Shaping pressure rapid prediction method and device

Abstract

According to the shaping pressure rapid prediction method provided by the embodiment of the invention, the finite element model of the actual scanning data of the product part is constructed through the finite element model of the product design data and the deviation of the scanning data; and calculating by adopting a finite element numerical solution method to obtain a pressure value required to be applied to enable the actual scanning data finite element model to be matched with the product design data finite element model. According to the method provided by the embodiment of the invention, the shaping pressure rapid prediction model driven by data can be established, the field shape correction efficiency of the metal thin piece product is greatly improved, and the precision quality is guaranteed. The embodiment of the invention further provides a related device.

Description

Technical Field

[0001] The invention relates to the technical field of stamping dies, and in particular to a method and a device for quickly predicting shaping pressure. Background Art

[0002] Sheet metal stamping is an important metal plastic forming method, which has been widely used in aerospace, automobile locomotive, motor and electrical appliances, daily necessities manufacturing and other industrial fields. Stamping uses molds and stamping equipment to apply pressure to metal sheets to obtain stamped parts with certain shapes, sizes and performance. The shaping process in stamping is an important means to ensure the stability of part dimensional accuracy. It uses the mold to correct the fillet radius and dimensional shape, etc., so that the blank will produce a small plastic deformation locally or as a whole, so as to achieve the purpose of improving the dimensional accuracy of the formed parts. Therefore, the shaping process is widely used, not only for the production of stamped parts, but also for the correction of thin metal products (such as metal mobile phone cases).

[0003] For traditional stamping parts production, since the shape and size of stamping parts are stable during the production process, the shaping pressure of the shaping process can remain unchanged once it is verified and determined. However, for the shaping of thin metal products (such as metal mobile phone cases), the situation is quite the opposite. Thin metal products themselves have low rigidity and are easy to deform. The deformation caused by the influence of external processing forces during the processing process makes it difficult to ensure the consistency of flatness quality. Moreover, the wall of thin metal products themselves is thin, and the quality of shaping will directly depend on whether the value of the applied shaping pressure is appropriate. How to quickly predict the corresponding shaping pressure based on the actual dimensional deviation of product parts is the key to improving the efficiency of shaping of thin metal products and ensuring the precision quality.

[0004] The traditional shaping pressure prediction method is to use stamping forming simulation technology to simulate the shaping process, and obtain the required shaping pressure by calculating the collision contact force between the shaping die and the workpiece. This method is suitable for the shaping analysis of stamping parts in the product design stage, and the finite element models of the shaping die and the workpiece are derived from the product design data. If the traditional shaping pressure prediction method is used for the actual scanning data of product parts, it is also necessary to construct a corresponding finite element model for each product part through scanning data processing technology according to the actual state. This modeling work is time-consuming and laborious; moreover, the forming contact algorithm used in the forming simulation calculation itself also consumes a lot of computing time. Therefore, the traditional shaping pressure prediction method cannot meet the production needs of "on-site detection and real-time correction", which is not conducive to the correction application based on the actual size deviation of product parts, especially the correction production of thin metal products (such as metal mobile phone cases). Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for rapid prediction of shaping pressure, establish a data-driven rapid prediction model for shaping pressure, and greatly improve the efficiency of on-site shaping of thin metal products and ensure accuracy and quality.

[0006] In order to achieve the above-mentioned purpose, the present invention provides a method and device for quickly predicting shaping pressure, which can quickly and effectively improve the efficiency of on-site shaping and ensure the accuracy and quality.

[0007] In a first aspect, an embodiment of the present application provides a method for quickly predicting plastic surgery pressure, comprising the following steps:

[0008] 101. Obtain product design data of the parts, perform finite element meshing, and obtain a finite element model A;

[0009] 102. Obtain the actual scanning data of the parts and align them with the product design data;

[0010] 103. Determine the node deviation calculation result between the actual scan data and the product design data;

[0011] 104. According to the node deviation calculation result, the position of each node of the finite element model A is updated to determine the finite element model B;

[0012] 105. In the finite element model B, displacement is applied to each node in the direction of the deviation corresponding to the node deviation calculation result in the opposite direction, and the node force required to be applied when each node in the finite element model B is pushed back to the original corresponding position in the finite element model A is calculated by using the finite element numerical solution method;

[0013] 106. Calculate the sum of all the nodal forces in the same direction in the shaping direction to obtain the shaping pressure.

[0014] In combination with the first aspect, in an implementation of the embodiment of the present application, after step 106, the following steps are further included:

[0015] The prediction accuracy of the plastic surgery pressure is adjusted by a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected from production practice.

[0016] In combination with the first aspect, in an implementation of the embodiment of the present application, step 104 includes:

[0017] 1041. Determine the moving direction and displacement value of each node of the finite element model A according to the node deviation calculation result;

[0018] 1042. Calculate the coordinates of each node of the finite element model B according to the coordinates, moving direction and displacement value of each node of the finite element model A to obtain the finite element model B.

[0019] In combination with the first aspect, in an implementation of the embodiment of the present application, step 105 includes:

[0020] 1051. Determine the node displacement applied to each node in the finite element model B in the opposite direction of the deviation direction corresponding to the node deviation calculation result according to the coordinates of each node in the finite element model B and the coordinates of each node in the finite element model A;

[0021] 1052. Determine the finite element nodal forces based on nodal displacements;

[0022] 1053. Determine the nodal force required to be applied when each node in the finite element model B is pushed back to its original corresponding position in the finite element model A based on the finite element nodal force.

[0023] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1053 includes:

[0024] According to the finite element node force, the node force F is calculated by the first formula node ;

[0025] The first formula includes:

[0026]

[0027] Among them, F node is the nodal force, is the finite element node force, m is the surrounding node force F node The number of finite elements adjacent to the corresponding node, i is the i-th finite element.

[0028] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1052 includes:

[0029] According to the node displacement, the finite element node force is calculated by the second and third formulas.

[0030] The second formula is:

[0031]

[0032] in, is the element stiffness matrix, is the unit node displacement;

[0033] The third formula is:

[0034]

[0035] Among them, B represents the stress matrix, D is the elastic coefficient matrix, e represents the unit e, and Ω represents the integration area.

[0036] In combination with the first aspect, in an implementation of the embodiment of the present application, step 106 includes:

[0037] Calculate the sum of the values ​​of the group of nodal force components with positive values ​​to obtain the shaping pressure;

[0038] Alternatively, calculate the sum of the values ​​of a group of nodal force components with negative values ​​to obtain the shaped pressure.

[0039] In a second aspect, an embodiment of the present application provides a device for rapid prediction of plastic surgery pressure, comprising:

[0040] An acquisition module is used to acquire product design data of a part and to acquire actual scanning data of the part;

[0041] Processing modules for:

[0042] Perform finite element meshing on the acquired product design data to obtain a finite element model A;

[0043] Perform position registration of the acquired actual scanning data with the product design data;

[0044] Determine the node deviation calculation results between the actual scan data and the product design data;

[0045] According to the node deviation calculation results, the position of each node of the finite element model A is updated to determine the finite element model B;

[0046] In the finite element model B, displacement is applied to each node in the direction of the deviation corresponding to the node deviation calculation result in the opposite direction, and the node force required to be applied when each node in the finite element model B is pushed back to the original corresponding position in the finite element model A is calculated by using the finite element numerical solution method;

[0047] The sum of the components of all nodal forces in the same direction in the shaping direction is calculated to obtain the shaping pressure.

[0048] In conjunction with the second aspect, in an implementation manner of the embodiment of the present application, the processing module is further configured to:

[0049] The prediction accuracy of the plastic surgery pressure is adjusted by a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected from production practice.

[0050] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein the computer program implements the method described in the first aspect when executed by a processor.

[0051] In a fourth aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0052] It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

[0053] The embodiment of the present application provides a method for rapid prediction of shaping pressure, which constructs a finite element model of the actual scanning data of the product parts through the finite element model of the product design data and the deviation of the scanning data, and uses the finite element numerical solution method to calculate the pressure value required to make the finite element model of the actual scanning data match the finite element model of the product design data. Then, the theoretical prediction of the shaping pressure is adjusted for accuracy using the big data of production practice, and a data-driven rapid shaping pressure prediction model is obtained through a traditional regression model or an artificial intelligence machine learning model, which can be used to directly predict the optimal shaping pressure based on the actual measured deviation of the part, thereby greatly improving the on-site correction efficiency of the part deviation and ensuring the dimensional accuracy of the finished part.

[0054] Compared with traditional shaping pressure prediction methods, the finite element model used in the method of the present invention is only based on product design data and scanning data, and the model construction method is simple and fast, avoiding the time-consuming and labor-intensive finite element modeling of shaping molds and reverse modeling of parts based on scanning data in traditional shaping pressure prediction methods; and the finite element numerical solution method used in the method of the present invention is a fast displacement method known in the industry, which can meet the application requirements of "real-time output results". In contrast, the forming contact algorithm used in traditional shaping pressure prediction methods is complex and time-consuming to calculate.

[0055] Furthermore, the shaping pressure rapid prediction model established by the method of the present invention can be further iterated and trained with the support of big data from production practice, and the model accuracy and production adaptability can be improved. However, the traditional shaping pressure prediction method is difficult to iterate and train using big data from production practice, and cannot meet the production requirements of "on-site detection and real-time correction", and is not suitable for on-site correction applications of actual deviations of product parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0057] Figure 1A flowchart of a method for rapid prediction of plastic surgery pressure provided in an embodiment of the present application;

[0058] Figure 2 A flowchart of an implementation method of the present application embodiment

[0059] Figure 3 An example diagram of the product design CAD design data provided in the embodiment of the present application;

[0060] Figure 4 An example diagram of a finite element model A provided in an embodiment of the present application;

[0061] Figure 5 An example diagram of actual scan data of product parts provided in the embodiment of the present application;

[0062] Figure 6 Deviation cloud diagram between actual scan data and product design data provided in the embodiment of the present application;

[0063] Figure 7 A node displacement distribution diagram corresponding to a displacement applied in the reverse direction of the deviation in the actual scanning data provided in the embodiment of the present application;

[0064] Figure 8 A schematic diagram of the internal modules of a device for rapid prediction of plastic surgery pressure provided in an embodiment of the present application;

[0065] Fig. 9 A schematic diagram of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The purpose of the present invention is to provide a method and device for rapid prediction of shaping pressure, establish a data-driven rapid prediction model for shaping pressure, and greatly improve the efficiency of on-site shaping of thin metal products and ensure accuracy and quality.

[0067] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 creative work are within the scope of protection of the present invention.

[0068] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0069] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0070] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0071] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0072] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0073] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0074] Figure 1 A flowchart of a method for rapid prediction of shaping pressure provided in an embodiment of the present application is shown in FIG. Figure 1As shown, the method comprises the following steps:

[0075] 101. Obtain product design data of the parts, perform finite element meshing, and obtain a finite element model A;

[0076] In the embodiment of the present application, the existing finite element professional software in the industry (such as HYPERMESH, ANSA, etc.) can be used to perform finite element meshing on the product design data.

[0077] In practical applications, there may be many ways to perform finite element mesh division, which is not limited in the embodiments of the present application.

[0078] 102. Obtain the actual scanning data of the parts and align them with the product design data;

[0079] In the embodiment of the present application, the point cloud registration technology known in the industry can be used to positionally register the acquired actual scanning data with the product design data.

[0080] In practical applications, there may be many ways to perform position alignment, which are not limited in the embodiments of the present application.

[0081] 103. Determine the node deviation calculation result between the actual scan data and the product design data;

[0082] In the embodiment of the present application, the deviation analysis technology known in the industry can be used to calculate the absolute deviations at various locations after the actual scan data and the product design data are aligned.

[0083] In practical applications, other methods may also be used to determine the node deviation calculation results between the actual scanning data and the product design data, which is not limited in the embodiments of the present application.

[0084] 104. According to the node deviation calculation result, the position of each node of the finite element model A is updated to determine the finite element model B;

[0085] In an embodiment of the present application, each node position of the finite element model A of the product design data can be updated to the actual scanning data of the product part according to the calculation result of its node deviation, so as to construct a finite element model B that is consistent with the actual scanning data of the product part.

[0086] For example, the coordinates of the i-th node of the finite element model A are (x i ,y i ), and the vector representing the node deviation calculation result is (m, n), then the coordinates of the i-th node in the finite element model B can be calculated as (x i +m,y i +n).

[0087] In the embodiment of the present application, step 104 may include the following steps:

[0088] 1041. Determine the moving direction and displacement value of each node of the finite element model A according to the node deviation calculation result;

[0089] The moving direction and displacement value of each node can be represented by the above-mentioned vector.

[0090] 1042. Calculate the coordinates of each node of the finite element model B according to the coordinates, moving direction and displacement value of each node of the finite element model A to obtain the finite element model B.

[0091] In practical applications, the position of each node of the finite element model A can be updated according to the node deviation calculation results in other ways to determine the finite element model B, which is not limited in the embodiments of the present application.

[0092] 105. In the finite element model B, displacement is applied to each node in the direction of the deviation corresponding to the node deviation calculation result in the opposite direction, and the node force required to be applied when each node in the finite element model B is pushed back to the original corresponding position in the finite element model A is calculated by using the finite element numerical solution method;

[0093] In the embodiment of the present application, the following steps may be included:

[0094] 1051. Determine, according to the coordinates of each node in the finite element model B and the coordinates of each node in the finite element model A, a node displacement applied to each node in the finite element model B in the opposite direction of the deviation direction corresponding to the node deviation calculation result;

[0095] It can be understood that the displacement method is a finite element algorithm known in the industry that uses node angular displacement and node linear displacement to solve the static equilibrium equation, that is, the internal force of the entire structure is calculated by the node displacement. Therefore, the node displacement applied to each node in the finite element model B in the opposite direction of the deviation direction corresponding to the node deviation calculation result can be determined by the displacement method, which can be expressed by node angular displacement or node linear displacement.

[0096] 1052. Determine a finite element node force according to the node displacement;

[0097] In the embodiment of the present application, the finite element node force is calculated by the second formula and the third formula according to the node displacement:

[0098] The second formula is:

[0099]

[0100] in, is the element stiffness matrix, is the unit node displacement;

[0101] The third formula is:

[0102]

[0103] Wherein, B represents the stress matrix (also called the strain matrix), D is the elastic coefficient matrix, e represents the unit e, and Ω represents the integral region. It is understandable that some parameters required in the stress matrix B, the elastic coefficient matrix D and the related formulas can be preset or set based on experience, and the embodiments of the present application do not limit this.

[0104] In the embodiment of the present application, the second formula and the third formula are finite element node force calculation formulas. The displacement applied to each node in the finite element model B is known, and the finite element node force It can be calculated by the second and third formulas.

[0105] 1053. Determine the nodal force required to be applied when each node in the finite element model B is pushed back to its original corresponding position in the finite element model A based on the finite element nodal force.

[0106] In the embodiment of the present application, the node force F is calculated by the first formula according to the finite element node force: node ;

[0107] The first formula includes:

[0108]

[0109] Among them, F node is the nodal force, is the finite element node force, m is the surrounding node force F node The number of finite elements adjacent to the corresponding node, i is the i-th finite element. It can be understood that the node force F node is the node force of each finite element at that location of all the adjacent m finite elements around the node The sum of .

[0110] 106. Calculate the sum of all the nodal forces in the same direction in the shaping direction to obtain the shaping pressure.

[0111] In the embodiment of the present application, according to the static balance, the sum of all the node force components calculated in the shaping direction is zero, that is, the resultant force of the action force and the reaction force is zero. Assuming that the sum of the group of node force components with positive values ​​is the action force, the sum of the group of node force components with negative values ​​is the reaction force. The absolute value of the sum of any group of components is the shaping pressure. Therefore, the shaping pressure can be obtained by calculating the sum of the values ​​of the group of node force components with positive values; or, the shaping pressure can be obtained by calculating the sum of the values ​​of the group of node force components with negative values.

[0112] In some embodiments, after step 106, the following steps are further included:

[0113] The prediction accuracy of the plastic surgery pressure is adjusted by a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected from production practice.

[0114] In data analysis, regression models are important tools for predicting continuous target variables. Traditional regression models or AI machine learning models range from simple linear regression to complex deep learning models. They can use big data from production practice to calibrate the theoretical prediction of shaping pressure, establish a data-driven shaping pressure rapid prediction model, and directly obtain the optimal shaping pressure through the shaping pressure rapid prediction model based on the measured deviation of the parts, thereby greatly improving the on-site correction efficiency of part deviations and ensuring the dimensional accuracy of the finished parts.

[0115] As can be seen from the above, the method for rapid prediction of shaping pressure based on the actual scanning data of product parts provided by the present invention is different from the traditional shaping pressure prediction method. The traditional shaping pressure prediction method is to simulate the shaping process by using stamping forming simulation technology, and obtain the required shaping pressure by calculating the collision contact force between the shaping mold and the workpiece. Therefore, the traditional shaping pressure prediction method requires time-consuming and labor-intensive finite element modeling of the shaping mold and reverse modeling of the workpiece according to the scanning data, and the calculation of the forming contact algorithm adopted is complex and very time-consuming, which cannot meet the production requirements of "on-site detection and real-time correction", and is not suitable for on-site correction applications of actual deviations of product parts. The finite element model of the method described in the present invention is only based on product design data and scanning data, the model construction method is simple and fast, and the finite element numerical solution method used is a displacement method known in the industry for fast solution, which can meet the application requirements of "real-time output results", and then with the support of big data in production practice, a data-driven rapid shaping pressure prediction model can be established, which greatly improves the on-site correction efficiency of part deviations and ensures the dimensional accuracy of finished parts.

[0116] In one implementation of the embodiment of the present application, the following may be included: Figure 2 The process shown. Figure 2This is a flowchart of an implementation method of an embodiment of the present application, and the process includes:

[0117] S10. Input product design data of the part and perform finite element meshing to obtain a finite element model A of the product design data.

[0118] In the embodiment of the present application, the existing finite element professional software in the industry (such as HYPERMESH, ANSA, etc.) is used to perform finite element meshing on the product design data.

[0119] S20: Input the actual scan data of the product parts and align the positions with the product design data.

[0120] In an embodiment of the present application, the point cloud registration technology known in the industry can be used to positionally register the actual scanning data of the product parts with the product design CAD geometric data or the finite element model A.

[0121] S30, calculating the absolute deviation between the actual scanning data and the product design data.

[0122] In this step, the deviation analysis technology known in the industry can be used to calculate the absolute deviations of the actual scan data and the product design data after position registration.

[0123] S40. According to the deviation calculation result, the position of each node of the finite element model A is updated to construct a finite element model B that is consistent with the actual scanning data of the product part.

[0124] In this step, each node position of the product design data finite element model A can be updated to the actual scan data of the product part according to the calculation result of its node deviation, so as to construct a finite element model B that matches the actual scan data of the product part.

[0125] S50. In the finite element model B, displacement is applied to each node in the reverse direction of its deviation direction, and the node force required to be applied when each node is pushed back to its original corresponding position in the finite element model A is calculated using a finite element numerical solution method.

[0126] The displacement method is a finite element algorithm known in the industry that uses node angular displacement and node linear displacement to solve the static equilibrium equation, that is, the internal force of the entire structure is calculated by the node displacement.

[0127] As shown in Formula 1, the node force F node is the node force of each finite element at that location of all the adjacent m finite elements around the node The sum of

[0128]

[0129] Formula 2 shows the industry-known formula for calculating finite element node forces. Figure 6 As shown in the figure, the displacements applied to each node in the finite element model B are known, and the finite element node forces It can be calculated by formula 2.

[0130]

[0131]

[0132] in and are the unit node force and unit node displacement, respectively. is the element stiffness matrix.

[0133] S60. Calculate the sum of the components of all nodal forces in the same direction in the shaping direction to obtain the shaping pressure.

[0134] According to static equilibrium, the sum of all node force components calculated in the shaping direction is zero, that is, the resultant force of the action force and the reaction force is zero. Assuming that the sum of the node force components with positive values ​​is the action force, the sum of the node force components with negative values ​​is the reaction force. The absolute value of the sum of any group of components is the shaping pressure.

[0135] S70. Collect big data from production practice to calibrate the theoretical prediction of shaping pressure, and obtain a rapid prediction model for shaping pressure through traditional regression models or artificial intelligence machine learning models.

[0136] In data analysis, regression models are important tools for predicting continuous target variables. Traditional regression models or AI machine learning models range from simple linear regression to complex deep learning models. They can use big data from production practice to calibrate the theoretical prediction of shaping pressure, establish a data-driven shaping pressure rapid prediction model, and directly obtain the optimal shaping pressure through the shaping pressure rapid prediction model based on the measured deviation of the parts, thereby greatly improving the on-site correction efficiency of part deviations and ensuring the dimensional accuracy of the finished parts.

[0137] Combination Figures 3 to 7 The application examples of the plastic surgery pressure rapid prediction method provided in the embodiment of the present application are as follows:

[0138] Figure 3 This is an example of the product design CAD design data provided in the embodiment of the present application. The product is an aluminum alloy thin product (material thickness 1.0 mm).

[0139] For example Figure 3 The product shown in FIG. 1 is processed as in step 101 above to obtain Figure 4The model after finite element meshing shown in FIG. is finite element model A. Specifically, the existing finite element professional software (such as HYPERMESH, ANSA, etc.) in the industry can be used to Figure 3 The product design data shown in the figure is divided into finite element meshes to obtain the following Figure 4 Finite element model A shown.

[0140] Get the actual scan data of the part and get Figure 5 The data model corresponding to the actual scan data shown is then processed as in step 102 above, and the acquired actual scan data of the part is aligned with the product design data.

[0141] Next, the above-mentioned step 103 is performed to determine the node deviation calculation result between the actual scan data and the product design data, such as Figure 6 As shown, the deviation value is approximately between 0 and 3.3 mm.

[0142] Next, the above-mentioned steps 104 and 105 are processed. During the process, the node displacement corresponding to the displacement applied in the opposite direction of the deviation corresponding to the node deviation calculation result to each node in the finite element model B can be calculated, such as Figure 7 As shown, the values ​​of the node displacements are between 0 and 3.320e+00.

[0143] Next, the above-mentioned step 106 is processed. According to the static balance, the sum of all the node force components calculated in the shaping direction is zero, that is, the resultant force of the action force and the reaction force is zero. Assuming that the sum of the group of node force components with positive values ​​is the action force, the sum of the group of node force components with negative values ​​is the reaction force. The absolute value of the sum of any group of components is the shaping pressure. Table 1 shows that the shaping pressure calculation result in this application example is 5.46E+04 Newton.

[0144]

[0145] Table 1

[0146] In the application example of the present application, the shaping pressure can be further adjusted. Specifically, big data from production practice can be collected to calibrate the accuracy of the theoretical prediction of the shaping pressure, and a rapid prediction model for the shaping pressure can be obtained through a traditional regression model or an artificial intelligence machine learning model.

[0147] In data analysis, regression models are important tools for predicting continuous target variables. Traditional regression models or AI machine learning models range from simple linear regression to complex deep learning models. They can use big data from production practice to calibrate the theoretical prediction of shaping pressure, establish a data-driven shaping pressure rapid prediction model, and directly obtain the optimal shaping pressure through the shaping pressure rapid prediction model based on the measured deviation of the parts, thereby greatly improving the on-site correction efficiency of part deviations and ensuring the dimensional accuracy of the finished parts.

[0148] Figure 8 This is a schematic diagram of the internal modules of a plastic surgery pressure rapid prediction device provided in an embodiment of the present application. The internal modules of the plastic surgery pressure rapid prediction device 800 include:

[0149] The acquisition module 801 is used to acquire the product design data of the part and the actual scanning data of the part;

[0150] Processing module 802 is used to execute or implement the above Figure 1 The corresponding steps are step 101, step 102, step 103, step 104, step 105, and step 106 in each embodiment.

[0151] In some embodiments, the processing module 802 is also used to adjust the prediction accuracy of the plastic surgery pressure through a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected in production practice.

[0152] Fig. 9 Schematic diagram of a data processing device provided in an embodiment of the present application. The data processing device 900 includes a memory 902, a processor 901, and a computer program 903 stored in the memory 902 and executable on the processor 901. When the processor 901 executes the computer program 903, the following is achieved: Figure 1 The corresponding methods of each embodiment.

[0153] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0154] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0155] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0156] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0159] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0160] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for rapid prediction of shaping pressure, characterized in that: include:

101. Obtain product design data of the parts, perform finite element meshing, and obtain a finite element model A; 102. Acquire actual scanning data of the part, and perform position registration with the product design data; 103. Determine a calculation result of a node deviation between the actual scan data and the product design data; 104. According to the node deviation calculation result, update the position of each node of the finite element model A to determine the finite element model B; 105. In the finite element model B, a displacement is applied to each node in the direction of the deviation corresponding to the node deviation calculation result in the reverse direction, and a finite element numerical solution method is used to calculate the node force that needs to be applied when each node in the finite element model B is pushed back to the original corresponding position in the finite element model A; 106. Calculate the sum of all the nodal force components in the same direction in the shaping direction to obtain the shaping pressure.

2. The method according to claim 1, characterized in that: After step 106, the following steps are further included: The prediction accuracy of the plastic surgery pressure is adjusted by a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected in production practice.

3. The method according to claim 1 or 2, characterized in that: The step 104 includes: 1041. Determine the moving direction and displacement value of each node of the finite element model A according to the node deviation calculation result; 1042. Calculate the coordinates of each node of the finite element model B according to the coordinates of each node of the finite element model A, the moving direction, and the displacement value to obtain the finite element model B.

4. The method according to claim 1 or 2, characterized in that: The step 105 comprises: 1051. Determine, according to the coordinates of each node in the finite element model B and the coordinates of each node in the finite element model A, a node displacement applied to each node in the finite element model B in the opposite direction of the deviation direction corresponding to the node deviation calculation result; 1052. Determine a finite element node force according to the node displacement; 1053. Determine, based on the finite element node force, the node force that needs to be applied when each node in the finite element model B is pushed back to its original corresponding position in the finite element model A.

5. The method according to claim 4, characterized in that The step 1053 includes: According to the finite element node force, the node force F is calculated by the first formula node ; The first formula includes: Among them, F node is the nodal force, is the finite element node force, m is the surrounding node force F node The number of finite elements adjacent to the corresponding node, i is the i-th finite element.

6. The method according to claim 5, characterized in that The step 1052 includes: According to the node displacement, the finite element node force is calculated by the second formula and the third formula. The second formula is: in, is the element stiffness matrix, is the unit node displacement; The third formula is: Among them, B represents the stress matrix, D is the elastic coefficient matrix, e represents the unit e, and Ω represents the integration area.

7. The method according to claim 1 or 2, characterized in that: The step 106 includes: Calculate the sum of the values ​​of a group of nodal force components with positive values ​​to obtain the shaping pressure; Or, the shaping pressure is obtained by calculating the sum of the values ​​of a group of node force components whose values ​​are negative.

8. A rapid prediction device for shaping pressure, characterized in that: include: An acquisition module, used to acquire product design data of a part and to acquire actual scan data of the part; Processing modules for: Performing finite element meshing on the obtained product design data to obtain a finite element model A; Performing position registration on the acquired actual scanning data and the product design data; Determine a node deviation calculation result between the actual scan data and the product design data; According to the node deviation calculation result, the position of each node of the finite element model A is updated to determine the finite element model B; In the finite element model B, a displacement is applied to each node in the direction of the deviation corresponding to the node deviation calculation result in the reverse direction, and a finite element numerical solution method is used to calculate the node force that needs to be applied when each node in the finite element model B is pushed back to the original corresponding position in the finite element model A; The sum of the components of all the nodal forces in the same direction in the shaping direction is calculated to obtain the shaping pressure.

9. The device according to claim 8, characterized in that The processing module is also used for: The prediction accuracy of the plastic surgery pressure is adjusted by a regression model or an artificial intelligence machine learning model, and the regression model or the artificial intelligence machine learning model is trained based on big data collected in production practice.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images