Extrusion die design method, device and equipment and storage medium

Abstract

The embodiment of the invention provides an extrusion die design method, device and equipment and a storage medium, and relates to the technical field of industrial machining.The method comprises the steps that a sectional material cross section image of a to-be-designed die is obtained, target structure features are extracted from the sectional material cross section image through a preset neural network model, and the target structure features are obtained; obtaining a target design structure from a historical mold design structure according to the target structure characteristics, obtaining design knowledge corresponding to the to-be-designed mold, obtaining a design text corresponding to the design knowledge from a knowledge graph, and fusing the target design structure with the design text to obtain a target design structure; and obtaining an engineering drawing corresponding to the to-be-designed mold. According to the method, the data of each link in the mold design process is collected, so that quick search of related information is realized, effective reuse of mold design knowledge is realized, and the quality and efficiency of mold design are improved.

Description

Technical Field

[0001] This invention relates to the field of industrial processing technology, and more specifically, to a method, apparatus, equipment, and storage medium for designing extrusion dies. Background Technology

[0002] Existing aluminum profile extrusion die designs typically rely heavily on experience and the skills of seasoned craftsmen, making them difficult to pass on and replicate. Aluminum processing companies need to design multiple dies daily based on different user requirements. However, the entire design cycle for extrusion dies is lengthy, requiring repeated trial runs and modifications, resulting in high costs. Furthermore, the lack of scientific and quantitative design guidance leads to a low first-time success rate for extrusion dies. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide an extrusion die design method, apparatus, equipment and storage medium to solve the problem of low success rate of existing profile extrusion dies.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a method for designing an extrusion die, comprising: Obtain a cross-sectional image of the profile to be designed, and extract the target structural features from the cross-sectional image of the profile using a preset neural network model; The target design structure is obtained from the historical mold design structure based on the target structural features; Obtain the design knowledge corresponding to the mold to be designed, and retrieve the design text corresponding to the design knowledge from the knowledge graph; The target design structure is integrated with the design text to obtain engineering drawings corresponding to the mold to be designed.

[0005] In an optional implementation, the step of extracting target structural features from the profile cross-sectional image using a preset neural network model includes: Obtain historical profile surface drawings, and annotate the profile surface structure in the historical profile surface drawings to obtain the historical profile surface structure features; The preset neural network model is used to annotate the cross-sectional image of the profile according to the historical profile surface structural features, so as to obtain the target structural features corresponding to the mold to be designed.

[0006] In an optional implementation, the target structural features include the target structural location and the target structural type, and the step of obtaining the target design structure from historical mold design structures based on the structural features includes: The historical structure location and historical structure type corresponding to the historical mold design structure are extracted using the preset neural network model. Calculate the positional similarity between the historical structure location and the target structure location, and calculate the type similarity between the historical structure type and the target structure type; Based on the location similarity and the type similarity, the target design structure is obtained from the historical mold design structure.

[0007] In an optional implementation, after the step of extracting the target structural features from the profile cross-sectional image using a preset neural network model, the method includes: Obtain historical floor plan drawings; The historical profile surface drawings and historical planar design drawings are identified and classified to obtain graphic data corresponding to the profile cross-section and mold design. A mold design dataset is generated based on the graphical data.

[0008] In an optional implementation, the location similarity includes grid area similarity and grid location similarity, and the step of calculating the location similarity between the historical structure location and the target structure location includes: Obtain the historical structure parameters corresponding to the historical mold design structure from the mold design dataset, and import the historical mold design structure into a preset mesh according to the historical structure parameters; Obtain the target structure parameters corresponding to the target structure, and import the profile cross-section image into the preset grid according to the target structure parameters; Obtain the first grid number threshold and the first grid position occupied by the profile cross-section image in the preset grid; Obtain the threshold value of the number of second grids and the position of the second grid in the preset grid for the historical mold design structure; The grid area similarity is calculated based on the first grid number threshold and the second grid number threshold, and the grid position similarity is calculated based on the first grid position and the second grid position.

[0009] In an optional implementation, the step of obtaining the design text corresponding to the design knowledge from the knowledge graph includes: Determine the knowledge type corresponding to the design knowledge, and identify the knowledge node corresponding to the knowledge type from the knowledge graph; Obtain the corresponding knowledge text based on the knowledge node, and adjust the knowledge text according to the design knowledge to obtain the design text.

[0010] In an optional implementation, the step of fusing the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed includes: The target design structure is subjected to feature extraction to obtain a structural feature vector; Obtain the design parameters corresponding to the design text, and convert the design parameters into a parameter vector; The structural feature vector and the parameter vector are fused to obtain a fusion result, which is then input into a drawing generation tool to output the engineering drawing.

[0011] In a second aspect, the present invention provides an extrusion die design apparatus, comprising: The feature extraction module is used to acquire the cross-sectional image of the profile of the mold to be designed, and extract the target structural features from the cross-sectional image of the profile through a preset neural network model; The structure acquisition module is used to acquire the target design structure from historical mold design structures based on the target structural features; The knowledge acquisition module is used to acquire design knowledge corresponding to the mold to be designed, and to retrieve design text corresponding to the design knowledge from the knowledge graph; The drawing design module is used to integrate the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed.

[0012] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing machine-executable instructions executable by the processor, the processor executing the machine-executable instructions to implement the extrusion die design method described in the first aspect.

[0013] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the extrusion die design method described in the first aspect.

[0014] This invention provides a method, apparatus, equipment, and storage medium for designing extrusion dies. It extracts features from the cross-sectional image of the die profile, obtains the corresponding historical die design structure based on the extraction results, and retrieves relevant design text from a knowledge graph. The design text is then used to integrate and adjust the historical die design structure to obtain engineering drawings. This invention achieves rapid retrieval of relevant information and effective reuse of die design knowledge by collecting data from various stages of the die design process, thereby improving the quality and efficiency of die design.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A block diagram of an electronic device provided by an embodiment of the present invention is shown; Figure 2 A flowchart illustrating an extrusion die design method provided by an embodiment of the present invention is shown; Figure 3 This diagram illustrates a dataset structure provided by an embodiment of the present invention. Figure 4 A schematic flowchart of a profile surface image matching method provided by an embodiment of the present invention is shown; Figure 5 This diagram illustrates a principle of knowledge graph construction provided by an embodiment of the present invention. Figure 6 This diagram illustrates a knowledge graph structure provided by an embodiment of the present invention. Figure 7 A functional block diagram of an extrusion die design device provided in an embodiment of the present invention is shown.

[0018] icon: 100 - Electronic equipment; 110 - Memory; 120 - Processor; 130 - Communication module; 700 - Extrusion die design device; 710 - Feature extraction module; 720 - Structure acquisition module; 730 - Knowledge acquisition module; 740 - Drawing design module. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0021] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0022] Please refer to Figure 1 , Figure 1 This is a block diagram of an electronic device 100 provided in this embodiment. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, processor 120, and communication module 130 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0023] The memory 110 is used to store programs or data. The memory 110 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0024] The processor 120 is used to read / write data or programs stored in the memory 110 and to perform corresponding functions.

[0025] The communication module 130 is used to establish a communication connection between the electronic device 100 and other communication terminals through the network, and to send and receive data through the network.

[0026] It should be understood that, Figure 1 The structure shown is only a schematic diagram of the electronic device 100. The electronic device 100 may also include components that are larger than... Figure 1The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0027] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating an extrusion die design method provided in this embodiment. The method can... Figure 1 The method is performed by an electronic device in the device, and includes: S210. Obtain a cross-sectional image of the profile of the mold to be designed, and extract the target structural features from the cross-sectional image of the profile using a preset neural network model.

[0028] When designing extrusion dies, clients typically provide CAD drawings of the profile surface. These drawings are then used to generate CAD drawings for the die's planar design, which are then used to design the die itself. The core of the profile surface CAD drawing is defining the cross-sectional shape of the final extruded profile, essentially serving as a standard cross-sectional view of the finished product. It does not involve the structural details of the die, focusing only on key information such as the profile's shape and dimensions. It is one of the core bases for subsequent die design, determining the final appearance and basic specifications of the extruded product.

[0029] The core of CAD drawings for mold planar design is to present the complete structure and manufacturing requirements of the extrusion mold, serving as a construction guide for mold processing, assembly, and trial molding. Based on the profile plan drawings, it must solve the problem of how to extrude raw materials into the target profile, and must cover the design, fit relationships, and processing technology of each component of the mold.

[0030] Different profile cross-sectional images may correspond to different mold planar design images. If a corresponding mold planar design image is designed from scratch for each profile cross-sectional image, it will not only be inefficient, but also cannot guarantee accuracy. However, there may be some identical or similar designs in some historical mold design records. Therefore, relevant data in historical mold design records can be reused to reduce workload.

[0031] First, target structural features can be extracted from profile cross-sectional images. This extraction process can be performed using a pre-set neural network model. This model can be trained using relevant data from historical mold design records. For example, historical profile cross-sectional images and their corresponding historical structural features can be obtained. These images are then input into the neural network model, and the model's output is the corresponding historical structural features. This allows the pre-set neural network model to accurately extract structural features from any profile cross-sectional image.

[0032] S220. Obtain the target design structure from the historical mold design structure based on the target structural features.

[0033] After extracting the structural features from the profile cross-section image, the target structure can be searched in historical mold design data to determine the most similar historical structural features. Then, the historical cross-section image corresponding to the historical structural features is determined, and the mold planar design image corresponding to the historical cross-section image is searched. The design structure corresponding to the mold planar design image is taken as the target design structure.

[0034] S230. Obtain the design knowledge corresponding to the mold to be designed, and obtain the design text corresponding to the design knowledge from the knowledge graph.

[0035] In addition to the image, the cross-sectional image of the profile of the mold to be designed also includes relevant text descriptions and parameters, such as length, width, area, perimeter, material, etc. These text descriptions and parameters all belong to design knowledge. However, this design knowledge is usually quite scattered, and mold design tools or software usually cannot recognize it properly. Therefore, the design knowledge can be used to search in the knowledge graph to obtain the complete design text corresponding to the design knowledge.

[0036] S240. The target design structure is integrated with the design text to obtain engineering drawings corresponding to the mold to be designed.

[0037] The target design structure is then merged with the design text, and the merged result is input into the drawing generation software to obtain the final engineering drawings.

[0038] This embodiment achieves rapid retrieval of relevant information and effective reuse of mold design knowledge by collecting data from various stages of the mold design process, thereby improving the quality and efficiency of mold design.

[0039] In one embodiment, after the step of extracting target structural features from the profile cross-sectional image using a preset neural network model, the method includes: Obtain historical floor plan drawings; The historical profile surface drawings and historical planar design drawings are identified and classified to obtain graphic data corresponding to the profile cross-section and mold design. A mold design dataset is generated based on the graphical data.

[0040] Please refer to Figure 3 , Figure 3 This is a schematic diagram of a dataset structure provided in this embodiment.

[0041] The dataset mainly classifies and stores various information contained in the drawings. Among them, the profile CAD drawings mainly include the product cross-section, length, width, perimeter, area and material. The planar design CAD drawings mainly include the die holes, flow dividers, flow bridges, welding chambers and actual extrusion machine models. Flow dividers include the number, area and location.

[0042] Since the dataset is generated based on historical data, each profile CAD drawing corresponds to a planar design CAD drawing. A corresponding search engine can be generated for the dataset. Simply input the profile drawing into the search engine to find the corresponding planar design drawing.

[0043] This embodiment constructs a mold design dataset by using historical profile surface drawings and historical planar design drawings, so that the corresponding historical planar design drawings can be queried based on the historical profile surface drawings, providing a data foundation for the reuse of historical data.

[0044] In one embodiment, the step of extracting target structural features from the profile cross-sectional image using a preset neural network model includes: Obtain historical profile surface drawings, and annotate the profile surface structure in the historical profile surface drawings to obtain the historical profile surface structure features; The preset neural network model is used to annotate the cross-sectional image of the profile according to the historical profile surface structural features, so as to obtain the target structural features corresponding to the mold to be designed.

[0045] Historical profile drawings can be categorized into eight types based on their profile surface structure characteristics: cantilever, annular groove, deep groove, hollow, long convex edge, hollow with other structures inside, hook type, and shallow groove. When annotating, the structural information can be stored in a JSON file in VOC or COCO format using the Labelme annotation tool.

[0046] Then, the cross-sectional image of the mold to be designed is annotated in the same way to obtain the corresponding target structural features.

[0047] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating a profile surface image matching method provided in this embodiment.

[0048] In one embodiment, the target structural features include the target structural location and the target structural type, and the step of obtaining the target design structure from historical mold design structures based on the structural features includes: The historical structure location and historical structure type corresponding to the historical mold design structure are extracted using the preset neural network model. Calculate the positional similarity between the historical structure location and the target structure location, and calculate the type similarity between the historical structure type and the target structure type; Based on the location similarity and the type similarity, the target design structure is obtained from the historical mold design structure.

[0049] The preset neural network model can be the YOLOv5 model. First, the model is used to locate the target structural features in the cross-sectional image, as well as the corresponding position, area, and structural type of the target structural features. Similarly, the model is used to extract the historical position, historical area, and historical structural type corresponding to the historical mold design structure. Then, the extracted information is classified and compared, and the target design structure is determined based on the comparison results.

[0050] Classification comparison mainly includes two aspects: positional similarity comparison and type similarity comparison.

[0051] The type similarity can be compared in the following way: Since the structure types mainly include cantilever, annular groove, deep groove, hollow, long convex edge, hollow containing other structures, hook type and shallow groove, and each structure has been labeled in advance, the structure types corresponding to the same position can be judged based on the labels corresponding to the same position to obtain the type similarity.

[0052] Additionally, for comparisons with unknown similarities, such as Figure 3 As shown, the historical structural parameters corresponding to the historical mold design structure can be obtained from the mold design dataset first. Based on these parameters, the historical mold design structure can be imported into a preset grid. The historical structural parameters are the parameters of the profile surface CAD drawing in the dataset, such as length, width, perimeter, and area. The preset grid can be a 9×9 grid, an 18×18 grid, etc., and the number and distribution of grids can be set according to actual needs.

[0053] Then, the target structure parameters corresponding to the target structure are obtained, and the cross-sectional image of the profile is imported into the preset grid according to the target structure parameters. Similarly, the length, width, perimeter and area of ​​the target structure are obtained and imported into the preset grid.

[0054] Then, the first grid number threshold and the first grid position occupied by the profile cross-section image in the preset grid are obtained, and the second grid number threshold and the second grid position occupied by the historical mold design structure in the preset grid are obtained. The grid number threshold can be the number of grids occupied by the profile cross-section image.

[0055] The grid area similarity is calculated based on the first grid number threshold and the second grid number threshold, and the grid position similarity is calculated based on the first grid position and the second grid position.

[0056] When performing similarity calculations, the minimum cost maximum flow algorithm can be used. Based on the given structural similarity constraints, the optimal structural matching scheme is found by optimizing the objective function (i.e., evaluating the cost of different matching schemes) and finding the scheme with the minimum total cost.

[0057] After determining the optimal structural matching scheme, the CAD drawing of the profile surface corresponding to the optimal structural matching scheme can be input into the dataset for searching, thereby obtaining the corresponding target plan design CAD drawing.

[0058] This embodiment compares the profile cross-section image and the historical mold design structure from multiple aspects to determine the target design structure that is most similar to the profile cross-section image. Then, based on the target design structure, it performs a reverse search in the dataset to determine the target planar design CAD drawing, thereby realizing the reuse of historical planar design drawings and reducing the workload of mold design.

[0059] Please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating the principle of knowledge graph construction provided in this embodiment.

[0060] When constructing a knowledge graph, discrete design knowledge scattered in CAD drawings and process documents, such as machine parameters, mold dimensions, extrusion ratios, and test results, can be structured and correlated to obtain the corresponding knowledge graph.

[0061] Please refer to Figure 6 , Figure 6 This is a schematic diagram of a knowledge graph structure provided in this embodiment.

[0062] After organizing and classifying the relevant knowledge of mold design, we can obtain different knowledge nodes and the relationships between them, with each knowledge node corresponding to relevant data.

[0063] In one implementation, the step of obtaining the design text corresponding to the design knowledge from the knowledge graph includes: Determine the knowledge type corresponding to the design knowledge, and identify the knowledge node corresponding to the knowledge type from the knowledge graph; Obtain the corresponding knowledge text based on the knowledge node, and adjust the knowledge text according to the design knowledge to obtain the design text.

[0064] After analyzing the design knowledge of the mold to be designed, the corresponding knowledge type is determined, and then the design text related to the design knowledge can be found by searching in the knowledge graph.

[0065] In one embodiment, the step of fusing the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed includes: The target design structure is subjected to feature extraction to obtain a structural feature vector; Obtain the design parameters corresponding to the design text, and convert the design parameters into a parameter vector; The structural feature vector and the parameter vector are fused to obtain a fusion result, which is then input into a drawing generation tool to output the engineering drawing.

[0066] When generating engineering drawings, an API can be used in conjunction with AutoCAD to automatically generate design drawings based on user needs.

[0067] Specifically, the number of diversion holes is first predicted based on the structural feature vector. Then, together with the number vector and related physical constraints, it is used as input parameters. Using parametric formulas, the geometric dimensions and positional distribution of the diversion holes are automatically adjusted. Finally, through the CAD API interface, engineering drawings that can be used for production are automatically generated with one click.

[0068] To perform the corresponding steps in the above embodiments and various possible methods, an implementation of an extrusion die design apparatus is given below. Please refer to [link / reference]. Figure 7 , Figure 7 This is a functional block diagram of an extrusion die design device provided in an embodiment of the present invention. It should be noted that the basic principle and technical effects of the extrusion die design device provided in this embodiment are the same as those in the above embodiments. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. The extrusion die design device 700 includes: The feature extraction module 710 is used to acquire a cross-sectional image of the profile of the mold to be designed, and extract the target structural features from the cross-sectional image of the profile through a preset neural network model; The structure acquisition module 720 is used to acquire the target design structure from historical mold design structures based on the target structure features; The knowledge acquisition module 730 is used to acquire design knowledge corresponding to the mold to be designed, and to acquire design text corresponding to the design knowledge from the knowledge graph; The drawing design module 740 is used to integrate the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed.

[0069] Optionally, the above modules can be stored in the form of software or firmware. Figure 1 The memory shown is stored in or embedded in the operating system (OS) of the extrusion die design device, and can be accessed by... Figure 1 The processor executes the commands. Meanwhile, the data and program code required to execute these modules can be stored in memory.

[0070] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0071] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0072] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion 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 this 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.

[0073] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for designing an extrusion die, characterized in that, include: Obtain a cross-sectional image of the profile to be designed, and extract the target structural features from the cross-sectional image of the profile using a preset neural network model; The target design structure is obtained from the historical mold design structure based on the target structural features; Obtain the design knowledge corresponding to the mold to be designed, and retrieve the design text corresponding to the design knowledge from the knowledge graph; The target design structure is integrated with the design text to obtain engineering drawings corresponding to the mold to be designed.

2. The extrusion die design method according to claim 1, characterized in that, The step of extracting target structural features from the cross-sectional image of the profile using a preset neural network model includes: Obtain historical profile surface drawings, and annotate the profile surface structure in the historical profile surface drawings to obtain the historical profile surface structure features; The preset neural network model is used to annotate the cross-sectional image of the profile according to the historical profile surface structural features, so as to obtain the target structural features corresponding to the mold to be designed.

3. The extrusion die design method according to claim 2, characterized in that, The target structural features include the target structural location and the target structural type. The step of obtaining the target design structure from the historical mold design structure based on the structural features includes: The historical structure location and historical structure type corresponding to the historical mold design structure are extracted using the preset neural network model. Calculate the positional similarity between the historical structure location and the target structure location, and calculate the type similarity between the historical structure type and the target structure type; Based on the location similarity and the type similarity, the target design structure is obtained from the historical mold design structure.

4. The extrusion die design method according to claim 3, characterized in that, After the step of extracting the target structural features from the cross-sectional image of the profile using a preset neural network model, the method includes: Obtain historical floor plan drawings; The historical profile surface drawings and historical planar design drawings are identified and classified to obtain graphic data corresponding to the profile cross-section and mold design. A mold design dataset is generated based on the graphical data.

5. The extrusion die design method according to claim 4, characterized in that, The location similarity includes grid area similarity and grid location similarity. The step of calculating the location similarity between the historical structure location and the target structure location includes: Obtain the historical structure parameters corresponding to the historical mold design structure from the mold design dataset, and import the historical mold design structure into a preset mesh according to the historical structure parameters; Obtain the target structure parameters corresponding to the target structure, and import the profile cross-section image into the preset grid according to the target structure parameters; Obtain the first grid number threshold and the first grid position occupied by the profile cross-section image in the preset grid; Obtain the threshold value of the number of second grids and the position of the second grid in the preset grid for the historical mold design structure; The grid area similarity is calculated based on the first grid number threshold and the second grid number threshold, and the grid position similarity is calculated based on the first grid position and the second grid position.

6. The extrusion die design method according to claim 1, characterized in that, The step of obtaining the design text corresponding to the design knowledge from the knowledge graph includes: Determine the knowledge type corresponding to the design knowledge, and identify the knowledge node corresponding to the knowledge type from the knowledge graph; Obtain the corresponding knowledge text based on the knowledge node, and adjust the knowledge text according to the design knowledge to obtain the design text.

7. The extrusion die design method according to claim 6, characterized in that, The step of fusing the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed includes: The target design structure is subjected to feature extraction to obtain a structural feature vector; Obtain the design parameters corresponding to the design text, and convert the design parameters into a parameter vector; The structural feature vector and the parameter vector are fused to obtain a fusion result, which is then input into a drawing generation tool to output the engineering drawing.

8. An extrusion die design device, characterized in that, include: The feature extraction module is used to acquire the cross-sectional image of the profile of the mold to be designed, and extract the target structural features from the cross-sectional image of the profile through a preset neural network model; The structure acquisition module is used to acquire the target design structure from historical mold design structures based on the target structural features; The knowledge acquisition module is used to acquire design knowledge corresponding to the mold to be designed, and to retrieve design text corresponding to the design knowledge from the knowledge graph; The drawing design module is used to integrate the target design structure with the design text to obtain engineering drawings corresponding to the mold to be designed.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor to implement the extrusion die design method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the extrusion die design method as described in any one of claims 1-7.

Images