Lateral pressure core body generation method, device, equipment and storage medium

Abstract

This invention relates to the field of mold design technology, and discloses a method, apparatus, equipment, and storage medium for generating a side-pressure core body. The method involves collecting process input data, identifying geometric features in the process input data based on a B-rep data structure, and constructing a local coordinate system for the side-pressure core. The parting line is discretized into a set of spatial points and mapped to the local coordinate system. An envelope operation is performed on the mapped spatial point set to generate an initial envelope contour. Based on the initial envelope contour, a fusion structure of the working part and the flange part of the side-pressure core body is generated. Based on the fusion structure of the working part and the flange part, the optimal offset distance between the back plane and the top plane is determined, a closed offset contour line is constructed, and stretching, segmentation, and subtraction operations are performed to obtain the final structure of the side-pressure core body. This invention achieves rapid generation of a slender side-pressure core body structure, reducing workload.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mold design, and in particular to a side pressure core main body generation method, device, equipment and storage medium. BACKGROUND

[0002] The side pressure core is an important component for providing side pressure in a stamping die, mainly applied to the pressure area where the strength or stress condition of the positive pressure core cannot meet the pressure requirement, and common applications include side repair sequence back doors, side walls, side repair sequence wing panels and complex structural parts in automobile cover parts. The existing design method of the side pressure core completely relies on manual design, and the designer needs to have rich design experience, and the design process is time-consuming and laborious. SUMMARY

[0003] The present application relates to the technical field of mold design, and in particular to a side pressure core main body generation method, device, equipment and storage medium.

[0004] The first aspect of the present application provides a side pressure core main body generation method, which comprises:

[0005] Collecting process input data, identifying geometric features in the process input data based on B-rep data structure, wherein the process input data at least includes a back-off direction line, a parting line and a process profile, and the geometric features at least include a boundary line and an intersection surface;

[0006] Determining a Z-axis vector according to the back-off direction line, calculating and correcting X-axis and Y-axis vectors in combination with the position relationship between the parting line and the process profile, and constructing a side pressure core local coordinate system;

[0007] Discretizing the parting line into a spatial point set and mapping it to the local coordinate system, and performing envelope operation on the mapped spatial point set by fusing NSGA-II algorithm to generate an initial envelope contour body;

[0008] Generating a fusion structure of the working part and the flange part of the side pressure core main body based on the initial envelope contour body;

[0009] Based on the fusion structure of the working part and the flange part, determining the optimal offset distance of the back plane and the top plane, constructing a closed offset contour line and completing stretching, segmentation and difference operation to obtain the final structure of the side pressure core main body.

[0010] Optionally, in the first implementation manner of the first aspect of the present application, the parting line is discretized into a spatial point set and mapped to the local coordinate system, and the mapped spatial point set is subjected to envelope operation by fusing NSGA-II algorithm to generate an initial envelope contour body, which comprises:

[0011] Sampling points are uniformly selected along the parting line according to the preset sampling interval to form a spatial point set. The coordinates of each sampling point in the spatial point set are transformed and calculated according to the 3×3 coordinate transformation matrix and the origin coordinates of the local coordinate system to form a mapped spatial point set.

[0012] The envelope operation parameters are set as decision variables and variable constraints, wherein the decision variables include at least the positive X expansion, negative X expansion, positive Y expansion, negative Y expansion, positive Z expansion, negative Z expansion, and rounding requirements in each direction;

[0013] Randomly generate N individuals that meet the variable constraints, each individual corresponding to a set of envelope operation parameters, to form the initial population;

[0014] Using the compactness of the envelope contour and the integrity of the point set coverage as dual objective functions, each individual in the initial population is evaluated, and different non-dominated layers are divided.

[0015] For each individual in a non-dominated layer, calculate the distance between each individual in the non-dominated layer and its neighboring individuals in the target space to obtain the crowding value;

[0016] The crossover rate and mutation rate are adjusted based on the crowding value, and the offspring population is generated by crossover operation and optimized by mutation operation.

[0017] The initial population is merged with the mutated offspring population to form a mixed population of size 2N. The mixed population is then subjected to non-dominated sorting to divide a new non-dominated layer. Individuals are selected from the new non-dominated layer to form a new generation of parent population of size N.

[0018] Repeat the iteration until the preset maximum number of iterations is reached. Select the best individual from the first non-dominated layer of the final population and extract the decision variables corresponding to the best individual.

[0019] Based on the optimal expansion amount among the determined decision variables, the spatial point set in the local coordinate system is expanded in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction. Then, it is rounded according to the optimal rounding requirement to finally obtain the initial envelope contour of the side pressure core.

[0020] Optionally, in a second implementation of the first aspect of the present invention, the step of adjusting the crossover rate and mutation rate based on the crowding value, and using crossover operation to generate the offspring population and mutation operation to optimize the offspring population includes:

[0021] A tournament selection mechanism is adopted. k individuals are randomly selected from the initial population. The non-dominance level and crowding of the individuals are compared. Individuals with higher non-dominance level and greater crowding are selected as parent individuals. This process is repeated until N parent individuals are selected to form a parent pairing pool.

[0022] Obtain the non-dominant level of each parent pair in the parent pairing pool. and Calculate the cross-distribution index according to the formula. :

[0023]

[0024] in, Indicates the highest non-dominant rank in the initial population. The value range is [0,1];

[0025] For each pair of parent individuals, the decision variables are encoded, a crossover point is randomly selected, the encoded segments to the right of the crossover point are swapped, and the offspring parameters are adjusted using the crossover distribution index. The decision variable values ​​for the offspring individuals are then calculated.

[0026]

[0027] in, For the first parent individual's first One decision variable, For the second parent individual One decision variable, For the first generation of individuals There are 1 decision variables, where parent 1 and parent 2 are a pair of individuals selected, and offspring 1 and offspring 2 are two new individuals generated from parent 1 and parent 2.

[0028] Repeat the iteration until N offspring individuals are generated, forming the initial offspring population;

[0029] For each individual in the initial offspring population, a random number is generated. If the random number is less than the adjusted mutation rate, a mutation operation is performed on the decision variable of the current individual. After completing the mutation judgment and mutation operation for all individuals, the optimized offspring population is obtained, where the random number is a number between 0 and 1.

[0030] Optionally, in a third implementation of the first aspect of the present invention, generating a fusion structure between the working part of the side pressure core body and the flange part based on the initial envelope contour includes:

[0031] Based on the initial envelope contour, an AABB bounding box is constructed as the root node, and an OBB bounding box is constructed as the child node inside the AABB bounding box.

[0032] Traverse the AABB bounding box, extract the region where the AABB bounding box and the intersecting surface do not overlap spatially, and for the retained region, select the segmentation direction that is consistent with the extension direction of the intersecting surface based on the spatial orientation of the intersecting surface;

[0033] For the inner OBB bounding box of the reserved area, determine the overlapping boundary and spatial connection relationship between the intersecting surface and the OBB bounding box to obtain the range of the intersecting area;

[0034] Based on the determined intersection area range, adjust the segmentation boundary parameters between the working part and the flange part in the initial envelope contour body;

[0035] Based on the segmentation boundary parameters and the spatial extension length of the intersecting surfaces, the wrapping range of the AABB bounding box and the OBB bounding box is dynamically adjusted to form a two-layer hierarchical bounding box tree structure.

[0036] The initial structures of the working part and the flange part are integrated to form an initial fusion structure. The initial fusion structure is then subjected to a second traversal test through the double-layer hierarchical surrounding box tree structure, and finally the fusion structure of the working part and the flange part of the side pressure core body is obtained.

[0037] Optionally, in a fourth implementation of the first aspect of the present invention, the step of dynamically adjusting the enclosure range of the AABB bounding box and the OBB bounding box based on the segmentation boundary parameters and the spatial extension length of the intersecting surface includes:

[0038] Expand the corresponding range of the AABB bounding box outward, where the expansion amount is the extension length of the intersecting surface in the extension direction, determine the maximum and minimum coordinate values ​​of the AABB bounding box in the X, Y, and Z directions, and form the adjusted AABB bounding range;

[0039] Based on the spatial orientation of the intersecting surfaces, the initial orientation of the OBB bounding box is set, and the enclosing range of the OBB bounding box is initially determined with reference to the adjusted AABB bounding box range.

[0040] Traverse the contour features of the intersecting surfaces to make the OBB bounding box fit the contour, and adjust the azimuth angle of the OBB bounding box according to the connection relationship between the segmentation boundary and the intersecting surfaces.

[0041] Check whether the adjusted OBB bounding box is completely inside the AABB bounding box. If there is any excess, readjust the AABB bounding box range.

[0042] Optionally, in a fifth implementation of the first aspect of the present invention, the step of determining the optimal offset distance between the back plane and the top plane based on the fusion structure of the working part and the flange part, constructing a closed offset contour line and completing stretching, segmentation and subtraction operations to obtain the final structure of the side pressure core body includes:

[0043] Set the range of offset distance values, and randomly generate a combination of back plane offset distance and top plane offset distance as the initial solution, wherein the initial solution is the starting point of the simulated annealing algorithm;

[0044] Based on the initial solution, a new solution is generated by random perturbation. If the new solution is better, it is taken as the current best solution. Otherwise, the acceptance probability is calculated based on the current simulated annealing temperature. When the acceptance probability meets the preset conditions, the new solution is accepted.

[0045] The current temperature is reduced according to the set cooling coefficient, a new combination of offset distances is generated, and the iteration is repeated until the algorithm temperature drops to the preset termination temperature to obtain the current optimal solution, where the current optimal solution is the optimal offset distance between the back plane and the top plane.

[0046] Based on the optimal offset distance, the back plane and top plane on the fused structure are offset. Using the offset back plane and top plane as boundaries, and combined with other contour boundaries of the fused structure, closed offset contour lines are sequentially connected to obtain the closed offset contour lines.

[0047] The closed offset contour line is stretched along a preset direction to form the corresponding three-dimensional structure, and the boundary line is obtained. After the boundary line is offset along the positive Z direction, it is stretched along the Y direction.

[0048] The fused structure and the stretched three-dimensional structure are intersected and divided. The excess part located on the negative Z side of the fused structure is deleted. The difference operation is performed on the divided fused structure to remove the overlapping part, and the final structure of the side pressure core is obtained.

[0049] Optionally, in the sixth implementation of the first aspect of the present invention, the step of generating a new solution by random perturbation based on the initial solution, and if the new solution is better, then the new solution is taken as the current optimal solution; otherwise, the acceptance probability is calculated based on the current simulated annealing algorithm temperature, and the new solution is accepted when the acceptance probability meets a preset condition, includes:

[0050] For the backplane offset distance and topplane offset distance of the current optimal solution, generate random perturbation terms that follow a preset probability distribution. These perturbation terms are then superimposed onto the current solution to obtain a new solution.

[0051]

[0052] in, This indicates a new interpretation. Indicates the first Offset distance of the wheel back plane. Indicates the first Offset distance of the wheel top plane, The random perturbation term represents the distance of the back plane offset. The random perturbation term represents the offset distance of the top plane;

[0053] Calculate the objective function value of the current optimal solution and the objective function value of the new solution, and solve for the difference. ,like The current optimal solution is updated directly to ,like The acceptance probability is calculated based on the current simulated annealing algorithm temperature:

[0054]

[0055] in, Indicates the probability of acceptance. Indicates the probability of acceptance. Simulate the current temperature of the annealing algorithm during each iteration;

[0056] Generate a uniformly distributed random number in the interval [0, 1]. ,like Then update ,like Then reject the new solution and retain the original one. .

[0057] A second aspect of the present invention provides a side-pressure core body generating apparatus, the side-pressure core body generating apparatus comprising:

[0058] The data acquisition module is used to acquire process input data and identify geometric features in the process input data based on the B-rep data structure. The process input data includes at least a retraction direction line, a parting line, and a process surface, and the geometric features include at least a boundary line and an intersecting surface.

[0059] The coordinate system construction module is used to determine the Z-axis vector based on the retraction direction line, and calculate and correct the X-axis and Y-axis vectors based on the positional relationship between the parting line and the process surface to construct a local coordinate system for the side pressure core.

[0060] The envelope operation module is used to discretize the parting line into a set of spatial points and map it to the local coordinate system. It then integrates the NSGA-II algorithm to perform envelope operation on the mapped set of spatial points to generate an initial envelope contour volume.

[0061] The structure generation module is used to generate a fusion structure of the working part and the flange part of the side pressure core body based on the initial envelope contour.

[0062] The determination module is used to determine the optimal offset distance between the back plane and the top plane based on the fusion structure of the working part and the flange part, construct the closed offset contour line and complete the stretching, segmentation and subtraction operations to obtain the final structure of the side pressure core body.

[0063] A third aspect of the present invention provides a side-pressure core body generating apparatus, the side-pressure core body generating apparatus including a memory and at least one processor, the memory storing instructions; the at least one processor calling the instructions in the memory to cause the side-pressure core body generating apparatus to perform the various steps of the side-pressure core body generating method as described in any of the preceding claims.

[0064] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the side-pressure core body generation method as described in any of the preceding claims.

[0065] The technical solution provided by this invention involves collecting process input data, identifying geometric features in the process input data based on the B-rep data structure, determining the Z-axis vector based on the retraction direction line, calculating and correcting the X-axis and Y-axis vectors based on the positional relationship between the parting line and the process surface, and constructing a local coordinate system for the side-pressure core. The parting line is discretized into a set of spatial points and mapped to the local coordinate system. The NSGA-II algorithm is then used to perform envelope operations on the mapped spatial point sets to generate an initial envelope contour. Based on the initial envelope contour, a fusion structure of the working part and the flange part of the side-pressure core body is generated. Based on the fusion structure of the working part and the flange part, the optimal offset distance between the back plane and the top plane is determined, a closed offset contour line is constructed, and stretching, segmentation, and subtraction operations are performed to obtain the final structure of the side-pressure core body. This invention achieves rapid generation of a slender side-pressure core body structure, reduces workload, and greatly improves design efficiency and intelligence. Attached Figure Description

[0066] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0067] Figure 1 This is a schematic diagram of the first embodiment of the side-pressure core body generation method provided by the present invention;

[0068] Figure 2 A schematic diagram of a second embodiment of the side-pressure core body generation method provided by the present invention;

[0069] Figure 3 A schematic diagram of a third embodiment of the side-pressure core body generation method provided by the present invention;

[0070] Figure 4 This is a schematic diagram of the structure of the side-pressure core body generating device provided in an embodiment of the present invention;

[0071] Figure 5This is a schematic diagram of the structure of the side-pressure core body generating device provided in an embodiment of the present invention. Detailed Implementation

[0072] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0073] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 A schematic diagram of the first embodiment of the side-pressure core body generation method provided by the present invention is shown. The method specifically includes the following steps:

[0074] Step 101: Collect process input data and identify geometric features in the process input data based on the B-rep data structure;

[0075] In this embodiment, the process input data comes from the process technology documents and 3D model data of the stamping die design for automotive side panel parts. It includes at least the return direction line used to clarify the movement direction of the side pressing core, the parting line dividing the die cavity and the core, and the process surface directly related to the forming of the part. At the same time, the constraint parameters in the process design are collected. Based on the geometric topology analysis capability of the B-rep data structure, the collected process input data is deeply analyzed to automatically identify the key geometric features. The geometric features include at least boundary lines and intersecting surfaces. The boundary lines specifically cover the complete contour boundary of the parting line, the edge contour boundary of the process surface, the intersection line of the return direction line and the process surface, and the boundary line of the parting line and the process surface. The intersecting surfaces include the intersecting surface formed by the parting line after being stretched in a specific direction and the process surface, the intersecting surface formed by the projection of the return direction line onto the process surface, and the connecting intersecting surface between different process surfaces.

[0076] Step 102: Determine the Z-axis vector based on the retraction direction line, and calculate and correct the X-axis and Y-axis vectors based on the positional relationship between the parting line and the process surface to construct a local coordinate system for the side-pressure core.

[0077] In this embodiment, based on the return direction line of the input process information, the vector with a positive z-value is set as the z-coordinate vector Z of the local coordinate system. According to the Cartesian right-hand rule, the vector perpendicular to the z-direction of the absolute coordinate system and vector Z is calculated as the temporary vector X. Then, the vector perpendicular to vector Z and temporary vector X is calculated as the temporary vector Y. Based on the principle that the y-coordinate vector Y of the local coordinate system should point from the parting line to the inside of the process surface, the positional relationship between the parting line and the process surface in the input process information is used to determine whether the temporary vector Y needs to be reversed, and finally the y-coordinate vector Y of the local coordinate system is determined. Again, according to the Cartesian right-hand rule, the vector perpendicular to vector Y and vector Z is calculated as the x-coordinate vector X of the local coordinate system. The local coordinate system of the side pressure core is constructed with the zero point of the absolute coordinate system as the origin, vector X as the x-axis, vector Y as the y-axis, and vector Z as the z-axis. The zero point of the absolute coordinate system refers to the origin used to establish the global reference datum, and its specific location is set at the intersection of the lower die reference surface and the parting line of the stamping die.

[0078] Step 103: Discretize the parting line into a set of spatial points and map it to the local coordinate system. Then, use the NSGA-II algorithm to perform envelope operations on the mapped set of spatial points to generate an initial envelope contour.

[0079] In this embodiment, after discretizing the parting line, a series of spatial point sets in the absolute coordinate system are obtained. According to the spatial rectangular coordinate transformation formula, the spatial point set P in the local coordinate system is obtained. The rectangular envelope of the local coordinate system is calculated based on the point set P. The rectangular envelope is rounded to 5 in the positive X and negative X directions, 5 in the negative Y direction, 5 in the positive Y direction after being expanded by 100mm, and 5 in the positive Z and negative Z directions after being expanded by 50mm, resulting in the initial envelope contour B0 of the side pressure core.

[0080] Step 104: Generate the fusion structure of the working part and the flange part of the side pressure core body based on the initial envelope contour;

[0081] In this embodiment, based on the initial envelope contour, an AABB bounding box is constructed as the root node, and an OBB bounding box is constructed as a child node inside the AABB bounding box. The AABB bounding boxes are traversed to identify areas where the AABB bounding box and the intersecting surface do not spatially overlap. For the retained areas, a segmentation direction consistent with the extension direction of the intersecting surface is selected based on the spatial orientation of the intersecting surface. For the inner OBB bounding box of the retained areas, the overlapping boundary and spatial connection relationship between the intersecting surface and the OBB bounding box are determined to obtain the range of the intersecting area. Based on the determined range of the intersecting area, the segmentation boundary parameters of the working part and the flange part in the initial envelope contour are adjusted. Based on the segmentation boundary parameters and the spatial extension length of the intersecting surface, the enclosure range of the AABB bounding box and the OBB bounding box is dynamically adjusted to form a two-layer hierarchical bounding box tree structure. The preliminary structures of the working part and the flange part are integrated to form a preliminary fusion structure. The preliminary fusion structure is then traversed and tested a second time through the two-layer hierarchical bounding box tree structure to finally obtain the fusion structure of the working part and the flange part of the side-pressure core body.

[0082] In this embodiment, the range corresponding to the AABB bounding box is expanded outward, where the expansion amount is the extension length of the intersecting surface in the extension direction. The maximum and minimum coordinate values ​​of the AABB bounding box in the X, Y, and Z directions are determined to form the adjusted AABB bounding range. Based on the spatial orientation of the intersecting surface, the initial orientation of the OBB bounding box is set. Using the adjusted AABB bounding box range as a reference, the bounding range of the OBB bounding box is initially determined. The contour features of the intersecting surface are traversed to make the OBB bounding box fit the contour. Based on the connection relationship between the segmentation boundary and the intersecting surface, the azimuth angle of the OBB bounding box is adjusted. It is checked whether the adjusted OBB bounding box is completely inside the AABB bounding box. If there is an excess part, the range of the AABB bounding box is readjusted. If there is no excess part, the range of the AABB bounding box does not need to be adjusted.

[0083] In this embodiment, a two-layer hierarchical bounding box tree structure is constructed based on the initial envelope contour. The outer layer preferentially constructs AABB as the root node. According to the maximum / minimum coordinates of the X, Y, and Z directions of the initial envelope contour in the local coordinate system, the bounding box can quickly wrap the entire initial envelope contour, and the construction process does not require complex geometric calculations, which is more efficient. Inside the AABB bounding box, OBB is constructed as a child node for the approximate partitions of the working part and the flange part in the initial envelope contour. The pose of the OBB is adjusted according to the geometric contour features of the corresponding partition to make it fit the spatial shape of the working part and the flange part better, reducing the redundant space in the bounding box.

[0084] By traversing the 3D boundary of the outer AABB bounding box and combining the planar equations of the intersecting surfaces, the spatial overlap relationship between the AABB bounding box and the intersecting surfaces is calculated. If the boundary of a certain region of the AABB does not intersect with the planar equation of the intersecting surface, and the region is completely located on the non-working side of the intersecting surface, the non-overlapping region is directly removed. For the regions that are retained and overlap with the intersecting surfaces, the spatial extension direction of the intersecting surfaces is analyzed, and a segmentation direction consistent with the extension direction is selected. For example, if the intersecting surfaces mainly extend along the X direction, the segmentation direction is set to the X direction to ensure that the key regions related to the intersecting surfaces are accurately retained after segmentation, and to avoid misjudgment of regions caused by the conflict between the segmentation direction and the extension direction of the intersecting surfaces.

[0085] By analyzing the positional relationship between the vertices of the OBB bounding box and the intersecting surface, we can initially determine whether there is an overlap between the OBB and the intersecting surface. Then, by calculating the intersection points of the OBB edges and the intersecting surface, we can determine the specific coordinates of the overlapping boundary and form a closed overlapping boundary outline. At the same time, we can analyze the spatial connection relationship between the intersecting surface and the OBB bounding box, including the degree of fit between the intersecting surface and the OBB, and the connection method between the overlapping boundary and the OBB edges. By combining this information, we can accurately delineate the three-dimensional range of the intersecting area and determine the specific position and size of the area within the OBB bounding box.

[0086] Based on the determined intersection area, the segmentation boundary parameters of the working part and the flange part in the initial envelope contour are adjusted in reverse. The segmentation boundary parameters include the parting line offset distance, the height of the stretching sheet, and the spatial orientation of the segmentation surface. For example, if the intersection area is offset by 5mm in the positive Y direction, the offset distance of the parting line in the positive Y direction is adjusted from 30mm to 35mm; if the length of the intersection area extends in the Z direction, the Z-direction stretching height of the stretching sheet is adjusted accordingly to ensure that the segmentation boundary of the working part and the flange part can accurately avoid the interference risk of the intersection area, while conforming to the spatial constraints of the intersection surface to ensure the reasonable connection of the two structural parts.

[0087] Based on the adjusted segmentation boundary parameters, preliminary structures for the working part and the flange part are generated separately. The two structures are then aligned in spatial orientation and integrated to form a preliminary fusion structure. During the integration process, it is ensured that there are no gaps or overlaps at the connection surfaces of the working part and the flange part. The preliminary fusion structure is then subjected to a second traversal test using a double-layer hierarchical enclosing box tree structure: the outer AABB quickly checks for redundant areas in the fusion structure that exceed the preset range, while the inner OBB finely checks for interference at the connection points between the working part and the flange part, and at the overlap points between the fusion structure and the intersecting surfaces. If any problems are detected, the segmentation boundary parameters are finely adjusted until there are no abnormalities in the second traversal. Finally, a complete, interference-free, and process-compliant fusion structure of the side-pressure core main body working part and flange part is obtained.

[0088] Step 105: Based on the fusion structure of the working part and the flange part, determine the optimal offset distance between the back plane and the top plane, construct the closed offset contour line and complete the stretching, segmentation and subtraction operations to obtain the final structure of the side pressure core body.

[0089] In this embodiment, the parting line is stretched along the Z direction to obtain sheet body F1. Sheet body F1 is used to divide body B0. After removing the excess body located on the negative Y side of sheet body F1, body B1 is obtained. Body B1 is then the initial body for determining the side pressure core within one side of the cutting edge. The parting line is offset by 30mm along the positive Y direction to obtain the parting line offset line. The parting line offset line is stretched along the Z direction to obtain sheet body F2. Sheet body F2 is used to divide body B1. Based on the positional relationship between the divided body sets and the parting line, the body close to the parting line is body B2, and the body far from the parting line is body B3. Body B2 is then the initial body for the working part of the side pressure core body, and body B3 is the initial body for the flange part of the side pressure core body. The process surface is divided into body B2. After deleting the redundant body on the negative Z side of the process surface, body B4 is obtained. At this time, body B4 is the working part of the side pressure core body with detailed surface features. The boundary line S1 formed by the F1 sheet and the process surface is obtained on body B4. The boundary line S1 is offset by 50mm along the positive Z direction and then by 10mm along the positive Y direction to obtain the cutting edge clearance dividing line. The cutting edge clearance dividing line is stretched along the negative Y direction and the positive Z direction respectively to obtain the sheet body and then stitched together to obtain sheet body F3. Body B4 is divided with sheet body F3. After deleting the redundant body far away from the process surface, body B5 is obtained. At this time, body B5 is the working part of the side pressure core body.

[0090] In this embodiment, the boundary line S2 formed by the F2 sheet and the process surface on body B5 is obtained. After offsetting the boundary line S2 by 40mm in the positive Z direction, the lower surface auxiliary line is obtained. The lower surface auxiliary line is stretched in the Y direction to obtain sheet F4. Body B3 is divided by sheet F4. After deleting the redundant body on the negative Z side of sheet F4, body B6 is obtained. At this time, body B6 is the flange part of the side pressure core body. Body B5 and body B6 are merged to obtain body B7. At this time, body B7 is the side pressure core body. The back plane F5 at the farthest point in the positive Y direction on body B7 is obtained. The F5 plane is offset to ensure that the distance between the F5 plane and sheet F1 is about 120mm. The top plane F6 at the farthest point in the positive Z direction on body B7 is obtained. The F6 plane is offset to ensure that the minimum distance between the F6 plane and sheet F4 is about 200mm. The outer contour line S3 of the F6 plane is obtained. After offsetting S3 inward by 40mm, a closed offset contour line is obtained. After stretching the closed offset contour line, body B8 is obtained. After offsetting the boundary line S2 along the positive Z direction by 80mm, body F7 is obtained. Body B8 is divided by body F7. After deleting the redundant body on the negative Z side of body F7, the difference of body B7 is obtained, resulting in body B9. At this time, body B9 is the final structure of the slender side pressure core body for the side panel parts. The optimal offset distance includes: the cutting edge clearance area is offset by 50mm along the Z direction and 10mm along the Y direction. The lower surface auxiliary line is offset by 40mm along the Z direction. The optimal distance between the back plane and the corresponding body of the parting line is about 120mm. The minimum distance between the top plane and the lower surface auxiliary body is not less than 200mm. The outer contour is offset inward by 40mm to form a closed reinforcement structure. The transition dividing body is offset by 80mm along the Z direction.

[0091] In this embodiment of the invention, key geometric features such as boundary lines and intersecting surfaces in the process input data are accurately identified through the B-rep data structure. A dedicated local coordinate system is constructed by combining the positional relationship between the parting line and the process surface, effectively avoiding deviations caused by traditional manual benchmark setting. This ensures that the segmentation boundaries and envelope contours of the working part and flange part are highly compatible with process requirements, significantly reducing the risk of structural interference and significantly improving design accuracy. The NSGA-II algorithm is integrated to perform envelope operations on the mapped discrete point set of the parting line. Initial envelope contours are automatically generated through multi-objective optimization, eliminating the need for repeated manual adjustments to parameters such as expansion and rounding requirements. Simultaneously, the bounding box algorithm dynamically adjusts parameters during the fusion structure generation process, achieving automated integration of the working part and flange part, significantly reducing design workload and greatly improving design efficiency. The simulated annealing algorithm is used to determine the optimal offset between the back plane and the top plane. The distance, combined with the smooth construction, stretching, and subtraction of the closed offset contour line, forms a top hollow structure that meets the requirements of spatial compactness and improves the stability and service life of the side pressure core. The entire design process is driven by geometric features based on process input data. From the construction of the local coordinate system to the generation of the fused structure, it is precisely matched with core process elements such as the return direction line, parting line, and process surface. When the process input changes, the algorithm quickly iterates and adjusts the parameters without redesigning the entire process. It can flexibly adapt to the design requirements of slender side pressure cores for different side parts, reducing the repetitive labor costs caused by process changes. The double-layer hierarchical enclosing box tree structure realizes the precise positioning and dynamic adjustment of parameters in the intersecting area. Combined with multi-objective optimization algorithms and automatic geometric feature recognition technology, it reduces the dependence on designer experience, has strong versatility, and provides an efficient and feasible solution for the intelligent design of stamping dies.

[0092] Please see Figure 2 A schematic diagram of a second embodiment of the side-pressure core body generation method provided by the present invention, the method comprising:

[0093] Step 201: Select sampling points evenly along the parting line according to the preset sampling interval to form a spatial point set. Based on the 3×3 coordinate transformation matrix and the origin coordinates of the local coordinate system, transform and calculate the coordinates of each sampling point in the spatial point set to form the mapped spatial point set.

[0094] In this embodiment, a sampling point is selected every 10 mm at the sampling interval. For curvatures greater than 0.02 mm... -1 For complex segments, the sampling interval is reduced to 5mm to ensure complete representation of the spatial contour of the parting line; by collecting the three-dimensional coordinates of the parting line point by point, a spatial point set in the absolute coordinate system is formed; the 3×3 coordinate transformation matrix is ​​determined based on the spatial orientation relationship between the local coordinate system and the absolute coordinate system, and the coordinates of each sampling point in the spatial point set are transformed and calculated one by one to finally form the spatial point set mapped in the local coordinate system.

[0095] Step 202: Set the envelope operation parameters as decision variables and variable constraints;

[0096] In this embodiment, the decision variables include at least the positive X-axis expansion, negative X-axis expansion, positive Y-axis expansion, negative Y-axis expansion, positive Z-axis expansion, negative Z-axis expansion, and rounding requirements for each direction: the values ​​of the positive X-axis and negative X-axis expansion are in the range of 5-20mm, which needs to be adapted to the distribution range of the X-axis of the parting line; the positive Y-axis expansion needs to consider the working stroke requirements of the pressure core, with a value range of 80-120mm, and the negative Y-axis expansion is 5-10mm; the positive Z-axis and negative Z-axis expansion needs to meet the backlash and interference avoidance requirements, with a value range of 40-60mm; the rounding requirements for each direction are uniformly rounded to integer multiples of 5, adapting to the standardization requirements of mold processing. The variable constraints include: the expanded envelope must completely contain the mapped spatial point set to ensure the integrity of the point set coverage; the expansion amount in each direction cannot exceed the preset value range to avoid the envelope being too large, resulting in structural redundancy, or too small, failing to meet the structural generation space; the rounded boundary values ​​must meet the positional constraints of the process surface and the parting line, and must not conflict with key geometric features.

[0097] Step 203: Randomly generate N individuals that meet the variable constraints, each individual corresponding to a set of envelope operation parameters, to form the initial population;

[0098] In this embodiment, N=100 is preferred. During the individual generation process, a random number generator is used to independently select values ​​within the constraints of each decision variable. For example, the positive expansion amount of X is randomly selected between 5-20mm, and the positive expansion amount of Y is randomly selected between 80-120mm, while ensuring that the rounding requirements of each direction are met. After each individual is generated, constraint verification is performed: it is checked whether each expansion amount is within the preset range, whether the rounded boundary value is an integer multiple of 5, and whether the expanded virtual envelope can completely contain the mapping point set. Individuals that do not meet the constraints are directly discarded and regenerated, and finally 100 individuals that meet all the variable constraints are formed to form the initial population.

[0099] Step 204: Using the compactness of the envelope contour volume and the integrity of the point set coverage as dual objective functions, evaluate each individual in the initial population and divide it into different non-dominated layers;

[0100] In this embodiment, the compactness of the envelope contour is calculated by quantifying the volume of the envelope; the smaller the volume, the better the compactness. The point set coverage integrity is evaluated by the positional relationship between all sampling points in the mapping point set and the envelope. If all sampling points are within the envelope and the minimum distance from the sampling point to the boundary of the envelope is not less than 3mm, it is determined to be a complete coverage, and is represented by a 0-1 quantization value, where 1 is complete coverage and 0 is incomplete coverage. During the evaluation, the dual objective function value of each individual is calculated first, and then the non-dominated layers are divided according to the non-dominated sorting rules: individuals in which no other individual is inferior to the individual in both objective functions and at least one objective function is superior are divided into the first non-dominated layer; among the remaining individuals, individuals without a dominated relationship are divided into the second non-dominated layer according to the same rules, and so on, until all individuals are divided into the corresponding non-dominated layers.

[0101] Step 205: For each individual in a non-dominated layer, calculate the distance between each individual in the non-dominated layer and its neighboring individuals in the target space to obtain the crowding value;

[0102] In this embodiment, the crowding value is used to characterize the uniformity of population distribution in the target space. The target space is a multidimensional space composed of various objective functions in the optimization problem. In the target space, each individual uses its value under each objective function as its coordinate. Before calculation, individuals in the same non-dominated layer are sorted from small to large according to the envelope volume. Individuals with the same volume are sorted from high to low according to the point set coverage integrity. For boundary individuals sorted at the beginning and end of the layer, their crowding value is set to ∞ to ensure that boundary individuals are preferentially retained in subsequent selections.

[0103] Step 206: Adjust the crossover rate and mutation rate based on the crowding value, and use crossover operation to generate offspring population and mutation operation to optimize offspring population;

[0104] In this embodiment, the adjustment of crossover rate and mutation rate follows the principle of increasing when population diversity is insufficient and decreasing when diversity is sufficient. The average crowding degree of each non-dominated layer is calculated. If the average crowding degree is less than 0.5, the crossover rate is adjusted from the initial 0.9 to 0.95 and the mutation rate is adjusted from the initial 0.3 to 0.35. If the average crowding degree is greater than or equal to 0.5, the crossover rate of 0.9 and the mutation rate of 0.3 are kept unchanged.

[0105] In this embodiment, a tournament selection mechanism is adopted. k individuals are randomly selected from the initial population. The non-dominance level and crowding degree of the individuals are compared. Individuals with higher non-dominance level and greater crowding degree are selected as parent individuals. This process is repeated until N parent individuals are selected to form a parent pairing pool.

[0106] Obtain the non-dominant level of each parent pair in the parent pairing pool. and Calculate the cross-distribution index according to the formula. :

[0107]

[0108] in, Indicates the highest non-dominant rank in the initial population. The value range is [0,1];

[0109] For each pair of parent individuals, the decision variables are encoded, a crossover point is randomly selected, the encoded segments to the right of the crossover point are swapped, and the offspring parameters are adjusted using the crossover distribution index. The decision variable values ​​for the offspring individuals are then calculated.

[0110]

[0111] in, For the first parent individual's first One decision variable, For the second parent individual One decision variable, For the first generation of individuals There are 1 decision variables, where parent 1 and parent 2 are a pair of individuals selected, and offspring 1 and offspring 2 are two new individuals generated from parent 1 and parent 2.

[0112] Repeat the iteration until N offspring individuals are generated, forming the initial offspring population;

[0113] For each individual in the initial offspring population, a random number is generated. If the random number is less than the adjusted mutation rate, a mutation operation is performed on the decision variable of the current individual. After completing the mutation judgment and mutation operation for all individuals, the optimized offspring population is obtained, where the random number is a number between 0 and 1.

[0114] In this embodiment, the mutation judgment process includes: generating a random number between 0 and 1 for each individual in the initial offspring population; if the random number is less than the adjusted mutation rate, then performing a mutation operation on the decision variable of that individual; otherwise, keeping its original encoding unchanged; the mutation judgment process completes the judgment of the mutation triggering conditions for all individuals, thereby obtaining the offspring population after mutation processing.

[0115] Step 207: Merge the initial population with the mutated offspring population to form a mixed population of size 2N. Perform non-dominated sorting on the mixed population, divide it into a new non-dominated layer, select individuals from the new non-dominated layer, and finally form a new generation of parent population of size N.

[0116] In this embodiment, the initial population and the mutated offspring population are merged to form a mixed population of size 2N. The mixed population is then re-sorted using non-dominated sorting to create new non-dominated layers. Individuals are then selected according to a selection rule based on non-dominated layer priority and crowding. Individuals are first selected from the first non-dominated layer in descending order of crowding. If the number of individuals in this layer is less than N, all individuals are selected, and the selection continues from the second non-dominated layer in descending order of crowding. This process is repeated until a total of N individuals are selected, ultimately forming a new generation of parent population of size N. During the selection process, individuals with high crowding are prioritized to ensure that the new generation population is evenly distributed in the target space. At the same time, the optimal individuals in each non-dominated layer are retained to maintain the optimization level of the population.

[0117] Step 208: Repeat the iteration until the preset maximum number of iterations is reached. Select the best individual from the first non-dominated layer of the final population and extract the decision variables corresponding to the best individual.

[0118] In this embodiment, if the biobjective function value of the optimal individual in the population does not show significant improvement for 20 consecutive generations during the iteration process, the iteration can be terminated early to avoid invalid computation. After the iteration is terminated, the optimal individual is selected from the first non-dominated layer of the final population. The selection criterion is the individual with the highest crowding. This individual has both the optimal envelope contour compactness and can ensure the integrity of the point set coverage. At the same time, it is the farthest from other individuals in the target space, representing the optimal balance of biobjective optimization. All decision variables corresponding to this optimal individual are extracted, including the optimal expansion amount in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction, as well as the rounding requirements in each direction.

[0119] Step 209: Based on the optimal expansion amount among the determined decision variables, expand the spatial point set in the local coordinate system in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction, and then round it according to the optimal rounding requirement to finally obtain the initial envelope contour of the side pressure core.

[0120] In this embodiment, based on the optimal expansion amount among the determined decision variables, the spatial point set in the local coordinate system is expanded in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction. When expanding in the X direction, the maximum value of the X coordinate of the spatial point set plus the optimal expansion amount in the positive X direction is used as the positive X boundary of the envelope, and the minimum value of the X coordinate of the spatial point set minus the optimal expansion amount in the negative X direction is used as the negative X boundary. The Y and Z directions are expanded according to the same logic to ensure that the expanded envelope completely contains all sampling points and meets the process space requirements. After the expansion is completed, the boundary values ​​of each direction are rounded according to the optimal rounding requirement (rounded to an integer multiple of 5). For example, when the calculated value of the positive X boundary is 123mm, it is rounded to 125mm, and when the negative X boundary is -42mm, it is rounded to -40mm to ensure that the boundary values ​​meet the standardization requirements of mold processing. Finally, based on the rounded boundaries of each direction, a three-dimensional rectangular envelope is constructed, which is the initial envelope contour B0 of the side pressure core.

[0121] Please see Figure 3 A schematic diagram of the third embodiment of the side-pressure core body generation method provided by the present invention, the method comprising:

[0122] Step 301: Set the range of values ​​for the offset distance, and randomly generate a combination of the back plane offset distance and the top plane offset distance as the initial solution;

[0123] In this embodiment, the back plane offset distance needs to ensure that the distance between the back plane F5 and the sheet body F1 after offset is between 110-130mm, so the value range is set to 5-30mm; the top plane offset distance needs to ensure that the minimum distance between the top plane F6 and the sheet body F4 after offset is between 190-210mm, so the value range is set to 0-20mm; the back plane offset distance and the top plane offset distance are independently selected within the value range by a random number generator to form a set of parameter combinations, such as a back plane offset of 15mm and a top plane offset of 10mm. This combination is used as the initial solution of the simulated annealing algorithm. The initial solution needs to be constrained and verified to ensure that the corresponding plane distance after offset meets the process requirements.

[0124] In this embodiment, the initial solution refers to a set of back plane offset distance and top plane offset distance values ​​generated randomly within a set offset distance range. This combination serves as the starting point for the simulated annealing algorithm's iterative optimization, i.e., the initial state of the current optimal solution. Since the optimization process relies on searching from an initial point, the selection of the initial solution directly affects the algorithm's convergence speed and global optimization capability. A uniform random sampling strategy is used to generate the initial solution to ensure that it has a certain representativeness within the feasible region. In subsequent iterations, new solutions are continuously generated based on this initial solution, and the acceptance criterion is used to determine whether to update the current optimal solution, ultimately approximating the global optimal solution.

[0125] Step 302: Based on the initial solution, generate a new solution by random perturbation. If the new solution is better, it is taken as the current best solution. Otherwise, the acceptance probability is calculated based on the current simulated annealing temperature. When the acceptance probability meets the preset conditions, the new solution is accepted.

[0126] In this embodiment, random perturbation terms following a preset probability distribution are generated for the back plane offset distance and top plane offset distance of the current optimal solution, respectively. These perturbation terms are then superimposed onto the current solution to obtain a new solution.

[0127]

[0128] in, This indicates a new interpretation. Indicates the first Offset distance of the wheel back plane. Indicates the first Offset distance of the wheel top plane, The random perturbation term represents the distance of the back plane offset. The random perturbation term represents the offset distance of the top plane;

[0129] Calculate the objective function value of the current optimal solution and the objective function value of the new solution, and solve for the difference. ,like The current optimal solution is updated directly to ,like The acceptance probability is calculated based on the current simulated annealing algorithm temperature:

[0130]

[0131] in, Indicates the probability of acceptance. Indicates the probability of acceptance. Simulate the current temperature of the annealing algorithm during each iteration;

[0132] Generate a uniformly distributed random number in the interval [0, 1]. ,like Then update ,like Then reject the new solution and retain the original one. .

[0133] In this embodiment, the preset probability distribution refers to the pre-set probability distribution model used to generate random perturbation terms. The random perturbation terms adopt a normal distribution with a mean of 0 and a standard deviation of σ. The standard deviation is dynamically adjusted according to the current iteration round and gradually decreases in subsequent iterations according to the exponential decay law, so as to achieve a balance between the initial global exploration and the later local fine search.

[0134] In this embodiment, the objective function value is used as an evaluation index for the simulated annealing algorithm to quantify the comprehensive performance of the side pressure core structure under different offset distance combinations. The algorithm continuously compares the objective function value of the new solution with the objective function value of the current solution, and combines the probability of accepting a poor solution under the current temperature control to achieve a smooth transition from global exploration to local fine-tuning, and finally converges to the optimal offset distance combination that meets the requirements.

[0135] Step 303: Reduce the current temperature according to the set cooling coefficient, regenerate a new combination of offset distances, repeat the iteration until the algorithm temperature drops to the preset termination temperature, and obtain the current optimal solution, where the current optimal solution is the optimal offset distance between the back plane and the top plane.

[0136] In this embodiment, the current temperature is reduced according to a set cooling coefficient, such as 0.95. The initial temperature is set to 100. After the temperature is reduced, the random perturbation process is repeated to generate new offset distance combinations. The merits and acceptance probabilities are calculated again. The iteration continues until the algorithm temperature drops to the preset termination temperature. After the iteration terminates, the currently retained optimal solution is the optimal offset distance between the back plane and the top plane that meets the process constraints and dual-objective optimization requirements. This ensures that the distance between the back plane and F1 and the top plane and F4 after offsetting are in the optimal range, while balancing the structural weight and strength.

[0137] In this embodiment, the superiority / inferiority judgment refers to the process of determining whether the new solution is better than the current optimal solution based on the magnitude relationship of the objective function values.

[0138] Step 304: Based on the optimal offset distance, offset the back plane and top plane on the fused structure. Using the offset back plane and top plane as boundaries, and combining them with other contour boundaries of the fused structure, sequentially connect to obtain the closed offset contour line.

[0139] In this embodiment, based on the obtained optimal offset distance, the back plane F5 and the top plane F6 on the fused structure B7 are offset: the back plane F5 is offset along the positive Y direction by the optimal offset distance, and the top plane F6 is offset along the positive Z direction by the optimal offset distance, resulting in the offset back plane F5 and top plane F6. F6 To add new boundaries, in conjunction with other contour boundaries of the fusion structure B7, including the cutting edge side edge of the working part, the lower surface contour of the flange part, and the connecting edge of the process surface, the endpoints of each boundary are smoothly connected in sequence according to spatial orientation to ensure that the connected contours have no self-intersections and no sharp corner defects, and finally form a closed offset contour line, which defines the scope of the top hollow structure.

[0140] Step 305: Stretch the closed offset contour line along the preset direction to form the corresponding three-dimensional structure, obtain the boundary line, offset the boundary line along the positive Z direction, and then stretch it along the Y direction.

[0141] In this embodiment, the closed offset contour line is stretched along a preset direction, and the stretching height is set to 80mm to form the corresponding three-dimensional structure B8. The boundary line S2 between the working part and the flange part in the fused structure B7 is extracted, that is, the boundary line formed by the division of the F2 sheet and the process surface on the B5 body. The boundary line S2 is offset by 80mm along the positive Z direction to obtain the offset boundary line S2. Then S2 The material is stretched bidirectionally along the Y-axis, covering the entire Y-span of the three-dimensional structure B8, to form a sheet F7 for segmentation.

[0142] Step 306: Divide the fused structure and the stretched three-dimensional structure by intersection, delete the excess part located on the negative Z side of the fused structure, perform a difference operation on the divided fused structure, remove the overlapping part, and obtain the final structure of the side pressure core body.

[0143] In this embodiment, the fused structure B7 and the stretched three-dimensional structure B8 are intersected and divided. Using sheet F7 as a dividing tool, the three-dimensional structure B8 is trimmed, and the excess part located on the negative side of sheet F7Z is deleted to obtain the target three-dimensional structure B8 that meets the requirements of the hollowing range. Using the fused structure B7 as the target body and the target three-dimensional structure B8 as the tool body, a Boolean difference operation is performed to remove the part that overlaps with B8 from B7, thereby forming the top hollow structure. After the difference operation, the geometric integrity of the obtained structure is checked to see if there are any defects such as free surfaces or non-closed boundaries. If so, they are repaired by a surface-filling algorithm. Finally, the final structure B9, which includes the working part, the flange part, and the top hollow structure, is obtained. This structure meets all the requirements of process strength, spatial compactness, and backlash avoidance.

[0144] Please see Figure 4 A schematic diagram of the structure of the side-pressure core body generating device provided in this embodiment of the invention. The device includes:

[0145] Data acquisition module 401 is used to acquire process input data and identify geometric features in the process input data based on the B-rep data structure. The process input data includes at least the retraction direction line, parting line, and process surface, and the geometric features include at least the boundary line and intersecting surface.

[0146] The coordinate system construction module 402 is used to determine the Z-axis vector based on the retraction direction line, and calculate and correct the X-axis and Y-axis vectors based on the positional relationship between the parting line and the process surface to construct the local coordinate system of the side pressure core.

[0147] The envelope operation module 403 is used to discretize the parting line into a set of spatial points and map it to a local coordinate system. It integrates the NSGA-II algorithm to perform envelope operation on the mapped set of spatial points to generate an initial envelope contour volume.

[0148] The structure generation module 404 is used to generate the fusion structure of the working part and the flange part of the side pressure core body based on the initial envelope contour.

[0149] The determination module 405 is used to determine the optimal offset distance between the back plane and the top plane based on the fusion structure of the working part and the flange part, construct the closed offset contour line and complete the stretching, segmentation and subtraction operations to obtain the final structure of the side pressure core body.

[0150] Figure 5 This is a schematic diagram of a side-pressure core body generating device 600 provided in an embodiment of the present invention. The side-pressure core body generating device 600 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. The memory 620 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the side-pressure core body generating device 600. Furthermore, the processor 610 may be configured to communicate with the storage media 630 and execute the series of instruction operations in the storage media 630 on the side-pressure core body generating device 600 to implement the method provided in the above embodiment.

[0151] The side-pressure core body generating device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input / output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 5 The structure of the side-pressure core body generating device shown does not constitute a limitation on the computer device provided by the present invention. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0152] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform each step of the side-pressure core body generation method provided in the above embodiments.

[0153] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described equipment or apparatus / unit can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0154] If the integrated unit is implemented as 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a side-pressure core body, characterized in that, include: Collect process input data, and identify geometric features in the process input data based on the B-rep data structure. The process input data includes at least a retraction direction line, a parting line, and a process surface. The geometric features include at least a boundary line and an intersecting surface. The Z-axis vector is determined based on the retraction direction line. The X-axis and Y-axis vectors are calculated and corrected based on the positional relationship between the parting line and the process surface to construct a local coordinate system for the side-pressure core. The parting line is discretized into a set of spatial points and mapped to the local coordinate system. The NSGA-II algorithm is then used to perform envelope operations on the mapped set of spatial points to generate an initial envelope contour volume. The fusion structure of the working part and the flange part of the side pressure core body is generated based on the initial envelope contour. Based on the fusion structure of the working part and the flange part, the optimal offset distance between the back plane and the top plane is determined, a closed offset contour line is constructed, and stretching, segmentation and subtraction operations are completed to obtain the final structure of the side pressure core body. The parting line is discretized into a set of spatial points and mapped to the local coordinate system. The NSGA-II algorithm is then used to perform envelope operations on the mapped set of spatial points to generate an initial envelope contour volume, including: Sampling points are uniformly selected along the parting line according to the preset sampling interval to form a spatial point set. The coordinates of each sampling point in the spatial point set are transformed and calculated according to the 3×3 coordinate transformation matrix and the origin coordinates of the local coordinate system to form a mapped spatial point set. The envelope operation parameters are set as decision variables and variable constraints, wherein the decision variables include at least the positive X expansion, negative X expansion, positive Y expansion, negative Y expansion, positive Z expansion, negative Z expansion, and rounding requirements in each direction; Randomly generate N individuals that meet the variable constraints, each individual corresponding to a set of envelope operation parameters, to form the initial population; Using the compactness of the envelope contour and the integrity of the point set coverage as dual objective functions, each individual in the initial population is evaluated, and different non-dominated layers are divided. For each individual in a non-dominated layer, calculate the distance between each individual in the non-dominated layer and its neighboring individuals in the target space to obtain the crowding value; The crossover rate and mutation rate are adjusted based on the crowding value, and the offspring population is generated by crossover operation and optimized by mutation operation. The initial population is merged with the mutated offspring population to form a mixed population of size 2N. The mixed population is then subjected to non-dominated sorting to divide a new non-dominated layer. Individuals are selected from the new non-dominated layer to form a new generation of parent population of size N. Repeat the iteration until the preset maximum number of iterations is reached. Select the best individual from the first non-dominated layer of the final population and extract the decision variables corresponding to the best individual. Based on the optimal expansion amount among the determined decision variables, the spatial point set in the local coordinate system is expanded in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction. Then, it is rounded according to the optimal rounding requirement to finally obtain the initial envelope contour of the side pressure core.

2. The method for generating a side-pressure core body as described in claim 1, characterized in that, The process of adjusting the crossover and mutation rates based on crowding values, and using crossover operations to generate the offspring population and mutation operations to optimize the offspring population, includes: A tournament selection mechanism is adopted. k individuals are randomly selected from the initial population. The non-dominance level and crowding of the individuals are compared. Individuals with higher non-dominance level and greater crowding are selected as parent individuals. This process is repeated until N parent individuals are selected to form a parent pairing pool. Obtain the non-dominant level of each parent pair in the parent pairing pool. and Calculate the cross-distribution index according to the formula. : in, Indicates the highest non-dominant rank in the initial population. The value range is [0,1]; For each pair of parent individuals, the decision variables are encoded, a crossover point is randomly selected, the encoded segments to the right of the crossover point are swapped, and the offspring parameters are adjusted using the crossover distribution index. The decision variable values ​​for the offspring individuals are then calculated. in, For the first generation of the father One decision variable, For the second generation of the father One decision variable, For the first generation One decision variable, For the second generation There are 1 decision variables, where parent 1 and parent 2 are a pair of individuals selected, and offspring 1 and offspring 2 are two new individuals generated from parent 1 and parent 2. Repeat the iteration until N offspring individuals are generated, forming the initial offspring population; For each individual in the initial offspring population, a random number is generated. If the random number is less than the adjusted mutation rate, a mutation operation is performed on the decision variable of the current individual. After completing the mutation judgment and mutation operation for all individuals, the optimized offspring population is obtained, where the random number is a number between 0 and 1.

3. The method for generating a side-pressure core body as described in claim 1, characterized in that, The fusion structure of the working part and the flange part of the side pressure core body is generated based on the initial envelope contour, including: Based on the initial envelope contour, an AABB bounding box is constructed as the root node, and an OBB bounding box is constructed as the child node inside the AABB bounding box. Traverse the AABB bounding box, extract the region where the AABB bounding box and the intersecting surface do not overlap spatially, and for the retained region, select the segmentation direction that is consistent with the extension direction of the intersecting surface based on the spatial orientation of the intersecting surface; For the inner OBB bounding box of the reserved area, determine the overlapping boundary and spatial connection relationship between the intersecting surface and the OBB bounding box to obtain the range of the intersecting area; Based on the determined intersection area range, adjust the segmentation boundary parameters between the working part and the flange part in the initial envelope contour body; Based on the segmentation boundary parameters and the spatial extension length of the intersecting surfaces, the wrapping range of the AABB bounding box and the OBB bounding box is dynamically adjusted to form a two-layer hierarchical bounding box tree structure. The initial structures of the working part and the flange part are integrated to form an initial fusion structure. The initial fusion structure is then subjected to a second traversal test through the double-layer hierarchical surrounding box tree structure, and finally the fusion structure of the working part and the flange part of the side pressure core body is obtained.

4. The method for generating a side-pressure core body as described in claim 3, characterized in that, The dynamic adjustment of the enclosure range of the AABB bounding box and the OBB bounding box based on the segmentation boundary parameters and the spatial extension length of the intersecting surface includes: Expand the corresponding range of the AABB bounding box outward, where the expansion amount is the extension length of the intersecting surface in the extension direction, determine the maximum and minimum coordinate values ​​of the AABB bounding box in the X, Y, and Z directions, and form the adjusted AABB bounding range; Based on the spatial orientation of the intersecting surfaces, the initial orientation of the OBB bounding box is set, and the enclosing range of the OBB bounding box is initially determined with reference to the adjusted AABB bounding box range. Traverse the contour features of the intersecting surfaces to make the OBB bounding box fit the contour, and adjust the azimuth angle of the OBB bounding box according to the connection relationship between the segmentation boundary and the intersecting surfaces. Check whether the adjusted OBB bounding box is completely inside the AABB bounding box. If there is any excess, readjust the AABB bounding box range.

5. The method for generating a side-pressure core body as described in claim 1, characterized in that, Based on the fusion structure of the working part and the flange part, the optimal offset distance between the back plane and the top plane is determined, a closed offset contour line is constructed, and stretching, segmentation, and subtraction operations are completed to obtain the final structure of the side pressure core body, including: Set the range of offset distance values, and randomly generate a combination of back plane offset distance and top plane offset distance as the initial solution, wherein the initial solution is the starting point of the simulated annealing algorithm; Based on the initial solution, a new solution is generated by random perturbation. If the new solution is better, it is taken as the current best solution. Otherwise, the acceptance probability is calculated based on the current simulated annealing temperature. When the acceptance probability meets the preset conditions, the new solution is accepted. The current temperature is reduced according to the set cooling coefficient, a new combination of offset distances is generated, and the iteration is repeated until the algorithm temperature drops to the preset termination temperature to obtain the current optimal solution, where the current optimal solution is the optimal offset distance between the back plane and the top plane. Based on the optimal offset distance, the back plane and top plane on the fused structure are offset. Using the offset back plane and top plane as boundaries, and combined with other contour boundaries of the fused structure, closed offset contour lines are sequentially connected to obtain the closed offset contour lines. The closed offset contour line is stretched along a preset direction to form the corresponding three-dimensional structure, and the boundary line is obtained. After the boundary line is offset along the positive Z direction, it is stretched along the Y direction. The fused structure and the stretched three-dimensional structure are intersected and divided. The excess part located on the negative Z side of the fused structure is deleted. The difference operation is performed on the divided fused structure to remove the overlapping part, and the final structure of the side pressure core is obtained.

6. The method for generating a side-pressure core body as described in claim 5, characterized in that, The process involves generating a new solution through random perturbation based on the initial solution. If the new solution is better, it is adopted as the current optimal solution; otherwise, the acceptance probability is calculated based on the current simulated annealing temperature. When the acceptance probability meets a preset condition, the new solution is accepted, including: For the backplane offset distance and topplane offset distance of the current optimal solution, generate random perturbation terms that follow a preset probability distribution. These perturbation terms are then superimposed onto the current solution to obtain a new solution. in, This indicates a new interpretation. Indicates the first Offset distance of the wheel back plane. Indicates the first Offset distance of the wheel top plane, The random perturbation term represents the distance of the back plane offset. The random perturbation term represents the offset distance of the top plane; Calculate the objective function value of the current optimal solution and the objective function value of the new solution, and solve for the difference. ,like The current optimal solution is updated directly to ,like The acceptance probability is calculated based on the current simulated annealing algorithm temperature: in, Indicates the probability of acceptance. Indicates the probability of acceptance. The current temperature of the simulated annealing algorithm is measured during each round of iteration; Generate a uniformly distributed random number in the interval [0, 1]. ,like Then update ,like Then reject the new solution and retain the original one. .

7. A device for generating a side-pressure core body, characterized in that, include: The data acquisition module is used to acquire process input data and identify geometric features in the process input data based on the B-rep data structure. The process input data includes at least a retraction direction line, a parting line, and a process surface, and the geometric features include at least a boundary line and an intersecting surface. The coordinate system construction module is used to determine the Z-axis vector based on the retraction direction line, and calculate and correct the X-axis and Y-axis vectors based on the positional relationship between the parting line and the process surface to construct a local coordinate system for the side pressure core. The envelope operation module is used to discretize the parting line into a set of spatial points and map it to the local coordinate system. It then integrates the NSGA-II algorithm to perform envelope operations on the mapped spatial point set, generating an initial envelope contour. This involves uniformly selecting sampling points along the parting line according to a preset sampling interval to form a spatial point set. Based on a 3×3 coordinate transformation matrix and the origin coordinates of the local coordinate system, the coordinates of each sampling point in the spatial point set are transformed and calculated to form the mapped spatial point set. Envelope operation parameters are set as decision variables and variable constraints. The decision variables include at least the positive X-axis expansion, negative X-axis expansion, positive Y-axis expansion, negative Y-axis expansion, positive Z-axis expansion, negative Z-axis expansion, and rounding requirements for each direction. N individuals that meet the variable constraints are randomly generated, each corresponding to a set of envelope operation parameters, forming an initial population. Each individual in the initial population is evaluated using the compactness of the envelope contour and the completeness of the point set coverage as dual objective functions. Divide the population into different non-dominated layers; for each individual in the non-dominated layer, calculate the distance between each individual in the non-dominated layer and its neighboring individuals in the target space to obtain the crowding value; adjust the crossover rate and mutation rate based on the crowding value, and use crossover operation to generate offspring population and mutation operation to optimize the offspring population; merge the initial population with the mutated offspring population to form a mixed population of size 2N, perform non-dominated sorting on the mixed population, divide the population into new non-dominated layers, select individuals from the new non-dominated layers, and finally form a new generation of parent population of size N; repeat the iteration until the preset maximum number of iterations is reached, select the best individual from the first non-dominated layer of the final population, and extract the decision variables corresponding to the best individual; according to the optimal expansion amount in the determined decision variables, expand the spatial point set in the local coordinate system in the positive X direction, negative X direction, positive Y direction, negative Y direction, positive Z direction, and negative Z direction, and then round according to the optimal rounding requirement to finally obtain the initial envelope contour of the side pressure core; The structure generation module is used to generate a fusion structure of the working part and the flange part of the side pressure core body based on the initial envelope contour. The determination module is used to determine the optimal offset distance between the back plane and the top plane based on the fusion structure of the working part and the flange part, construct the closed offset contour line and complete the stretching, segmentation and subtraction operations to obtain the final structure of the side pressure core body.

8. A side-pressure core body generating device, characterized in that, The side-pressure core body generating device includes a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the side-pressure core body generating device to perform each step of the side-pressure core body generating method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the side-pressure core body generation method as described in any one of claims 1-6.

Images