A method and system for constructing a multimodal knowledge graph for extrusion dies

Abstract

This invention provides a method and system for constructing a multimodal knowledge graph for extrusion dies. It constructs ontology models for extruded products, die design processes, and simulation and verification processes. On one hand, it effectively organizes and stores text data, image / photo data, 2D CAD drawings, 3D models, simulation videos, and other data from the extrusion die design process within the knowledge graph, enabling effective association, retrieval, and reuse of design data. On the other hand, it uses the knowledge graph to record key design knowledge points during the design process and associates them with corresponding design data, recording design decision information, thereby achieving effective reuse of design knowledge.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of knowledge management technology in the manufacturing industry, and in particular to a method and system for constructing a multimodal knowledge graph for extrusion dies. Background Technology

[0002] Extrusion dies are key process equipment for extrusion production, and they significantly impact the quality, efficiency, and cost of extruded products. High-quality die design and manufacturing require extensive experience and knowledge accumulation. Therefore, constructing a knowledge graph for extrusion dies can effectively store, organize, and reuse die design knowledge. Using a knowledge graph, various types of knowledge generated during the extrusion die design process and their interrelationships can be effectively acquired and represented, thereby enabling the efficient retrieval and reuse of design data, information, and knowledge.

[0003] Currently, the extrusion die industry lacks an industry knowledge graph. Instead, it relies on databases to store CAD drawings, 3D models, simulation results, and other design data on computer hard drives or relational databases. This results in time-consuming and laborious data retrieval, and the accumulation of die design-related data and information over time makes it difficult to accurately locate the required design data and information, or to effectively reuse this data and information to improve design efficiency. Furthermore, for document-based data, current practices are still at the document retrieval stage, failing to quickly find precise information within documents through semantic search. The design knowledge hidden behind the design data and information is even more difficult to record and store effectively. Summary of the Invention

[0004] This invention provides a method and system for constructing a multimodal knowledge graph for extrusion dies, in order to solve the problems in the prior art where document-type data cannot be quickly retrieved through semantic retrieval, and where design data and the design knowledge hidden behind the information are difficult to record and store effectively.

[0005] In a first aspect, embodiments of the present invention provide a method for constructing a multimodal knowledge graph for extrusion dies, including:

[0006] Based on the first basic information, geometric information, technical information, and first personnel information of the extruded product, a first ontological model of the extruded product is constructed; based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed; based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed, wherein the third ontological model includes a simulation model and an on-site verification model;

[0007] Based on a graph database, the entities, attributes, and relationships in the first, second, and third ontology models are organized and stored. The first ontology model is used as the main entity, and is associated with the first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, and is associated with the third basic information through subordinate relationships. It is associated with simulation parameter entities through setting relationships, and with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, and is associated with field trial mold information through subordinate relationships.

[0008] As a preferred option, it also includes:

[0009] Record each entity and its corresponding attribute information in an Excel spreadsheet, save it as a CSV file, and then connect and store it in the graph database.

[0010] Preferably, the first basic information is used to record the identification characteristics of the extruded product, including product name, drawing number, customer source, manufacturer, contact number, email, and fax; the geometric information is used to record the geometric features of the extruded product, including the maximum outer diameter, outer circumference, maximum transverse length, maximum longitudinal width, fillet radius, and thickness; the technical information is used to record relevant information for manufacturing the extruded product, including the type of extruder, materials used, weight per unit length, mechanical performance requirements of the product, and technical requirements; the first personnel information is used to record relevant personnel information for manufacturing the extruded product, including the designer, drafter, checker, and approver.

[0011] Preferably, during the mold design process, the second basic information includes the mold name, mold type, design time, type of extruder used, extrusion ratio, and materials used in manufacturing; the two-dimensional drawing information describes key information related to the design of the two-dimensional CAD drawing, including the maximum diameter and thickness of the mold, the scale of the drawing, file format, and storage address; the three-dimensional model information records the type, file format, and storage address of the three-dimensional model; the mold hole information includes the number, shape, and location of the mold holes; the working zone information records the height distribution of the mold working zone and related calculation data; the technical requirements record the technical requirements during mold production and manufacturing, including chamfering, filleting, and clearance; and the second personnel information records the designer, reviewer, and approver of the mold design.

[0012] Preferably, the third basic information is used to record the mold model, simulation date, target extrusion press type, and personnel conducting the simulation; the simulation parameters are used to set simulation-related parameters, including process parameters, workpiece parameters, mold parameters, and encountered problems; the simulation results are used to record the analysis of the simulation results, including screenshot analysis results and video analysis results; the stress information is used to record the stress simulation results; the strain information is used to record the strain of the mold along the X, Y, and Z axes in the simulation results; the pressure information is used to record the average pressure condition and the pressure curve of the entire process in the simulation results; the temperature information is used to record the maximum and minimum temperatures and temperature distribution diagram during the simulation process; the flow rate information is used to record the maximum and minimum speeds of the metal extrusion flow and the flow rate distribution diagram; the welding status is used to record the fusion of the metal extrusion in the mold welding chamber, including the extreme values ​​of welding and the welding length diagram; the on-site mold trial information is used to record the results of the on-site mold trial, including the trial date, trial results, photos of the trial results, analysis and explanation, comparison with simulation results, mold repair methods, and personnel.

[0013] Preferably, the method further includes: determining that the simulated model entity has a predictive relationship with the field verification model entity, and that the field verification model entity has a verification relationship with the simulated model entity.

[0014] Secondly, embodiments of the present invention provide a multimodal knowledge graph construction system for extrusion dies, comprising:

[0015] The knowledge graph pattern layer construction module constructs a first ontological model of the extruded product based on the first basic information, geometric information, technical information, and first personnel information of the extruded product; it constructs a second ontological model of the mold design process based on the second basic information, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information of the mold design process; and it constructs a third ontological model of the simulation and verification process based on the third basic information, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information of the simulation and verification process. The third ontological model includes a simulation model and an on-site verification model.

[0016] The knowledge graph data layer construction module organizes and stores the entities, attributes, and relationships in the first, second, and third ontology models based on a graph database. Specifically, the first ontology model is used as the main entity, associated with first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, associated with second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, associated with third basic information through subordinate relationships, associated with simulation parameter entities through setting relationships, and associated with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, associated with field trial mold information through subordinate relationships.

[0017] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for constructing a multimodal knowledge graph for extrusion dies as described in the first aspect of the present invention.

[0018] Fourthly, embodiments of the present invention provide a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the multimodal knowledge graph construction method for extrusion dies as described in the first aspect of the present invention.

[0019] This invention provides a method and system for constructing a multimodal knowledge graph for extrusion dies. It constructs ontology models for extruded products, die design processes, and simulation and verification processes. On one hand, it effectively organizes and stores text data, image / photo data, 2D CAD drawings, 3D models, simulation videos, and other data from the extrusion die design process within the knowledge graph, enabling effective association, retrieval, and reuse of design data. On the other hand, it uses the knowledge graph to record key design knowledge points during the design process and associates them with corresponding design data, recording design decision information, thereby achieving effective reuse of design knowledge. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method for constructing a multimodal knowledge graph for extrusion dies according to an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the extruded product body model according to an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the mold design body model according to an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the simulation verification ontology model according to an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0027] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0028] The terms "first" and "second" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a system, product, or device that includes a series of components or units is not limited to the listed components or units, but may optionally include unlisted components or units, or may optionally include other components or units inherent to such products or devices. In the description of this application, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] Currently, the extrusion die industry lacks an industry knowledge graph. Instead, it relies on databases to store CAD drawings, 3D models, simulation results, and other design data on computer hard drives or relational databases. This results in time-consuming and laborious data retrieval, and the accumulation of die design-related data and information over time makes it difficult to accurately locate the required design data and information, or to effectively reuse this data and information to improve design efficiency. Furthermore, for document-based data, current practices are still at the document retrieval stage, failing to quickly find precise information within documents through semantic search. The design knowledge hidden behind the design data and information is even more difficult to record and store effectively.

[0031] Therefore, embodiments of the present invention provide a method and system for constructing a multimodal knowledge graph for extrusion dies. On one hand, it effectively organizes and stores text data, image / photo data, 2D CAD drawings, 3D models, simulation videos, and other data from the extrusion die design process into a knowledge graph, enabling effective association, retrieval, and reuse of design data. On the other hand, the knowledge graph focuses on recording key design knowledge points during the design process and associates them with corresponding design data, recording design decision information, thereby achieving effective reuse of design knowledge. The following description, in conjunction with the accompanying drawings, illustrates a method and system for constructing a multimodal knowledge graph for extrusion dies according to this embodiment.

[0032] Figure 1 To provide a method for constructing a multimodal knowledge graph for extrusion dies according to an embodiment of the present invention, the method includes:

[0033] Based on the first basic information, geometric information, technical information, and first personnel information of the extruded product, a first ontological model of the extruded product is constructed; based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed; based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed, wherein the third ontological model includes a simulation model and an on-site verification model;

[0034] In this embodiment, constructing a knowledge graph for extrusion dies first requires building an ontology model as the schema layer of the knowledge graph. Ontology models are constructed for extruded products, die design processes, and simulation and verification processes, respectively.

[0035] The construction of the extruded product's ontological model (first ontological model) mainly involves designing and associating four key pieces of information: basic information, geometric information, technical information, and personnel information, such as... Figure 2As shown, the first basic information records the identifying characteristics of the extruded product, such as product name, drawing number, customer origin, manufacturer, contact number, email, and fax. Geometric information includes the geometric features of the extruded product, including the maximum outer diameter, outer circumference, maximum transverse length, maximum longitudinal width, fillet radius, and thickness. Technical information includes relevant information for manufacturing the product, including the type of extruder, materials used, weight per unit length, mechanical performance requirements, and other technical requirements. Finally, the first personnel information includes information about the personnel involved in manufacturing the product, such as the designer, drafter, checker, and approver.

[0036] The construction of the mold design's main model involves designing and associating seven aspects to describe the relevant data and information of the mold design: secondary basic information, 2D drawing information, 3D model information, die hole information, working zone information, technical requirements, and secondary personnel information. The secondary basic information includes the mold's name, type, design time, type of extruder used, extrusion ratio, and materials used in production. The 2D drawing information describes key information related to the mold's 2D CAD drawing, such as the mold's maximum diameter, thickness, drawing scale, file format, and storage location. The corresponding 3D model information records the 3D model's type, file format, and storage location. Die hole information includes the number, shape, and location of the die holes. The working zone information records the height distribution of the mold's working zone and related calculation data. Technical requirements include the technical requirements for mold manufacturing, such as chamfering, filleting, and clearance. The secondary personnel information records the mold design's designer, reviewer, and approver.

[0037] The knowledge graph for simulation and verification is constructed by summarizing and associating various data generated during simulation and field testing. The simulation aspect includes nine areas of information: basic information, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and field trial mold information. The basic information records the mold model, simulation date, applicable extrusion press type, and personnel involved in the simulation. Simulation parameters are the relevant simulation parameters, including process parameters, workpiece parameters, mold parameters, and encountered problems. Simulation results record the analysis of the simulation results, including screenshots and videos. Stress information records key stress simulation results, primarily advanced stress analysis results and bridge stress analysis results. Correspondingly, strain information records the mold strain along the X, Y, and Z axes in the simulation results. Pressure information records the average pressure and pressure curve throughout the simulation. Temperature information records the maximum and minimum temperatures and temperature distribution during the simulation. Flow rate information records the maximum and minimum flow rates of the extruded metal and its distribution. The welding information records the fusion of extruded metal in the mold welding chamber, including extreme welding values ​​and weld length diagrams. For on-site mold trial information, the main records include the results of the on-site mold trials, such as the trial date, results, photos of the results, analysis and explanations, comparison with simulation results, mold repair methods, and personnel involved.

[0038] Based on a graph database, the entities, attributes, and relationships in the first, second, and third ontology models are organized and stored. The first ontology model is used as the main entity, and is associated with the first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, and is associated with the third basic information through subordinate relationships. It is associated with simulation parameter entities through setting relationships, and with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, and is associated with field trial mold information through subordinate relationships.

[0039] After designing the ontology model, the next step is to construct the data layer of the extrusion die knowledge graph. This embodiment of the invention uses a graph database to organize and store the relevant information summarized in the ontology model, corresponding to the entities, attributes, and relationships in the graph database, thereby recording and creating interrelationships between the information and knowledge elements in the ontology model.

[0040] Among them, such as Figure 2The diagram shown is a schematic of the first entity model (extruded product entity model) in an embodiment of the present invention. 'Extruded product' is a main entity (first entity model), associated with four entities—'First Basic Information', 'Geometric Information', 'Technical Information', and 'First Personnel Information'—through the dependency relationship 'has'. For the 'First Basic Information' entity, its attribute values ​​include 'Product Name', 'Drawing Number', 'Manufacturer', 'Contact Number', 'Email', and 'Fax'. The 'Geometric Information' entity has attributes such as 'Maximum Outer Diameter', 'Circumference', 'Maximum Length', 'Maximum Width', 'Fillet', and 'Thickness'. The 'Technical Information' entity includes attributes such as 'Extrusion Machine Type', 'Material', 'Weight', 'X-axis Modulation Moment', 'Y-axis Modulation Moment', 'X-axis Moment of Inertia', 'Y-axis Moment of Inertia', 'Other Technical Requirements', and 'Remarks'. The 'First Personnel Information' entity includes attributes such as 'Designer', 'Drafter', 'Checker', and '...'.

[0041] 'Approver', etc.

[0042] like Figure 3 The diagram shown is a schematic of the second entity model (mold design entity model) in an embodiment of the present invention. The 'mold design' entity (second entity model) is also associated with seven entities through a hierarchical relationship: 'second basic information', 'two-dimensional drawing information', 'three-dimensional model information', 'mold hole information', 'working zone information', 'technical requirements', and 'second personnel information'. Among them, the 'second basic information' entity includes the following attributes: 'name', 'model', 'time', 'extrusion machine',

[0043] 'Extrusion ratio', 'Material', etc. The '2D drawing information' entity includes attributes such as: 'Maximum diameter',

[0044] The entity "3D Model Information" includes attributes such as "Thickness," "Scale," "File Format," and "Storage Address." The entity "Die Hole Information" includes attributes such as "Number," "Shape," and "Location." The entity "Working Zone Information" includes attributes such as "Height Distribution" and "Calculated Data." The entity "Technical Requirements" includes attributes such as "Chamfer," "Fillet," "Air Cut Amount," and "Remarks." The entity "Secondary Personnel Information" includes attributes such as "Designer," "Reviewer," and "Approver."

[0045] like Figure 4The diagram shown is a schematic of the third ontology model (simulation verification ontology model) in an embodiment of the present invention. The simulation and verification part includes a 'simulation simulation' entity and a 'field verification' entity. The simulation simulation model entity is determined to have a predictive relationship with the field verification model entity, while the field verification model entity is determined to have a verification relationship with the simulation simulation model entity. The simulation simulation model is connected to the 'third basic information' entity based on a subordinate relationship, to the 'simulation parameters' entity through a 'setting' relationship, and to the 'stress information,' 'strain information,' 'pressure information,' and 'temperature information' through a 'simulation result' relationship.

[0046] The entities 'Flow Rate Information' and 'Welding Status' are linked. Specifically, the attributes of the 'Third Basic Information' entity include: 'Die Model', 'Simulation Date', 'Extrusion Press Model', and 'Simulation Personnel'.

[0047] The 'Simulation Parameters' entity includes 'Process Parameters', 'Workpiece Parameters', and 'Mold Parameters' through hierarchical relationships. The 'Stress Information' entity's attributes include 'Advanced Stress' and 'Bridge Stress'. The 'Strain Information' entity's attributes include 'X-axis Strain', 'Y-axis Strain', and 'Z-axis Strain'.

[0048] The attributes of the 'Pressure Information' entity include: 'Average Pressure' and 'Pressure Curve'. The attributes of the 'Temperature Information' entity include: 'Maximum Value', 'Minimum Value', and 'Distribution Map'. The attributes of the 'Flow Rate' entity include: 'Maximum Value', 'Minimum Value', and 'Flow Rate Distribution Map'. For the 'Field Trial' entity, attributes are included through hierarchical relationships: 'Trial Date', 'Trial Result', 'Trial Result Photo', 'Analysis Description', 'Comparison with Simulation Results', 'Temperature Repair Method', and 'Temperature Repair Personnel', etc.

[0049] Record each entity and its corresponding attribute information in an Excel spreadsheet, save it as a CSV file, and then connect and store it in the graph database.

[0050] This invention also provides a multimodal knowledge graph construction system for extrusion dies, based on the multimodal knowledge graph construction method for extrusion dies described in the above embodiments, including:

[0051] The knowledge graph pattern layer construction module constructs a first ontological model of the extruded product based on the first basic information, geometric information, technical information, and first personnel information of the extruded product; it constructs a second ontological model of the mold design process based on the second basic information, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information of the mold design process; and it constructs a third ontological model of the simulation and verification process based on the third basic information, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information of the simulation and verification process. The third ontological model includes a simulation model and an on-site verification model.

[0052] The knowledge graph data layer construction module organizes and stores the entities, attributes, and relationships in the first, second, and third ontology models based on a graph database. Specifically, the first ontology model is used as the main entity, associated with first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, associated with second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, associated with third basic information through subordinate relationships, associated with simulation parameter entities through setting relationships, and associated with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, associated with field trial mold information through subordinate relationships.

[0053] Based on the same concept Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a cross-section-based pipe traversal method, which includes:

[0054] Based on the first basic information, geometric information, technical information, and first personnel information of the extruded product, a first ontological model of the extruded product is constructed; based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed; based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed, wherein the third ontological model includes a simulation model and an on-site verification model;

[0055] Based on a graph database, the entities, attributes, and relationships in the first, second, and third ontology models are organized and stored. The first ontology model is used as the main entity, and is associated with the first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, and is associated with the third basic information through subordinate relationships. It is associated with simulation parameter entities through setting relationships, and with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, and is associated with field trial mold information through subordinate relationships.

[0056] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] Based on the same concept, embodiments of the present invention also provide a non-transitory computer-readable storage medium storing a computer program containing at least one piece of code executable by a master control device to control the master control device to implement the steps of the multimodal knowledge graph construction method for extrusion dies as described in the above embodiments. For example, it includes:

[0058] Based on the first basic information, geometric information, technical information, and first personnel information of the extruded product, a first ontological model of the extruded product is constructed; based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed; based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed, wherein the third ontological model includes a simulation model and an on-site verification model;

[0059] Based on a graph database, the entities, attributes, and relationships in the first, second, and third ontology models are organized and stored. The first ontology model is used as the main entity, and is associated with the first basic information, geometric information, technical information, and first personnel information through subordinate relationships. The second ontology model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as an entity, and is associated with the third basic information through subordinate relationships. It is associated with simulation parameter entities through setting relationships, and with stress, strain, pressure, temperature, flow rate, and welding conditions through simulation result relationships. The field verification model is used as an entity, and is associated with field trial mold information through subordinate relationships.

[0060] Based on the same technical concept, this application also provides a computer program, which, when executed by a main control device, is used to implement the above-described method embodiments.

[0061] The program may be stored, in whole or in part, on a storage medium packaged with the processor, or in part or in whole on a memory not packaged with the processor.

[0062] Based on the same technical concept, this application also provides a processor for implementing the above-described method embodiments. The processor can be a chip.

[0063] In summary, the present invention provides a method and system for constructing a multimodal knowledge graph for extrusion dies, which constructs graphs for extrusion products, die design processes, and simulation and verification processes, respectively.

[0064] Its ontological model effectively organizes and stores text data, image / photo data, 2D CAD drawings, 3D models, simulation videos, and other data from the extrusion die design process within a knowledge graph, enabling effective association, retrieval, and reuse of design data. Furthermore, it utilizes the knowledge graph to...

[0065] The key design knowledge points in the design process were recorded and associated with the corresponding design data, and design decision information was recorded, thereby realizing the effective reuse of design knowledge.

[0066] The various embodiments of the present invention can be combined arbitrarily to achieve different technical effects.

[0067] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, in the form of a computer program product.

[0068] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the process described in this application is generated.

[0069] Function. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the calculation...

[0070] Machine commands can be transmitted from a website, computer, server, or data center to another network via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0071] The data is transmitted to a website, computer, server, or data center. The computer-readable storage medium can be any available medium accessible to a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., magnetic media).

[0072] Floppy disks, hard disks, magnetic tapes, optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0073] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the above method embodiments.

[0074] The aforementioned storage media include ROM or random access memory (RAM), magnetic disks or optical disks, and other media capable of storing program code.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a multimodal knowledge graph for extrusion dies, characterized in that, include: Based on the first basic information, geometric information, technical information and first personnel information of the extruded product, a first ontological model of the extruded product is constructed. Based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed. Based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed. The third ontological model includes a simulation model and an on-site verification model. Based on the graph database, the entities, attributes and relationships in the first ontology model, the second ontology model and the third ontology model are organized and stored. The first ontology model is used as the main entity and is associated with the first basic information, geometric information, technical information and the first personnel information through subordinate relationships. The second body model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as the entity, and is associated with the third basic information through subordinate relationships. The simulation parameter entity is associated with the simulation result relationship, and stress, strain, pressure, temperature, flow rate, and welding status are associated with the simulation result relationship. The field verification model is used as the entity, and is associated with the field trial mold information through subordinate relationships.

2. The method for constructing a multimodal knowledge graph for extrusion dies according to claim 1, characterized in that, Also includes: Record each entity and its corresponding attribute information in an Excel spreadsheet, save it as a CSV file, and then connect and store it in the graph database.

3. The method for constructing a multimodal knowledge graph for extrusion dies according to claim 1, characterized in that, The first basic information records the identifying characteristics of the extruded product, including product name, drawing number, customer source, manufacturer, contact number, email, and fax. The geometric information records the geometric features of the extruded product, including the maximum outer diameter, outer circumference, maximum transverse length, maximum longitudinal width, fillet radius, and thickness. The technical information records relevant information for manufacturing the extruded product, including the type of extruder, materials used, weight per unit length, mechanical performance requirements, and technical requirements. The first personnel information records relevant personnel information for manufacturing the extruded product, including the designer, drafter, checker, and approver.

4. The method for constructing a multimodal knowledge graph for extrusion dies according to claim 1, characterized in that, In the mold design process, the second basic information includes the mold name, mold type, design time, extruder type, extrusion ratio, and materials used in manufacturing; the two-dimensional drawing information describes key information related to the two-dimensional CAD drawing, including the mold's maximum diameter, thickness, drawing scale, file format, and storage address; the three-dimensional model information records the type, file format, and storage address of the three-dimensional model; the die hole information includes the number, shape, and location of the die holes; the working zone information records the height distribution of the die's working zone and related calculation data; the technical requirements record the technical requirements during mold production and manufacturing, including chamfering, filleting, and clearance; the second personnel information records the mold designer, reviewer, and approver.

5. The method for constructing a multimodal knowledge graph for extrusion dies according to claim 1, characterized in that, The third basic information is used to record the mold model, the date of the simulation, the type of extrusion press targeted, and the personnel conducting the simulation; the simulation parameters are used to set simulation-related parameters, including process parameters, workpiece parameters, mold parameters, and problems encountered; the simulation results are used to record the analysis of the simulation results, including screenshot analysis results and video analysis results. The stress information is used to record stress simulation results; The strain information is used to record the strain of the mold along the X, Y, and Z axes in the simulation results; the pressure information is used to record the average pressure and the pressure curve of the entire process in the simulation results. The temperature information is used to record the maximum and minimum temperatures and temperature distribution during the simulation process; the flow rate information is used to record the maximum and minimum speeds of the metal extrusion flow and the flow rate distribution; the welding status is used to record the fusion of the metal extrusion in the mold welding chamber, including the extreme values ​​of welding and the welding length diagram; the on-site mold trial information is used to record the results of the on-site mold trial, including the trial date, trial results, photos of the trial results, analysis and explanation, comparison with simulation results, mold repair methods, and personnel.

6. The method for constructing a multimodal knowledge graph for extrusion dies according to claim 1, characterized in that, Also includes: The relationship between the entities in the simulation model and the entities in the field verification model is determined to be predictive, while the relationship between the entities in the field verification model and the entities in the simulation model is determined to be verification.

7. A multimodal knowledge graph construction system for extrusion dies, characterized in that, include: The knowledge graph pattern layer construction module constructs the first ontology model of the backlogged products based on the first basic information, geometric information, technical information, and first personnel information of the backlogged products. Based on the second basic information of the mold design process, two-dimensional drawing information, three-dimensional model information, mold hole information, working zone information, technical requirements, and second personnel information, a second ontological model of the mold design process is constructed. Based on the third basic information of the simulation and verification process, simulation parameters, simulation results, stress information, strain information, pressure information, temperature information, flow rate information, welding status, and on-site mold trial information, a third ontological model of the simulation and verification process is constructed. The third ontological model includes a simulation model and an on-site verification model. The knowledge graph data layer construction module organizes and stores the entities, attributes and relationships in the first ontology model, the second ontology model and the third ontology model based on the graph database. The first ontology model is used as the main entity and is associated with the first basic information, geometric information, technical information and the first personnel information through subordinate relationships. The second body model is used as the main entity, and is associated with the second basic information, two-dimensional drawings, three-dimensional models, mold holes, working zones, technical requirements, and second personnel information through subordinate relationships. The simulation model is used as the entity, and is associated with the third basic information through subordinate relationships. The simulation parameter entity is associated with the simulation result relationship, and stress, strain, pressure, temperature, flow rate, and welding status are associated with the simulation result relationship. The field verification model is used as the entity, and is associated with the field trial mold information through subordinate relationships.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for constructing a multimodal knowledge graph for extrusion dies as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method for constructing a multimodal knowledge graph for extrusion dies as described in any one of claims 1 to 6.

Images