending and unfolding calculation of a metal sheet, comprising the following steps:

[0007] Conduct metal sheet bending simulation test: Use simulation software to conduct metal sheet bending simulation test with different material properties, different process parameters, and different size parameters. Make several planes perpendicular to the thickness direction of the metal sheet, divide the metal sheet into layers along the planes, calculate the length of each layer in the bending process, take the layer with the length closest to the original length as the neutral layer, and record the simulation test results;

[0008] Establish a metal sheet bending simulation database: perform parameterized processing on the simulation test, obtain the neutral layer position coefficient based on the simulation test results, perform sampling and parameterized simulation again, and repeat this cycle; establish a metal sheet bending simulation database based on the material properties, process parameters, dimensional parameters and simulation results of the metal sheet;

[0009] Training the neutral layer position coefficient model: Analyze the data in the database, obtain the main influencing factors of material properties, process parameters, and dimensional parameters, select the main influencing factors for model training, and obtain the neutral layer position coefficient model.

[0010] This technical solution can effectively solve the problem of large randomness of the neutral layer position during the bending process of metal plates, and improve the accuracy and reliability of neutral layer positioning.

[0011] In some of the embodiments, in the step of performing a metal sheet bending simulation test, the method for calculating the length of each layer during the bending process is as follows: a rectangular coordinate system is established with a vertex of the metal sheet as the origin, the side passing through the vertex in the plate length direction as the x-axis, and the side passing through the vertex in the plate thickness direction as the y-axis, and the metal sheet is gridded along the directions parallel to the x-axis and the y-axis to obtain n grid points; during the bending process, the horizontal coordinate of the i-th grid point at time t is recorded as x i , the vertical coordinate is y i ; Let the horizontal coordinate of the i+1th grid point at time t be x i+1 , the vertical coordinate is y i+1 ; According to formula (1), calculate the length L of the plate at the layer where the i-th grid point is located at time t during the bending process t , the expression of formula (1) is:

[0012]

[0013] This technical solution uses a rectangular coordinate system and a grid division method to accurately calculate the changes of each grid point during the bending process.

[0014] In some embodiments, the step of performing the metal sheet bending simulation test also includes recording the thickness change of the sheet during the bending process, and calculating the sheet thickness T at time t during the bending process according to formula (2): t , the expression of formula (2) is:

[0015] T t =|y max -y min |(2);

[0016] In formula (2), y max is the ordinate of the innermost layer of the metal sheet at time t during the bending process, y min It is the ordinate of the outermost layer of the metal sheet at time t during the bending process.

[0017] This technical solution effectively improves the accuracy and reliability of the simulation test by recording the change in plate thickness during the bending process and calculating the plate thickness using formula (2).

[0018] In some of the embodiments, in the step of performing a metal sheet bending simulation test, the simulation test results are saved in the form of an ODB file; in the step of establishing a metal sheet bending simulation database, the ODB file is post-processed and calculated to obtain the neutral layer position coefficient.

[0019] In some embodiments, in the step of performing a metal sheet bending simulation test, the material properties include the elastic modulus and yield strength of the metal sheet, the process parameters include the angular velocity of the bending machine and the friction coefficient between the bending machine and the metal sheet, and the dimensional parameters include the bending radius and the sheet thickness. This technical solution can comprehensively consider the influence of different factors on the bending effect and improve the accuracy of the simulation test.

[0020] In some embodiments, in the step of training the neutral layer position coefficient model, the elastic modulus of the metal sheet, the yield strength of the metal sheet, the angular velocity of the bending machine, the friction coefficient between the bending machine and the metal sheet, the bending radius, and the thickness of the sheet are used as influencing factors of the change of the neutral layer position during the bending process of the metal sheet, and each influencing factor is analyzed to obtain the main influencing factors of the change of the neutral layer position during the bending process of the metal sheet. This technical solution can ensure the effectiveness and applicability of the model.

[0021] In some embodiments, the method for analyzing each influencing factor includes: calculating the Pareto value of each influencing factor and performing a single factor analysis on each influencing factor. This technical solution accurately evaluates the impact of each factor on the neutral layer position by calculating the Pareto value of each influencing factor and performing a single factor analysis.

[0022] In some embodiments, training the neutral layer position coefficient model further includes: optimizing the parameters of the neutral layer position coefficient model so that the optimized model evaluation index satisfies MAE<0.03 and RMSE<0.05. This technical solution ensures the high accuracy and reliability of the model.

[0023] Based on the above scheme, the method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet in the embodiment of the present invention improves the reliability of the neutral layer position data by conducting a metal sheet bending simulation test, accurately simulating the bending process under various processing conditions; by constructing a database containing a variety of materials and process conditions, it provides rich data for subsequent model training; through model analysis, it can accurately predict the neutral layer position, enhancing the practicality and adaptability of the neutral layer positioning method. In summary, this embodiment can effectively solve the problem of large randomness of the neutral layer position during the bending process of the metal sheet, and improve the accuracy and reliability of the neutral layer positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 It is a flow chart of the method for locating the position of the neutral layer during the bending and unfolding calculation of the metal sheet of the present invention;

[0026] Figure 2 The 4 galvanized sheet materials selected in Example 1;

[0027] Figure 3 A schematic diagram of mesh division of one of the metal plates in Example 1;

[0028] Figure 4 is the Pareto value of each influencing factor in Example 1;

[0029] Figure 5 This is an analysis diagram of the influence of plate thickness T on the neutral layer position coefficient in Example 1;

[0030] Figure 6 This is an analysis diagram of the influence of the angular velocity ω of the bending machine on the neutral layer position coefficient in Example 1;

[0031] Figure 7 This is the analysis diagram of the influence of bending radius R on the neutral layer position coefficient;

[0032] Figure 8 is the yield strength of the metal sheet σ s Analysis diagram of the influence on the neutral layer position coefficient;

[0033] Fig. 9 This is the analysis diagram of the influence of the friction coefficient μ between the bending machine and the metal sheet on the neutral layer position coefficient;

[0034] Fig.10 This is an analysis diagram of the influence of the elastic modulus E of the metal sheet on the neutral layer position coefficient. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0036] In the description of the present invention, it should be understood that the terms "center", "lateral", "longitudinal", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0037] like Figure 1 As shown, in one embodiment of the method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet of the present invention, the method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet includes the steps of performing a metal sheet bending simulation test, establishing a metal sheet bending simulation database, and training a neutral layer position coefficient model; wherein the step of performing a metal sheet bending simulation test includes: using simulation software to perform a metal sheet bending simulation test with different material properties, different process parameters, and different size parameters, making a plurality of planes perpendicular to the thickness direction of the metal sheet, dividing the metal sheet into layers along the planes, calculating the length of each layer during the bending process, and placing the layer closest to the original The layer with the longest layer length is taken as the neutral layer, and the simulation test results are recorded; the steps of establishing a metal sheet bending simulation database include: parameterizing the simulation test, and obtaining the neutral layer position coefficient according to the simulation test results, and sampling and parameterized simulation are performed again, and this cycle is repeated; according to the material properties, process parameters, dimensional parameters and simulation results of the metal sheet, a metal sheet bending simulation database is established; the steps of training the neutral layer position coefficient model include: analyzing the data in the database, obtaining the main influencing factors in the material properties, process parameters and dimensional parameters, selecting the main influencing factors for model training, and obtaining the neutral layer position coefficient model.

[0038] In the above-mentioned exemplary embodiment, the method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet accurately simulates the bending process under various processing conditions by conducting a metal sheet bending simulation test, thereby improving the reliability of the neutral layer position data; by constructing a database containing a variety of materials and process conditions, it provides rich data for subsequent model training; through model analysis, the neutral layer position can be accurately predicted, thereby enhancing the practicality and adaptability of the neutral layer positioning method. In summary, this embodiment can effectively solve the problem of large randomness of the neutral layer position during the bending process of the metal sheet, and improve the accuracy and reliability of the neutral layer positioning.

[0039] In some embodiments, in the step of performing a metal sheet bending simulation test, the method for calculating the length of each layer during the bending process is as follows: a rectangular coordinate system is established with a vertex of the metal sheet as the origin, the side passing through the vertex along the length direction of the sheet as the x-axis, and the side passing through the vertex along the thickness direction as the y-axis, and the metal sheet is meshed along the directions parallel to the x-axis and the y-axis to obtain n mesh points; during the bending process, the horizontal coordinate of the i-th mesh point at time t is recorded as x i , the vertical coordinate is y i ; Let the horizontal coordinate of the i+1th grid point at time t be x i+1 , the vertical coordinate is y i+1 ; According to formula (1), calculate the length L of the plate at the layer where the i-th grid point is located at time t during the bending process t , the expression of formula (1) is:

[0040]

[0041] This embodiment uses a rectangular coordinate system and a grid division method to accurately calculate the changes of each grid point during the bending process.

[0042] Furthermore, the metal sheet bending simulation test step also includes recording the thickness change of the sheet during the bending process, and calculating the sheet thickness T at time t during the bending process according to formula (2): t , the expression of formula (2) is:

[0043] T t =|y max -y min |(2);

[0044] In formula (2), y max is the ordinate of the innermost layer of the metal sheet at time t during the bending process, y min It is the ordinate of the outermost layer of the metal sheet at time t during the bending process.

[0045] This embodiment records the change in plate thickness during the bending process and uses formula (2) to calculate the plate thickness, thereby effectively improving the accuracy and reliability of the simulation test and providing important data support for the precise positioning of the neutral layer.

[0046] In some embodiments, in the step of performing a metal sheet bending simulation test, the simulation test results are saved in the form of an ODB file; in the step of establishing a metal sheet bending simulation database, the ODB file is post-processed and calculated to obtain a neutral layer position coefficient.

[0047] In some embodiments, in the step of performing a metal sheet bending simulation test, the material properties include the elastic modulus and yield strength of the metal sheet, the process parameters include the angular velocity of the bending machine and the friction coefficient between the bending machine and the metal sheet, and the dimensional parameters include the bending radius and the thickness of the sheet. In the simulation test, the influence of different factors on the bending effect is comprehensively considered by combining the material properties (elastic modulus and yield strength), process parameters (angular velocity of the bending machine and friction coefficient) and dimensional parameters (bending radius and sheet thickness), so as to improve the accuracy of the simulation test.

[0048] In some embodiments, in the step of training the neutral layer position coefficient model, the elastic modulus of the metal sheet, the yield strength of the metal sheet, the angular velocity of the bending machine, the friction coefficient between the bending machine and the metal sheet, the bending radius, and the thickness of the sheet are used as influencing factors of the change of the neutral layer position during the bending process of the metal sheet, and each influencing factor is analyzed to obtain the main influencing factors of the change of the neutral layer position during the bending process of the metal sheet. In the step of training the model, the elastic modulus, yield strength, angular velocity of the bending machine, friction coefficient, bending radius, and thickness of the metal sheet are selected to analyze and determine the main influencing factors to ensure the effectiveness and applicability of the model.

[0049] In some embodiments, the method for analyzing each influencing factor includes: calculating the Pareto value of each influencing factor and performing a single factor analysis on each influencing factor. By calculating the Pareto value of each influencing factor and performing a single factor analysis, the influence of each factor on the neutral layer position is accurately evaluated, and the prediction ability of the model is optimized.

[0050] In some embodiments, training the neutral layer position coefficient model further includes: optimizing parameters of the neutral layer position coefficient model so that the optimized model evaluation index satisfies MAE<0.03 and RMSE<0.05 to ensure high accuracy and reliability of the model.

[0051] Example 1

[0052] Combine the following Figure 1-Figure 10 The specific structure and working process of an embodiment of the method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet of the present invention are described as follows:

[0053] 1) Conduct metal sheet bending simulation test

[0054] Using simulation software, metal sheet bending simulation tests with different material properties, different process parameters, and different size parameters are conducted. Several planes are made perpendicular to the thickness direction of the metal sheet, and the metal sheet is layered along the planes. The length of each layer during the bending process is calculated, and the layer with the length closest to the original length is taken as the neutral layer. The thickness change during the bending process is recorded, and the simulation test results are recorded. The simulation test results are saved in the form of an ODB file. In this embodiment, Figure 2 As shown, four galvanized sheet materials are selected for simulation experiments, and the material properties of the four materials are shown in Table 1.

[0055] Table 1 Properties of four galvanized sheet materials in the simulation test of Example 1

[0056]

[0057] In this step, the method for calculating the length of each layer in the bending process is as follows: a rectangular coordinate system is established with a vertex of the metal sheet as the origin, the side passing through the vertex in the length direction of the sheet as the x-axis, and the side passing through the vertex in the thickness direction as the y-axis, and the metal sheet is meshed along the directions parallel to the x-axis and the y-axis to obtain n mesh points; during the bending process, the horizontal coordinate of the i-th mesh point at time t is recorded as x i , the vertical coordinate is y i ; Let the horizontal coordinate of the i+1th grid point at time t be x i+1 , the vertical coordinate is y i+1 ; According to formula (1), calculate the length L of the plate at the layer where the i-th grid point is located at time t during the bending process t , the expression of formula (1) is:

[0058]

[0059] In this embodiment, Figure 3 As shown, a layer is divided every 0.02 mm perpendicular to the plate thickness direction, and a layer is divided every 0.02 mm perpendicular to the plate length direction. It should be noted that Figure 3 The meshing along the direction perpendicular to the length of the plate only shows the meshing of the main bending area.

[0060] In this step, the plate thickness T at time t during the bending process is calculated according to formula (2): t , the expression of formula (2) is:

[0061] T t =|y max -y min |(2);

[0062] In formula (2), y max is the ordinate of the innermost layer of the metal sheet at time t during the bending process, y minis the ordinate of the outermost layer of the metal sheet at time t during the bending process; in this embodiment, y max is the ordinate of point No.3, y min is the vertical coordinate of point No.6.

[0063] It should be noted that the material properties include the elastic modulus E and yield strength σ of the metal sheet. s The process parameters include the angular velocity ω of the bending machine and the friction coefficient μ between the bending machine and the metal sheet, and the dimensional parameters include the bending radius R and the sheet thickness T.

[0064] 2) Establish a metal sheet bending simulation database

[0065] The simulation test is parameterized, and according to the simulation test results, the ODB file is post-processed to calculate the neutral layer position coefficient, and sampling and parameterized simulation are performed again, and this cycle is repeated; according to the material properties, process parameters, size parameters and simulation results of the metal sheet, a metal sheet bending simulation database is established. Table 2 shows some test data of the parameterized simulation in this embodiment.

[0066] Table 2 Partial experimental data of parameterized simulation in Example 1

[0067]

[0068]

[0069] 3) Training the neutral layer position coefficient model

[0070] Analyze the data in the database to obtain the main influencing factors of material properties, process parameters, and dimensional parameters, select the main influencing factors for model training, and obtain the neutral layer position coefficient model; optimize the parameters of the neutral layer position coefficient model so that the evaluation indicators of the optimized model meet MAE<0.03 and RMSE<0.05.

[0071] In this step, the elastic modulus of the metal sheet, the yield strength of the metal sheet, the angular velocity of the bending machine, the friction coefficient between the bending machine and the metal sheet, the bending radius, and the thickness of the sheet are used as influencing factors of the change in the position of the neutral layer during the bending process of the metal sheet, and each influencing factor is analyzed to obtain the main influencing factors of the change in the position of the neutral layer during the bending process of the metal sheet. The method for analyzing each influencing factor includes: calculating the Pareto value of each influencing factor, and performing single factor analysis on each influencing factor.

[0072] In Example 1, Figure 4 As shown, by calculating the Pareto value of each influencing factor, it can be seen that the plate thickness, the angular velocity of the bending machine and the bending radius have a greater influence on the neutral layer position coefficient.

[0073] The analysis diagram obtained by univariate analysis is as follows Figure 5-10 As shown,

[0074] Figure 5 The figure shows the influence of plate thickness T on the neutral layer position coefficient. The horizontal axis is the plate thickness value, and the vertical axis is the radius of the neutral layer. It can be seen that the neutral layer of the plate will gradually shift from the outer layer to the inner layer as the plate thickness increases, and the speed of change is from fast to slow. This may be because during the bending process of thicker plates, the inner side, i.e. the compression side, is more likely to produce larger plastic deformation, which causes the neutral layer to migrate inward.

[0075] Figure 6 The figure shows the influence of the angular velocity ω of the bending machine on the position coefficient of the neutral layer. The horizontal axis is the angular velocity value of the bending machine, and the vertical axis is the radius of the neutral layer. It shows that the influence of the angular velocity of the lower die on the neutral layer is consistent with the trend of the plate thickness, but the speed of change is from slow to fast. This may be because the larger angular velocity intensifies the compression of the inner side of the plate, resulting in the faster the angular velocity, the more the neutral layer migrates inward.

[0076] Figure 7 The figure shows the influence of the bending radius R on the neutral layer position coefficient. The horizontal axis is the bending radius value, and the vertical axis is the radius of the neutral layer. It can be seen that the bending radius shows that the neutral layer migrates from the inside to the outside first, and then from the outside to the inside. When the bending radius is about 20mm, the migration of the neutral layer reaches a peak in the outer layer. When the bending radius is smaller, the neutral layer migrates inward, which may be due to the smaller curvature causing the inner compressive strain to be greater. As the bending radius increases, the curvature decreases, the strain difference between the inside and the outside decreases, and the neutral layer migrates outward. However, when the bending radius continues to increase to a certain extent, the neutral layer begins to migrate inward again, which may be because the bending degree becomes weaker and the compression and tension effects are balanced.

[0077] Figure 8 is the yield strength of the metal sheet σ s The influence on the neutral layer position coefficient, the horizontal axis is the yield strength value, and the vertical axis is the radius of the neutral layer. It can be seen that the influence of yield strength on the migration of the neutral layer is not significant, the change trend is relatively gentle, and the neutral layer generally migrates to the outer layer.

[0078] Fig. 9 This is the influence of the friction coefficient μ between the bending machine and the metal sheet on the neutral layer position coefficient. The horizontal axis is the friction coefficient value, and the vertical axis is the radius of the neutral layer. It can be seen that the friction coefficient has a small influence trend, the change trend is relatively gentle, and the influence on the migration amount of the neutral layer shows a decreasing trend.

[0079] Fig.10This is the influence of the elastic modulus E of the metal sheet on the position coefficient of the neutral layer. The horizontal axis is the elastic modulus value, and the vertical axis is the radius of the neutral layer. It can be seen that the influence of the elastic modulus on the neutral layer is consistent with the friction coefficient.

[0080] Depend on Figure 5-10 It can be seen that the thickness of the plate, the angular velocity of the bending machine and the bending radius have a more obvious influence on the neutral layer position coefficient, accounting for 87%. Therefore, the thickness of the plate, the angular velocity of the bending machine and the bending radius are used as the main influencing factors for model training.

[0081] Through the description of multiple embodiments of the method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet of the present invention, it can be seen that the embodiment of the method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet of the present invention has at least one or more of the following advantages:

[0082] 1. The method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet provided by the present invention can accurately simulate the bending process under various processing conditions by conducting a metal sheet bending simulation test, thereby improving the reliability of the neutral layer position data;

[0083] 2. The method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet provided by the present invention provides rich data for subsequent model training by constructing a database containing a variety of materials and process conditions;

[0084] 3. The neutral layer position positioning method during the bending and unfolding calculation of the metal plate provided by the present invention can accurately predict the neutral layer position through model analysis, thereby enhancing the practicality and adaptability of the neutral layer positioning method.

[0085] Finally, it should be noted that: the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0086] The above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or some technical features can be replaced by equivalents without departing from the spirit of the technical solution of the present invention, which should be included in the scope of the technical solution for protection of the present invention.

Claims

1. A method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet, characterized in that: The following steps are involved: Conduct metal sheet bending simulation test: Use simulation software to conduct metal sheet bending simulation test with different material properties, different process parameters, and different size parameters. Make several planes perpendicular to the thickness direction of the metal sheet, divide the metal sheet into layers along the planes, calculate the length of each layer in the bending process, take the layer with the length closest to the original length as the neutral layer, and record the simulation test results; Establish a metal sheet bending simulation database: perform parameterized processing on the simulation test, obtain the neutral layer position coefficient based on the simulation test results, perform sampling and parameterized simulation again, and repeat this cycle; establish a metal sheet bending simulation database based on the material properties, process parameters, dimensional parameters and simulation results of the metal sheet; Training the neutral layer position coefficient model: Analyze the data in the database, obtain the main influencing factors of material properties, process parameters, and dimensional parameters, select the main influencing factors for model training, and obtain the neutral layer position coefficient model.

2. The method for locating the neutral layer position during the bending and unfolding calculation of metal sheet according to claim 1 is characterized in that: In the metal sheet bending simulation test step, the method for calculating the length of each layer in the bending process is as follows: a rectangular coordinate system is established with a vertex of the metal sheet as the origin, the side passing through the vertex in the length direction of the sheet as the x-axis, and the side passing through the vertex in the thickness direction as the y-axis, and the metal sheet is meshed along the directions parallel to the x-axis and the y-axis to obtain n grid points; during the bending process, the horizontal coordinate of the i-th grid point at time t is recorded as x i , the vertical coordinate is y i ; Let the horizontal coordinate of the i+1th grid point at time t be x i+1 , the vertical coordinate is y i+1 ; According to formula (1), calculate the length L of the plate at the layer where the i-th grid point is located at time t during the bending process t , the expression of formula (1) is:

3. The method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet according to claim 2 is characterized in that: The metal sheet bending simulation test steps also include recording the thickness change of the sheet during the bending process, and calculating the sheet thickness T at time t during the bending process according to formula (2): t , the expression of formula (2) is: T t =|and max -and min |(2); In formula (2), y max is the ordinate of the innermost layer of the metal sheet at time t during the bending process, y min It is the ordinate of the outermost layer of the metal sheet at time t during the bending process.

4. The method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet according to claim 1, characterized in that: In the step of performing a metal sheet bending simulation test, the simulation test results are saved in the form of an ODB file; in the step of establishing a metal sheet bending simulation database, the ODB file is post-processed and calculated to obtain a neutral layer position coefficient.

5. The method for locating the neutral layer position during the bending and unfolding calculation of metal sheet according to claim 1, characterized in that: In the metal sheet bending simulation test steps, the material properties include the elastic modulus and yield strength of the metal sheet, the process parameters include the angular velocity of the bending machine and the friction coefficient between the bending machine and the metal sheet, and the dimensional parameters include the bending radius and the sheet thickness.

6. The method for locating the neutral layer position during the bending and unfolding calculation of the metal sheet according to claim 5, characterized in that: In the step of training the neutral layer position coefficient model, the elastic modulus of the metal sheet, the yield strength of the metal sheet, the angular velocity of the bending machine, the friction coefficient between the bending machine and the metal sheet, the bending radius, and the thickness of the sheet are taken as influencing factors of the change of the neutral layer position during the bending process of the metal sheet, and each influencing factor is analyzed to obtain the main influencing factors of the change of the neutral layer position during the bending process of the metal sheet.

7. The method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet according to claim 6, characterized in that: The analysis method for each influencing factor includes: calculating the Pareto value of each influencing factor and performing single factor analysis on each influencing factor.

8. The method for locating the neutral layer position during the bending and unfolding calculation of a metal sheet according to claim 6, characterized in that: Training the neutral layer position coefficient model also includes: optimizing parameters of the neutral layer position coefficient model so that evaluation indicators of the optimized model meet MAE<0.03 and RMSE<0.05.

Images