Stamping die cavity optimization method based on stress distribution thermal map of mine tray

Abstract

The embodiment of the application discloses a stamping die cavity optimization method based on a stress distribution thermal map of a mine tray, and the method comprises the following steps: obtaining a stress distribution thermal map of a target mine tray in a stamping forming process; constructing a corresponding stress topology skeleton network; generating a corresponding streamline feature field, which is used for characterizing material flow continuity, flow turning degree and flow convergence degree; obtaining stress direction distribution information of a target service working condition of the target mine tray, and constructing a target stress direction field according to the stress direction distribution information; generating a streamline deviation evaluation result; determining an abnormal guide area in the target cavity according to the streamline deviation evaluation result, and analyzing the influence degree of each abnormal guide area on a material flow path; and performing reverse optimization on the stamping die cavity according to the cavity optimization parameters. The application improves the overall supporting reliability and production efficiency of the mine tray.

Description

Technical Field

[0001] This application relates to the field of metal stamping technology, and in particular to a method for optimizing the cavity of a stamping die based on a thermal diagram of stress distribution in a mining pallet. Background Technology

[0002] Mining pallets are important load-bearing components in mine support, tunnel support, and geotechnical engineering support systems. They are primarily used to transfer the preload applied by anchor bolts to the surrounding rock or support structure surface, thereby improving the overall support effect. Existing mining pallets are typically manufactured using sheet metal stamping processes, where stamping dies are used to form a spatial structure with a certain load-bearing capacity from sheet metal.

[0003] During the stamping process, the metal material undergoes complex plastic flow under the constraint of the die cavity, accompanied by stress redistribution. To improve the forming quality of pallets, existing technologies typically utilize finite element simulation, stress cloud diagram analysis, or stress thermographic analysis to evaluate stress concentration areas, deformation areas, and potential cracking areas during the stamping process. Based on this, the die structure parameters are adjusted and optimized to reduce stress concentration and improve forming quality.

[0004] However, most existing technologies focus on analyzing the stress distribution during the stamping process, primarily evaluating the quality of mold design based on the magnitude of stress peaks, the degree of stress concentration, or the thickness reduction. While these methods can improve forming quality to some extent, their focus on the forming process itself often fails to reflect the matching between the internal flow path of the metal material and the actual stress direction of the tray during service.

[0005] In fact, the material flow path formed during the stamping process of metal materials has a significant impact on the subsequent load-bearing performance of the pallet. When there is a large deviation between the material flow direction and the main stress direction of the pallet during actual service, even if there is no obvious stress concentration during the forming stage, problems such as local fatigue damage, crack propagation, or reduced load-bearing capacity may still occur under long-term loads. Therefore, how to further identify the material flow path characteristics based on the stress distribution characteristics formed during the stamping process, and perform reverse optimization of the mold cavity in combination with the target service conditions of the pallet, thereby improving the matching degree between the material flow path and the service stress direction, has become an urgent technical problem to be solved. Summary of the Invention

[0006] This application provides a method for optimizing the cavity of a stamping die based on a thermal map of stress distribution in a mining pallet, which solves the problems of imprecise stress analysis, low matching degree between forming streamline and service stress, and insufficient targeted cavity optimization in the prior art.

[0007] This application provides the following solution: According to a first aspect, a method for optimizing the cavity of a stamping die based on a stress distribution heat map of a mining pallet is provided. The method includes: acquiring a stress distribution heat map of a target mining pallet during the stamping process; constructing a corresponding stress topology skeleton network based on the stress peak value and gradient in the stress distribution heat map; analyzing the flow path characteristics of the metal material during the forming process based on the stress topology skeleton network, and generating a corresponding streamline feature field, wherein the streamline feature field is used to characterize the continuity of material flow, the degree of flow inflection, and the degree of flow convergence; acquiring the force direction distribution information of the target service condition of the target mining pallet, and constructing a target force direction field based on the force direction distribution information; generating a streamline deviation evaluation result based on the matching relationship between the streamline feature field and the target force direction field; determining abnormal guiding regions in the target cavity based on the streamline deviation evaluation result, and analyzing the degree of influence of each abnormal guiding region on the material flow path; generating cavity optimization parameters based on the degree of influence corresponding to each abnormal guiding region, and performing reverse optimization of the stamping die cavity based on the cavity optimization parameters.

[0008] According to one achievable method in an embodiment of this application, the step of constructing a corresponding stress topology skeleton network based on the stress peak values ​​and gradients in the stress distribution heatmap includes: performing image segmentation processing on the stress distribution heatmap to obtain multiple stress feature regions; extracting color distribution features, texture features, and edge features corresponding to each stress feature region; identifying multiple local stress peak nodes based on the color distribution features, texture features, and edge features; extracting the main stress propagation path based on the image gradient continuity between adjacent stress feature regions; identifying stress bifurcation nodes and stress convergence nodes based on the image connectivity between each main stress propagation path; and constructing a stress topology skeleton network based on the local stress peak nodes, the stress bifurcation nodes, the stress convergence nodes, and the main stress propagation paths.

[0009] According to one achievable method in an embodiment of this application, after identifying multiple local stress peak nodes, the method further includes: performing target recognition processing on the local stress peak nodes; generating node feature vectors based on the color gradient change features, texture change features, and edge change features corresponding to the area surrounding the local stress peak nodes; identifying key stress nodes and non-key stress nodes based on the similarity between the feature vectors of each node; and correcting the stress topology skeleton network based on the key stress nodes.

[0010] According to one achievable method in an embodiment of this application, the step of analyzing the flow path characteristics of metallic materials during the forming process based on the stress topology skeleton network and generating a corresponding streamline feature field includes: extracting the image skeleton direction corresponding to the main stress propagation path based on the stress topology skeleton network; generating the main material flow direction based on each image skeleton direction; generating streamline bifurcation degree parameters based on the number of bifurcations and bifurcation angles corresponding to each stress bifurcation node; generating streamline aggregation degree parameters based on the number of convergences and convergence intensities corresponding to each stress convergence node; generating streamline inflection degree parameters based on the curvature changes corresponding to each image skeleton direction; and generating a streamline feature field based on the main material flow direction, the streamline bifurcation degree parameters, the streamline aggregation parameters, and the streamline inflection degree parameters.

[0011] According to one achievable method in an embodiment of this application, after generating the streamline feature field, the method further includes: using the main material flow direction in the streamline feature field as the propagation reference direction to establish a flow feature propagation vector; performing branching and expansion processing on the flow feature propagation vector according to the streamline bifurcation degree parameter to generate multiple propagation paths; performing path convergence constraint processing on each propagation path according to the streamline convergence degree parameter to form local flow convergence units; performing nonlinear correction on the propagation direction of each propagation path according to the streamline turning degree parameter to generate a set of corrected propagation paths; and updating the streamline feature field based on the set of corrected propagation paths.

[0012] According to one achievable method in an embodiment of this application, the step of constructing a target force direction field based on the force direction distribution information includes: parsing the force direction distribution information to obtain the force direction and force intensity corresponding to each region of the target mining pallet; generating a local force direction vector based on the force direction corresponding to each region; generating a direction weight parameter based on the force intensity corresponding to each region; and constructing a target force direction field based on each local force direction vector and the corresponding direction weight parameter.

[0013] According to one achievable method in this application embodiment, generating a streamline deviation evaluation result based on the matching relationship between the streamline feature field and the target force direction field includes: extracting the main material flow direction, streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter corresponding to each region from the streamline feature field; extracting the target force direction corresponding to each region from the target force direction field; calculating the directional deviation between the main material flow direction and the target force direction corresponding to each region; generating a directional matching degree parameter based on the directional deviation; generating a streamline stability parameter by combining the streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter; and generating a streamline deviation evaluation result based on the directional matching degree parameter and the streamline stability parameter.

[0014] According to one achievable method in an embodiment of this application, determining the abnormal guiding region in the target cavity based on the streamline deviation evaluation result includes: identifying abnormal streamline regions exceeding a preset threshold in the streamline deviation evaluation result; performing reverse topology tracing analysis along the main material flow direction corresponding to the abnormal streamline region; determining key stress bifurcation nodes or key stress convergence nodes that cause streamline deviation; determining the cavity contact region corresponding to the key node based on the projection position or contact correspondence of the key stress bifurcation node or key stress convergence node on the mold cavity; and determining the cavity contact region as the abnormal guiding region in the target cavity.

[0015] According to one achievable method in the embodiments of this application, the analysis of the influence of each abnormal guiding region on the material flow path includes: performing local structural disturbance simulation on each abnormal guiding region; obtaining the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree before and after the local structural disturbance simulation; and generating influence degree parameters based on the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree.

[0016] According to the second aspect, a stamping die cavity optimization system based on a stress distribution heat map of a mining pallet is provided. The system includes: a stress heat map acquisition module for acquiring a stress distribution heat map of the target mining pallet during the stamping process; a stress topology skeleton network construction module for constructing a corresponding stress topology skeleton network based on the stress peak values ​​and gradients in the stress distribution heat map; a streamline feature field generation module for analyzing the flow path characteristics of the metal material during the forming process based on the stress topology skeleton network and generating a corresponding streamline feature field, wherein the streamline feature field characterizes the continuity of material flow, the degree of flow inflection, and the degree of flow convergence; and a target force direction field. The system includes a construction module for acquiring the force direction distribution information of the target service condition of the target mining pallet and constructing the target force direction field based on the force direction distribution information; a streamline deviation evaluation module for generating streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field; an abnormal guiding region determination module for determining abnormal guiding regions in the target cavity based on the streamline deviation evaluation results and analyzing the degree of influence of each abnormal guiding region on the material flow path; and a cavity optimization module for generating cavity optimization parameters based on the degree of influence corresponding to each abnormal guiding region and performing reverse optimization of the stamping die cavity based on the cavity optimization parameters.

[0017] According to the specific embodiments provided in this application, the following technical effects are disclosed: This invention transforms the stress distribution thermogram during the stamping process of mining pallets into a stress topological skeleton network, and further generates streamline feature fields characterizing the continuity, turning point, and convergence of material flow. Simultaneously, it constructs a target stress direction field under service conditions, achieving precise matching between the forming flow characteristics and the actual service stress direction. Based on the streamline deviation evaluation results, abnormal guiding regions in the target cavity can be quickly located. By quantifying the influence of each region on the material flow path, targeted cavity optimization parameters are generated, ultimately completing the reverse optimization of the mold cavity. This method overcomes the limitations of traditional methods that rely solely on experience or trial molding iterations, significantly improving the matching degree between material flow uniformity and service performance, reducing forming defects, lowering the number of trial moldings and mold development costs, and enhancing the overall support reliability and production efficiency of mining pallets. It possesses strong practicality and technological advancement.

[0018] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of a method for optimizing the cavity of a stamping die based on a thermal diagram of stress distribution in a mining pallet, provided in an embodiment of this application; Figure 2 A schematic diagram illustrating the process of converting a distribution heatmap into a stress topology skeleton network, as provided in the embodiments of this application; Figure 3 This application provides a structural block diagram of a stamping die cavity optimization system based on a thermal map of stress distribution in a mining pallet, as shown in the embodiments of this application. Figure 4 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0022] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0023] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0024] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0025] Figure 1 A flowchart illustrating the method for optimizing the cavity of a stamping die based on a thermal map of stress distribution in a mining pallet, provided in this application embodiment. Figure 1 As shown, the method may include the following steps: Step 101: Obtain the stress distribution thermogram of the target mining pallet during the stamping process.

[0026] Step 102: Based on the stress peak value and gradient in the stress distribution heatmap, construct the corresponding stress topology skeleton network.

[0027] Step 103: Based on the stress topology skeleton network, analyze the flow path characteristics of the metal material during the forming process and generate the corresponding streamline feature field. The streamline feature field is used to characterize the continuity of material flow, the degree of flow turning and the degree of flow convergence.

[0028] Step 104: Obtain the force direction distribution information of the target service condition of the target mining pallet, and construct the target force direction field based on the force direction distribution information.

[0029] Step 105: Based on the matching relationship between the streamline feature field and the target force direction field, generate streamline deviation evaluation results.

[0030] Step 106: Determine the abnormal guiding regions in the target cavity based on the streamline deviation evaluation results, and analyze the degree of influence of each abnormal guiding region on the material flow path.

[0031] Step 107: Generate cavity optimization parameters based on the degree of influence corresponding to each abnormal guiding area, and perform reverse optimization of the stamping die cavity according to the cavity optimization parameters.

[0032] As can be seen from the above process, this invention transforms the stress distribution thermogram during the stamping process of mining pallets into a stress topological skeleton network, and further generates streamline feature fields characterizing the continuity, turning degree, and convergence degree of material flow. Simultaneously, it constructs a target stress direction field under service conditions, achieving precise matching between the forming flow characteristics and the actual service stress direction. Based on the streamline deviation evaluation results, abnormal guiding regions in the target cavity can be quickly located, and by quantifying the influence of each region on the material flow path, targeted cavity optimization parameters are generated, ultimately completing the reverse optimization of the mold cavity. This method overcomes the limitations of traditional methods that rely solely on experience or trial molding iterations, significantly improving the matching degree between material flow uniformity and service performance, reducing forming defects, lowering the number of trial moldings and mold development costs, and enhancing the overall support reliability and production efficiency of mining pallets. It possesses strong practicality and technological advancement.

[0033] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments. First, the above step 101, namely "obtaining the stress distribution thermogram of the target mining pallet during the stamping process", will be described in detail with reference to the embodiments.

[0034] Mining pallets are important support components in underground engineering projects such as coal mines and tunnels. They are used in conjunction with anchor bolts, nuts, etc., and are mainly installed at the ends of anchor bolts in the roof or sidewalls of roadways. The optimization target of this application is the stamping die, and the target mining pallet is the product manufactured based on the optimization target of this invention. Based on its stress requirements during use, the cavity of the stamping die is inversely optimized. The stress distribution heat map is a visualization result generated after numerical simulation of the stamping process of the mining pallet using finite element analysis software.

[0035] In practical implementation, a finite element simulation model is first established based on the initial mold cavity geometry of the target mining pallet, the material properties of the metal sheet, and the stamping process parameters. Professional stamping simulation software is then used to dynamically simulate the entire stamping process, including the contact between the sheet metal and the mold cavity, plastic deformation, and stress-strain evolution. Through simulation calculations, key stress indicators such as equivalent stress, maximum principal stress, or shear stress at various times and in various regions during the forming process are obtained.

[0036] The simulation results are then visualized as a color-coded cloud map, forming a stress distribution heatmap. This heatmap uses different colors to visually represent the magnitude of stress values; high-stress areas are typically displayed in red or warm colors, while low-stress areas are displayed in blue or cool colors, clearly showing the concentration and gradient distribution of stress in different parts of the tray. This heatmap not only reflects the stress state of the material during the forming process but also provides an intuitive data foundation for the subsequent construction of the topological skeleton network.

[0037] By acquiring this stress distribution heatmap, the stress evolution of the target mining pallet during stamping can be comprehensively captured, especially the location of stress peaks and propagation paths. This information is directly related to the flow behavior of the metal material, which helps in subsequent steps to analyze flow path characteristics and compare them with the stress direction under service conditions. The implementation of this step ensures that the entire optimization method is based on an accurate simulation of the actual forming physical process, providing a reliable input data source for the reverse optimization of the cavity.

[0038] The following describes in detail step 102, namely "constructing a corresponding stress topology skeleton network based on the stress peak value and gradient in the stress distribution heatmap", with reference to the embodiments.

[0039] This step transforms the original continuous color stress cloud map into a structured topological network, which facilitates the subsequent accurate extraction of material flow path features. Figure 2 This is a schematic diagram illustrating the process of converting a heat map of stress distribution into a stress topology skeleton network, as provided in the embodiments of this application. It is divided into three main stages. From left to right: the left side shows the original stress distribution heat map during the stamping and forming process of the target mining pallet, with color cloud maps displaying different stress level regions; the middle side shows multiple stress feature regions and local stress peak nodes identified after image segmentation processing; the right side shows the final constructed stress topology skeleton network, where large dots represent local stress peak nodes, thick solid lines represent the main path of stress propagation, medium dots represent stress bifurcation nodes, small dots represent stress convergence nodes, and arrows indicate the direction of stress propagation.

[0040] Specifically, image segmentation processing is performed on the stress distribution heatmap, dividing the entire heatmap into multiple stress feature regions with similar stress levels. During the segmentation process, the natural boundaries of color transitions are comprehensively considered to ensure that the stress values ​​within each region are relatively uniform, while there are obvious stress gradient changes between regions, thereby providing clear regional units for subsequent feature extraction.

[0041] Specifically, the stress distribution heatmap output from the finite element method (FEM) simulation is converted into a digital image in a standard RGB or HSV color space. Then, a hybrid segmentation method based on thresholding and region growing is employed. The process is as follows: Based on the actual distribution range of stress values, multiple gradient threshold intervals are set. For example, the equivalent stress value is divided into several levels, such as 0-100MPa, 100-200MPa, 200-300MPa, and above 300MPa, with each level corresponding to a preliminary color category. Next, the pixel with the most significant color change in the heatmap is used as a seed point, and a region growing algorithm is used for segmentation. Starting from each seed point, the algorithm expands to surrounding neighboring pixels. When the color difference between adjacent pixels is less than a preset similarity threshold and the stress value gradient change is continuous, they are grouped into the same stress feature region. When a color abrupt change or the gradient exceeds the set threshold, growth stops and a new region boundary is established. In this way, the heatmap can be naturally segmented into multiple stress feature regions with relatively uniform internal stress levels and clear boundaries. To further improve segmentation accuracy, a watershed algorithm can be introduced after initial segmentation for boundary refinement: the heatmap is converted into a gradient amplitude image, and the local minima of each stress feature region are used as watershed markers to accurately extract the watershed lines between regions, thus avoiding over-segmentation or under-segmentation. The final output of multiple stress feature regions not only preserves the global continuity of stress distribution in the original heatmap but also provides independent and structured data units for subsequent extraction of color distribution features, texture features, and edge features. This implementation method is simple to operate, computationally efficient, and stably applicable to stress distribution heatmap processing of mining pallets of different specifications.

[0042] Next, the color distribution features, texture features, and edge features corresponding to each stress feature region are extracted. The color distribution features reflect the concentration and range of stress values ​​within the region, the texture features depict the fluctuation pattern of stress within the region, and the edge features highlight the drastic gradient changes at the region boundaries. Through comprehensive analysis of these multi-dimensional image features, multiple local stress peak nodes can be accurately identified. These nodes typically correspond to the local extreme points with the highest stress values ​​in the thermogram, serving as important indicators of stress concentration and material flow anomalies.

[0043] Then, the main stress propagation path is extracted based on the continuity of image gradients between adjacent stress feature regions. This process connects the peak nodes along the direction with the smoothest gradient change and the best continuity, forming a backbone path representing the main stress propagation trend. Simultaneously, based on the image connectivity between the main stress propagation paths, stress bifurcation nodes and stress convergence nodes are further identified. Bifurcation nodes indicate locations where stress diffuses from one main path in multiple directions, while convergence nodes represent regions where stress from multiple paths converge.

[0044] Finally, based on the aforementioned local stress peak nodes, stress bifurcation nodes, stress convergence nodes, and main stress propagation paths, a complete stress topology skeleton network is constructed. This network is presented in the form of nodes and edges in graph theory, clearly depicting the topological relationships of stress propagation during the forming process. It provides a structured and highly abstract mathematical model foundation for subsequent generation of streamline feature fields and analysis of material flow continuity, degree of inflection, and degree of convergence.

[0045] Preferably, after identifying multiple local stress peak nodes, the present invention further includes: performing target recognition processing on the local stress peak nodes; generating node feature vectors based on the color gradient change features, texture change features, and edge change features corresponding to the area surrounding the local stress peak nodes; identifying key stress nodes and non-key stress nodes based on the similarity between the feature vectors of each node; and correcting the stress topology skeleton network based on the key stress nodes.

[0046] Specifically, the process begins by performing target recognition processing on each local stress peak node. This process extracts the image region within a certain radius around the node as the analysis object. Then, based on the color gradient change features, texture change features, and edge change features corresponding to this region, a node feature vector is generated. The color gradient change features reflect the intensity and direction of stress diffusion outward from the node, the texture change features depict the local fluctuation pattern of stress distribution near the node, and the edge change features highlight the abrupt stress changes at the node boundaries. These multi-dimensional features together constitute a high-dimensional feature vector, which can comprehensively characterize the unique properties of each peak node.

[0047] Next, cluster analysis or distance calculation is performed based on the similarity between the feature vectors of each node to identify critical stress nodes and non-critical stress nodes. Critical stress nodes are typically those core nodes whose feature vectors differ significantly from other nodes, have a high degree of stress concentration, and have a significant impact on the overall stress propagation, while non-critical stress nodes are relatively minor nodes that may be caused by simulation noise or local minor fluctuations.

[0048] Finally, the stress topology skeleton network is modified based on the identified key stress nodes. Specifically, this includes retaining or strengthening the weights of key nodes and their associated paths, and appropriately weakening or deleting non-key nodes and their connecting edges, thereby optimizing the simplicity and representativeness of the entire topology and making the skeleton network more accurately reflect the main stress propagation laws during the forming process.

[0049] Furthermore, after extracting the main stress propagation path based on the continuous change relationship of stress gradient between local stress peak nodes, the present invention may further include: performing directional continuity analysis on each main stress propagation path and calculating the consistency of stress gradient direction at adjacent sampling points; identifying stable propagation segments and disturbed propagation segments in the path based on the consistency of stress gradient direction; assigning path weights to the stable propagation segments, wherein the path weights are used to characterize the degree of stress concentration in the corresponding propagation direction; and reconstructing each main stress propagation path based on the path weights to obtain the reconstructed main stress propagation path.

[0050] Specifically, the consistency of stress gradient direction at adjacent sampling points along the path is first calculated. This calculation uses consecutive sampling points along the path as units, comparing the similarity of the angle or cosine of the stress gradient vector directions between adjacent points. A high consistency indicates that the stress propagation direction along that segment of the path is stable and continuous; a low consistency indicates that there are significant directional fluctuations or disturbances along the path.

[0051] Next, stable propagation segments and disturbed propagation segments in the path are identified based on the stress gradient direction consistency. Stable propagation segments refer to continuous path sections where the direction consistency exceeds a preset threshold; these segments represent the main and reliable propagation trend of stress during the forming process. Disturbed propagation segments, on the other hand, refer to sections with lower direction consistency and greater influence from local noise or secondary factors. This identification process filters out unrepresentative path segments.

[0052] Next, path weights are assigned to the stable propagation segments. These path weights characterize the degree of stress concentration along the corresponding propagation direction and are typically calculated based on factors such as the average stress value, length, and gradient intensity of the path segment. Higher weights indicate a greater influence of the propagation direction on the overall stress distribution and should be given higher priority in subsequent analyses.

[0053] Finally, the main stress propagation paths are reconstructed based on path weights to obtain the reconstructed main stress propagation paths. During the reconstruction process, the connections of high-weight stable segments are strengthened, while perturbation segments are appropriately weakened or smoothed, thereby forming a simpler, more continuous, and physically meaningful main path structure.

[0054] Through this series of image processing and topology construction operations, the present invention can transform complex stress distribution heatmaps into calculable and traceable skeleton structures, effectively improving the accuracy of anomaly guidance region location and the targeted nature of cavity reverse optimization.

[0055] The following describes in detail step 103, namely, "analyzing the flow path characteristics of the metal material during the forming process based on the stress topology skeleton network, generating a corresponding streamline feature field, wherein the streamline feature field is used to characterize the continuity of material flow, the degree of flow turning, and the degree of flow convergence," with reference to the embodiments.

[0056] This step involves constructing a streamline characteristic field based on the stress topology skeleton network. The streamline characteristic field can comprehensively characterize the flow continuity, flow turning degree, and flow convergence degree of metallic materials during the stamping process, providing a quantitative basis for subsequent matching analysis with the working force direction field.

[0057] First, the image skeleton direction corresponding to the main stress propagation path is extracted based on the stress topology skeleton network. By refining the main paths in the skeleton network, the centerline direction vector of each path is obtained, thus directly mapping the stress propagation trend to the dominant direction of the potential material flow. This extraction process fully utilizes the structural information of the topology network to ensure the physical rationality of the flow direction.

[0058] Next, the main material flow direction is generated based on the skeleton orientation of each image. For each main path, the main material flow direction can be represented as a unit direction vector:

[0059] in, For the first The skeleton direction vector of the main path. This corresponds to the main flow direction of the material.

[0060] The streamline bifurcation degree parameter is generated based on the number of bifurcations and the bifurcation angle corresponding to each stress bifurcation node. The bifurcation degree parameter can be defined as:

[0061] In the formula, For the number of branches, For each bifurcation angle, This is a weighting coefficient based on stress intensity. The higher this parameter, the more likely the material flow is to branch and diffuse in this region.

[0062] The streamline aggregation degree parameter is generated based on the aggregation quantity and aggregation intensity corresponding to each stress convergence node. The aggregation degree parameter can be expressed as:

[0063] in, To aggregate quantity, The stress intensity at each convergence path, The convergence angle. This parameter reflects the intensity of material convergence towards a localized region.

[0064] Furthermore, streamline turning parameters are generated based on the curvature changes corresponding to the skeleton directions of each image. These turning parameters can be calculated using the average curvature of consecutive sampling points along the path.

[0065] In the formula, For curvature, For the change in orientation angle between adjacent sampling points, The arc length is the value of the arc. This parameter characterizes the degree of tortuosity of the material flow path.

[0066] Finally, based on the material's main flow direction, streamline bifurcation parameters, streamline convergence parameters, and streamline inflection parameters, a streamline feature field is generated. This feature field can be represented as a set of feature vectors for each region:

[0067] As one feasible approach, after generating the streamline feature field, the method further includes: establishing a flow feature propagation vector by using the main material flow direction in the streamline feature field as the propagation reference direction; performing branching and expansion processing on the flow feature propagation vector according to the streamline bifurcation degree parameter to generate multiple propagation paths; performing path convergence constraint processing on each propagation path according to the streamline convergence degree parameter to form local flow convergence units; performing nonlinear correction on the propagation direction of each propagation path according to the streamline inflection degree parameter to generate a set of corrected propagation paths; and updating the streamline feature field based on the set of corrected propagation paths.

[0068] This update process is based on the initial streamline feature field. Through operations such as propagation vector construction, branch expansion, convergence constraint, and nonlinear correction, it generates a set of corrected propagation paths that better conform to the actual physical laws of forming, and finally updates the streamline feature field with higher accuracy.

[0069] First, the main flow direction of the material in the streamline characteristic field is used as the propagation reference direction to establish a flow characteristic propagation vector. For each region, this propagation vector can be defined as:

[0070] in, This is the unit vector in the main flow direction of the material. This is a scalar scaling factor based on local stress intensity. This vector represents the main trend and intensity of material flow.

[0071] Next, the flow characteristic propagation vector is branched and expanded according to the streamline bifurcation degree parameter to generate multiple propagation paths. Branch expansion can be achieved in the following way: for the bifurcation degree parameter... In higher regions, based on the main propagation vector, several sub-vectors are generated according to the bifurcation angle:

[0072] In the formula, For rotation matrix, For the bifurcation angle, This is a decay coefficient based on the number of bifurcations. This process allows us to simulate the real flow behavior of materials diffusing in multiple directions at bifurcation nodes.

[0073] Based on the streamline convergence parameter, path convergence constraints are applied to each propagation path to form local flow convergence units. Regarding the convergence parameter... In higher regions, a convergence constraint is introduced to bring adjacent propagation paths closer together:

[0074] in, The constraint strength coefficient, It is the propagation vector of the flow characteristics. This is the flow characteristic propagation vector after correction by convergence constraints. The direction is towards the convergence center. This constraint treatment can effectively form flow units where material converges towards local areas, reflecting the material accumulation trend in actual forming.

[0075] Subsequently, the propagation direction of each propagation path is nonlinearly corrected based on the streamline inflection parameter, generating a set of corrected propagation paths. The nonlinear correction can employ a curvature-related correction function:

[0076] In the formula, This is the flow characteristic propagation vector after nonlinear transition correction. The transition sensitivity coefficient, This is a parameter for the degree of streamline transition. For normal adjustment vector, This is the curvature correction factor. This correction can smooth out excessively curved paths while retaining necessary turning features, making the propagation path more consistent with the continuity of metal plastic flow.

[0077] Finally, the streamline feature field is updated based on the modified propagation path set. By remapping the modified path parameters back to the original feature field, parameters such as the main flow direction, bifurcation degree, aggregation degree, and turning degree of each region are adjusted to obtain the updated streamline feature field.

[0078] The following describes in detail step 104, namely, "obtaining the force direction distribution information of the target service condition of the target mining pallet and constructing the target force direction field based on the force direction distribution information", with reference to the embodiments.

[0079] The target service condition refers to the stress environment and usage state of the target mining pallet during normal operation in actual engineering applications, also known as the actual service conditions or working conditions. As a mining support component, the target service condition of the mining pallet mainly includes the support scenarios for the roof and walls in coal mines, tunnels, or underground engineering projects. In these scenarios, the pallet needs to withstand the vertical pressure transmitted from the roof strata, the axial force generated by the preload, the lateral shear force caused by the deformation of the surrounding rock, and possible dynamic impact loads. Different mine geological conditions will result in different service conditions, such as high preload conditions, shear-dominated conditions, or combined load conditions.

[0080] First, it is necessary to obtain the force direction distribution information of the target mining pallet under the target service conditions. This information usually comes from actual engineering measurements, finite element service simulations, or relevant industry standards, such as the roof pressure, preload, and lateral shear force borne by the pallet under coal mine roof support conditions. By performing force analysis on different areas of the pallet, the main force directions and intensity data of each area are obtained, providing the original input for constructing the directional field.

[0081] The force direction distribution information is analyzed to obtain the force direction and intensity corresponding to each area of ​​the target mining pallet. Based on the analysis results, a local force direction vector is generated for each area. This vector can be represented as:

[0082] in, For the first The local force direction vector of each region , , These represent the force components of the region along the three coordinate axes. This vector directly reflects the main force trend in the region.

[0083] Then, directional weight parameters are generated based on the force intensity corresponding to each region. The weight parameters can be calculated as follows:

[0084] In the formula, For the first The directional weights of each region Let the magnitude of the force vector in this region be denoted as . This represents the total number of regions. This weight reflects the degree to which the stress on different regions affects the overall structural performance; regions with greater strength have higher weights.

[0085] Finally, the target force direction field is constructed based on the local force direction vectors and corresponding direction weight parameters. This direction field can be represented as a vector field covering the entire pallet area:

[0086] in, For the region The spatial distribution function. Through this construction process, a continuous field distribution that can comprehensively describe the force direction and relative importance of each position during the service of the pallet is obtained.

[0087] Through the above steps, the present invention successfully established the target force direction field under service conditions, enabling quantitative matching and comparison of the streamline characteristic field during the forming process. This allows for the accurate detection of flow guidance deviations in the cavity design, providing a scientific and quantitative basis for subsequent determination of abnormal guidance areas and reverse optimization of the mold cavity.

[0088] The following describes in detail step 105, namely, "generating streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field", with reference to the embodiments.

[0089] This step objectively assesses the rationality of the current mold cavity design by quantitatively comparing the material flow characteristics with the actual service stress requirements, providing a scientific basis for the subsequent determination of abnormal guidance areas.

[0090] First, the main material flow direction, streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter corresponding to each region are extracted from the streamline feature field. Simultaneously, the target force direction corresponding to each region is extracted from the target force direction field. These extraction operations ensure that the two fields achieve region-level correspondence within the same spatial coordinate system, laying the data foundation for matching analysis.

[0091] Next, the directional deviation between the main material flow direction and the target force direction for each region is calculated. The directional deviation can be calculated using vector cosine similarity or the included angle; the specific formula is as follows:

[0092] in, This is the vector representing the main flow direction of the material. Let the direction vector of the force acting on the target be . This is the directional deviation angle between the two. The smaller the deviation angle, the better the match between the flow direction and the force direction.

[0093] An orientation matching parameter is generated based on the orientation deviation. The orientation matching parameter can be defined as:

[0094] In the formula, This is an adjustment coefficient. The higher the value of this parameter, the stronger the consistency between the material flow direction and the service force direction.

[0095] Streamline stability parameters are generated by combining streamline bifurcation, streamline convergence, and streamline inflection parameters. Stability parameters It can be obtained through weighted summation calculation:

[0096] in, , , These are the weighting coefficients for each parameter. Use small positive numbers to avoid the denominator being zero. , , These are the streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline deflection degree parameter, respectively. The higher the parameter, the better the overall stability of the streamlines in terms of bifurcation, convergence, and deflection.

[0097] Finally, streamline deviation evaluation results are generated based on the orientation matching degree parameter and the streamline stability parameter. The overall streamline deviation evaluation result can be expressed as:

[0098] In the formula, This is the weighting coefficient for directional matching. The smaller the value of this evaluation result, the higher the degree of matching between the streamline characteristics and the target force direction field; conversely, there is a large deviation, and cavity optimization is required.

[0099] Through this complete matching and evaluation process, the present invention can accurately quantify the deficiencies of the current mold cavity in guiding material flow, providing reliable quantitative guidance for subsequent reverse topology tracing and targeted optimization, and ultimately achieving a unified improvement in forming quality and service performance.

[0100] The following describes in detail step 106, namely, "determining the abnormal guiding region in the target cavity based on the streamline deviation evaluation results, and analyzing the degree of influence of each abnormal guiding region on the material flow path," with reference to the embodiments.

[0101] Based on the streamline deviation evaluation results, the abnormal guiding regions in the target cavity are determined, and the influence of each abnormal guiding region on the material flow path is analyzed. These two steps are closely linked. Through quantitative evaluation and reverse tracing, the streamline deviation problem is located in a specific cavity geometric region, and its influence is further quantified, providing a reliable basis for generating optimization parameters.

[0102] First, identify abnormal streamline regions in the streamline deviation evaluation results that exceed a preset threshold. This threshold can be set according to specific tray specifications and engineering requirements, for example, the streamline deviation evaluation results... Regions with a value greater than 0.6 are marked as abnormal streamline regions:

[0103] in, A preset deviation threshold is set. This screening method can quickly identify key areas where the material flow characteristics and the direction of service force are significantly mismatched.

[0104] A reverse topology tracing analysis is performed along the main material flow direction corresponding to the abnormal streamline region. This tracing process starts with the main material flow direction vector of the abnormal region and searches backward in the stress topology skeleton network against the flow direction, gradually tracing back to upstream topological nodes until the source node causing the streamline deviation is found. This reverse analysis fully utilizes the topological connectivity of the skeleton network, enabling efficient location of the root cause of the problem.

[0105] Identify the critical stress bifurcation or convergence nodes that cause streamline deviation. These critical nodes are typically the core locations that lead to significant deviations in material flow direction, excessive bifurcation, or abnormal convergence. By comparing the weights of each node's impact on downstream streamline stability, the most influential critical nodes are selected.

[0106] Based on the projection positions or contact correspondences of the key stress bifurcation nodes or key stress convergence nodes on the mold cavity, the cavity contact areas corresponding to the key nodes are determined. This correspondence is established through finite element mesh mapping or geometric projection algorithms to ensure that the stress nodes can be accurately mapped to the actual geometric surface positions of the mold cavity.

[0107] The cavity contact area is identified as the abnormal guiding area in the target cavity. These abnormal guiding areas are the parts of the mold cavity that need to be optimized, such as areas with unreasonable fillet transitions, improper resistance distribution on the blank holder surface, or defects in the material flow path design.

[0108] After identifying the abnormal guidance regions, the analysis of the influence of each abnormal guidance region on the material flow path includes: performing local structural disturbance simulation on each abnormal guidance region; obtaining the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree before and after the local structural disturbance simulation; and generating influence degree parameters based on the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree.

[0109] Specifically, while keeping the overall mold model unchanged, small-scale local perturbations are made to the cavity geometry of the abnormal guiding area, such as slightly adjusting the fillet radius, changing the blank holder angle, or adding tiny guide channels. Then, the finite element forming simulation is rerun to obtain the stress distribution thermograms before and after the perturbation, and the corresponding streamline characteristic field is regenerated. Through this controlled local simulation, the impact of a single-region modification on the overall material flow path can be evaluated in isolation.

[0110] Obtain the changes in streamline bifurcation, streamline convergence, and streamline inflection before and after the local structural disturbance simulation. Positive changes indicate that the disturbance exacerbates flow instability, while negative changes indicate that flow stability is improved.

[0111] Influence parameters are generated based on the changes in streamline bifurcation, streamline convergence, and streamline inflection. These influence parameters can be calculated using a weighted comprehensive model.

[0112] In the formula, , , These represent the changes in streamline bifurcation, convergence, and inflection, respectively. , , The weighting coefficient for each variable can be determined based on engineering experience or sensitivity analysis. The larger the value of this parameter, the greater the influence of the abnormal guiding region on the material flow path, making it a key area that needs to be prioritized in cavity optimization.

[0113] Through this quantitative analysis process, the present invention can elevate the degree of influence of the abnormal guiding area from qualitative judgment to quantitative assessment, providing scientific guidance for generating fillet correction parameters, pressing resistance correction parameters and material flow correction parameters, ensuring that cavity optimization is both efficient and stable, and ultimately significantly improving the forming quality and service performance of mining pallets.

[0114] The following describes in detail step 107, namely, "generating cavity optimization parameters based on the degree of influence corresponding to each abnormal guiding region, and performing reverse optimization of the stamping die cavity based on the cavity optimization parameters", with reference to the embodiments.

[0115] This step transforms the previously quantified impact parameters into specific optimization schemes that can be directly applied to mold modification, ensuring that the optimization process is scientific, efficient, and targeted.

[0116] First, based on the influence degree parameters of each abnormal guiding region, corresponding cavity optimization parameters are generated. Specifically, for regions with high influence, a fillet correction parameter is generated based on the change in streamline turning degree. This parameter is used to adjust the fillet radius of the cavity transition region to mitigate the abrupt turning of material flow. A blanking resistance correction parameter is generated based on the change in streamline convergence degree. This parameter is used to optimize the surface roughness, inclination angle, or add damping structures to the blanking surface, thereby controlling the flow resistance of material in the convergence region. A material guiding correction parameter is generated based on the change in streamline bifurcation degree. This parameter is used to add or adjust structures such as guide channels and bosses on the cavity surface to guide the material to flow uniformly in the expected direction. The generation process of these optimization parameters usually combines the magnitude and positive / negative direction of the influence degree parameters, and uses mapping functions or empirical rule tables for calculation to ensure that the parameter adjustment range matches the severity of the problem.

[0117] Then, the stamping die cavity is reverse-engineered based on the generated cavity optimization parameters. In practice, engineers or CAE software import these parameters into the die's 3D model and make targeted modifications to the cavity geometry corresponding to abnormal guiding areas, such as increasing or decreasing the fillet radius, changing the shape of the blank holder surface, and redesigning the material flow channels. After the modifications are completed, forming simulation is performed again to verify that the streamline deviation evaluation results have been improved until the preset optimization target is achieved.

[0118] This invention breaks away from the traditional trial-and-error approach in mold design, realizing an intelligent reverse design process from problem diagnosis to precise correction. The optimized mold cavity significantly improves the continuity and uniformity of material flow, reduces forming defects, and enhances the stress matching performance of mining pallets under service conditions. Ultimately, it shortens the mold development cycle, reduces production costs, and improves the overall reliability and support effect of the product.

[0119] One specific embodiment of the present invention is illustrated using a certain type of square mining pallet as an example. The pallet has dimensions of 150mm × 150mm × 6mm, is made of Q235 steel plate, and is manufactured using a single-action deep drawing stamping process. The initial mold cavity is designed based on traditional experience. First, a three-dimensional model of the pallet and the initial mold model are established using DYNAFORM finite element simulation software. The sheet thickness is set to 6mm, the stamping speed to 50mm / s, the friction coefficient to 0.12, and the blank holder force to 80kN. The entire stamping process is simulated, and a stress distribution heat map is output.

[0120] Subsequently, the heat map was segmented according to the method of this invention to extract color, texture, and edge features, identify local stress peak nodes, and construct a stress topology skeleton network. The main path was reconstructed through directional continuity analysis to generate a streamline feature field. Simultaneously, based on the typical service conditions of this pallet in coal mine roof support (vertical preload of 150kN and lateral shear force accounting for approximately 30%), a target force direction field was constructed. After evaluating streamline deviations, four abnormal guiding areas were identified, mainly concentrated in the rounded corner transition area of ​​the pallet edge and around the central protruding horn hole.

[0121] Local structural disturbance simulations were performed sequentially on each abnormal region to quantify the changes in streamline bifurcation, aggregation, and inflection, generating parameters to assess the degree of influence. The final cavity optimization parameters were: the edge radius was corrected from R8mm to R12mm, the pressure surface resistance coefficient was reduced by 15%, and two shallow guide channels were added in the severely bifurcated areas. After completing the cavity reverse optimization, a new forming simulation was performed for verification.

[0122] The tests used the same process parameters to compare and simulate the molds before and after optimization, and to verify them through actual trial stamping. Before optimization, the maximum streamline deviation evaluation result during pallet forming was 0.68, the material thickness reduction rate reached a maximum of 18.5%, and slight wrinkles appeared at the edges. After optimization, the streamline deviation evaluation result decreased to 0.29, the material flow uniformity improved by approximately 57%, the thickness reduction rate decreased to 9.2%, and the wrinkle defects were completely eliminated. Service condition simulation showed that the maximum stress concentration factor of the pallet decreased by 22%, and the load-bearing uniformity improved by 31%. After actual trial stamping of 100 samples, the product qualification rate increased from 87% to 98.5%, the number of mold iterations decreased from 7 to 2, and the mold development cycle was shortened by approximately 45%. The above results fully verify the effectiveness and superiority of the method of the present invention.

[0123] According to another embodiment, a stamping die cavity optimization system based on a stress distribution heat map of a mining pallet is provided. Figure 3 A schematic block diagram of a stamping die cavity optimization system based on a thermal map of stress distribution in a mining pallet, according to one embodiment, is shown. Figure 3 As shown, the system includes: The stress-thermal map acquisition module 301 is used to acquire the stress distribution thermal map of the target mining pallet during the stamping process.

[0124] The stress topology skeleton network construction module 302 is used to construct a corresponding stress topology skeleton network based on the stress peak value and gradient in the stress distribution heatmap.

[0125] The streamline feature field generation module 303 is used to analyze the flow path characteristics of the metal material during the forming process based on the stress topology skeleton network and generate a corresponding streamline feature field. The streamline feature field is used to characterize the continuity of material flow, the degree of flow turning and the degree of flow convergence.

[0126] The target force direction field construction module 304 is used to obtain the force direction distribution information of the target service condition of the target mining pallet, and construct the target force direction field according to the force direction distribution information.

[0127] The streamline deviation evaluation module 305 is used to generate streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field.

[0128] The abnormal guidance region determination module 306 is used to determine the abnormal guidance region in the target cavity based on the streamline deviation evaluation result, and analyze the degree of influence of each abnormal guidance region on the material flow path.

[0129] The cavity optimization module 307 is used to generate cavity optimization parameters based on the degree of influence of each abnormal guiding area, and to perform reverse optimization of the stamping die cavity based on the cavity optimization parameters.

[0130] As an implementable approach, the stress topology skeleton network construction module 302 constructs a corresponding stress topology skeleton network based on the stress peaks and gradients in the stress distribution heatmap, including: performing image segmentation processing on the stress distribution heatmap to obtain multiple stress feature regions; extracting color distribution features, texture features, and edge features corresponding to each stress feature region; identifying multiple local stress peak nodes based on the color distribution features, texture features, and edge features; extracting the main stress propagation path based on the image gradient continuity between adjacent stress feature regions; identifying stress bifurcation nodes and stress convergence nodes based on the image connectivity between each main stress propagation path; and constructing a stress topology skeleton network based on the local stress peak nodes, the stress bifurcation nodes, the stress convergence nodes, and the main stress propagation paths.

[0131] As an implementable approach, after identifying multiple local stress peak nodes, the stress topology skeleton network construction module 302 further includes: performing target recognition processing on the local stress peak nodes; generating node feature vectors based on the color gradient change features, texture change features, and edge change features corresponding to the area surrounding the local stress peak nodes; identifying key stress nodes and non-key stress nodes based on the similarity between the feature vectors of each node; and correcting the stress topology skeleton network based on the key stress nodes.

[0132] As an implementable approach, the streamline feature field generation module 303 analyzes the flow path characteristics of the metallic material during the forming process based on the stress topology skeleton network, and generates a corresponding streamline feature field, including: extracting the image skeleton direction corresponding to the main stress propagation path based on the stress topology skeleton network; generating the main material flow direction based on each image skeleton direction; generating streamline bifurcation degree parameters based on the number and angle of bifurcation corresponding to each stress bifurcation node; generating streamline aggregation degree parameters based on the number and intensity of convergence corresponding to each stress convergence node; generating streamline turning degree parameters based on the curvature change corresponding to each image skeleton direction; and generating a streamline feature field based on the main material flow direction, the streamline bifurcation degree parameters, the streamline aggregation degree parameters, and the streamline turning degree parameters.

[0133] As an implementable approach, after the streamline feature field generation module 303 generates the streamline feature field, it further includes: establishing a flow feature propagation vector by taking the main material flow direction in the streamline feature field as the propagation reference direction; performing branch expansion processing on the flow feature propagation vector according to the streamline bifurcation degree parameter to generate multiple propagation paths; performing path convergence constraint processing on each propagation path according to the streamline convergence degree parameter to form local flow convergence units; performing nonlinear correction on the propagation direction of each propagation path according to the streamline inflection degree parameter to generate a set of corrected propagation paths; and updating the streamline feature field based on the set of corrected propagation paths.

[0134] As an implementable method, the target force direction field construction module 304 constructs the target force direction field based on the force direction distribution information, including: parsing the force direction distribution information to obtain the force direction and force intensity corresponding to each area of ​​the target mining pallet; generating local force direction vectors based on the force direction corresponding to each area; generating direction weight parameters based on the force intensity corresponding to each area; and constructing the target force direction field based on each local force direction vector and the corresponding direction weight parameters.

[0135] As an implementable approach, the streamline deviation evaluation module 305 generates streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field, including: extracting the main material flow direction, streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter corresponding to each region from the streamline feature field; extracting the target force direction corresponding to each region from the target force direction field; calculating the directional deviation between the main material flow direction and the target force direction corresponding to each region; generating a directional matching degree parameter based on the directional deviation; generating a streamline stability parameter by combining the streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter; and generating a streamline deviation evaluation result based on the directional matching degree parameter and the streamline stability parameter.

[0136] As an implementable approach, the abnormal guiding region determination module 306 determines the abnormal guiding region in the target cavity based on the streamline deviation evaluation result, including: identifying abnormal streamline regions exceeding a preset threshold in the streamline deviation evaluation result; performing reverse topology tracing analysis along the main material flow direction corresponding to the abnormal streamline region; determining the key stress bifurcation node or key stress convergence node that causes streamline deviation; determining the cavity contact region corresponding to the key node based on the projection position or contact correspondence of the key stress bifurcation node or key stress convergence node on the mold cavity; and determining the cavity contact region as the abnormal guiding region in the target cavity.

[0137] As an implementable approach, the abnormal guidance region determination module 306 analyzes the degree of influence of each abnormal guidance region on the material flow path, including: performing local structural disturbance simulation on each abnormal guidance region; obtaining the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree before and after the local structural disturbance simulation; and generating influence degree parameters based on the changes in streamline bifurcation degree, streamline aggregation degree, and streamline inflection degree.

[0138] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. Components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0139] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0140] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0141] And an electronic device comprising: one or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0142] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0143] in, Figure 4 An exemplary architecture of an electronic device is shown, which may include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420 can communicate with each other via a communication bus 430.

[0144] The processor 410 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0145] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 420 can store the operating system 421 for controlling the operation of the electronic device 400, and the basic input / output system (BIOS) 422 for controlling the low-level operations of the electronic device 400. Additionally, it can store a web browser 423, a data storage management system 424, and a stamping die cavity optimization system 425 based on the stress distribution heat map of a mining pallet, etc. The aforementioned stamping die cavity optimization system 425 based on the stress distribution heat map of a mining pallet can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 420 and is called and executed by the processor 410.

[0146] Input / output interface 413 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0147] Network interface 414 is used to connect a communication module (not shown in the figure) to enable communication and interaction between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0148] Bus 430 includes a pathway for transmitting information between various components of the device, such as processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420.

[0149] It should be noted that although the above-described device only shows the processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, memory 420, bus 430, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0150] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0151] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for optimizing the cavity of a stamping die based on a thermal diagram of stress distribution in a mining pallet, characterized in that, The method includes: Obtain a thermal map of stress distribution during the stamping process of the target mining pallet; Based on the stress peak value and gradient in the stress distribution heatmap, a corresponding stress topology skeleton network is constructed. Based on the stress topology skeleton network analysis, the flow path characteristics of metallic materials during the forming process are analyzed, and the corresponding streamline feature field is generated. The streamline feature field is used to characterize the continuity of material flow, the degree of flow turning and the degree of flow convergence. Obtain the force direction distribution information of the target service condition of the target mining pallet, and construct the target force direction field based on the force direction distribution information; Based on the matching relationship between the streamline feature field and the target force direction field, a streamline deviation evaluation result is generated; Based on the streamline deviation evaluation results, the abnormal guiding regions in the target cavity are determined, and the degree of influence of each abnormal guiding region on the material flow path is analyzed. Cavity optimization parameters are generated based on the degree of influence corresponding to each abnormal guiding region, and the cavity of the stamping die is reverse optimized based on the cavity optimization parameters.

2. The method according to claim 1, characterized in that, The step of constructing a corresponding stress topology skeleton network based on the stress peak value and gradient in the stress distribution heatmap includes: Image segmentation processing is performed on the stress distribution heatmap to obtain multiple stress feature regions; Extract the color distribution features, texture features, and edge features corresponding to each stress feature region; Multiple local stress peak nodes are identified based on the color distribution characteristics, texture characteristics, and edge characteristics. The main path of stress propagation is extracted based on the continuity of image gradients between adjacent stress feature regions; Identify stress bifurcation nodes and stress convergence nodes based on the image connectivity between the main stress propagation paths; A stress topology skeleton network is constructed based on the local stress peak nodes, stress bifurcation nodes, stress convergence nodes, and the main stress propagation path.

3. The method according to claim 2, characterized in that, After identifying multiple local stress peak nodes, the method further includes: Target identification processing is performed on the local stress peak nodes; Node feature vectors are generated based on the color gradient change features, texture change features, and edge change features of the region surrounding the local stress peak node. Key stress nodes and non-key stress nodes are identified based on the similarity between the feature vectors of each node; The stress topology skeleton network is modified based on the key stress nodes.

4. The method according to claim 2, characterized in that, The process of analyzing the flow path characteristics of metallic materials during the forming process based on the stress topology skeleton network and generating corresponding streamline feature fields includes: Based on the stress topology skeleton network, the image skeleton direction corresponding to the main path of stress propagation is extracted; The main material flow direction is generated based on the skeleton direction of each image. Generate streamline bifurcation parameters based on the number of bifurcations and bifurcation angles corresponding to each stress bifurcation node; Streamline aggregation parameters are generated based on the number and intensity of convergence at each stress convergence node. Streamline turning point parameters are generated based on the curvature changes corresponding to the skeleton directions of each image. A streamline feature field is generated based on the main flow direction of the material, the streamline bifurcation parameter, the streamline convergence parameter, and the streamline inflection parameter.

5. The method according to claim 4, characterized in that, After generating the streamline feature field, the method further includes: Using the main flow direction of the material in the streamline feature field as the propagation reference direction, a flow feature propagation vector is established. The flow feature propagation vector is branched and expanded according to the streamline bifurcation degree parameter to generate multiple propagation paths. Based on the streamline convergence parameter, each propagation path is subjected to path convergence constraint processing to form a local flow convergence unit; The propagation direction of each propagation path is nonlinearly corrected based on the streamline turning degree parameter to generate a set of corrected propagation paths; The streamline feature field is updated based on the modified propagation path set.

6. The method according to claim 1, characterized in that, The step of constructing the target force direction field based on the force direction distribution information includes: Analyze the force direction distribution information to obtain the force direction and force intensity corresponding to each area of ​​the target mining pallet; Generate local force direction vectors based on the force direction corresponding to each region; Generate directional weight parameters based on the force intensity corresponding to each region; The target force direction field is constructed based on the local force direction vectors and corresponding direction weight parameters.

7. The method according to claim 1, characterized in that, The process of generating streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field includes: Extract the main material flow direction, streamline bifurcation degree parameter, streamline convergence degree parameter and streamline inflection degree parameter corresponding to each region from the streamline feature field; Extract the target force direction corresponding to each region from the target force direction field; Calculate the directional deviation between the main material flow direction and the target force direction for each region; Generate orientation matching parameters based on the orientation deviation; The streamline stability parameters are generated by combining the streamline bifurcation degree parameter, streamline convergence degree parameter, and streamline inflection degree parameter. The streamline deviation evaluation result is generated based on the direction matching degree parameter and the streamline stability parameter.

8. The method according to claim 2, characterized in that, The step of determining the abnormal guiding region in the target cavity based on the streamline deviation evaluation result includes: Identify abnormal streamline regions in the streamline deviation evaluation results that exceed a preset threshold; Perform reverse topology tracing analysis along the main material flow direction corresponding to the abnormal streamline region; Identify the key stress bifurcation nodes or key stress convergence nodes that cause streamline deviation; Based on the projection position or contact correspondence of the key stress bifurcation node or key stress convergence node on the mold cavity, determine the cavity contact area corresponding to the key node; The cavity contact area is defined as the abnormal guiding area in the target cavity.

9. The method according to claim 1, characterized in that, The analysis of the impact of each abnormal guiding region on the material flow path includes: Perform local structural disturbance simulations for each abnormal guidance region; Obtain the changes in streamline bifurcation, streamline convergence, and streamline inflection before and after the local structural disturbance simulation. The influence degree parameters are generated based on the changes in streamline bifurcation degree, streamline convergence degree, and streamline inflection degree.

10. A stamping die cavity optimization system based on a stress distribution heat map of a mining pallet, characterized in that, The system includes: The stress-thermal map acquisition module is used to acquire the stress distribution thermal map of the target mining pallet during the stamping process; The stress topology skeleton network construction module is used to construct a corresponding stress topology skeleton network based on the stress peak value and gradient in the stress distribution heatmap. The streamline feature field generation module is used to analyze the flow path characteristics of metal materials during the forming process based on the stress topology skeleton network and generate the corresponding streamline feature field. The streamline feature field is used to characterize the continuity of material flow, the degree of flow turning and the degree of flow convergence. The target force direction field construction module is used to obtain the force direction distribution information of the target service condition of the target mining pallet, and construct the target force direction field based on the force direction distribution information. The streamline deviation evaluation module is used to generate streamline deviation evaluation results based on the matching relationship between the streamline feature field and the target force direction field. An abnormal guiding region determination module is used to determine the abnormal guiding region in the target cavity based on the streamline deviation evaluation results, and to analyze the degree of influence of each abnormal guiding region on the material flow path. The cavity optimization module is used to generate cavity optimization parameters based on the degree of influence of each abnormal guiding area, and to perform reverse optimization of the stamping die cavity based on the cavity optimization parameters.

Images