Ship part machining process reasoning method and system based on knowledge graph

Abstract

The invention provides a ship part machining process reasoning method and system based on a knowledge graph. The method comprises the following steps: establishing a machining process knowledge graph database; the machining technology knowledge graph database comprises part attribute data, machining data and incidence relation data set between the part attribute data and the machining data; traversing part attribute data in the design model, and storing the part attribute data in a part attribute database; a part needing to be machined is determined, and a machining process reasoning request is established; and in response to the machining process reasoning request, extracting part attribute data from the part attribute database, and obtaining machining data corresponding to the current part based on the machining process knowledge graph database. According to the method, the problem of information islands between the design content and the design object is solved through the constructed machining technology knowledge graph database, tight coupling of the part attribute data and the machining data is achieved, the machining data is obtained through automatic reasoning based on the part attribute data, and the standardization degree and the design efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of ship parts machining, and more specifically, to a ship parts machining process reasoning method and system based on a knowledge graph. Background Art

[0002] The machining process of hull parts mainly refers to the allowance process and shrinkage process that affect the contour of the parts.

[0003] In the traditional mode, the process of part allowance and shrinkage is mainly reflected in the precision layout diagram, which is often drawn based on the data of the mother ship and on-site construction experience. When designers are designing the process of allowance and shrinkage, they need to check the precision layout diagram repeatedly, which leads to low process design efficiency and accuracy. Summary of the invention

[0004] The purpose of this application is to provide a method and system for reasoning about the machining process of ship parts based on a knowledge graph. By constructing a machining process knowledge graph library, it solves the problem of information islands between design content and design objects, realizes the tight coupling of part attribute data and machining data, and realizes automatic reasoning based on part attribute data to obtain machining data, thereby improving the degree of standardization and design efficiency.

[0005] In the first aspect, a ship parts machining process reasoning method based on knowledge graph is provided, including:

[0006] S1. Establish a machining process knowledge graph library; the machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between part attribute data and machining data;

[0007] S2, traversing the part attribute data in the design model and storing them in a part attribute database;

[0008] S3, determining the parts that need to be machined, and establishing a machining process reasoning request for the current parts;

[0009] S4. In response to a machining process reasoning request, extract part attribute data of the current part from a part attribute database, and obtain machining data corresponding to the current part based on a machining process knowledge graph library.

[0010] In an implementable solution, the part attribute data includes at least ship type information, region information, part boundary position, and component type information;

[0011] Machining data includes allowance value, allowance type, shrinkage direction and shrinkage amount.

[0012] In an practicable solution, in step S1, based on the machining process knowledge of historical parts, the association relationship data between the part attribute data and the machining data of the same part is established:

[0013] The associated relationship data includes excess process format data and shrinkage process format data;

[0014] The margin process format data includes ship type information, area information, part boundary position, and the corresponding bound margin value and margin type;

[0015] The shrinkage process format data includes ship type information, area information, component type information, and the shrinkage direction and shrinkage amount bound to it.

[0016] In an practicable solution, in step S1, the step of establishing a machining process knowledge graph library further includes:

[0017] A rule-based reasoning model is established and stored in the machining process knowledge graph library. The rule-based reasoning model uses the allowance process format data and shrinkage process format data in the machining process knowledge graph library as parameter basis, and transforms the previous process of manually determining the machining process of curved parts into a process of automatically searching for corresponding allowance values, allowance types, shrinkage directions and shrinkage amounts based on ship shape information, area information, part boundary positions and component type information.

[0018] In an practicable solution, in step S1, the step of establishing a machining process knowledge graph library further includes:

[0019] Taking the ship type information, area information, part boundary position, and component type information in the machining process knowledge graph library as input, and the corresponding allowance value, allowance type, shrinkage direction, and shrinkage amount as output, a training data set is constructed. The part machining process inference model is trained through machine learning methods and stored in the machining process knowledge graph library.

[0020] In an implementable solution, in step S4, in response to the machining process reasoning request, the step of extracting part attribute data of the current part from the part attribute database, and obtaining machining data corresponding to the current part based on the machining process knowledge graph library includes:

[0021] S41, in response to the machining process reasoning request, extracting part attribute data of the current part from the part attribute database;

[0022] S42, input the extracted part attribute data into the rule reasoning model; if the corresponding machining data is obtained, then end; if the machining data is not obtained, proceed to the next step;

[0023] S43, inputting the extracted part attribute data into the machining process reasoning model, and then determining the machining data through machine learning training;

[0024] S44, adding the extracted part attribute data and the final confirmed machining data into the training data set, and updating and training the machining process reasoning model.

[0025] In an implementable solution, the ship parts machining process reasoning method based on knowledge graph also includes:

[0026] S5, binding the machining data obtained in step S4 with the part model, and storing them in a part machining process database;

[0027] S6. Determine all parts to be processed, extract machining data bound to the current part model from the part machining process database, form a part machining process task package and send it out.

[0028] In an implementable solution, the ship type information is the ship type to which the part belongs, including at least a container ship, a gas ship, and a car roll-on / roll-off ship;

[0029] The area information is the installation area of ​​the part, including at least the cargo hold, engine room, bow, stern, and upper structure;

[0030] The part boundary position includes the position of the part boundary in the X-axis direction, the Y-axis direction, and the Z-axis direction;

[0031] The component type information is the assembly to which the part belongs, including at least bracket assembly, deck assembly, inner bottom assembly, horizontal girder assembly, and box assembly;

[0032] The allowance type is based on the compensation amount that occurs at each stage from machining to assembly of the part, and the allowance value is a specific numerical value;

[0033] The shrinking directions include X direction, Y direction, and Z direction, and the shrinking amounts include shrinking amount values ​​in the X direction, Y direction, and Z direction.

[0034] In the second aspect, a ship parts machining process reasoning system based on knowledge graph is also provided, including a building module, an acquisition module, a storage module, a request module and a reasoning module;

[0035] The establishment module is used to establish a machining process knowledge graph library; the machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between the part attribute data and the machining data;

[0036] The acquisition module is used to traverse the part attribute data in the design model and store it in a part attribute database;

[0037] The storage module is used to store at least a machining process knowledge graph library and a part attribute database;

[0038] The request module is used to determine the parts that need to be machined and establish the machining process reasoning request for the current part;

[0039] The reasoning module is used to respond to the machining process reasoning request, extract the part attribute data of the current part from the part attribute database, and obtain the machining data corresponding to the current part based on the machining process knowledge graph library.

[0040] In an implementable solution, the ship parts machining process reasoning system based on knowledge graph also includes an output module, a sorting module, and a task issuing module;

[0041] The output module is used to send out the inferred machining data;

[0042] The sorting module is used to receive the machining data sent by the output module, bind the machining data with the part model, and store them in a part machining process database; the part machining process database is stored in the storage module;

[0043] The task issuing module is used to determine all the parts to be processed, extract the machining data bound to the current part model from the part machining process database, form a part machining process task package and issue it.

[0044] Compared with the prior art, the beneficial effects of this application include at least:

[0045] The ship parts machining 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 machining process knowledge graph library, and realizes the tight coupling of part attribute data and machining data. And based on the machining process reasoning request, with known part attribute data and through the machining process knowledge graph library, the corresponding machining data can be automatically inferred, which improves the design efficiency of the machining process of the part and helps to improve the efficiency of ship production and construction. At the same time, the automatic reasoning process, based on the standard data of the machining process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original design of part machining process based on empirical data, and help to obtain relatively more accurate machining data, which is beneficial to improve the subsequent machining quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] Figure 1 It is a flowchart of a first method for reasoning about machining process of ship parts based on knowledge graph according to an embodiment of the present application;

[0048] Figure 2 It is a flowchart of a second method for reasoning about machining process of ship parts based on knowledge graph according to an embodiment of the present application;

[0049] Figure 3 It is a structural schematic diagram of a ship parts machining process reasoning system based on a knowledge graph according to an embodiment of the present application;

[0050] Figure 4 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] 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.

[0052] 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.

[0053] like Figure 1 As shown, the embodiment of the present application first provides a ship parts machining process reasoning method based on a knowledge graph, including:

[0054] S1. Establish a machining process knowledge graph library; the machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between part attribute data and machining data;

[0055] S2, traversing the part attribute data in the design model and storing them in a part attribute database;

[0056] S3, determining the parts that need to be machined, and establishing a machining process reasoning request for the current parts;

[0057] S4. In response to a machining process reasoning request, extract part attribute data of the current part from a part attribute database, and obtain machining data corresponding to the current part based on a machining process knowledge graph library.

[0058] The ship parts machining 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 machining process knowledge graph library, and realizes the tight coupling of part attribute data and machining data. And based on the machining process reasoning request, with known part attribute data and through the machining process knowledge graph library, the corresponding machining data can be automatically inferred, which improves the design efficiency of the machining process of the part and helps to improve the efficiency of ship production and construction. At the same time, the automatic reasoning process, based on the standard data of the machining process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original design of part machining process based on empirical data, and help to obtain relatively more accurate machining data, which is beneficial to improve the subsequent machining quality.

[0059] In one embodiment, the part attribute data may include at least ship type information, region information, part boundary position, and component type information, and the machining data may include at least margin value, margin type, shrinkage direction, and shrinkage amount.

[0060] In one embodiment, the ship type information is the ship type to which the part belongs, which may include at least a container ship, a gas ship, and a car roll-on / roll-off ship;

[0061] The area information is the installation area of ​​the part, including at least the cargo hold, engine room, bow, stern, and upper structure;

[0062] The part boundary position includes the position of the part boundary in the X-axis direction, the Y-axis direction, and the Z-axis direction;

[0063] The component type information is the assembly to which the part belongs, including at least bracket assembly, deck assembly, inner bottom assembly, horizontal girder assembly, and box assembly;

[0064] The allowance type is based on the compensation that occurs at each stage from processing to assembly of the part, such as welding compensation, process A stage compensation, process B stage compensation, process C stage compensation, process P stage compensation, process E stage compensation, process Z stage compensation, processing compensation, etc. The allowance value is a specific numerical value;

[0065] The shrinking directions include X direction, Y direction, and Z direction, and the shrinking amounts include shrinking amount values ​​in the X direction, Y direction, and Z direction.

[0066] In one embodiment, in step S1, based on the machining process knowledge of historical parts, the association relationship data between the part attribute data and the machining data of the same part is established:

[0067] The associated relationship data includes excess process format data and shrinkage process format data;

[0068] The margin process format data includes ship type information, area information, part boundary position, and the corresponding bound margin value and margin type;

[0069] The shrinkage process format data includes ship type information, area information, component type information, and the shrinkage direction and shrinkage amount bound to it.

[0070] For example, a margin process format data may be represented as shown in FIG1 .

[0071] Table 1 Process format data example table

[0072] Ship Type area Part boundary location Allowance value (mm) Margin Type box ship cargo hold FR63+, BL14-, DK3200- h Welding compensation

[0073] FR63+, BL14-, and DK3200- in Table 1 represent the positions of the part boundary in the X-axis direction, the Y-axis direction, and the Z-axis direction, respectively, where FRXX represents the position of the part boundary in the X-axis direction, BLXX represents the position of the part boundary in the Y-axis direction, and DKXX represents the position of the part boundary in the Z-axis direction; where "+" and "-" represent the positive and negative directions of the boundary in each coordinate direction.

[0074] For another example, a reduced volume process format data may be represented as shown in Figure 2.

[0075] Table 2 Example of shrinkage process format data

[0076] Ship Type area Part Type Shrinkage direction Shrinkage(mm) box ship cargo hold Deck assembly X direction, Y direction, Z direction m, n, p

[0077] Among them, m, n, and p in Table 2 represent the shrinkage amounts along the X direction, the Y direction, and the Z direction, respectively. The shrinkage direction may be only one direction or multiple directions, and the shrinkage amounts in each direction may be the same or different.

[0078] In one embodiment, in step S1, the step of establishing a machining process knowledge graph library may also include:

[0079] A rule-based reasoning model is established and stored in the machining process knowledge graph library. The rule-based reasoning model uses the allowance process format data and shrinkage process format data in the machining process knowledge graph library as parameter basis, and transforms the previous process of manually determining the machining process of curved parts into a process of automatically searching for corresponding allowance values, allowance types, shrinkage directions and shrinkage amounts based on ship shape information, area information, part boundary positions and component type information.

[0080] In one embodiment, in step S1, the step of establishing a machining process knowledge graph library may also include:

[0081] Taking the ship type information, area information, part boundary position, and component type information in the machining process knowledge graph library as input, and the corresponding allowance value, allowance type, shrinkage direction, and shrinkage amount as output, a training data set is constructed. The part machining process inference model is trained through machine learning methods and stored in the machining process knowledge graph library.

[0082] In one embodiment, in step S4, in response to the machining process reasoning request, the step of extracting part attribute data of the current part from the part attribute database, and obtaining machining data corresponding to the current part based on the machining process knowledge graph library includes:

[0083] S41, in response to the machining process reasoning request, extracting part attribute data of the current part from the part attribute database;

[0084] S42, input the extracted part attribute data into the rule reasoning model; if the corresponding machining data is obtained, then end; if the machining data is not obtained (it can be judged manually or multiple threshold parameters are set to judge whether some parameter values ​​in the machining data meet the corresponding threshold parameters), then proceed to the next step;

[0085] S43, inputting the extracted part attribute data into the machining process reasoning model, and then determining the machining data through machine learning training;

[0086] S44, adding the extracted part attribute data and the final confirmed machining data into the training data set, and updating and training the machining process reasoning model.

[0087] In the above steps, by combining the rule reasoning model and the machine learning method training reasoning, it is possible to find the existing standard machining data in the machining process knowledge map library as much as possible. When there is no corresponding part attribute data in the library and the ideal machining data cannot be obtained, the machine learning method can be used to train and infer new part attribute data and machining data to meet the machining process design requirements. It can be seen that this method ensures that the corresponding machining data can be obtained in the end through the dual reasoning mode.

[0088] In one embodiment, if Figure 2 As shown, the ship parts machining process reasoning method based on knowledge graph can also include:

[0089] S5, binding the machining data obtained in step S4 with the part model, and storing them in a part machining process database;

[0090] S6. Determine all parts to be processed, extract machining data bound to the current part model from the part machining process database, form a part machining process task package and send it out.

[0091] like Figure 3 As shown, the embodiment of the present application also provides a ship parts machining process reasoning system based on knowledge graph, including an establishment module 10, an acquisition module 20, a storage module 30, a request module 40 and a reasoning module 50;

[0092] The establishment module 10 is used to establish a machining process knowledge graph library; the machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between the part attribute data and the machining data;

[0093] The acquisition module 20 is used to traverse the part attribute data in the design model and store it in a part attribute database;

[0094] The storage module 30 is used to store at least a machining process knowledge graph library and a part attribute database;

[0095] The request module 40 is used to determine the part that needs to be machined and establish a machining process reasoning request for the current part;

[0096] The reasoning module 50 is used to respond to a machining process reasoning request, extract part attribute data of the current part from the part attribute database, and obtain machining data corresponding to the current part based on the machining process knowledge graph library.

[0097] In one embodiment, if Figure 3 As shown, the ship parts machining process reasoning system based on knowledge graph also includes an output module 60, a sorting module 70, and a task issuing module 80;

[0098] The output module 60 is used to send out the inferred machining data;

[0099] The sorting module 70 is used to receive the machining data sent by the output module 60, bind the machining data with the part model, and store it in a part machining process database; the part machining process database is stored in the storage module 30;

[0100] The task issuing module 80 is used to determine all parts to be processed, extract machining data bound to the current part model from the part machining process database, form a part machining process task package and issue it.

[0101] 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.

[0102] 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 ship parts machining process reasoning method based on the knowledge graph.

[0103] Corresponding to the above method embodiments, 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 embodiment of the ship parts machining process reasoning method based on the knowledge graph are implemented.

[0104] 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.

[0105] Corresponding to the above method embodiment, the present application also provides a computer program product. When the instructions in the computer program product are executed by the processor, the steps shown in the embodiment of the ship parts machining process reasoning method based on the knowledge graph are implemented.

[0106] 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 ship parts machining process reasoning method based on knowledge graph, characterized in that: include: S1. Establish a machining process knowledge graph library; The machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between the part attribute data and the machining data; S2, traversing the part attribute data in the design model and storing them in a part attribute database; S3, determining the parts that need to be machined, and establishing a machining process reasoning request for the current parts; S4. In response to a machining process reasoning request, extract part attribute data of the current part from a part attribute database, and obtain machining data corresponding to the current part based on a machining process knowledge graph library.

2. The ship parts machining process reasoning method based on knowledge graph according to claim 1 is characterized in that: The part attribute data at least includes ship type information, area information, part boundary position, and component type information; The machining data includes an allowance value, an allowance type, a shrinkage direction, and a shrinkage amount.

3. The ship parts machining process reasoning method based on knowledge graph according to claim 2 is characterized in that: In step S1, based on the machining process knowledge of historical parts, the association relationship data between the part attribute data and the machining data of the same part is established: The association relationship data includes surplus process format data and shrinkage process format data; The margin process format data includes ship type information, area information, part boundary position, and the corresponding bound margin value and margin type; The shrinkage process format data includes ship type information, area information, component type information, and the shrinkage direction and shrinkage amount bound thereto.

4. The ship parts machining process reasoning method based on knowledge graph according to claim 3 is characterized in that: In step S1, the step of establishing a machining process knowledge graph library also includes: A rule-based reasoning model is established and stored in a machining process knowledge graph library. The rule-based reasoning model uses the allowance process format data and the shrinkage process format data in the machining process knowledge graph library as parameter basis, and transforms the previous process of manually determining the machining process of curved parts into a process of automatically searching for corresponding allowance values, allowance types, shrinkage directions, and shrinkage amounts based on ship shape information, area information, part boundary positions, and component type information.

5. The ship parts machining process reasoning method based on knowledge graph according to claim 4 is characterized in that: In step S1, the step of establishing a machining process knowledge graph library also includes: Taking the ship type information, area information, part boundary position, and component type information in the machining process knowledge graph library as input, and the corresponding allowance value, allowance type, shrinkage direction, and shrinkage amount as output, a training data set is constructed. The part machining process inference model is trained through machine learning methods and stored in the machining process knowledge graph library.

6. The ship parts machining process reasoning method based on knowledge graph according to claim 5 is characterized in that: In step S4, in response to the machining process reasoning request, the step of extracting part attribute data of the current part from the part attribute database, and obtaining machining data corresponding to the current part based on the machining process knowledge graph library includes: S41, in response to the machining process reasoning request, extracting part attribute data of the current part from the part attribute database; S42, input the extracted part attribute data into the rule reasoning model; if the corresponding machining data is obtained, then end; if the machining data is not obtained, proceed to the next step; S43, inputting the extracted part attribute data into the machining process reasoning model, and then determining the machining data through machine learning training; S44, adding the extracted part attribute data and the final confirmed machining data into the training data set, and updating and training the machining process reasoning model.

7. The ship parts machining process reasoning method based on knowledge graph according to claim 1 is characterized in that: Also includes: S5, binding the machining data obtained in step S4 with the part model, and storing them in a part machining process database; S6. Determine all parts to be processed, extract machining data bound to the current part model from the part machining process database, form a part machining process task package and send it out.

8. The ship parts machining process reasoning method based on knowledge graph according to claim 2 is characterized in that: The ship type information is the ship type to which the part belongs, including at least a container ship, a gas ship, and a car roll-on / roll-off ship; The area information is the installation area of ​​the part, including at least the cargo hold, engine room, bow, stern, and upper structure; The part boundary position includes the position of the part boundary in the X-axis direction, the Y-axis direction, and the Z-axis direction; The component type information is the assembly to which the part belongs, including at least bracket assembly, deck assembly, inner bottom assembly, horizontal girder assembly, and box assembly; The allowance type is based on the compensation amount that occurs at various stages from machining to assembly of the part, and the allowance value is a specific numerical value; The shrinking directions include an X direction, a Y direction, and a Z direction, and the shrinking amounts include shrinking amount values ​​in the X direction, the Y direction, and the Z direction.

9. A ship parts machining process reasoning system based on knowledge graph, characterized in that: It includes a building module (10), an acquisition module (20), a storage module (30), a request module (40) and an inference module (50); The establishment module (10) is used to establish a machining process knowledge graph library; the machining process knowledge graph library includes part attribute data and machining data, and also includes association relationship data set between the part attribute data and the machining data; The acquisition module (20) is used to traverse the part attribute data in the design model and store it in a part attribute database; The storage module (30) is used to store at least a machining process knowledge graph library and a part attribute database; The request module (40) is used to determine the part that needs to be machined and establish a machining process reasoning request for the current part; The reasoning module (50) is used to extract part attribute data of the current part from the part attribute database in response to a machining process reasoning request, and obtain machining data corresponding to the current part based on a machining process knowledge graph library.

10. The ship parts machining process reasoning system based on knowledge graph according to claim 9 is characterized in that: It also includes an output module (60), a sorting module (70), and a task issuing module (80); The output module (60) is used to send out the inferred machining data; The sorting module (70) is used to receive the machining data sent by the output module (60), bind the machining data with the part model, and store them in a part machining process database; the part machining process database is stored in the storage module (30); The task issuing module (80) is used to determine all parts to be processed, extract machining data bound to the current part model from the part machining process database, form a part machining process task package and issue it.

Images