A mold 3D simulation analysis method

Abstract

The present application relates to a 3D simulation analysis method for a mold, which obtains a 3D CAD model of the mold, performs preprocessing and meshing, encrypts the mesh in key areas, calculates stress values ​​using finite element analysis, optimizes the mesh through iterative calculations until convergence requirements are met, and obtains stress distribution. A support vector machine regression algorithm is used to establish a nonlinear prediction model of stress characteristics and fatigue life, and the mold structure is optimized. The optimization plan is converted into a CAD model and a processing program is generated to achieve accurate prediction of the mold fatigue life and automated optimization design, thereby improving the mold service life and reliability, and providing important technical support for 3D simulation analysis of mold design and manufacturing.

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to a mold 3D simulation analysis method. Background Art

[0002] Mold fatigue life prediction and optimization is a complex engineering problem involving multiple interrelated technical challenges. During use, molds are subjected to complex cyclic loads, and their internal stress distribution is highly nonlinear and uneven. Traditional simplified analysis methods have difficulty capturing this complex stress state, which can easily lead to huge deviations in life prediction. Even using the finite element method for refined modeling, there are still challenges in ensuring the rationality of mesh division and the accuracy of boundary conditions. The fatigue failure mechanism of molds is very complex, involving multiple stages of crack initiation and propagation. A single stress indicator cannot fully reflect the fatigue damage process. It is urgent to extract the most representative characteristic parameters from massive stress analysis data and establish a quantitative relationship between stress state and fatigue life. Mold structure optimization design faces many challenges. While ensuring mold strength and rigidity, it is necessary to target and improve local high-stress areas. It is necessary to avoid material waste caused by over-design and ensure that the optimized structure still has good processability and economy. It is necessary to establish an organic connection between simulation analysis, life prediction, and structural optimization.

[0003] The solution proposed by the present invention to the above-mentioned shortcomings is: through refined 3D CAD models and encrypted grid division, the complex stresses inside the mold can be accurately captured, key stress characteristic parameters can be extracted, and a nonlinear prediction model can be established to comprehensively reflect fatigue damage. Through simulation analysis and structural optimization, high-stress areas can be improved, over-design can be avoided, and the processability and economy of the optimized structure can be ensured. At the same time, iterative optimization can reduce stress concentration and improve fatigue life. The prediction accuracy can be verified through actual tests, cutting parameters can be optimized, and processing accuracy and surface quality can be improved, thereby effectively solving the defects in the existing technology. Summary of the Invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the purpose of this application is to provide a mold 3D simulation analysis method.

[0005] The mold 3D simulation analysis method described in this application includes the following steps:

[0006] S1. Based on the three-dimensional CAD model of the mold, the mold is spatially discretized using a tetrahedral mesh. The mesh is encrypted during mesh division in the sharp corners and thin-walled parts of the stress concentration area. The stress concentration area is selected as the key area, and the relative error of the stress value in the key area is calculated. The calculation formula for the relative error is: |(σ_n-σ_n-1) / σ_n-1|, where σ_n is the stress value at the current mesh density and σ_n-1 is the stress value at the previous mesh density.

[0007] S2. For the three-dimensional CAD model of the mold after meshing in step S1, input the elastic modulus and Poisson's ratio parameters of the mold material, apply the mold working load and direction, set the displacement constraints and contact conditions, and solve the displacement and stress components of each node of the mold using finite element analysis software;

[0008] S3. Select a color scale based on the yield strength of the mold material in step S2 to generate a stress distribution cloud map, adjust the viewing angle to highlight the distribution characteristics of the stress concentration area, and add dimension annotations;

[0009] S4, extracting features from the stress distribution cloud map of step S3, obtaining the numerical values ​​and spatial coordinates of the maximum principal stress value and the von Mises stress value, calculating the stress gradient direction and amplitude, and quantitatively evaluating the uniformity of the stress distribution;

[0010] S5. Based on the fatigue performance data of the mold material, a support vector machine regression algorithm is used to establish a nonlinear prediction model of stress characteristic parameters and mold fatigue life. The maximum principal stress value, von Mises stress value, and stress gradient amplitude in step S4 are selected as characteristic parameters, and the fatigue life is used as label data. Cross-validation is performed using a grid search method to determine the kernel function type, regularization parameter, and kernel function parameter of the support vector machine.

[0011] S6. Using the nonlinear prediction model in step S5, determine whether the stress concentration of the current mold design exceeds the material fatigue strength limit. If so, chamfer sharp corners in the mold structure and reinforce thin-walled areas. If not, no treatment is performed, thereby obtaining an optimized mold design.

[0012] S7. Re-performing finite element analysis on the mold design optimized in step S6, extracting stress characteristic parameters, calculating the maximum stress reduction and the improvement in the uniformity of stress distribution, and using these to predict the increase in fatigue life;

[0013] S8. Convert the mold design optimized in step S6 into a three-dimensional CAD model, import it into computer-aided manufacturing software for tool path planning and cutting parameter selection, simulate the CNC machining process and estimate the machining time, generate a CNC machining program, and upload it to the CNC machine tool for machining.

[0014] Preferably, in the step S1, the three-dimensional CAD model data of the mold is obtained, the model is preprocessed, and meshing is performed; stress concentration areas are determined according to the structural characteristics and stress distribution of the mold, and the stress concentration areas include sharp corners and thin-walled parts, and are marked as key areas; the mold is spatially discretized using a tetrahedral mesh to generate an initial mesh model; during the meshing process, the mesh of the key area is encrypted; finite element analysis is performed to calculate the stress value of each unit at the current mesh density to obtain a stress distribution cloud map of the entire mold; the units in the key area are selected, their stress values ​​are extracted, and the relative error between the stress value at the current mesh density and the stress value at the previous mesh density is calculated;

[0015] The calculation formula of the relative error is: |(σ_n-σ_n-1) / σ_n-1|, σ_n is the stress value under the current grid density, and σ_n-1 is the stress value under the previous grid density;

[0016] Determine whether the calculated relative error is less than the preset threshold: if so, the current grid size is considered to meet the convergence requirements and the calculation is stopped; if not, return to the key area to further refine the grid and recalculate;

[0017] Based on the final mesh model, finite element analysis is performed to obtain the stress distribution of the mold under actual working conditions, which is used to identify stress concentration areas and weak links.

[0018] Preferably, in the step S2, the three-dimensional CAD model of the mold is discretized using a grid division method according to the geometric shape and structural characteristics of the mold to generate a finite element model; the mechanical performance parameters of the mold material, including the elastic modulus and Poisson's ratio, are obtained, and are input into the finite element analysis software as material properties, and the material properties are input into each unit of the mold finite element model; the size and direction of the external load on the mold are determined, and are applied as boundary conditions to the corresponding positions of the finite element model, and displacement constraints of the mold are set at the same time, including limiting the movement of degrees of freedom; the contact relationship and contact properties between the various components of the mold are defined, including contact type, contact surface, friction coefficient, and contact pairs are established in the finite element model; the solution module of the finite element analysis software is called, the solution method and convergence criterion are selected, and the force analysis of the mold finite element model is performed to obtain the deformation field and stress field distribution results of the mold under the working load; the displacement component and stress component data of each node of the mold are extracted from the finite element analysis results, and according to the size and distribution characteristics of the data, whether the mold meets the strength and stiffness requirements under the working load is judged, and the stress concentration area is identified;

[0019] If the deformation and stress levels of the mold exceed the preset range, a finite element analysis model is constructed based on the optimized mold design, and material properties, boundary conditions, and load conditions are set to perform finite element solution calculations.

[0020] Extract stress characteristic parameters from the finite element analysis results, including the maximum stress value and stress distribution uniformity index. Use the fatigue life prediction model and the stress characteristic parameters to calculate the fatigue life of the optimized mold and obtain the fatigue life increase. Use the stress distribution cloud diagram and stress uniformity index to evaluate the uniformity of the stress distribution of the optimized mold.

[0021] If the maximum stress reduction and fatigue life increase both reach the preset thresholds, and the uniformity of stress distribution meets the requirements, the optimized mold design solution is output.

[0022] Preferably, in step S3, a mapping relationship between a color scale and a stress value is established according to the yield strength of the mold material for generating a stress distribution cloud map; the stress distribution of the mold under stress is calculated by a finite element analysis method to obtain stress value data of each area; a stress distribution cloud map is generated according to the mapping relationship between the stress value data and the color scale, where different colors represent different stress value ranges; image processing is performed on the generated stress distribution cloud map, and the viewing angle and rendering parameters are adjusted; dimension annotations are added to the stress distribution cloud map to mark the size information of key areas; an image segmentation algorithm is used to divide the stress distribution cloud map into regions to identify the location and range of stress concentration areas; based on the regional division results, the stress value data of the stress concentration area is extracted and statistical analysis is performed to obtain characteristic parameters of the stress concentration degree and distribution; the uniformity of the overall stress distribution is quantitatively evaluated by calculating the mean square error of the local stress gradient amplitude; based on the quantitative evaluation results of the uniformity of the stress distribution, a clustering algorithm is used to partition the stress distribution cloud map to identify high-risk areas with uneven stress distribution.

[0023] Preferably, in step S4, a mapping relationship between a color scale and a stress value is established according to the yield strength of the mold material to generate a stress distribution cloud map; the stress distribution of the mold under the stress state is calculated by a finite element analysis method to obtain stress value data of each area; a stress distribution cloud map is generated according to the mapping relationship between the stress value data and the color scale; image processing is performed on the generated stress distribution cloud map, and features are extracted from the cloud map using an image processing algorithm to obtain a digital representation of the stress distribution; the maximum principal stress value and the von Mises stress value are determined for the extracted digital representation of the stress distribution. The numerical size and spatial coordinates corresponding to the maximum principal stress value and the von Mises stress value are calculated; the gradient direction and gradient amplitude of the stress in space are calculated according to the spatial coordinates of the maximum principal stress value and the von Mises stress value; if the gradient amplitude exceeds a preset threshold, it is judged that the stress distribution is uneven, and the area is marked using a machine learning algorithm; the uniformity of the entire stress distribution cloud map is evaluated, and the uniformity of the overall stress distribution is quantitatively evaluated by calculating the mean square error of the local stress gradient amplitude; based on the quantitative evaluation results of the uniformity of the stress distribution, the stress distribution cloud map is partitioned using a clustering algorithm to identify high-risk areas with uneven stress distribution.

[0024] Preferably, in the step S5, fatigue performance data of the mold material are obtained, including the maximum principal stress value, the von Mises stress value, the stress characteristic parameters of the stress gradient amplitude and the corresponding fatigue life data; the obtained stress characteristic parameters and fatigue life data are preprocessed to remove outliers and noise data, and the data are normalized; based on the preprocessed data, a support vector machine regression algorithm is used to establish a nonlinear prediction model between stress characteristic parameters and fatigue life; a grid search method is used to traverse different kernel function types, regularization parameters and kernel function parameter combinations, and cross-validation is performed to evaluate the prediction performance of the nonlinear prediction model; based on the cross Verify the results and determine the optimal support vector machine model parameters, including the kernel function type, regularization parameter, and kernel function parameter; use the optimized support vector machine model to predict the stress characteristic parameters of the new mold material to obtain its corresponding fatigue life prediction value; compare the predicted fatigue life with the actual test results to evaluate the prediction accuracy of the nonlinear prediction model; use the finite element analysis method to calculate the stress distribution of the mold under the working state, and obtain the stress concentration area and stress concentration coefficient; use the calculated stress concentration coefficient as input and substitute it into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level;

[0025] If the mold fatigue life is lower than the preset threshold corresponding to the material fatigue strength limit, the current mold design is judged to have a high degree of stress concentration and requires structural optimization. For stress concentration areas, a chamfering method is used to set a circular arc transition with a certain radius at sharp corners. For thin-walled areas, reinforcing ribs are added in the thin-walled areas to increase the cross-sectional area.

[0026] The optimized mold is re-analyzed by finite element analysis to calculate stress distribution and predict fatigue life.

[0027] Preferably, in the step S6, fatigue performance data of the mold material is obtained, including the maximum principal stress value, the von Mises stress value, the stress characteristic parameters of the stress gradient amplitude and the corresponding fatigue life data; the obtained stress characteristic parameters and fatigue life data are preprocessed to remove outliers and noise data, and the data is normalized; based on the preprocessed data, a nonlinear prediction model between the stress characteristic parameters and fatigue life is established using a support vector machine regression algorithm; a grid search method is used to traverse different kernel function types, regularization parameters and kernel function parameter combinations, and cross-validation is performed to evaluate the prediction performance of the model; based on the cross-validation results, the optimal support vector is determined. The machine model parameters include kernel function type, regularization parameter and kernel function parameter; the optimized support vector machine model is used to predict the stress characteristic parameters of the new mold material to obtain its corresponding fatigue life prediction value; the finite element analysis method is used to calculate the stress distribution of the mold under the working state, and the stress concentration area and stress concentration coefficient are obtained; the calculated stress concentration coefficient is used as input and substituted into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level; the predicted mold fatigue life is compared with the fatigue strength limit value of the material to determine whether the stress concentration degree of the current mold design exceeds the fatigue strength limit of the material;

[0028] If the mold fatigue life is lower than the preset threshold corresponding to the material fatigue strength limit, the current mold design is judged to have a high degree of stress concentration and requires structural optimization. For stress concentration areas, a chamfering method is used to set arc transitions of a certain radius at sharp corners. For thin-walled areas, reinforcing ribs are pre-set in the thin-walled areas to increase the cross-sectional area. The optimized mold is then re-analyzed with finite element analysis to calculate the stress distribution and predict the fatigue life.

[0029] If the fatigue life of the optimized mold is still lower than the preset threshold corresponding to the material fatigue strength limit, the mold structure design will continue to be iteratively optimized until the fatigue life requirements are met;

[0030] Through iterative optimization, the stress concentration of the mold is gradually reduced and the fatigue life of the mold is improved; the optimized mold design scheme is compared with the original design scheme to evaluate the optimization effect; by comparing the stress distribution, stress concentration factor and fatigue life prediction value before and after optimization, the optimization effect is quantified and the final mold design scheme is determined. The final mold design scheme is converted into a three-dimensional model and the CNC machining code required for mold processing is generated; according to the generated CNC machining code, the mold is processed and manufactured, and the processed mold is subjected to actual fatigue testing to verify the accuracy of the fatigue life prediction model and the effectiveness of the optimization design.

[0031] Preferably, in step S7, according to the optimized mold design scheme, a finite element analysis model is constructed, material properties, boundary conditions and load conditions are set, and the stress distribution of the mold in the working state is calculated using a finite element solution method to obtain the stress concentration area and stress concentration coefficient; stress characteristic parameters are extracted from the finite element analysis results, including the maximum stress value and the stress distribution uniformity index, which are compared with the stress characteristic parameters before optimization, and the reduction range of the maximum stress value is calculated to determine whether the preset threshold is reached. If not, the mold design optimization iteration is continued; the calculated stress concentration coefficient is used as input and substituted into the pre-established fatigue life prediction model. Predict the fatigue life of the mold under the current stress level and obtain the fatigue life increase; determine whether the fatigue life increase reaches the preset percentage. If not, return to continue the mold design optimization iteration until the fatigue life increase is no less than 20% of the original life; evaluate the stress distribution uniformity of the optimized mold through stress distribution cloud diagrams and stress uniformity indicators. If the uniformity does not meet the requirements, use chamfering treatment methods for stress concentration areas, setting arc transitions of a certain radius at sharp corners to improve stress distribution uniformity; for thin-walled areas, preset reinforcement ribs in the thin-walled areas to increase the cross-sectional area, reduce the stress concentration level, and obtain the optimized mold design solution;

[0032] Re-perform finite element analysis on the mold design optimized in step S6, calculate the stress distribution, extract the maximum stress value and stress uniformity index, and determine whether it meets the preset threshold requirements;

[0033] If the maximum stress reduction and fatigue life increase both reach the preset thresholds, and the stress distribution uniformity meets the requirements, the optimized mold design scheme is output and the final mold structure parameters are determined;

[0034] The optimized mold design plan is passed to the next link for mold processing and manufacturing, completing the mold design optimization process.

[0035] Preferably, in step S8, a three-dimensional CAD model is constructed according to the optimized mold design scheme, and the CAD model is imported into the CAM software through the model conversion interface for subsequent processing; in the CAM software, the cutting parameters such as tool type, cutting amount, and feed speed are selected, the tool motion path is planned, and a NC machining program is generated; the machining simulation function provided by the CAM software is used to simulate the NC machining process, analyze the interference between the tool and the workpiece and the cutting force, estimate the machining time, and optimize the cutting parameters and tool path; the generated NC machining program is converted into a code format that can be recognized by the NC machine tool through the post-processor, and uploaded to the NC system, and the NC machine tool controls the tool movement according to the machining program instructions, and dynamically adjusts the cutting parameters through online monitoring of tool wear and workpiece size during the machining process; after the machining is completed, the key dimensions of the workpiece are detected by the on-machine probe, the detection data are compared and analyzed with the CAD model, the machining accuracy and surface quality are evaluated, and a quality feedback report is generated; according to the quality feedback report, the NC machining program and cutting parameters are optimized and adjusted, and the optimized machining plan is applied to subsequent batch production;

[0036] If the machining accuracy and surface quality do not meet the requirements, return to adjust the cutting parameters and tool path, and regenerate the NC machining program until the machining quality meets the requirements;

[0037] Save the optimized NC machining program and cutting parameters to the process database.

[0038] The 3D simulation analysis method for a mold described in this application has the advantages of first performing finite element analysis on the mold, ensuring calculation accuracy through mesh encryption and convergence analysis, then extracting stress distribution characteristics, including parameters of maximum principal stress, von Mises stress, and stress gradient, and using a support vector machine regression algorithm to establish a nonlinear prediction model of these stress characteristics and fatigue life. Based on the prediction results, structural optimization is performed on areas exceeding the fatigue strength limit, including chamfers and stiffeners. Iterative analysis and optimization are performed until the stress reduction and life increase reach preset targets. Finally, the optimization solution is converted into a CAD model and a machining program is generated.

[0039] The present invention realizes accurate prediction and automated optimization design of mold fatigue life, effectively improves the service life and reliability of the mold, and provides important technical support for 3D simulation analysis of mold design and manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is the process of a mold 3D simulation analysis method described in this application Figure 1 ;

[0041] Figure 2 This is the process of a mold 3D simulation analysis method described in this application Figure 2 ;

[0042] Figure 3 This is the process of a mold 3D simulation analysis method described in this application Figure 3 . DETAILED DESCRIPTION

[0043] like Figure 1-Figure 3 As shown, the mold 3D simulation analysis method described in this application includes the following steps:

[0044] S1. Based on the three-dimensional CAD model of the mold, the mold is spatially discretized using a tetrahedral mesh. The mesh is encrypted during mesh division in the sharp corners and thin-walled parts of the stress concentration area. The stress concentration area is selected as the key area, and the relative error of the stress value in the key area is calculated. The calculation formula for the relative error is: |(σ_n-σ_n-1) / σ_n-1|, where σ_n is the stress value at the current mesh density and σ_n-1 is the stress value at the previous mesh density.

[0045] S2. For the three-dimensional CAD model of the mold after meshing in step S1, input the elastic modulus and Poisson's ratio parameters of the mold material, apply the mold working load and direction, set the displacement constraints and contact conditions, and solve the displacement and stress components of each node of the mold using finite element analysis software;

[0046] S3. Select a color scale based on the yield strength of the mold material in step S2 to generate a stress distribution cloud map, adjust the viewing angle to highlight the distribution characteristics of the stress concentration area, and add dimension annotations;

[0047] S4, extracting features from the stress distribution cloud map of step S3, obtaining the numerical values ​​and spatial coordinates of the maximum principal stress value and the von Mises stress value, calculating the stress gradient direction and amplitude, and quantitatively evaluating the uniformity of the stress distribution;

[0048] S5. Based on the fatigue performance data of the mold material, a support vector machine regression algorithm is used to establish a nonlinear prediction model of stress characteristic parameters and mold fatigue life. The maximum principal stress value, von Mises stress value, and stress gradient amplitude in step S4 are selected as characteristic parameters, and the fatigue life is used as label data. Cross-validation is performed using a grid search method to determine the kernel function type, regularization parameter, and kernel function parameter of the support vector machine.

[0049] S6. Using the nonlinear prediction model in step S5, determine whether the stress concentration of the current mold design exceeds the material fatigue strength limit. If so, chamfer sharp corners in the mold structure and reinforce thin-walled areas. If not, no treatment is performed, thereby obtaining an optimized mold design.

[0050] S7. Re-performing finite element analysis on the mold design optimized in step S6, extracting stress characteristic parameters, calculating the maximum stress reduction and the improvement in the uniformity of stress distribution, and using these to predict the increase in fatigue life;

[0051] S8. Convert the mold design optimized in step S6 into a three-dimensional CAD model, import it into computer-aided manufacturing software for tool path planning and cutting parameter selection, simulate the CNC machining process and estimate the machining time, generate a CNC machining program, and upload it to the CNC machine tool for machining.

[0052] like Figure 1-Figure 3 As shown, in step S1, according to the three-dimensional CAD model of the mold, the mold is spatially discretized using a tetrahedral grid, and the grid is encrypted during the grid division process of the sharp corners and thin-walled parts in the stress concentration area. These areas are selected as key areas, and the relative errors of the stress values ​​in the key areas are calculated; the relative error calculation formula is: |(σ_n-σ_n-1) / σ_n-1|, where σ_n is the stress value under the current grid density, and σ_n-1 is the stress value under the previous level grid density. When the relative error is less than the preset threshold, it is considered that the grid size meets the convergence requirements.

[0053] Furthermore, in step S1, the three-dimensional CAD model data of the mold is obtained, the model is pre-processed, and the integrity and rationality of the model are checked to ensure that the model can be meshed;

[0054] According to the structural characteristics and stress distribution of the mold, the stress concentration areas are determined, mainly including sharp corners and thin-walled areas. These areas are marked as key areas, and the mold is spatially discretized using tetrahedral meshes to generate an initial mesh model.

[0055] During the meshing process, mesh encryption is performed in key areas to increase mesh density;

[0056] Perform finite element analysis to calculate the stress value of each unit at the current mesh density and obtain the stress distribution cloud map of the entire mold; select units in key areas, extract their stress values, and calculate the relative error between the stress value at the current mesh density and the stress value at the previous mesh density. The formula for calculating the relative error is: |(σ_n-σ_n-1) / σ_n-1|, where σ_n is the stress value at the current mesh density and σ_n-1 is the stress value at the previous mesh density.

[0057] Determine whether the calculated relative error is less than the preset threshold,

[0058] If so, the current grid size is considered to meet the convergence requirements and the calculation is stopped;

[0059] If not, return to further refine the grid in the key area, increase the grid density, and recalculate;

[0060] Through iterative calculations, the mesh model is continuously optimized until the relative error meets the preset threshold requirements, and the final mesh model that meets the convergence requirements is obtained; based on the final mesh model, finite element analysis is performed to obtain the stress distribution of the mold under actual working conditions, and identify stress concentration areas and weak links; the mesh model that meets the convergence requirements and the corresponding stress distribution cloud map are output to provide data support for subsequent mold structure optimization and manufacturing process optimization.

[0061] Specifically, in step S1, the three-dimensional CAD model data of the mold is first obtained and imported into the CAD software using the IGES and STEP universal formats. The model is repaired and simplified to eliminate factors such as small faces and sharp corners that affect mesh division.

[0062] Then, based on the structural characteristics and stress distribution of the mold, the curvature analysis method is used to determine the stress concentration area, and the area with a curvature greater than 0.5mm^-1 is marked as the critical area;

[0063] Then, the mold is spatially discretized using tetrahedral meshes to generate an initial mesh model. The mesh size is set to 5 mm, and a mesh size of 0.5 mm is used for encryption in key areas.

[0064] Perform finite element analysis and use the von Mises stress criterion to calculate the stress value of each unit and obtain the stress distribution cloud map of the entire mold;

[0065] Select the elements in the critical area, extract their stress values, and calculate the relative error. If the relative error is greater than 5%, return to the meshing step, reduce the mesh size in the critical area to 50% of the original size, and recalculate.

[0066] Through iterative calculation, the mesh model is continuously optimized until the relative error is less than 5%, and the final mesh model that meets the convergence requirements is obtained;

[0067] Based on the final mesh model, finite element analysis was performed, using static analysis to calculate the stress distribution of the mold under actual working conditions. Areas where the stress was greater than 80% of the material's yield strength were identified as stress concentration areas and weak links.

[0068] Finally, the mesh model file and stress distribution cloud map are output to provide data support for subsequent mold structure optimization and manufacturing process optimization.

[0069] like Figure 1-Figure 3As shown, in step S2, for the three-dimensional CAD model of the mold after meshing in step S1, the elastic modulus and Poisson's ratio parameters of the mold material are input, the mold working load and direction are applied, the displacement constraints and contact conditions are set, and the displacement and stress components of each node of the mold are solved by finite element analysis software.

[0070] Furthermore, in step S2, the three-dimensional CAD model of the mold is discretized using a meshing method according to the geometric shape and structural characteristics of the mold to generate a finite element model;

[0071] Obtain the mechanical properties of the mold material, including elastic modulus and Poisson's ratio, input them into the finite element analysis software as material properties, and assign the material properties to each unit of the mold finite element model;

[0072] Determine the size and direction of the external load on the mold, apply it as a boundary condition to the corresponding position of the finite element model, and set the displacement constraint conditions of the mold, including limiting the movement of the degrees of freedom;

[0073] Define the contact relationship and contact properties between the various components of the mold, including contact type, contact surface, friction coefficient, and establish contact pairs in the finite element model;

[0074] Call the solution module of the finite element analysis software, select the solution method and convergence criteria, perform force analysis on the mold finite element model, and obtain the deformation field and stress field distribution results of the mold under the working load. Extract the displacement component and stress component data of each node of the mold from the finite element analysis results. Based on the size and distribution characteristics of the data, determine whether the mold meets the strength and stiffness requirements under the working load, and identify stress concentration areas.

[0075] If the deformation and stress level of the mold exceed the allowable range, a finite element analysis model is constructed based on the optimized mold design plan, and material properties, boundary conditions and load conditions are set to perform finite element solution calculations;

[0076] Stress characteristic parameters, including maximum stress value and stress distribution uniformity index, are extracted from the finite element analysis results. The fatigue life of the optimized mold is calculated using the fatigue life prediction model in combination with the stress characteristic parameters, and the fatigue life increase is obtained. The uniformity of the stress distribution of the optimized mold is evaluated through the stress distribution cloud map and stress uniformity index. If the maximum stress value reduction and fatigue life increase both reach the preset threshold value, and the uniformity of the stress distribution meets the requirements, the optimized mold design scheme is output, completing the design optimization process.

[0077] Specifically, in step S2, the mold solid model is first divided using a hexahedral mesh with a mesh size of 5 mm, generating a finite element model containing approximately 500,000 nodes and 300,000 elements;

[0078] Set the mold material to H13 hot work die steel, the elastic modulus to 210 GPa, and the Poisson's ratio to 0.3, and assign these material properties to all elements of the finite element model;

[0079] According to the actual working conditions, a pressure load of 3MPa is applied to the surface of the mold cavity, and full constraint is applied to the bottom surface of the mold;

[0080] Define the contact relationship between the mold components as surface-to-surface contact, set the friction coefficient to 0.1, and establish contact pairs on the mold parting surface and the slider surface;

[0081] Using ANSYS finite element analysis software, select the static analysis type, adopt the sparse matrix direct solution method, set the residual convergence criterion to 0.001, and perform force analysis and calculation on the mold;

[0082] The displacement and stress data of each node of the mold were extracted from the calculation results. It was found that the maximum deformation was 0.15mm and the maximum stress was 650MPa, located at the sharp corner of the mold cavity.

[0083] Since the maximum stress exceeds the yield strength of the material, the mold structure needs to be optimized;

[0084] According to the optimization plan, fillets were added to stress concentration areas, the slider guide method was adjusted, and finite element analysis was performed again;

[0085] After optimization, the maximum stress is reduced to 520MPa, the maximum deformation is reduced to 0.12mm, and fatigue life prediction shows that the number of uses can reach more than 500,000 times, meeting the design requirements;

[0086] Finally, through the stress cloud map and stress uniformity coefficient (uniformity coefficient increased from 1.8 to 1.5), it was verified that the stress distribution of the mold after optimization was more reasonable, and the design plan could be finalized and process preparation could be carried out.

[0087] like Figure 1-Figure 3 As shown, in step S3, a color scale is selected according to the yield strength of the mold material, a stress distribution cloud map is generated, and the viewing angle is adjusted to highlight the distribution characteristics of the stress concentration area, and dimension annotations are added.

[0088] Furthermore, in step S3, a mapping relationship between color scale and stress value is established according to the yield strength of the mold material for generating a stress distribution cloud map;

[0089] The stress distribution of the mold under stress is calculated by finite element analysis method to obtain the stress value data of each area;

[0090] Based on the mapping relationship between stress value data and color scale, a stress distribution cloud map is generated, with different colors representing different stress value ranges;

[0091] Perform image processing on the generated stress distribution cloud map and highlight the distribution characteristics of the stress concentration area by adjusting the viewing angle and rendering parameters;

[0092] Add dimension annotations to the stress distribution cloud map to mark the size information of key areas, use image segmentation algorithms to divide the stress distribution cloud map into regions, and identify the location and range of stress concentration areas;

[0093] According to the regional division results, the stress value data of the stress concentration area is extracted and statistically analyzed to obtain the characteristic parameters of the stress concentration degree and distribution;

[0094] By calculating the mean square error of the local stress gradient amplitude, the uniformity of the overall stress distribution is quantitatively evaluated.

[0095] According to the quantitative evaluation results of the uniformity of stress distribution, a clustering algorithm is used to partition the stress distribution cloud map and identify high-risk areas with uneven stress distribution.

[0096] Specifically, in step S3, a mapping relationship between a color scale and a stress value is established according to the yield strength of the mold material, including mapping the stress value range of 0-500 MPa to a blue to red color scale if the yield strength is 500 MPa;

[0097] Finite element analysis methods, including the use of ANSYS software, are used to mesh the mold and set boundary conditions to calculate the stress value data of each area of ​​the mold under stress.

[0098] According to the mapping relationship between stress value data and color scale, the stress distribution cloud map is generated using Python's matplotlib library, where different colors represent different stress value ranges;

[0099] Perform image processing on the generated stress distribution cloud map, including using the OpenCV library to adjust the viewing angle and rendering parameters, including lighting intensity and material properties, to highlight the distribution characteristics of the stress concentration area;

[0100] Add dimension annotations to the stress distribution cloud map, use the PIL library to add text annotations and arrow indicators in key areas, and mark key dimension information;

[0101] Image segmentation algorithms, including segmentation algorithms based on region growing, are used to divide stress distribution cloud images into regions and identify the location and range of stress concentration areas.

[0102] Based on the regional division results, the stress value data of the stress concentration area is extracted, and statistical analysis is performed using the NumPy library to calculate the average stress value and distribution characteristic parameters of the stress gradient in the stress concentration area;

[0103] The uniformity of the overall stress distribution is quantitatively assessed by calculating the mean square error of the local stress gradient amplitude, including using a sliding window method to slide a 20×20 pixel window on the stress distribution cloud map and calculating the mean square error of the stress gradient amplitude within each window;

[0104] Based on the quantitative evaluation results of stress distribution uniformity, the K-means clustering algorithm is used to partition the stress distribution cloud map and identify high-risk areas with uneven stress distribution, providing a basis for subsequent mold optimization design.

[0105] Specifically, the method further includes: in step S3, the yield strength is preset to 500 MPa through mapping relationship establishment, and a mapping relationship between the color scale and the stress value is established. The mapping range is preset to 0-500 MPa, corresponding to a blue to red color scale, including 0 MPa corresponding to blue and 500 MPa corresponding to red. The intermediate stress values ​​are assigned to the corresponding color gradient according to the linear interpolation method, and the color corresponding to 250 MPa is purple, which is between blue and red.

[0106] Finite element analysis was performed using ANSYS software, with a preset mesh size of 0.5 mm. Fixed constraints and actual working loads were set. The fixed constraints were implemented by simulating the mold support surface, while the actual working load was calculated through equivalent force conversion and distribution based on the stress conditions during mold operation.

[0107] The stress distribution cloud map was generated using Python's matplotlib library, and the OpenCV library was used to adjust the viewing angle and rendering parameters, including presetting the lighting intensity to 50% and the material attribute to metallic gloss. The PIL library was also used for dimensioning.

[0108] A segmentation algorithm based on region growing was used with a preset growth threshold of 150 MPa to identify stress concentration areas. The NumPy library was then used to extract relevant data. This involved comparing the stress values ​​of adjacent pixels starting from a seed point. If the stress value was greater than 150 MPa, it was included in the growing region until no new pixels met the criteria.

[0109] Perform statistical analysis to calculate the average stress value and stress gradient parameters. The sample size is preset to 100 data points. The mean square error of the local stress gradient amplitude is calculated using the sliding window method. The preset window movement step is 10 pixels. The uniformity of the stress distribution is evaluated, including the stress gradient, which is obtained by calculating the rate of change of the stress values ​​of adjacent data points.

[0110] Finally, the K-means clustering algorithm was used, with the number of cluster centers preset to 3, to perform cluster analysis and identify high-risk areas with uneven stress distribution. The preset threshold was 3 times the standard deviation of the mean square error. The mean and standard deviation of the stress gradient were calculated within each 10-pixel window, and then the standard deviations of all windows were averaged to obtain the mean square error.

[0111] like Figure 1-Figure 3 As shown, in step S4, feature extraction is performed on the stress distribution cloud map of step S3 to obtain the numerical values ​​and spatial coordinates of the maximum principal stress value and the von Mises stress value, calculate the stress gradient direction and amplitude, and quantitatively evaluate the uniformity of the stress distribution.

[0112] Furthermore, in step S4, a mapping relationship between color scale and stress value is established according to the yield strength of the mold material for generating a stress distribution cloud map;

[0113] The stress distribution of the mold under stress is calculated by finite element analysis method to obtain the stress value data of each area;

[0114] Based on the mapping relationship between stress value data and color scale, a stress distribution cloud map is generated, with different colors representing different stress value ranges;

[0115] Perform image processing on the generated stress distribution cloud map, use image processing algorithms to extract features from the cloud map, and obtain a digital representation of the stress distribution;

[0116] Based on the extracted digital representation of stress distribution, determine the numerical values ​​and spatial coordinates corresponding to the maximum principal stress value and the von Mises stress value;

[0117] According to the spatial coordinates of the maximum principal stress value and the von Mises stress value, the gradient direction and gradient amplitude of the stress in space are calculated;

[0118] If the gradient amplitude exceeds the preset threshold, it is judged that the stress distribution is uneven, and the machine learning algorithm is used to mark the area;

[0119] Evaluate the uniformity of the entire stress distribution cloud map and quantitatively evaluate the uniformity of the overall stress distribution by calculating the mean square error of the local stress gradient amplitude;

[0120] According to the quantitative evaluation results of the uniformity of stress distribution, a clustering algorithm is used to partition the stress distribution cloud map and identify high-risk areas with uneven stress distribution.

[0121] Specifically, in step S4, a mapping relationship between a color scale and a stress value is established according to the yield strength of the mold material, including mapping the stress value range of 0-500 MPa to a blue to red color scale if the yield strength is 500 MPa;

[0122] Finite element analysis methods, including the use of ANSYS software, were used to calculate the stress distribution of the mold under a load of 100 kN, and the stress value data of each grid cell was obtained;

[0123] Based on the mapping relationship between stress value data and color scale, a stress distribution cloud map is generated, including the area with stress value of 0-100MPa displayed in blue, the area with stress value of 100-200MPa displayed in green, and so on;

[0124] Perform image processing on the generated stress distribution cloud map, use the Canny edge detection algorithm to extract features from the cloud map, and obtain a digital representation of the stress distribution, including the gradient information of the stress value;

[0125] Based on the extracted digital representation of stress distribution, the maximum principal stress value is determined to be 450MPa, located at the coordinates (100,200) of the cloud map, and the von Mises stress value is 380MPa, located at the coordinates (150,250);

[0126] According to the spatial coordinates of the maximum principal stress value and the von Mises stress value, the Sobel operator is used to calculate that the stress gradient direction in space is 45 degrees and the gradient amplitude is 20 MPa / mm;

[0127] If the gradient amplitude exceeds the preset threshold of 15 MPa / mm, it is judged as uneven stress distribution, and the support vector machine algorithm is used to mark the area;

[0128] The uniformity of the entire stress distribution cloud map was evaluated. By calculating the mean square error of the local stress gradient amplitude, the uniformity evaluation value of the overall stress distribution was obtained to be 0.85.

[0129] According to the uniformity assessment value of stress distribution, the K-means clustering algorithm is used to partition the stress distribution cloud map and identify high-risk areas with uneven stress distribution, including classifying areas with stress gradient amplitude greater than 18 MPa / mm as high-risk areas.

[0130] like Figure 1-Figure 3As shown, in step S5, combined with the fatigue performance data of the mold material, the support vector machine regression algorithm is used to establish a nonlinear prediction model of stress characteristic parameters and mold fatigue life, the maximum principal stress value, von Mises stress value and stress gradient amplitude in step S4 are selected as characteristic parameters, and the fatigue life is used as label data. Cross-validation is performed through the grid search method to determine the kernel function type, regularization parameter and kernel function parameter of the support vector machine.

[0131] Furthermore, in step S5, fatigue performance data of the mold material is obtained, including maximum principal stress value, von Mises stress value, stress gradient amplitude stress characteristic parameter and corresponding fatigue life data;

[0132] Preprocess the acquired stress characteristic parameters and fatigue life data, remove outliers and noise data, and perform data normalization;

[0133] Based on the preprocessed data, a nonlinear prediction model between stress characteristic parameters and fatigue life is established using the support vector machine regression algorithm.

[0134] Through the grid search method, we traverse different kernel function types, regularization parameters and kernel function parameter combinations, perform cross-validation, and evaluate the prediction performance of the model;

[0135] Based on the cross-validation results, determine the optimal support vector machine model parameters, including kernel function type, regularization parameters, and kernel function parameters;

[0136] The optimized support vector machine model is used to predict the stress characteristic parameters of the new mold material and obtain its corresponding fatigue life prediction value;

[0137] The predicted fatigue life is compared with the actual test results to evaluate the prediction accuracy of the model. The finite element analysis method is used to calculate the stress distribution of the mold under working conditions and obtain the stress concentration area and stress concentration factor.

[0138] The calculated stress concentration factor is used as input and substituted into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level;

[0139] If the mold fatigue life is lower than the preset threshold corresponding to the material fatigue strength limit, it is determined that the stress concentration level of the current mold design is high and structural optimization is required;

[0140] For stress concentration areas, chamfering treatment is adopted to set arc transitions with a certain radius at sharp corners;

[0141] For thin-walled parts, the cross-sectional area is increased by reinforcing the ribs in the thin-walled area;

[0142] The optimized mold is re-analyzed by finite element analysis to calculate stress distribution and predict fatigue life.

[0143] Specifically, in step S5, first, the fatigue performance data of the mold material is obtained, including stress characteristic parameters such as the maximum principal stress value, the von Mises stress value, the stress gradient amplitude, and the corresponding fatigue life data. The preset data set contains 1000 samples, including 700 training sets, 200 validation sets, and 100 test sets. The acquired data is preprocessed to remove outliers and noise data, and the minimum-maximum normalization method is used to normalize the data to the [0,1] interval, with the preset minimum value being 0 and the maximum value being 1.

[0144] Then, based on the preprocessed data, the support vector machine regression algorithm was used to establish the model. Through the grid search method, the preset kernel function types included linear kernel, polynomial kernel (the degree was preset to 3), and radial basis kernel; the regularization parameter range was {0.1, 1, 10}; the kernel function parameter gamma value range was {0.001, 0.01, 0.1, 1}, and a 5-fold cross-validation was performed. The mean square error (MSE) of each cross-validation was calculated, and the MSE threshold was preset to 0.001. The parameter combination with the smallest MSE was selected as the optimal model parameter.

[0145] The optimized support vector machine model is used to predict the stress characteristic parameters of the new mold material and obtain the corresponding fatigue life prediction value. The predicted value is compared with the actual test results, and the mean absolute error and root mean square error evaluation indicators are calculated to evaluate the prediction accuracy of the model.

[0146] This includes calculating the mean absolute error (MAE) and root mean square error (RMSE) between the predicted value and the actual test result. The error thresholds for MAE and RMSE are preset to 0.05. If the error exceeds the threshold, the model parameters are adjusted and retrained.

[0147] Then, using the finite element analysis method, the 3D CAD model of the mold is imported into the finite element analysis software. The material properties, mesh division, load and boundary condition parameters are set to calculate the stress distribution of the mold under working conditions and obtain the stress concentration area and stress concentration coefficient.

[0148] This involves using finite element analysis with a preset mesh size of 0.5 mm to mesh the mold's 3D CAD model, setting material properties (elastic modulus, Poisson's ratio), setting the load condition to 1.5 times the actual working load, and boundary conditions such as fixed constraints and force loads. The stress distribution is calculated, stress concentration areas are identified, and the stress concentration factor threshold is preset to 3.

[0149] Substitute the calculated stress concentration factor into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level. If the mold fatigue life is lower than the preset threshold (100,000 times) corresponding to the material fatigue strength limit, it is determined that the stress concentration level of the current mold design is high and structural optimization is required;

[0150] A chamfering method is used for stress concentration areas, and a circular arc transition with a radius of 2mm is set at sharp corners;

[0151] For thin-walled areas, 3mm thick reinforcement ribs are preset in the thin-walled areas. The optimized mold is re-analyzed by finite element analysis to calculate the stress distribution and predict the fatigue life until the fatigue life requirements are met.

[0152] like Figure 1-Figure 3 As shown, in step S6, the trained fatigue life prediction model is used to determine whether the stress concentration level of the current mold design exceeds the fatigue strength limit of the material. If it exceeds the preset threshold, the sharp corners in the mold structure are chamfered and the thin-walled parts are reinforced.

[0153] Furthermore, in step S6, fatigue performance data of the mold material is obtained, including maximum principal stress value, von Mises stress value, stress gradient amplitude stress characteristic parameter and corresponding fatigue life data;

[0154] Preprocess the acquired stress characteristic parameters and fatigue life data, remove outliers and noise data, and perform data normalization;

[0155] Based on the preprocessed data, a nonlinear prediction model between stress characteristic parameters and fatigue life is established using the support vector machine regression algorithm.

[0156] Through the grid search method, we traverse different kernel function types, regularization parameters and kernel function parameter combinations, perform cross-validation, and evaluate the prediction performance of the model;

[0157] Based on the cross-validation results, determine the optimal support vector machine model parameters, including kernel function type, regularization parameters, and kernel function parameters;

[0158] The optimized support vector machine model is used to predict the stress characteristic parameters of the new mold material and obtain its corresponding fatigue life prediction value;

[0159] Finite element analysis method is used to calculate the stress distribution of the mold in the working state, and the stress concentration area and stress concentration coefficient are obtained;

[0160] The calculated stress concentration factor is used as input and substituted into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level;

[0161] Compare the predicted mold fatigue life with the fatigue strength limit of the material to determine whether the stress concentration of the current mold design exceeds the fatigue strength limit of the material;

[0162] If the mold fatigue life is lower than the preset threshold corresponding to the material fatigue strength limit, it is determined that the stress concentration level of the current mold design is high and structural optimization is required;

[0163] For stress concentration areas, chamfering treatment is adopted to set arc transitions with a certain radius at sharp corners;

[0164] For thin-walled parts, the cross-sectional area is increased by pre-setting reinforcing ribs in the thin-walled area;

[0165] Re-perform finite element analysis on the optimized mold to calculate stress distribution and predict fatigue life;

[0166] If the fatigue life of the optimized mold is still lower than the preset threshold corresponding to the material fatigue strength limit, the mold structure design will continue to be iteratively optimized until the fatigue life requirements are met;

[0167] Through iterative optimization, the stress concentration of the mold is gradually reduced and the fatigue life of the mold is improved;

[0168] Compare the optimized mold design with the original design to evaluate the optimization effect;

[0169] By comparing the stress distribution, stress concentration factor and fatigue life prediction value before and after optimization, the optimization effect is quantified and the final mold design solution is determined;

[0170] Convert the finalized mold design into a 3D model and generate the NC machining code required for mold processing;

[0171] The mold is processed and manufactured according to the generated CNC machining code, and actual fatigue testing is carried out on the processed mold to verify the accuracy of the fatigue life prediction model and the effectiveness of the optimized design.

[0172] Specifically, in step S6, fatigue testing is performed on the mold material to obtain fatigue life data at different stress levels, including stress characteristic parameters such as maximum principal stress value, von Mises stress value, and stress gradient amplitude;

[0173] The 3σ criterion was used to remove outliers, and the minimum-maximum normalization method was used to normalize the data to the interval [0,1].

[0174] Based on the normalized data, the Gaussian kernel function was selected, and different combinations of the regularization parameter C and the kernel function parameter γ were traversed by the grid search method. The prediction performance of the support vector machine regression model was evaluated using 5-fold cross validation, and the optimal parameter combination was obtained as C = 10, γ = 0.1;

[0175] Using the optimized support vector machine model, a finite element analysis was performed on the stress distribution of the mold in the working state. The stress concentration factor in the stress concentration area was found to be 2.5. Substituting this into the fatigue life prediction model, the fatigue life of the mold at the current stress level was predicted to be 10,000 cycles.

[0176] Comparing the predicted life with the material fatigue strength limit of 50,000 times, it was determined that the stress concentration level of the current mold design was high;

[0177] For stress concentration areas, a 2mm radius arc transition is used for chamfering, and a 3mm thick reinforcement rib is preset in the thin-wall area;

[0178] Finite element analysis of the optimized mold reduced the stress concentration factor to 1.8 and increased the fatigue life to 30,000 cycles, meeting the material fatigue strength limit requirements.

[0179] Comparing the stress concentration factor and fatigue life before and after optimization, the stress concentration factor was reduced by 28% and the fatigue life was increased by 2 times, verifying the effectiveness of the optimized design;

[0180] The optimized mold design was converted into a three-dimensional model, and CNC machining code was generated to complete mold manufacturing and actual fatigue testing. The test results were within 10% of the predicted life, verifying the accuracy of the fatigue life prediction model.

[0181] like Figure 1-Figure 2 As shown, in step S7, the mold design scheme optimized in step S6 is re-analyzed by finite element analysis to extract stress characteristic parameters, calculate the reduction range of the maximum stress value and the improvement degree of stress distribution uniformity, and predict the increase in fatigue life. If the reduction range of the maximum stress value is less than the preset threshold or the increase in fatigue life is less than the preset percentage, return to the previous step to continue optimization. The preset percentage can be set to an increase in fatigue life of not less than 20% of the original life.

[0182] Furthermore, in step S7, a finite element analysis model is constructed based on the optimized mold design scheme, material properties, boundary conditions, and load conditions are set, and the stress distribution of the mold in the working state is calculated using a finite element solution method to obtain the stress concentration area and stress concentration coefficient;

[0183] Extract stress characteristic parameters from the finite element analysis results, including the maximum stress value and stress distribution uniformity index, compare them with the stress characteristic parameters before optimization, calculate the reduction of the maximum stress value, and determine whether it reaches the preset threshold. If not, return to continue the mold design optimization iteration;

[0184] The calculated stress concentration factor is used as input and substituted into the pre-established fatigue life prediction model to predict the fatigue life of the mold under the current stress level and obtain the fatigue life increase;

[0185] Determine whether the increase in fatigue life reaches the preset percentage. If not, return to continue the mold design optimization iteration until the increase in fatigue life is no less than 20% of the original life.

[0186] The stress distribution uniformity of the optimized mold is evaluated through the stress distribution cloud map and stress uniformity index. If the uniformity does not meet the requirements, a chamfering method is used for the stress concentration area. A circular arc transition with a certain radius is set at the sharp corners to improve the stress distribution uniformity.

[0187] For thin-walled areas, by pre-setting reinforcing ribs in the thin-walled areas, the cross-sectional area is increased, the stress concentration is reduced, and an optimized mold design is obtained;

[0188] Re-perform finite element analysis on the mold design optimized in step S6, calculate the stress distribution, extract the maximum stress value and stress uniformity index, and determine whether it meets the preset threshold requirements;

[0189] If the maximum stress value reduction and fatigue life increase both reach the preset threshold, and the stress distribution uniformity meets the requirements, the optimized mold design scheme is output, the final mold structure parameters are determined, and the optimized mold design scheme is passed to the next link for mold processing and manufacturing, completing the mold design optimization process.

[0190] Specifically, in step S7, a finite element analysis model is first constructed in ANSYS software based on the optimized mold design scheme. The mold material is set to Cr12MoV, the elastic modulus is 210GPa, and the Poisson's ratio is 0.3. The temperature load during mold operation is 80°C and the pressure load is 150MPa. Tetrahedral meshing is used with a mesh size of 2mm. The mold stress distribution cloud map and the maximum stress value of 86MPa are obtained through solution calculation, which is located at the fillet of the mold cavity.

[0191] Extract the maximum stress values ​​before and after optimization, and calculate the reduction as (95-86) / 95=9.5%. This does not reach the preset threshold of 10%, so return to continue optimization.

[0192] Substituting the stress concentration factor of 1.8 into the Morrow fatigue life prediction model logσ=logC-1 / m·logN, and taking the material parameters C=2030, m=9.18, the calculated fatigue life is 82,000 times, which is 17.1% higher than the 70,000 times before optimization. However, it does not reach the preset percentage of 20%, so the optimization is returned to continue.

[0193] Through the stress distribution cloud map analysis, the stress gradient at the corner of the die is large, and the chamfer radius R5mm is used for transition. The stress value in the thin-walled area is high, and the preset thickness of the reinforcement rib is 5mm;

[0194] Finite element analysis was performed again on the optimized mold, and the maximum stress value was reduced to 78MPa, a decrease of 17.9%. The fatigue life was increased to 96,000 times, an increase of 37.1%. The uniformity of stress distribution was improved, meeting the preset requirements. The optimized mold design plan was output, completing the design optimization process.

[0195] like Figure 1-Figure 3 As shown, in step S8, the mold design scheme optimized in step S6 is converted into a three-dimensional CAD model, imported into computer-aided manufacturing software for tool path planning and cutting parameter selection, the CNC machining process is simulated and the machining time is estimated, and a CNC machining program is generated and uploaded to the CNC machine tool for machining.

[0196] Furthermore, in step S8, a three-dimensional CAD model is constructed according to the optimized mold design scheme, and the CAD model is imported into the CAM software through the model conversion interface for subsequent processing;

[0197] In the CAM software, select the cutting parameters of tool type, cutting amount, feed rate, plan the tool motion path, and generate the NC machining program;

[0198] Use the machining simulation function provided by CAM software to simulate the CNC machining process, analyze the interference between the tool and the workpiece and the cutting force, estimate the machining time, and optimize the cutting parameters and tool path;

[0199] The generated NC machining program is converted into a code format that can be recognized by the NC machine tool through the post-processor and uploaded to the NC system;

[0200] The CNC machine tool controls the tool movement according to the instructions of the machining program, and dynamically adjusts the cutting parameters by online monitoring of tool wear and workpiece size during the machining process;

[0201] After machining is completed, the key dimensions of the workpiece are inspected using an on-machine probe. The inspection data is compared and analyzed with the CAD model to evaluate machining accuracy and surface quality, and a quality feedback report is generated.

[0202] Optimize and adjust the CNC machining program and cutting parameters based on the quality feedback report, and apply the optimized machining plan to subsequent mass production;

[0203] If the machining accuracy and surface quality do not meet the requirements, return to step 2, adjust the cutting parameters and tool path, and regenerate the NC machining program until the machining quality meets the requirements;

[0204] The optimized CNC machining program and cutting parameters are saved in the process database to provide a reference for subsequent CNC machining of similar molds, thereby improving production efficiency and consistency of machining quality.

[0205] Specifically, in S8, according to the optimized mold design plan, a 3D CAD model was constructed using CATIA software, and the model was imported into UG CAM software using the STEP format;

[0206] In UG CAM, a 10mm diameter ball end mill was selected, with a spindle speed of 8000rpm, a feed rate of 800mm / min, a cutting depth of 0.5mm, and a lateral cutting depth of 0.3mm. A constant-height Z-axis machining strategy was used when planning the tool path, and the CNC machining G code was generated.

[0207] The machining simulation function of UG CAM was used to simulate the CNC machining process. The tool cutting force was calculated through finite element analysis, the cutting parameters were optimized, the feed speed was adjusted to 1000 mm / min, and the machining time was estimated to be 2.5 hours. The G code generated by post-processing was uploaded to the FANUC CNC system. The CNC machine tool controlled the tool movement according to the G code instructions. The Renishaw OMP60 probe was used to monitor the tool wear and workpiece size online. When the tool wear exceeded 0.2 mm, the compensation parameters were dynamically adjusted. After machining, the key dimensions of the workpiece were inspected using a Hexagon three-dimensional coordinate measuring machine. The measured data was compared and analyzed with the CAD model using the reverse engineering software Geomagic Control. The results showed a machining accuracy of 0.02 mm and a surface roughness of Ra 0.8 μm, which met the mold machining requirements. The machining parameters and tool path were optimized to compensate for the dimensional errors caused by tool wear and applied to mass production. The optimized machining parameters and G code were saved in the PLM system to realize the accumulation and reuse of process knowledge.

[0208] In the description of this application, the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0209] Those skilled in the art can make various other corresponding changes and deformations based on the technical solutions and concepts described above, and all of these changes and deformations should fall within the scope of protection of the claims of this application.

Claims

1. A mold 3D simulation analysis method, characterized in that: The following steps are involved: S1. Based on the three-dimensional CAD model of the mold, the mold is spatially discretized using a tetrahedral mesh. The mesh is encrypted during mesh division in the sharp corners and thin-walled parts of the stress concentration area. The stress concentration area is selected as the key area, and the relative error of the stress value in the key area is calculated. The calculation formula for the relative error is: |(σ_n-σ_n-1) / σ_n-1|, where σ_n is the stress value at the current mesh density and σ_n-1 is the stress value at the previous mesh density. S2. For the three-dimensional CAD model of the mold after meshing in step S1, input the elastic modulus and Poisson's ratio parameters of the mold material, apply the mold working load and direction, set the displacement constraints and contact conditions, and solve the displacement and stress components of each node of the mold using finite element analysis software; S3. Select a color scale based on the yield strength of the mold material in step S2 to generate a stress distribution cloud map, adjust the viewing angle to highlight the distribution characteristics of the stress concentration area, and add dimension annotations; S4, extracting features from the stress distribution cloud map of step S3, obtaining the numerical values ​​and spatial coordinates of the maximum principal stress value and the von Mises stress value, calculating the stress gradient direction and amplitude, and quantitatively evaluating the uniformity of the stress distribution; S5. Based on the fatigue performance data of the mold material, a support vector machine regression algorithm is used to establish a nonlinear prediction model of stress characteristic parameters and mold fatigue life. The maximum principal stress value, von Mises stress value, and stress gradient amplitude in step S4 are selected as characteristic parameters, and the fatigue life is used as label data. Cross-validation is performed using a grid search method to determine the kernel function type, regularization parameter, and kernel function parameter of the support vector machine. S6. Using the nonlinear prediction model in step S5, determine whether the stress concentration of the current mold design exceeds the material fatigue strength limit. If so, chamfer sharp corners in the mold structure and reinforce thin-walled areas. If not, no treatment is performed, thereby obtaining an optimized mold design. S7. Re-performing finite element analysis on the mold design optimized in step S6, extracting stress characteristic parameters, calculating the maximum stress reduction and the improvement in the uniformity of stress distribution, and using these to predict the increase in fatigue life; S8. Convert the mold design optimized in step S6 into a three-dimensional CAD model, import it into computer-aided manufacturing software for tool path planning and cutting parameter selection, simulate the CNC machining process and estimate the machining time, generate a CNC machining program, and upload it to the CNC machine tool for machining.

2. A mold 3D simulation analysis method according to claim 1, characterized in that: In step S1, the three-dimensional CAD model data of the mold is obtained, the model is preprocessed, and the stress concentration area is determined; The stress concentration area includes sharp corners and thin-walled parts. The stress concentration area is marked as a key area, an initial mesh model is obtained, and mesh encryption is performed on the key area. Calculating the stress value of each unit at the current grid density after mesh encryption to obtain a stress distribution cloud map of the entire mold; The relative error between the stress value at the current grid density and the stress value at the previous grid density is calculated based on the cells in the key area in the stress distribution cloud map.

3. A mold 3D simulation analysis method according to claim 1, characterized in that: In step S2, the three-dimensional CAD model of the mold is discretized using a meshing method to generate a finite element model, and the mechanical property parameters of the mold material are obtained. The mechanical property parameters include the elastic modulus and Poisson's ratio. The mechanical property parameters are input into finite element analysis software, and then the material properties are input into each unit of the finite element model. Applying the magnitude and direction of the external load as boundary conditions to the finite element model, setting displacement constraints of the mold, the displacement constraints including limiting the movement of degrees of freedom, and establishing contact pairs in the finite element model; The solution module of the finite element analysis software is called to perform a force analysis on the finite element model to obtain the deformation field and stress field distribution results of the mold under the working load, and to extract the displacement component and stress component data of each node of the mold.

4. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S3, a mapping relationship between a color scale and a stress value is established based on the yield strength of the mold material in step S2 for generating a stress distribution cloud map. The stress distribution of the mold under stress is calculated using a finite element analysis method to obtain stress value data for each region. generating the stress distribution cloud map according to the mapping relationship between the stress value data and the color scale; Performing image processing on the generated stress distribution cloud map, and adding dimension annotations to the stress distribution cloud map to mark the dimension information of key areas; Using an image segmentation algorithm to divide the stress distribution cloud map into regions to identify the location and range of stress concentration areas; After the area division, stress value data of the stress concentration area is extracted to obtain characteristic parameters of the stress concentration degree and distribution.

5. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S4, an image processing algorithm is used to extract features from the cloud image to obtain a digital representation of the stress distribution; The extracted digital representation of the stress distribution is used to determine the numerical values ​​and spatial coordinates corresponding to the maximum principal stress value and the von Mises stress value; According to the spatial coordinates of the maximum principal stress value and the von Mises stress value, the gradient direction and gradient amplitude of the stress in space are calculated to determine the stress distribution.

6. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S5, fatigue performance data of the mold material in step S4 is obtained, wherein the fatigue performance data includes a maximum principal stress value, a von Mises stress value, stress characteristic parameters of a stress gradient amplitude, and corresponding fatigue life data; Preprocessing the acquired stress characteristic parameters and fatigue life data; Based on the preprocessed data, a support vector machine regression algorithm is used to establish a nonlinear prediction model between stress characteristic parameters and fatigue life, and cross-validation is performed to evaluate the prediction performance of the model; Determining optimal support vector machine model parameters based on the cross-validation results to obtain an optimized support vector machine model, wherein the optimal support vector machine model parameters include a kernel function type, a regularization parameter, and a kernel function parameter; Using the optimized support vector machine model, the stress characteristic parameters of the new mold material are predicted to obtain the corresponding fatigue life prediction value; The predicted fatigue life is compared with the actual test results to evaluate the prediction accuracy of the model, and the stress distribution of the mold under working conditions is calculated to obtain the stress concentration area and stress concentration factor; The calculated stress concentration coefficient is used as input and substituted into the nonlinear prediction model to determine the degree of stress concentration.

7. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S6, the stress distribution of the mold under the working state is calculated using the finite element analysis method to obtain the stress concentration area and stress concentration coefficient. The stress concentration coefficient is substituted into the fatigue life prediction model to predict the fatigue life of the mold. The predicted mold fatigue life is compared with the fatigue strength limit value of the material to determine whether structural optimization is required.

8. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S7, a finite element analysis model is constructed based on the mold design optimized in step S6, and the stress distribution of the mold in the working state is calculated using a finite element solution method to obtain the stress concentration area and stress concentration coefficient; Extracting stress characteristic parameters from the results of the finite element analysis, comparing them with the stress characteristic parameters before optimization, and calculating the reduction amplitude of the maximum stress value to determine whether a preset threshold value has been reached; The stress concentration factor obtained by calculating the reduction amplitude of the maximum stress value is substituted into the nonlinear prediction model as input to predict the fatigue life of the mold under the current stress level, and the fatigue life increase is obtained to determine whether the fatigue life increase reaches a preset percentage; Evaluate the stress distribution uniformity of the optimized mold through stress distribution cloud diagram and stress uniformity index; The optimized mold design scheme is re-analyzed by finite element analysis to calculate the stress distribution, extract the maximum stress value and stress uniformity index, and determine whether the preset threshold requirements are met.

9. The mold 3D simulation analysis method according to claim 1, characterized in that: In step S8, a three-dimensional CAD model is constructed according to the mold design scheme optimized in step S6, and the CAD model is imported into the CAM software through the model conversion interface for processing; In the CAM software, the cutting parameters of tool type, cutting amount, and feed rate are selected, the tool motion path is planned, and the NC machining program is generated; The machining simulation function provided by CAM software is used to simulate the CNC machining process to analyze the interference between the tool and the workpiece and the cutting force, estimate the machining time, and optimize the cutting parameters and tool path.

10. A mold 3D simulation analysis method according to claim 9, characterized in that: The CNC machining program is converted into a G-code format recognized by the CNC machine tool by a post-processor and uploaded to the FANUC CNC system; The CNC machine tool controls the tool movement according to the machining program instructions in the G-code format, and dynamically adjusts the cutting parameters by online monitoring of tool wear and workpiece size; After machining is completed, the key dimensions of the workpiece are inspected using an on-machine probe, and the inspection data are compared and analyzed with the CAD model to evaluate machining accuracy and surface quality and obtain a quality feedback report.

Images