Welding process reasoning method and system based on knowledge graph

Abstract

The invention provides a welding process reasoning method and system based on a knowledge graph. The method comprises the steps that a welding process knowledge graph library is constructed; the welding process knowledge graph database at least comprises a welding process reasoning relation graph model, and the welding process reasoning relation graph model comprises a welding process incidence relation between the welding seam feature data and the welding process data and an internal incidence relation between internal data of the welding process data; weld joint characteristic data are obtained and determined; based on the determined weld joint feature data, a welding process reasoning request is established and sent out; and in response to a welding process reasoning request, inputting welding seam feature data based on the welding process reasoning relation map model, and reasoning to obtain welding process data. According to the method, the information island problem between the design content and the design object is solved by constructing the welding process knowledge graph database, tight coupling of the welding seam feature data and the welding process data is achieved, and automatic reasoning of the welding process data can be achieved.

Description

Technical Field

[0001] The present application relates to the technical field of ship welding technology, and in particular to a welding technology reasoning method and system based on a knowledge graph. Background Art

[0002] With the improvement of ship 3D digital design capabilities, model-based process design has gradually become the mainstream process design method.

[0003] At present, in terms of ship welding process design, paper welding process regulations are mainly issued to guide on-site welding operations. The process design process mainly relies on manual review of technical documents and materials for process design, and there is no correlation between the process design content and the three-dimensional process model, resulting in information islands between the process design content and the design object, which greatly affects the process design efficiency and production and construction efficiency. Summary of the invention

[0004] The purpose of this application is to provide a welding process reasoning method and system based on knowledge graph, which solves the information island problem between design content and design objects by constructing a welding process knowledge graph library, realizes the tight coupling of weld feature data and welding process data, and can realize automatic reasoning of welding process data.

[0005] The present application provides a welding process reasoning method based on a knowledge graph, which is characterized by comprising:

[0006] S1. Construct a welding process knowledge graph library; the welding process knowledge graph library at least includes a welding process reasoning relationship graph model, the welding process reasoning relationship graph model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data;

[0007] S2. Acquire and determine weld characteristic data;

[0008] S3. Establishing and issuing a welding process reasoning request based on the determined weld feature data;

[0009] S4. In response to a welding process reasoning request, based on a welding process reasoning relationship graph model, the weld feature data is input, and the welding process data corresponding to the current weld feature data is inferred.

[0010] In an implementable solution, the weld feature data includes at least weld position, weld shape, component material, component category, base material thickness, and information on whether there is a groove;

[0011] Welding process data at least includes welding method, groove form, welding material information, and welding parameters.

[0012] In an implementable solution, in step S4, in response to a welding process reasoning request, based on a welding process reasoning relationship graph model, inputting weld feature data, and inferring to obtain welding process data corresponding to the current weld feature data include:

[0013] S40, receiving weld feature data, and starting reasoning in response to a welding process reasoning request;

[0014] S41, inferring a welding method based on weld feature data;

[0015] S42, inferring the groove form based on the determined welding method and weld feature data;

[0016] S43, inferring welding material information based on the determined welding method, groove form and weld feature data;

[0017] S44. Infer welding parameters based on the determined welding method, groove form, welding material information and weld feature data.

[0018] In an implementable solution, in the weld feature data, the weld position includes at least flat welding, horizontal welding, vertical welding, and overhead welding, the base material plate thickness is set to thick, medium thick, medium thin, and thin according to a set parameter range, the base material plate thickness is the plate thickness at the weld, the groove presence or absence information includes groove presence and groove absence, the component material is the material information of the components constituting the weld, the weld shape includes the size parameters of the weld, and the component category includes the application scenario information of the components constituting the weld;

[0019] In the welding process data, the welding methods include at least arc welding, gas welding, pressure welding, and brazing; the groove forms include at least no groove, I-type groove, V-type groove, X-type groove, and Y-type groove; the welding material information includes the material information and diameter information of the welding material; and the welding parameters include at least welding current, welding voltage, welding speed, and gas flow rate.

[0020] In an implementable solution, in step S1, the welding process knowledge graph library also includes an assembly reasoning relationship graph model, the assembly reasoning relationship graph model includes a weld model, component attributes and component flow information, and an assembly process association relationship is established between the weld model and the component attributes, and between the component attributes and the component flow information;

[0021] Welding process reasoning methods also include:

[0022] S5, binding the welding process data inferred in step S4 with the weld model, and storing them in a weld welding process database;

[0023] S6, determining the component attributes, and inferring the component flow information of the current component based on the assembly process association relationship between the component attributes and the component flow information;

[0024] S7, screening out the components to be welded that have the same component flow direction information, and determining the component properties of these components;

[0025] S8, based on the assembly process association relationship between component attributes and weld models, infer all welding models to be welded in these components;

[0026] S9. Based on the determined welding model to be welded, the welding process data bound to the welding model is extracted from the welding process database of the weld, and a welding process task package is formed and issued.

[0027] In an practicable solution, in step S3, the welding process reasoning request at least includes the determined weld feature data and the service code, and the service code is associated with the information of the weld model, and the association is stored in a weld feature database;

[0028] In step S4, after the welding process data corresponding to the current weld feature data is inferred, the process further includes: forming a request response body with the service code and the inferred welding process data and sending the request response body;

[0029] In step S5, the step of binding the welding process data inferred in step S4 with the weld model and storing them in a weld process database includes:

[0030] S51, receiving the request response body, and extracting the service code and welding process data therein;

[0031] S52, searching for a corresponding weld model based on the service code;

[0032] S53, establishing a binding relationship between the welding process data and the weld model, and storing them in the weld welding process database.

[0033] In an implementable solution, after step S51, it also includes: S54, performing welding process data verification; if problems are found after verification based on actual needs, modifying the welding process data extracted from the request response body, and feeding back the modified information to the welding process knowledge graph library to correct the welding process reasoning relationship graph model.

[0034] In an implementable solution, in the assembly reasoning relationship graph model, the component attributes at least include structure information and assembly information, and the component flow information at least includes adapted assembly workshop information and welding equipment information.

[0035] In a second aspect, a welding process reasoning system based on a knowledge graph is also provided, comprising a building module, a first storage module, a process reasoning module, an acquisition module and a request module;

[0036] A module is established for constructing a welding process knowledge graph library; the welding process knowledge graph library at least includes a welding process reasoning relationship graph model, the welding process reasoning relationship graph model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data;

[0037] The first storage module is used to store the welding process knowledge graph library;

[0038] The acquisition module is used to acquire and determine weld characteristic data;

[0039] The request module is used to establish and issue a welding process reasoning request based on the determined weld feature data;

[0040] The process reasoning module is used to respond to the welding process reasoning request, input the weld feature data based on the welding process reasoning relationship graph model, and infer the welding process data corresponding to the current weld feature data.

[0041] In an implementable solution, the welding process reasoning system based on the knowledge graph further includes an output module, a receiving module, a sorting module, a second storage module, and a task issuing module;

[0042] The output module is used to send out the inferred welding process data;

[0043] The receiving module is used to receive the welding process data sent by the output module;

[0044] The sorting module is used to bind the welding process data with the weld model and store them in the weld process database;

[0045] The second storage module is used to store the welding process database of the weld;

[0046] The task issuing module is used to determine the attributes of the parts and components, and based on the assembly process association relationship between the attributes of the parts and the flow information of the parts, infer the part flow information of the current parts; it is used to screen out the parts to be welded with the same part flow information, and determine the attributes of these parts; it is used to infer all the welding models to be welded in these parts based on the assembly process association relationship between the attributes of the parts and the weld model; it is used to extract the welding process data bound to the welding model from the weld welding process database based on the determined welding model to be welded, form a welding process task package and issue it.

[0047] Compared with the prior art, the beneficial effects of this application include at least:

[0048] The welding process reasoning method based on knowledge graph of the present application solves the information island problem between design content and design object based on the constructed welding process knowledge graph library, and realizes the tight coupling of weld feature data and welding process data. And based on the welding process reasoning request, with known weld feature data and through the welding process knowledge graph library, the corresponding welding process data can be automatically inferred, which improves the efficiency of welding process design and helps to improve the efficiency of ship production and construction. At the same time, the process of automatic reasoning, based on the standard data of the welding process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original reliance on empirical data, and help to obtain relatively more accurate welding process data, which is conducive to improving the subsequent welding quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a flowchart of a first welding process reasoning method based on knowledge graph according to an embodiment of the present application;

[0051] Figure 2 It is a flowchart of a second welding process reasoning method based on knowledge graph according to an embodiment of the present application;

[0052] Figure 3 It is a structural schematic diagram of a welding process reasoning system based on a knowledge graph according to an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0055] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0056] like Figure 1 As shown, according to the first aspect of the present application, a welding process reasoning method based on a knowledge graph is first provided, comprising:

[0057] S1. Construct a welding process knowledge graph library; the welding process knowledge graph library at least includes a welding process reasoning relationship graph model, the welding process reasoning relationship graph model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data;

[0058] S2. Acquire and determine weld characteristic data;

[0059] S3. Establishing and issuing a welding process reasoning request based on the determined weld feature data;

[0060] S4. In response to a welding process reasoning request, based on a welding process reasoning relationship graph model, the weld feature data is input, and the welding process data corresponding to the current weld feature data is inferred.

[0061] The welding process reasoning method based on knowledge graph of the present application solves the information island problem between design content and design object based on the constructed welding process knowledge graph library, and realizes the tight coupling of weld feature data and welding process data. And based on the welding process reasoning request, with known weld feature data and through the welding process knowledge graph library, the corresponding welding process data can be automatically inferred, which improves the efficiency of welding process design and helps to improve the efficiency of ship production and construction. At the same time, the process of automatic reasoning, based on the standard data of the welding process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original reliance on empirical data, and help to obtain relatively more accurate welding process data, which is conducive to improving the subsequent welding quality.

[0062] In one embodiment, the weld feature data may at least include the weld position, weld shape, component material, component category, parent material thickness, groove information, joint form, etc., and the welding process data may at least include the welding method, groove form, welding material information, welding parameters, etc.

[0063] In one embodiment, in the weld feature data, the weld position may include at least flat welding, horizontal welding, vertical welding, and overhead welding. The base material plate thickness is set to thick, medium thick, medium thin, and thin according to a set parameter range. The base material plate thickness is the plate thickness at the weld. The information on whether there is a groove includes whether there is a groove or no groove. The component material is the material information of the components that constitute the weld. The weld shape includes the dimensional parameters of the weld (such as length and width, etc.). The component category includes application scenario information of the components that constitute the weld, such as outer plate components, inner bottom plate components, strong deck components, subsea valve components, sewage well components, etc.

[0064] The joint forms include butt joint and corner joint;

[0065] In the welding process data, the welding methods may include at least arc welding, gas welding, pressure welding, brazing, etc., and the welding method data may include the method name, characteristics, main process parameters, operation technical information, etc.; the groove form may include at least no groove, I-type groove, V-type groove, X-type groove, Y-type groove, etc., and may include the corresponding groove schematic diagram; the welding material information includes the material information and diameter information of the welding material; the welding parameters may include at least the welding current, welding voltage, welding speed, gas flow, etc.

[0066] In one embodiment, in step S4, in response to a welding process reasoning request, based on a welding process reasoning relationship graph model, inputting weld feature data, and inferring to obtain welding process data corresponding to the current weld feature data may include:

[0067] S40, receiving weld feature data, and starting reasoning in response to a welding process reasoning request;

[0068] S41. Inferring a welding method based on weld feature data; specifically, in the welding process knowledge atlas library, the welding process reasoning relationship atlas model infers the welding method based on information such as welding weld position, weld shape, component material, component category, base material plate thickness, groove information, joint form, etc.; for example, if the weld position is flat welding, the base material plate thickness is thick, and there is a groove, then the welding method is automatically inferred to be submerged arc welding through the relationship in the atlas;

[0069] S42, inferring the groove form based on the determined welding method and weld feature data; specifically, in the welding process knowledge atlas library, the welding process reasoning relationship atlas model infers the groove form according to the welding method and welding weld position, weld shape, component material, component category, parent material plate thickness, groove information, joint form and other information; for example, when the welding method of carbon dioxide gas shielded welding (arc welding) is adopted, when the parent material plate thickness exceeds 10mm, different groove forms are inferred according to the different thicknesses; for another example, if the joint form is butt joint, the welding method is submerged arc welding or flux-cored wire CO2 gas shielded welding, and the parent material plate thickness is thick plate, the groove form is inferred to be a Y-type groove;

[0070] S43, based on the determined welding method, groove form and weld feature data, the welding material information is inferred; specifically, in the welding process knowledge atlas library, the welding material information is inferred from the welding method, groove form and welding weld position, weld shape, component material, component category, parent material plate thickness, groove information, joint form and other information, including material information and diameter information; for example: if the groove form is Y-type or X-type, and the welding method is flux-cored CO2 gas shielded welding, the weld position is horizontal welding, and the component material is high-strength low-alloy steel (such as DH36, DH40, etc.), the material information inferred is a gas-shielded flux-cored welding wire for low-carbon steel and 490MPa-grade high-strength steel; further, the parent material plate thickness is thick, and the welding method is flux-cored CO2 gas shielded welding, the welding material is a gas-shielded flux-cored welding wire for low-carbon steel and 490MPa-grade high-strength steel, and the welding material diameter is inferred to be 1.2mm;

[0071] S44, based on the determined welding method, groove form, welding material information and weld feature data, the welding parameters are inferred; specifically, in the welding process knowledge atlas library, the welding process reasoning relationship atlas model is used to infer the welding parameters based on the welding method, groove form, welding material information and welding weld position, weld shape, component material, component category, parent material plate thickness, groove information, joint form and other information. For example, the weld position is flat welding, the welding method is flux-cored CO2 gas shielded welding, the groove form is a Y-shaped groove, and the welding material diameter is 1.2mm. It is inferred that the welding current is 250-260A, the welding voltage is 24-26V, the welding speed is 31-35cm / min, and the gas flow rate is 15-20L / min.

[0072] In one embodiment, in step S1, the welding process knowledge graph library also includes an assembly reasoning relationship graph model, which includes a weld model, component attributes, and component flow information. An assembly process association relationship is established between the weld model and the component attributes, and between the component attributes and the component flow information.

[0073] In one embodiment, in the assembly reasoning relationship graph model, the component attributes may at least include structural information and assembly information, and the component flow information may at least include the adapted assembly workshop information and welding equipment information. The structural information includes the structural characteristics of the component, and the assembly information includes the assembly method and assembly requirements between the components. The component flow information is used to indicate which workshop the component goes to and which equipment is used for processing.

[0074] In one embodiment, if Figure 2 As shown in the figure, the welding process reasoning method based on knowledge graph also includes:

[0075] S5, binding the welding process data inferred in step S4 with the weld model, and storing them in a weld welding process database;

[0076] S6, determining the component attributes, and inferring the component flow information of the current component based on the assembly process association relationship between the component attributes and the component flow information;

[0077] S7, filter out the parts to be welded that have the same parts flow direction information, and determine the parts attributes of these parts; the same parts flow direction information means that the assembly workshop information and welding equipment information of the parts are consistent and can be processed together;

[0078] S8, based on the assembly process association relationship between component attributes and weld models, infer all welding models to be welded in these components;

[0079] S9. Based on the determined welding model to be welded, the welding process data bound to the welding model is extracted from the welding process database of the weld, and a welding process task package is formed and issued.

[0080] Steps S5 to S9 can realize the automatic issuance of welding processes, the automatic generation and issuance of welding process task packages, and improve the control of the welding process.

[0081] In one embodiment, in step S3, the welding process reasoning request at least includes the determined weld feature data and the service code, and the service code is associated with the information of the weld model, and this association is stored in a weld feature database.

[0082] In one embodiment, in step S4, after inferring the welding process data corresponding to the current weld feature data, the step further includes: composing a request response body with the service code and the inferred welding process data and sending the request response body;

[0083] In one embodiment, in step S5, the step of binding the welding process data inferred in step S4 with the weld model and storing them in a weld process database includes:

[0084] S51, receiving the request response body, and extracting the service code and welding process data therein;

[0085] S52, searching for a corresponding weld model based on the service code;

[0086] S53, establishing a binding relationship between the welding process data and the weld model, and storing them in the weld welding process database.

[0087] In one embodiment, after step S51, it also includes: S54, performing welding process data verification; if problems are found after verification based on actual needs, modifying the welding process data extracted from the request response body, and feeding back the modified information to the welding process knowledge graph library to correct the welding process reasoning relationship graph model, thereby further improving the comprehensiveness and accuracy of the reasoning.

[0088] like Figure 3 As shown, the present application also provides a welding process reasoning system based on a knowledge graph, including an establishment module 11, a first storage module 12, a process reasoning module 13, an acquisition module 21 and a request module 22;

[0089] The establishment module 11 is used to construct a welding process knowledge map library; the welding process knowledge map library at least includes a welding process reasoning relationship map model, the welding process reasoning relationship map model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data;

[0090] The first storage module 12 is used to store the welding process knowledge graph library;

[0091] The acquisition module 21 is used to acquire and determine weld characteristic data;

[0092] The request module 22 is used to establish and issue a welding process reasoning request based on the determined weld feature data;

[0093] The process reasoning module 13 is used to respond to a welding process reasoning request, input weld feature data based on a welding process reasoning relationship graph model, and infer welding process data corresponding to the current weld feature data.

[0094] In one embodiment, if Figure 3 As shown, the welding process reasoning system based on the knowledge graph also includes an output module 14, a receiving module 23, a sorting module 24, a second storage module 25, and a task issuing module 26;

[0095] The output module 14 is used to send out the inferred welding process data;

[0096] The receiving module 23 is used to receive the welding process data sent by the output module 14;

[0097] The sorting module 24 is used to bind the welding process data with the weld model and store them in the weld welding process database;

[0098] The second storage module 25 is used to store the welding process database of the weld;

[0099] The task issuing module 26 is used to determine the attributes of the components, and based on the assembly process association relationship between the component attributes and the component flow information, infer the component flow information of the current component; it is used to screen out the components to be welded with the same component flow information, and determine the component attributes of these components; it is used to infer all the welding models to be welded in these components based on the assembly process association relationship between the component attributes and the weld model; it is used to extract the welding process data bound to the welding model from the weld welding process database based on the determined welding model to be welded, form a welding process task package and issue it.

[0100] Corresponding to the above method embodiment, Figure 4 As shown, the present application also provides an electronic device, which includes a processor 1 and a memory 2 storing computer program instructions. The processor 1 and the memory 2 can communicate with each other through a communication bus 3. The processor 1 is used to execute computer program instructions, and the memory 2 is used to store computer program instructions.

[0101] The processor 1 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the present embodiment. The memory 2 may include a high-speed RAM memory, or may also include a non-volatile memory, such as at least one disk memory. The processor 1 executes at least one computer program instruction to implement the steps shown in the embodiment of the welding process reasoning method based on the knowledge graph.

[0102] Corresponding to the above method embodiment, the present application also provides a computer-readable storage medium, on which computer program instructions are stored. When one or more computer program instructions are executed by a processor, the steps shown in the welding process reasoning method embodiment based on a knowledge graph are implemented.

[0103] Among them, computer storage media can be tangible media that can contain or store programs for use by or in combination with instruction execution systems, devices or equipment. Computer storage media can be machine-readable signal media or machine-readable storage media. Computer storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0104] Corresponding to the above method embodiment, the present application also provides a computer program product, and when the instructions in the computer program product are executed by a processor, the steps shown in the welding process reasoning method embodiment based on the knowledge graph are implemented.

[0105] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A welding process reasoning method based on knowledge graph, characterized in that: include: S1. Build a welding process knowledge graph library; The welding process knowledge graph library at least includes a welding process reasoning relationship graph model, the welding process reasoning relationship graph model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data; S2. Acquire and determine weld characteristic data; S3. Establishing and issuing a welding process reasoning request based on the determined weld feature data; S4. In response to a welding process reasoning request, based on a welding process reasoning relationship graph model, the weld feature data is input, and the welding process data corresponding to the current weld feature data is inferred.

2. The welding process reasoning method based on knowledge graph according to claim 1 is characterized in that: The weld feature data at least includes weld position, weld shape, component material, component type, parent material thickness, and information on whether there is a groove; The welding process data at least includes welding method, groove form, welding material information, and welding parameters.

3. The welding process reasoning method based on knowledge graph according to claim 2 is characterized in that: In step S4, in response to the welding process reasoning request, based on the welding process reasoning relationship graph model, the weld feature data is input, and the step of inferring and obtaining the welding process data corresponding to the current weld feature data includes: S40, receiving weld feature data, and starting reasoning in response to a welding process reasoning request; S41, inferring a welding method based on weld feature data; S42, inferring the groove form based on the determined welding method and weld feature data; S43, inferring welding material information based on the determined welding method, groove form and weld feature data; S44. Infer welding parameters based on the determined welding method, groove form, welding material information and weld feature data.

4. The welding process reasoning method based on knowledge graph according to claim 3 is characterized in that: In the weld feature data, the weld position includes at least flat welding, horizontal welding, vertical welding, and overhead welding; the base plate thickness is set to thick, medium thick, medium thin, and thin according to a set parameter range; the base plate thickness is the plate thickness at the weld; the groove presence or absence information includes groove presence and groove absence; the component material is the material information of the components constituting the weld; the weld shape includes the size parameters of the weld; and the component category includes application scenario information of the components constituting the weld; In the welding process data, the welding methods include at least arc welding, gas welding, pressure welding, and brazing; the groove forms include at least no groove, I-type groove, V-type groove, X-type groove, and Y-type groove; the welding material information includes material information and diameter information of the welding material; and the welding parameters include at least welding current, welding voltage, welding speed, and gas flow rate.

5. The welding process reasoning method based on knowledge graph according to any one of claims 1 to 4, characterized in that: In step S1, the welding process knowledge graph library also includes an assembly reasoning relationship graph model, which includes a weld model, component attributes, and component flow information, and an assembly process association relationship is established between the weld model and the component attributes, and between the component attributes and the component flow information; Welding process reasoning methods also include: S5, binding the welding process data inferred in step S4 with the weld model, and storing them in a weld welding process database; S6, determining the component attributes, and inferring the component flow information of the current component based on the assembly process association relationship between the component attributes and the component flow information; S7, screening out the components to be welded that have the same component flow direction information, and determining the component properties of these components; S8, based on the assembly process association relationship between component attributes and weld models, infer all welding models to be welded in these components; S9. Based on the determined welding model to be welded, the welding process data bound to the welding model is extracted from the welding process database of the weld, and a welding process task package is formed and issued.

6. The welding process reasoning method based on knowledge graph according to claim 5 is characterized in that: In step S3, the welding process reasoning request at least includes the determined weld feature data and the service code, and the service code is associated with the information of the weld model, and the association is stored in a weld feature database; In the step S4, after the welding process data corresponding to the current weld feature data is inferred, the step further includes: forming a request response body with the service code and the inferred welding process data and sending the request response body; In step S5, the step of binding the welding process data inferred in step S4 with the weld model and storing them in a weld process database includes: S51, receiving the request response body, and extracting the service code and welding process data therein; S52, searching for a corresponding weld model based on the service code; S53, establishing a binding relationship between the welding process data and the weld model, and storing them in the weld welding process database.

7. The welding process reasoning method based on knowledge graph according to claim 6 is characterized in that: After step S51, it also includes: S54, performing welding process data verification; if problems are found after verification based on actual needs, modifying the welding process data extracted from the request response body, and feeding back the modified information to the welding process knowledge graph library to correct the welding process reasoning relationship graph model.

8. The welding process reasoning method based on knowledge graph according to claim 5 is characterized in that: In the assembly reasoning relationship graph model, the component attributes at least include structure information and assembly information, and the component flow information at least includes adapted assembly workshop information and welding equipment information.

9. A welding process reasoning system based on knowledge graph, characterized in that: It comprises a building module (11), a first storage module (12), a process reasoning module (13), an acquisition module (21) and a request module (22); The establishment module (11) is used to construct a welding process knowledge graph library; the welding process knowledge graph library at least includes a welding process reasoning relationship graph model, the welding process reasoning relationship graph model includes weld feature data and welding process data, a welding process association relationship is established between the weld feature data and the welding process data, and an internal association relationship is established between the internal data of the welding process data; The first storage module (12) is used to store a welding process knowledge atlas library; The acquisition module (21) is used to acquire and determine weld characteristic data; The request module (22) is used to establish and issue a welding process reasoning request based on the determined weld feature data; The process reasoning module (13) is used to respond to a welding process reasoning request, input weld feature data based on a welding process reasoning relationship graph model, and infer welding process data corresponding to the current weld feature data.

10. The welding process reasoning system based on knowledge graph according to claim 9 is characterized in that: It also includes an output module (14), a receiving module (23), a sorting module (24), a second storage module (25), and a task issuing module (26); The output module (14) is used to send out the inferred welding process data; The receiving module (23) is used to receive welding process data sent by the output module (14); The collating module (24) is used to bind the welding process data with the weld model and store them in the weld process database; The second storage module (25) is used to store a weld process database; The task issuing module (26) is used to determine the component attributes, and based on the assembly process association relationship between the component attributes and the component flow information, infer the component flow information of the current component; to screen out the components to be welded with the same component flow information, and determine the component attributes of these components; to infer all the welding models to be welded in these components based on the assembly process association relationship between the component attributes and the weld model; and to extract the welding process data bound to the welding model from the weld welding process database based on the determined welding model to be welded, to form a welding process task package and issue it.

Images