A forging simulation method and related device

Abstract

The present invention discloses a forging simulation method and related devices, which relate to the field of forging technology. Obtain the current forging simulation parameters, input the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result, and the forging simulation model is constructed by a neural network learning the relationship between the forging simulation parameters and the standardized forging interpolation result. Among them, the standardized forging interpolation result is obtained after interpolating the forging simulation result. This application adopts a flexible interpolation method to process the forging simulation result, which can not only ensure the consistency of the forging simulation result and the standardized forging interpolation result before and after interpolation, but also meet the fixed format requirements of the fixed-length output of the neural network. Utilizing the fast prediction ability of the neural network, when applying the forging simulation model to process the current forging simulation parameters, the time for generating the forging simulation result can be greatly shortened, so as to meet the rapid prediction requirement for the forging simulation result.

Description

Technical Field

[0001] The present invention relates to the technical field of forging and pressing, and more specifically, to a forging and pressing simulation method and related devices. Background Art

[0002] In the forging and pressing forming process, the blank undergoes complex deformations under the action of external forces to form a target shape and meet specific mechanical property requirements. However, the non-linear material behavior, large deformations, and complex contact conditions involved in the forging and pressing process make the process design and optimization difficult. To accurately predict the deformation behavior and stress distribution during forging and pressing, numerical simulation (such as the finite element method) has become an indispensable tool. Numerical simulation can visually display the deformation process by simulating process parameters (such as blank geometric dimensions, material properties, and load conditions), and provide a reliable basis for tool design, defect prevention, and process optimization.

[0003] In forging and pressing simulation, the finite element method (FEM) is a classic and commonly used numerical solution method. The main processes include inputting the geometric dimensions and material properties of the blank, mesh generation, numerical solution, and subsequent result processing. However, since the number of mesh nodes in forging and pressing simulation changes dynamically with the deformation of the blank, each solution requires a large amount of time, resulting in a long time and low efficiency for forging and pressing simulation, and it is difficult to meet the need for rapid prediction based on the forging and pressing simulation results. Summary of the Invention

[0004] In view of this, the present invention discloses a forging and pressing simulation method and related devices to shorten the time for generating forging and pressing simulation results, improve the forging and pressing simulation efficiency, and meet the need for rapid prediction based on the forging and pressing simulation results.

[0005] A forging and pressing simulation method includes:

[0006] Obtain current forging and pressing simulation parameters;

[0007] Input the current forging and pressing simulation parameters into a pre-trained forging and pressing simulation model to obtain a forging and pressing simulation result, where the forging and pressing simulation model is obtained by using a neural network to learn the correspondence between forging and pressing simulation parameters and the standardized forging and pressing interpolation results obtained by using an interpolation method.

[0008] Optionally, the training process of the forging and pressing simulation model includes:

[0009] Determine the number of horizontal distribution points in the horizontal direction and the number of vertical distribution points in the vertical direction of the forging and pressing simulation result, where the number of horizontal distribution points and the number of vertical distribution points determine the resolution of the interpolation grid;

[0010] Batch obtain the finite element solutions obtained by processing the forging simulation parameters using the finite element method;

[0011] For each of the finite element solutions, obtain all the corresponding boundary points;

[0012] Connect all the boundary points in sequence to form a polygonal curve as the boundary of the interpolation region;

[0013] Based on the horizontal number of layout points and the vertical number of layout points, determine each interpolation point on and inside the polygonal curve;

[0014] Perform interpolation at the positions of each of the interpolation points using a preset interpolation function to obtain the standardized forging interpolation result;

[0015] Use the forging simulation parameters as training samples and the corresponding standardized forging interpolation results of the forging simulation parameters as sample labels to train a neural network to obtain the forging simulation model.

[0016] Optionally, the determining each interpolation point on and inside the polygonal curve based on the horizontal number of layout points and the vertical number of layout points includes:

[0017] Determine the interpolation point abscissa vector;

[0018] Based on each interpolation point abscissa in the interpolation point abscissa vector and the vertical number of layout points, determine the corresponding interpolation point ordinate;

[0019] Based on each interpolation point abscissa and a corresponding interpolation point ordinate, determine an interpolation point to obtain each interpolation point on and inside the polygonal curve.

[0020] Optionally, the process of determining the interpolation point abscissa vector includes:

[0021] Determine the maximum interpolation point abscissa and the minimum interpolation point abscissa of the polygonal curve in the horizontal direction;

[0022] According to the maximum interpolation point abscissa, the minimum interpolation point abscissa and the horizontal number of layout points, determine the distance between adjacent interpolation points to obtain the interpolation point abscissas corresponding to each interpolation point in the horizontal direction;

[0023] Based on all the interpolation point abscissas, obtain the interpolation point abscissa vector.

[0024] Optionally, the determining the corresponding interpolation point ordinate based on each interpolation point abscissa in the interpolation point abscissa vector and the vertical number of layout points includes:

[0025] Determine the intersection points of each abscissa of the interpolation point abscissa vector with the vertical axis of the polygon curve;

[0026] Based on the number of vertical axis intersection points included in the vertical axis intersection point vector and in combination with the number of vertical layout points, determine the number of interpolation points between adjacent intersection points;

[0027] Based on the number of interpolation points, determine the ordinates of each interpolation point.

[0028] Optionally, the step of based on the number of vertical axis intersection points included in the vertical axis intersection point vector and in combination with the number of vertical layout points, determining the number of interpolation points between adjacent intersection points includes:

[0029] Determine the total number of regions formed by adjacent intersection points in the vertical axis intersection point vector;

[0030] Allocate the number of vertical layout points according to the total number of regions to obtain the number of interpolation points between adjacent intersection points.

[0031] Optionally, the step of based on the number of vertical axis intersection points included in the vertical axis intersection point vector and in combination with the number of vertical layout points, determining the number of interpolation points between adjacent intersection points includes:

[0032] Determine the distances between adjacent intersection points in the vertical axis intersection point vector;

[0033] Allocate the number of vertical layout points according to each of the distances to obtain the number of interpolation points between adjacent intersection points.

[0034] Optionally, the step of based on the number of horizontal layout points and the number of vertical layout points, determining each interpolation point on and inside the polygon curve includes:

[0035] Determine the interpolation point ordinate vector;

[0036] Based on each interpolation point ordinate in the interpolation point ordinate vector and the number of horizontal layout points, determine the corresponding interpolation point abscissa;

[0037] Based on each interpolation point ordinate and a corresponding interpolation point abscissa, determine an interpolation point to obtain each interpolation point on and inside the polygon curve.

[0038] Optionally, the process of determining the interpolation point ordinate vector includes:

[0039] Determine the maximum interpolation point ordinate and the minimum interpolation point ordinate of the polygon curve in the vertical direction;

[0040] Determine the distance between two adjacent interpolation points according to the vertical coordinate of the maximum interpolation point, the vertical coordinate of the minimum interpolation point, and the number of vertical layout points, so as to obtain the vertical coordinate of each interpolation point corresponding to the vertical direction;

[0041] Based on all the vertical coordinates of the interpolation points, obtain the interpolation point vertical coordinate vector.

[0042] Optionally, the determining the corresponding interpolation point abscissa based on each interpolation point vertical coordinate in the interpolation point vertical coordinate vector and the number of horizontal layout points includes:

[0043] Determine the abscissa intersection point vector of the horizontal axis of the polygon curve for each interpolation point vertical coordinate in the interpolation point vertical coordinate vector;

[0044] Based on the number of intersection points included in the abscissa intersection point vector and in combination with the number of horizontal layout points, determine the number of interpolation points between adjacent intersection points;

[0045] Based on the number of interpolation points, determine the abscissa of each interpolation point.

[0046] Optionally, the determining the number of interpolation points between adjacent intersection points based on the number of intersection points included in the abscissa intersection point vector and in combination with the number of horizontal layout points includes:

[0047] Determine the total number of regions formed by adjacent intersection points in the abscissa intersection point vector;

[0048] Allocate the number of horizontal layout points according to the total number of regions, so as to obtain the number of interpolation points between adjacent intersection points.

[0049] Optionally, the determining the number of interpolation points between adjacent intersection points based on the number of intersection points included in the abscissa intersection point vector and in combination with the number of horizontal layout points includes:

[0050] Determine the distance between each adjacent intersection point in the abscissa intersection point vector;

[0051] Allocate the number of horizontal layout points according to each distance, so as to obtain the number of interpolation points between adjacent intersection points.

[0052] A forging simulation device includes:

[0053] A parameter acquisition unit, configured to acquire current forging simulation parameters;

[0054] A simulation unit, configured to input the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result, wherein the forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and a standardized forging interpolation result obtained by using an interpolation method.

[0055] A computer storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, any of the above forging simulation methods is implemented.

[0056] An electronic device includes: a memory and a processor;

[0057] The memory is used to store at least one instruction;

[0058] The processor is used to execute the at least one instruction to implement any of the above forging simulation methods.

[0059] As can be seen from the above technical solutions, the present invention discloses a forging simulation method and related devices, obtains current forging simulation parameters, inputs the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result, and the forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and the obtained standardized forging interpolation results by using an interpolation method. The present application uses a flexible interpolation method to process the forging simulation result, which can not only ensure the consistency of the forging simulation result and the standardized forging interpolation result before and after interpolation, but also meet the fixed format requirements of the fixed-length output of the neural network. By using the fast prediction ability of the neural network, when applying the forging simulation model to process the current forging simulation parameters, the time for generating the forging simulation result can be greatly shortened, thereby improving the forging simulation efficiency to meet the need for rapid prediction based on the forging simulation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained according to the disclosed drawings without creative efforts.

[0061] Figure 1 It is a flowchart of a forging simulation method disclosed in an embodiment of the present invention;

[0062] Figure 2 It is a flowchart of a training method for a forging simulation model disclosed in an embodiment of the present invention;

[0063] Figure 3 It is a flowchart of a method for determining each interpolation point on and inside a polygon curve based on the horizontal number of distribution points and the vertical number of distribution points disclosed in an embodiment of the present invention;

[0064] FIG. 4(1) is a schematic diagram of each interpolation point on a polygon curve disclosed in an embodiment of the present invention;

[0065] Figure 4(2) is a schematic diagram of each interpolation point on another polygon curve disclosed in an embodiment of the present invention;

[0066] Figure 5 It is a flowchart of a method for determining each interpolation point on a polygon curve and inside the polygon curve based on the horizontal number of layout points and the vertical number of layout points disclosed in an embodiment of the present invention;

[0067] Figure 6 It is a schematic diagram of each interpolation point on another polygon curve disclosed in an embodiment of the present invention;

[0068] Figure 7 It is a schematic structural diagram of a forging simulation device disclosed in an embodiment of the present invention;

[0069] Figure 8 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. Specific embodiments

[0070] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0071] An embodiment of the present invention discloses a forging simulation method and related device, which obtains current forging simulation parameters and inputs the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result. The forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and standardized forging interpolation results obtained by using an interpolation method. This application uses a flexible interpolation method to process the forging simulation result, which can not only ensure the consistency between the forging simulation result before and after interpolation and the standardized forging interpolation result, but also meet the fixed format requirements of the fixed-length output of the neural network. By using the fast prediction ability of the neural network, when applying the forging simulation model to process the current forging simulation parameters, the time for generating the forging simulation result can be greatly shortened, thereby improving the forging simulation efficiency to meet the requirement of rapid prediction based on the forging simulation result.

[0072] See Figure 1 , a flowchart of a forging simulation method disclosed in an embodiment of the present application, the method includes:

[0073] Step S101, obtain current forging simulation parameters.

[0074] Among them, the current forging simulation parameters mainly include material properties, geometric parameters, boundary conditions, loading conditions, etc.

[0075] Material properties include: yield strength, hardness, tensile strength, etc.

[0076] Geometric parameters include: parameters that directly affect the size and shape of the forging, such as length, width, thickness, etc., and parameters that affect the stress distribution and forming performance of the forging during the forming process, such as cutting width.

[0077] Boundary conditions and loading conditions include:

[0078] Firmware constraint: In the simulation, fixed constraints need to be applied to certain parts to simulate the fixed state in actual production.

[0079] Load application: According to the requirements of the forging process, corresponding loads such as pressure, temperature, etc. are applied.

[0080] Step S102: Input the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result.

[0081] Among them, the forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and the standardized forging interpolation results obtained by using an interpolation method.

[0082] Among them, the number of points included in all the standardized forging interpolation results in this application is the same to meet the fixed-length output requirement of the neural network.

[0083] The main function of the interpolation method is to estimate or predict the values of unknown data points between known data points. In this application, by processing the forging simulation parameters using the interpolation method, it can not only ensure the consistency of the finite element solutions obtained by using the finite element method before and after interpolation, but also meet the fixed format requirement of the fixed-length output of the neural network.

[0084] The prediction ability of the neural network has many advantages such as the ability to handle complex non-linear problems, high-precision prediction, strong generalization ability, strong adaptability, automatic feature extraction, large-scale data processing ability, and the ability to integrate with other machine learning technologies. These advantages enable the neural network to play an important role in the field of predictive analysis. In this application, a forging simulation model is obtained by training the neural network on the forging interpolation results. By using the prediction ability of the neural network, the time for forging simulation can be greatly shortened.

[0085] In summary, the present application discloses a forging simulation method, which obtains current forging simulation parameters and inputs the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result. The forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and standardized forging interpolation results obtained by using an interpolation method. The present application uses a flexible interpolation method to process the forging simulation result, which can not only ensure the consistency between the forging simulation result before and after interpolation and the standardized forging interpolation result, but also meet the fixed format requirements of the fixed-length output of the neural network. By utilizing the fast prediction ability of the neural network, when applying the forging simulation model to process the current forging simulation parameters, the time for generating the forging simulation result can be greatly shortened, thereby improving the forging simulation efficiency to meet the requirement of rapid prediction based on the forging simulation result.

[0086] See Figure 2 , the flowchart of a training method for a forging simulation model disclosed in an embodiment of the present application, the method includes:

[0087] Step S201, determine the number of horizontal distribution points of the forging simulation result in the horizontal direction and the number of vertical distribution points in the vertical direction.

[0088] Before starting interpolation, it is first necessary to determine the number of horizontal distribution points Nx of the forging simulation result in the horizontal direction (x direction) and the number of vertical distribution points Ny in the vertical direction (y direction).

[0089] The number of horizontal distribution points Nx and the number of vertical distribution points Ny determine the resolution of the interpolation grid, that is, how many interpolation points will be generated in the horizontal direction and how many interpolation points will be generated in the vertical direction.

[0090] The values of the number of horizontal distribution points Nx and the number of vertical distribution points Ny can be determined based on the accuracy of the forging simulation result and the computing resources.

[0091] Step S202, batch obtain all boundary points of the finite element solution obtained by processing the forging simulation parameters by using the finite element method.

[0092] The finite element method (FEM) is a numerical method for solving mathematical and physical problems. The basic idea of the finite element method is to discretize the continuous solution domain into a finite number of small elements, which are connected to each other through nodes to form a grid. Based on this, the finite element method solves the physical quantities at the grid nodes, such as displacement and stress, rather than the physical quantities in the entire region. The present application uses the finite element method to solve different forging simulation parameters to obtain different finite element solutions.

[0093] Step S203, for each of the finite element solutions, obtain all corresponding boundary points.

[0094] Step S204: Connect all the boundary points in sequence to form a polygonal curve that serves as the boundary of the interpolation region.

[0095] All the boundary points define the geometric boundary of the interpolation region of interest. In this application, these boundary points are connected in sequence to form a closed polygonal curve, and this polygonal curve represents the boundary of the interpolation region.

[0096] Step S205: Based on the horizontal number of layout points and the vertical number of layout points, determine each interpolation point on and inside the polygonal curve.

[0097] The horizontal number of layout points Nx determines how many interpolation points will be generated in the horizontal direction, and the vertical number of layout points Ny determines how many interpolation points will be generated in the vertical direction. Therefore, each interpolation point on and inside the polygonal curve can be determined based on the horizontal number of layout points Nx and the vertical number of layout points Ny.

[0098] Step S206: Use a preset interpolation function to perform interpolation at the positions of each interpolation point to obtain the standardized forging interpolation result.

[0099] In this application, the preset interpolation function can be any one or a combination of multiple ones among linear interpolation, nearest neighbor interpolation, cubic spline interpolation, bilinear interpolation, bicubic interpolation, Lagrange interpolation, Newton's interpolation, Chebyshev interpolation, radial basis function interpolation, and multivariate interpolation. Specifically, it can be selected according to the data characteristics and the required forging simulation accuracy, and this application does not make a limitation here.

[0100] Step S207: Use the forging simulation parameters as training samples and the standardized forging interpolation results corresponding to the forging simulation parameters as sample labels to train a neural network to obtain the forging simulation model.

[0101] In summary, when training the forging simulation model, the present application uses an interpolation method to process the forging simulation parameters. Therefore, it can not only ensure the accuracy of the forging interpolation results before and after interpolation, but also meet the fixed format requirements of the fixed-length output of the neural network. By utilizing the prediction ability of the neural network to quickly obtain results, when using the forging simulation model to process the current forging simulation parameters, the time for generating the forging simulation results can be greatly shortened, the forging simulation efficiency can be improved, so as to meet the need for rapid prediction based on the forging simulation results.

[0102] In one embodiment, referring to Figure 3 , the flowchart of a method for determining each interpolation point on and inside a polygon curve based on the number of horizontal layout points and the number of vertical layout points disclosed in the embodiment of the present application, that is, step S204 can specifically include:

[0103] Step S301: Determine the interpolation point abscissa vector.

[0104] Specifically, determine the maximum interpolation point abscissa xmax and the minimum interpolation point abscissa xmin of the polygon curve in the horizontal direction.

[0105] According to the maximum interpolation point abscissa xmax, the minimum interpolation point abscissa xmin, and the number of horizontal layout points Nx, determine the distance between two adjacent interpolation points, and obtain the interpolation point abscissas corresponding to each interpolation point in the horizontal direction.

[0106] Based on all the interpolation point abscissas, obtain the interpolation point abscissa vector.

[0107] It should be noted that the maximum interpolation point abscissa xmax and the minimum interpolation point abscissa xmin define the interpolation range in the horizontal direction. According to the interpolation range in the horizontal direction and the number of horizontal layout points Nx, the interpolation point abscissas corresponding to each interpolation point in the horizontal direction can be calculated.

[0108] The interpolation point abscissa vector x can be expressed as:

[0109] x = [xmin, xmin + △x,..., xmax].

[0110] Where, △x is the distance between two adjacent interpolation points in the horizontal direction.

[0111] The expression of △x is as follows:

[0112] .

[0113] Step S302: Based on each interpolation point abscissa in the interpolation point abscissa vector and the number of vertical layout points, determine the corresponding interpolation point ordinate.

[0114] Step S303: Based on the abscissa of each interpolation point and the corresponding ordinate of one interpolation point, determine an interpolation point, and obtain each interpolation point on and inside the polygon curve.

[0115] Each interpolation point is composed of an abscissa of the interpolation point and an ordinate of the interpolation point. When all the abscissas of the interpolation points and their corresponding ordinates of the interpolation points are determined, each interpolation point on and inside the polygon curve can be obtained. See the schematic diagrams of each interpolation point on and inside the polygon curve shown in Fig. 4(1) and Fig. 4(2) respectively.

[0116] In one embodiment, the process of determining the corresponding ordinate of the interpolation point based on each abscissa of the interpolation point in the abscissa vector of the interpolation point and the number of vertical layout points may specifically include:

[0117] Determine the intersection vector of the vertical axis of each abscissa of the interpolation point in the abscissa vector of the interpolation point and the polygon curve;

[0118] Based on the number of intersection points of the vertical axis contained in the intersection vector of the vertical axis, and in combination with the number of vertical layout points, determine the number of interpolation points between adjacent intersection points;

[0119] Determine the ordinates of each interpolation point based on the number of interpolation points.

[0120] Among them, there are various methods to determine the number of interpolation points between adjacent intersection points based on the number of intersection points of the vertical axis contained in the intersection vector of the vertical axis and in combination with the number of vertical layout points. The present application provides two implementation methods, specifically as follows:

[0121] Method 1

[0122] Determine the total number of regions formed by adjacent intersection points in the intersection vector of the vertical axis;

[0123] Distribute the number of vertical layout points according to the total number of regions to obtain the number of interpolation points between adjacent intersection points.

[0124] Illustrate with an example, specifically as follows:

[0125] The number of vertical layout points is represented by Ny.

[0126] If there are two intersection points in the intersection vector J of the vertical axis, which are J1 and J2 respectively, then Ny ordinate points y are evenly distributed between J1 and J2, that is, the number of interpolation points between J1 and J2 is Ny.

[0127] If there are three intersection points in the vertical axis intersection vector J, namely J1, J2, and J3, then the regions between J1 and J2 and between J2 and J3 can be interpolated respectively, with Ny / 2 points interpolated in each region, or unequal interpolation can be performed according to the size and shape of the regions.

[0128] If there are four intersection points in the vertical axis intersection vector J, namely J1, J2, J3, and J4, then the regions between J1 and J2 and between J3 and J4 can be interpolated respectively, with Ny / 2 points interpolated in each region.

[0129] If the number of intersection points in the vertical axis intersection vector J exceeds four, then it is necessary to reasonably distribute the Ny points among the segments according to the shape of the polygonal curve and the distribution of the intersection points.

[0130] Method 2:

[0131] Determine the distances between adjacent intersection points in the vertical axis intersection vector;

[0132] Distribute the vertical number of layout points according to each distance to obtain the number of interpolation points between adjacent intersection points.

[0133] In practical applications, Ny can also be distributed according to the distances between intersection points.

[0134] For example, assume that there are four intersection points in the vertical axis intersection vector J, namely J1, J2, J3, and J4. Then the interpolation can be performed according to the following steps:

[0135] 1. Calculate the distance d1 between J1 and J2 and the distance d2 between J3 and J4;

[0136] 2. According to the ratio of d1 and d2, distribute the Ny points into two regions in proportion. For example, if the ratio of d1 and d2 is 2:1, then 2Ny / 3 vertical coordinate points y are interpolated between J1 and J2, and Ny / 3 vertical coordinate points y are interpolated between J3 and J4. If Ny cannot be divided evenly, one interval can have one more point and the other interval can have one less point to ensure the total number of points is the same.

[0137] In one embodiment, refer to Figure 5 , a method flowchart for determining each interpolation point on and inside a polygonal curve based on the horizontal number of layout points and the vertical number of layout points disclosed in the embodiments of the present application may specifically include:

[0138] Step S401: Determine the interpolation point vertical coordinate vector.

[0139] Specifically, determine the maximum interpolation point vertical coordinate ymax and the minimum interpolation point vertical coordinate ymin of the polygonal curve in the vertical direction;

[0140] Determine the distance between two adjacent interpolation points according to the maximum interpolation point ordinate ymax, the minimum interpolation point ordinate ymin, and the number of vertical layout points Ny, and obtain the interpolation point ordinates corresponding to each interpolation point in the vertical direction;

[0141] Based on all the interpolation point ordinates, obtain the interpolation point ordinate vector.

[0142] It should be noted that the maximum interpolation point ordinate ymax and the minimum interpolation point ordinate ymin define the interpolation range in the horizontal direction. According to the interpolation range in the horizontal direction and the number of horizontal layout points Ny, the interpolation point ordinates corresponding to each interpolation point in the horizontal direction can be calculated.

[0143] The interpolation point ordinate vector y can be expressed as:

[0144] y = [ymin, ymin + △y,..., ymax].

[0145] Where △y is the distance between two adjacent interpolation points in the vertical direction.

[0146] The expression of △y is as follows:

[0147] .

[0148] Step S402: Based on each interpolation point ordinate in the interpolation point ordinate vector and the number of horizontal layout points, determine the corresponding interpolation point abscissa.

[0149] Step S403: Based on each interpolation point ordinate and the corresponding interpolation point abscissa, determine an interpolation point, and obtain each interpolation point on and inside the polygon curve.

[0150] Each interpolation point is composed of an interpolation point abscissa and an interpolation point ordinate. After all the interpolation point abscissas and their corresponding interpolation point ordinates are determined, each interpolation point on and inside the polygon curve can be obtained. For details, see Figure 6 The schematic diagram of each interpolation point on the polygon curve shown.

[0151] In one embodiment, the process of determining the corresponding interpolation point abscissa based on each interpolation point ordinate in the interpolation point ordinate vector and the number of horizontal layout points may specifically include:

[0152] Determine the intersection point vector of the horizontal axis of the polygon curve for each interpolation point ordinate in the interpolation point ordinate vector;

[0153] Determine the number of interpolation points between adjacent intersection points based on the number of intersection points included in the horizontal axis intersection vector and in combination with the horizontal layout points;

[0154] Determine the abscissas of each of the interpolation points based on the number of interpolation points.

[0155] Among them, there are multiple methods for determining the number of interpolation points between adjacent intersection points based on the number of intersection points included in the horizontal axis intersection vector and in combination with the horizontal layout points. This application provides two implementation methods, which are specifically as follows:

[0156] Method 1

[0157] Determine the total number of regions formed by adjacent intersection points in the horizontal axis intersection vector;

[0158] Allocate the horizontal layout points according to the total number of regions to obtain the number of interpolation points between adjacent intersection points.

[0159] Illustrate with examples, specifically as follows:

[0160] The horizontal layout points are represented by Nx.

[0161] If there are two intersection points in the horizontal axis intersection vector K, which are K1 and K2 respectively, then Nx abscissa points y are evenly distributed between K1 and K2, that is, the number of interpolation points between K1 and K2 is Nx.

[0162] If there are three intersection points in the horizontal axis intersection vector K, which are K1, K2, and K3 respectively, then the regions between K1 and K2 and between K2 and K3 can be interpolated respectively, with Nx / 2 points interpolated in each region, or unequal interpolation can be performed according to the size and shape of the regions.

[0163] If there are four intersection points in the horizontal axis intersection vector K, which are K1, K2, K3, and K4 respectively, then the regions between K1 and K2 and between K3 and K4 can be interpolated respectively, with Nx / 2 points interpolated in each region.

[0164] If the number of intersection points in the horizontal axis intersection vector K exceeds four, then it is necessary to reasonably allocate the Nx points among each segment according to the shape of the polygonal curve and the distribution of the intersection points.

[0165] Method 2:

[0166] Determine the distances between each pair of adjacent intersection points in the horizontal axis intersection vector;

[0167] Allocate the horizontal layout points according to each of the distances to obtain the number of interpolation points between adjacent intersection points.

[0168] In practical applications, Nx can also be allocated according to the distances between intersection points.

[0169] For example, assume that there are four intersection points in the vertical axis intersection vector K, namely: K1, K2, K3, and K4. Then, interpolation can be performed according to the following steps:

[0170] 1. Calculate the distance d1 between K1 and K2 and the distance d2 between K3 and K4;

[0171] 2. According to the ratio of d1 and d2, distribute the Nx points into two regions proportionally. For example, if the ratio of d1 and d2 is 2:1, then interpolate 2Nx / 3 vertical coordinate points x between K1 and K2, and interpolate Nx / 3 vertical coordinate points x between K3 and K4. If Nx cannot be divided evenly, one interval can have one more point and the other interval can have one less point to ensure that the total number of points is the same.

[0172] Corresponding to the above method embodiment, the present application discloses a forging simulation device.

[0173] See Figure 7 , a schematic structural diagram of a forging simulation device disclosed in an embodiment of the present application. The device may include:

[0174] A parameter acquisition unit 501, configured to acquire current forging simulation parameters.

[0175] Among them, the current forging simulation parameters mainly include material properties, geometric parameters, boundary conditions, loading conditions, etc.

[0176] A simulation unit 502, configured to input the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result.

[0177] Among them, the forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and the standardized forging interpolation results obtained by using an interpolation method.

[0178] The main function of the interpolation method is to estimate or predict the values of unknown data points between known data points. By processing the forging simulation parameters using the interpolation method in the present application, it can not only ensure the consistency of the finite element solutions obtained by using the finite element method before and after interpolation for the forging simulation parameters, but also meet the fixed format requirements of the fixed-length output of the neural network.

[0179] The prediction ability of the neural network has many advantages such as the ability to handle complex nonlinear problems, high-precision prediction, strong generalization ability, strong adaptability, automatic feature extraction, large-scale data processing ability, and the ability to integrate with other machine learning technologies. These advantages enable the neural network to play an important role in the field of predictive analysis. By training the forging interpolation results using a neural network to obtain a forging simulation model in the present application, and utilizing the prediction ability of the neural network, the time for forging simulation can be greatly shortened.

[0180] In summary, the present application discloses a forging simulation device, which obtains current forging simulation parameters and inputs the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result. The forging simulation model is obtained by using a neural network to learn the correspondence between forging simulation parameters and the standardized forging interpolation results obtained by using an interpolation method. The present application uses a flexible interpolation method to process the forging simulation results, which can not only ensure the consistency between the forging simulation results before and after interpolation and the standardized forging interpolation results, but also meet the fixed format requirements of the fixed-length output of the neural network. By using the fast prediction ability of the neural network, when the forging simulation model is used to process the current forging simulation parameters, the time for generating the forging simulation result can be greatly shortened, thereby improving the forging simulation efficiency to meet the requirement of rapid prediction according to the forging simulation result.

[0181] In one embodiment, the forging simulation device may further include:

[0182] A model training unit for training the forging simulation model.

[0183] Specifically, the model training unit may be used for:

[0184] Determine the number of horizontal layout points in the horizontal direction and the number of vertical layout points in the vertical direction of the forging simulation result, where the number of horizontal layout points and the number of vertical layout points determine the resolution of the interpolation grid;

[0185] Batch obtain the finite element solutions obtained by processing the forging simulation parameters by using the finite element method;

[0186] For each of the finite element solutions, obtain all the corresponding boundary points;

[0187] Connect all the boundary points in sequence to form a polygonal curve as the boundary of the interpolation region;

[0188] Based on the number of horizontal layout points and the number of vertical layout points, determine each interpolation point on and inside the polygonal curve;

[0189] Perform interpolation at the positions of each interpolation point by using a preset interpolation function to obtain the standardized forging interpolation result;

[0190] Use the forging simulation parameters as training samples and the corresponding standardized forging interpolation results of the forging simulation parameters as sample labels to train the neural network to obtain the forging simulation model.

[0191] In one embodiment, the process by which the model training unit determines each interpolation point on and inside the polygon curve based on the horizontal number of layout points and the vertical number of layout points may specifically include:

[0192] Determine the abscissa vector of the interpolation points;

[0193] Based on each abscissa of the interpolation points in the abscissa vector of the interpolation points and the vertical number of layout points, determine the corresponding ordinate of the interpolation points;

[0194] Based on each abscissa of the interpolation points and the corresponding ordinate of one of the interpolation points, determine an interpolation point, and obtain each interpolation point on and inside the polygon curve.

[0195] In one embodiment, the process by which the model training unit determines the abscissa vector of the interpolation points may specifically include:

[0196] Determine the maximum abscissa and the minimum abscissa of the interpolation points of the polygon curve in the horizontal direction;

[0197] According to the maximum abscissa, the minimum abscissa and the horizontal number of layout points, determine the distance between two adjacent interpolation points, and obtain the abscissa of the interpolation points corresponding to each interpolation point in the horizontal direction;

[0198] Based on all the abscissas of the interpolation points, obtain the abscissa vector of the interpolation points.

[0199] In one embodiment, the model training unit determines the corresponding ordinate of the interpolation points based on each abscissa of the interpolation points in the abscissa vector of the interpolation points and the vertical number of layout points, including:

[0200] Determine the vector of the intersection points of each abscissa of the interpolation points in the abscissa vector of the interpolation points with the vertical axis of the polygon curve;

[0201] Based on the number of intersection points on the vertical axis included in the vector of the intersection points on the vertical axis, and in combination with the vertical number of layout points, determine the number of interpolation points between adjacent intersection points;

[0202] Based on the number of interpolation points, determine each ordinate of the interpolation points.

[0203] In one embodiment, the process by which the model training unit determines the number of interpolation points between adjacent intersection points based on the number of intersection points on the vertical axis included in the vector of the intersection points on the vertical axis and in combination with the vertical number of layout points may specifically include:

[0204] Determine the total number of regions formed by adjacent intersection points in the vector of the intersection points on the vertical axis;

[0205] Distribute the vertical number of layout points according to the total number of the regions to obtain the number of interpolation points between adjacent intersection points.

[0206] In one embodiment, the model training unit determines the number of interpolation points between adjacent intersection points based on the number of vertical intersection points included in the vertical axis intersection point vector and in combination with the vertical number of layout points, including:

[0207] Determine the distances between each pair of adjacent intersection points in the vertical axis intersection point vector;

[0208] Distribute the vertical number of layout points according to each of the distances to obtain the number of interpolation points between adjacent intersection points.

[0209] In one embodiment, the model training unit determines each interpolation point on and inside the polygon curve based on the horizontal number of layout points and the vertical number of layout points, including:

[0210] Determine the interpolation point ordinate vector;

[0211] Based on each interpolation point ordinate in the interpolation point ordinate vector and the horizontal number of layout points, determine the corresponding interpolation point abscissa;

[0212] Based on each interpolation point ordinate and the corresponding interpolation point abscissa, determine an interpolation point, and obtain each interpolation point on and inside the polygon curve.

[0213] In one embodiment, the process by which the model training unit determines the interpolation point ordinate vector includes:

[0214] Determine the maximum interpolation point ordinate and the minimum interpolation point ordinate of the polygon curve in the vertical direction;

[0215] According to the maximum interpolation point ordinate, the minimum interpolation point ordinate and the vertical number of layout points, determine the distance between two adjacent interpolation points, and obtain the interpolation point ordinates corresponding to each interpolation point in the vertical direction;

[0216] Based on all the interpolation point ordinates, obtain the interpolation point ordinate vector.

[0217] In one embodiment, the model training unit determines the corresponding interpolation point abscissa based on each interpolation point ordinate in the interpolation point ordinate vector and the horizontal number of layout points, including:

[0218] Determine the horizontal axis intersection point vector of each interpolation point ordinate in the interpolation point ordinate vector and the polygon curve;

[0219] Determine the number of interpolation points between adjacent intersections based on the number of intersections included in the horizontal axis intersection vector and in combination with the horizontal layout points;

[0220] Determine the abscissas of each of the interpolation points based on the number of interpolation points.

[0221] It should be specifically noted that for the specific working principles of the components in the device embodiments, please refer to the corresponding parts of the method embodiments, which will not be elaborated here.

[0222] Corresponding to the above embodiments, the present application also discloses a computer storage medium. The computer storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the steps shown in the method embodiments of the forging simulation method are implemented.

[0223] Corresponding to the above embodiments, as Figure 8 shown, the present invention also provides an electronic device, which may include: a processor 1 and a memory 2;

[0224] Wherein, the processor 1 and the memory 2 complete mutual communication through a communication bus 3;

[0225] The processor 1 is used to execute at least one instruction;

[0226] The memory 2 is used to store at least one instruction;

[0227] The processor 1 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0228] The memory 2 may include a high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0229] Wherein, the processor executes at least one instruction to implement the steps shown in the method embodiments of the forging simulation method.

[0230] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0231] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. For the same or similar parts among the various embodiments, reference may be made to each other.

[0232] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A forging simulation method, characterized in that, Including: Obtain the current forging simulation parameters; Input the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result, where the forging simulation model is obtained by learning the correspondence between forging simulation parameters and a standardized forging interpolation result obtained by an interpolation method using a neural network; Among them, the training process of the forging simulation model includes: Determine the number of horizontal layout points in the horizontal direction and the number of vertical layout points in the vertical direction of the forging simulation result, where the number of horizontal layout points and the number of vertical layout points determine the resolution of the interpolation grid; Batch obtain the finite element solutions obtained by processing the forging simulation parameters using the finite element method; For each of the finite element solutions, obtain all corresponding boundary points; Sequentially connect all the boundary points in order to form a polygonal curve as the boundary of the interpolation region; Based on the number of horizontal layout points and the number of vertical layout points, determine each interpolation point on and inside the polygonal curve; Perform interpolation at the positions of each interpolation point using a preset interpolation function to obtain the standardized forging interpolation result; Use the forging simulation parameters as training samples and the standardized forging interpolation result corresponding to the forging simulation parameters as sample labels to train a neural network to obtain the forging simulation model.

2. The forging simulation method according to claim 1, characterized in that, Based on the number of horizontal layout points and the number of vertical layout points, determining each interpolation point on and inside the polygonal curve includes: Determine the interpolation point abscissa vector; Based on each interpolation point abscissa in the interpolation point abscissa vector and the number of vertical layout points, determine the corresponding interpolation point ordinate; Based on each interpolation point abscissa and a corresponding interpolation point ordinate, determine an interpolation point to obtain each interpolation point on and inside the polygonal curve.

3. The forging simulation method according to claim 2, wherein, The process of determining the interpolation point abscissa vector includes: Determine the maximum interpolation point abscissa and the minimum interpolation point abscissa of the polygonal curve in the horizontal direction; According to the maximum interpolation point abscissa, the minimum interpolation point abscissa, and the number of horizontal layout points, determine the distance between adjacent interpolation points to obtain the interpolation point abscissas corresponding to each interpolation point in the horizontal direction; Obtain the interpolation point abscissa vector based on all the interpolation point abscissas.

4. The forging simulation method according to claim 2 or 3, characterized in that, The determining the corresponding interpolation point ordinate based on each interpolation point abscissa in the interpolation point abscissa vector and the number of vertical layout points includes: Determine the vector of the intersection points of each interpolation point abscissa in the interpolation point abscissa vector with the vertical axis of the polygonal curve; Based on the number of vertical axis intersection points included in the vertical axis intersection point vector and in combination with the number of vertical layout points, determine the number of interpolation points between adjacent intersection points; Determine each interpolation point ordinate based on the number of interpolation points.

5. The forging simulation method according to claim 4, characterized in that, The determining the number of interpolation points between adjacent intersection points based on the number of vertical axis intersection points included in the vertical axis intersection point vector and in combination with the number of vertical layout points includes: Determine the total number of regions formed by adjacent intersection points in the vertical axis intersection point vector; Allocate the vertical layout points according to the total number of the regions to obtain the interpolation points between adjacent intersections.

6. The forging simulation method according to claim 4, wherein Determining the interpolation points between adjacent intersections based on the number of vertical axis intersections included in the vertical axis intersection vector and in combination with the vertical layout points includes: Determine the distances between each pair of adjacent intersections in the vertical axis intersection vector; Allocate the vertical layout points according to each of the distances to obtain the interpolation points between adjacent intersections.

7. The forging simulation method according to claim 1, wherein Based on the horizontal layout points and the vertical layout points, determine each interpolation point on and inside the polygonal curve, including: Determine the interpolation point ordinate vector; Based on each interpolation point ordinate in the interpolation point ordinate vector and the horizontal layout points, determine the corresponding interpolation point abscissa; Based on each interpolation point ordinate and a corresponding interpolation point abscissa, determine an interpolation point to obtain each interpolation point on and inside the polygonal curve.

8. The forging simulation method according to claim 7, wherein, The process of determining the interpolation point ordinate vector includes: Determine the maximum interpolation point ordinate and the minimum interpolation point ordinate of the polygonal curve in the vertical direction; According to the maximum interpolation point ordinate, the minimum interpolation point ordinate and the vertical layout points, determine the distance between two adjacent interpolation points to obtain the interpolation point ordinates corresponding to each interpolation point in the vertical direction; Based on all the interpolation point ordinates, obtain the interpolation point ordinate vector.

9. The forging simulation method according to claim 7 or 8, characterized in that Based on each interpolation point ordinate in the interpolation point ordinate vector and the horizontal layout points, determining the corresponding interpolation point abscissa includes: Determine the horizontal axis intersection vector of each interpolation point ordinate in the interpolation point ordinate vector and the polygonal curve; Based on the number of intersections included in the horizontal axis intersection vector and in combination with the horizontal layout points, determine the interpolation points between adjacent intersections; Based on the interpolation points, determine each interpolation point abscissa.

10. The forging simulation method according to claim 9, characterized in that Based on the number of intersections included in the horizontal axis intersection vector and in combination with the horizontal layout points, determining the interpolation points between adjacent intersections includes: Determine the total number of regions formed by adjacent intersections in the horizontal axis intersection vector; Allocate the horizontal layout points according to the total number of the regions to obtain the interpolation points between adjacent intersections.

11. The forging simulation method according to claim 9, characterized in that, Based on the number of intersections included in the horizontal axis intersection vector and in combination with the horizontal layout points, determining the interpolation points between adjacent intersections includes: Determine the distances between each pair of adjacent intersections in the horizontal axis intersection vector; Allocate the horizontal layout points according to each of the distances to obtain the interpolation points between adjacent intersections.

12. A forging simulation device, characterized in that, Includes: A parameter acquisition unit for acquiring current forging simulation parameters; A simulation unit for inputting the current forging simulation parameters into a pre-trained forging simulation model to obtain a forging simulation result, wherein the forging simulation model is obtained by learning the corresponding relationship between forging simulation parameters and a standardized forging interpolation result obtained by using an interpolation method by a neural network; A model training unit for training the forging simulation model; The model training unit can specifically be used for: Determine the number of horizontal sampling points in the horizontal direction and the number of vertical sampling points in the vertical direction of the forging simulation results, where the number of horizontal sampling points and the number of vertical sampling points determine the resolution of the interpolation grid; Batch obtain the finite element solutions obtained by processing the forging simulation parameters using the finite element method; For each of the finite element solutions, obtain all the corresponding boundary points; Sequentially connect all the boundary points in order to form a polygonal curve as the boundary of the interpolation region; Based on the number of horizontal sampling points and the number of vertical sampling points, determine each interpolation point on and inside the polygonal curve; Use a preset interpolation function to perform interpolation at the positions of each interpolation point to obtain the standardized forging interpolation result; Use the forging simulation parameters as training samples and the standardized forging interpolation result corresponding to the forging simulation parameters as sample labels to train a neural network to obtain the forging simulation model.

13. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, it implements the forging simulation method according to any one of claims 1 to 11.

14. An electronic device, characterized in that, The electronic device includes: a memory and a processor; The memory is used to store at least one instruction; The processor is used to execute the at least one instruction to implement the forging simulation method according to any one of claims 1 to 11.

Images