Ship bent plate forming process generation method and system based on knowledge graph

Abstract

The invention provides a ship curved plate forming process generation method and system based on a knowledge graph. The method comprises the steps that a curved plate forming process knowledge graph database is established; wherein the data comprise bent plate data, forming equipment data and process relation data set between the bent plate data and the forming equipment data; traversing the curved plate model, obtaining all curved plate data and storing the data into a curved plate model information base; a bent plate needing to be subjected to a forming process is determined, and a forming process reasoning request of the current bent plate is established; and in response to a curved plate forming process reasoning request, curved plate data are extracted from the curved plate model information library, and forming equipment data and process relation data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library. According to the method, tight coupling of the bent plate data, the forming equipment data and the process relation data is achieved through the constructed bent plate forming process knowledge graph database, the forming equipment data and the process relation data are obtained through automatic reasoning based on the bent plate data, and the bent plate design standardization degree and design efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of ship curved plate forming, and specifically, to a method and system for generating a ship curved plate forming process based on a knowledge graph. Background Art

[0002] The process design flow of ship curved plate forming is mainly based on the curved plate part design model, which is unfolded through the lofting and unfolding tool to provide drawings for the cutting of curved plate parts, and the processing datum reference lines are marked on the cut parts. Then, based on the material, curvature radius, size and thickness of the curved plate parts, according to theoretical analysis and processing operation experience, the part forming processing technology is executed, and the accuracy of the processed parts is tested through samples and sample boxes.

[0003] The ship curved plate forming is more difficult than other industries. In terms of part size, the maximum curved part size can exceed more than 10 meters, and the processing process has high requirements for the feeding method, processing equipment, and processing site; in terms of part type, the outer plate of the hull structure has a large linear variation, and the separated parts include saddle-shaped, sail-shaped, hyperbolic, spherical, conical, cylindrical and other types of complex ship outer plate parts; in terms of processing methods, the processing of curved parts includes hot and cold processing; in terms of forming equipment, it covers three-core rollers, hydraulic presses, CNC plate bending machines, oxyacetylene water and fire plate bending, etc.

[0004] However, there is currently a lack of effective management measures for ship forming process knowledge. On-site process execution is mainly based on the curved processing drawing, which is out of touch with the three-dimensional process design model. In addition, the process execution process relies more on the operating experience of the construction personnel. There is a large gap in the processing efficiency and results completed by different process executors. Summary of the invention

[0005] The purpose of this application is to provide a method and system for generating a ship curved plate forming process based on a knowledge graph. By constructing a curved plate forming process knowledge graph library, the method solves the information island problem between design content and design objects, realizes the tight coupling of curved plate data with forming equipment data and process relationship data, and realizes automatic reasoning based on curved plate data to obtain forming equipment data and process relationship data, thereby improving the degree of standardization and design efficiency.

[0006] In a first aspect, a method for generating a ship curved plate forming process based on a knowledge graph is provided, comprising:

[0007] S1. Establish a knowledge graph library of curved plate forming process; the knowledge graph library of curved plate forming process includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data;

[0008] S2, traversing the curved plate models in the design model, obtaining the curved plate data of all the curved plates and storing them in a curved plate model information library;

[0009] S3, determining the curved plate that needs to be formed, and establishing a forming process reasoning request for the current curved plate;

[0010] S4. In response to the curved plate forming process reasoning request, the curved plate data of the current curved plate is extracted from the curved plate model information library, and the forming equipment data and process relationship data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library.

[0011] In an practicable solution, in step S1, the step of establishing a knowledge graph library of curved plate forming process includes:

[0012] S11. Construct a model layer of the knowledge graph library of the curved plate forming process; the curved plate data and the forming equipment data are stored in the entity type data format, and the process relationship data are stored in the relationship type data format; the curved plate and the forming equipment are collectively referred to as entities;

[0013] The entity type data format is:

[0014] Entity_i={E-ID, E-Name, E-Attributes1, E-Attributes2,…};

[0015] Among them, Entity_i represents the i-th entity data;

[0016] E-ID is the bending plate number or molding equipment number, which specifies the unique identification of the entity in the world;

[0017] E-Name represents the name of the curved plate or the name of the forming equipment;

[0018] E-Attributes represent the attribute information of the curved plate or forming equipment;

[0019] The relationship type data format is:

[0020] Relationship_i={R-ID, R-Name, E-IDi, E-IDj, R-Attributes1, R-Attributes2,…}

[0021] Among them, Relationship_i represents the i-th process relationship data

[0022] R-ID is the process relationship number, which specifies the unique identifier of the process relationship in the world;

[0023] R-Name is the process relationship name;

[0024] E-IDi and E-IDj are the numbers of the two entities associated with this relationship, and the direction of the relationship is defined as from entity E-IDi to entity E-IDj;

[0025] R-Attributei represents the attribute information of the relationship;

[0026] S12. Constructing the data layer of the knowledge graph library of the curved plate forming process; including:

[0027] Based on the historical knowledge of curved plate forming process, the curved plate data, forming equipment data and process relationship data are extracted, and each data is stored in the data format of the model layer;

[0028] S13. Construct a curved plate process case library in the curved plate forming process knowledge graph library; take the curved plate data, forming equipment data and process relationship data extracted for a curved plate forming process knowledge in step S12 as a curved plate process case, and store it in the curved plate process case library.

[0029] In an practicable solution, in step S1, the step of establishing a knowledge graph library of the curved plate forming process further includes:

[0030] S14. Establish a rule-based reasoning model and store it in the knowledge graph library of the curved plate forming process. The rule-based reasoning model uses the process relationship data in the knowledge graph library of the curved plate forming process as a parameter basis, and transforms the previous process of manually determining the curved plate forming process into a process of automatically searching for corresponding forming equipment data and process relationship data from the curved plate data.

[0031] In an practicable solution, in step S1, the step of establishing a knowledge graph library of the curved plate forming process further includes:

[0032] S15. Using the curved plate data extracted in step S12 as input and the forming equipment data and process relationship data as output, a training data set is constructed, and a curved plate process reasoning model is obtained through training using a machine learning method, and the model is stored in a curved plate forming process knowledge graph library.

[0033] In an implementable solution, in step S4, in response to the curved plate forming process reasoning request, the curved plate data of the current curved plate is extracted from the curved plate model information library, and the forming equipment data and process relationship data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library, including:

[0034] S41, in response to the curved plate forming process reasoning request, extracting the curved plate data of the current curved plate from the curved plate model information library;

[0035] S42, based on the curved plate data, searching in the curved plate process case library whether there is a similar curved plate process case; if there is a similar case, extracting the molding equipment data and process relationship data of the similar curved plate process case, verifying and confirming the molding equipment data and process relationship data to obtain the finalized molding equipment data and process relationship data, and storing the current curved plate data and the corresponding molding equipment data and process relationship data as a new curved plate process case in the curved plate process case library; if there is no similar case, proceeding to the next step;

[0036] S43, using the extracted curved plate data as a parameter basis, inputting it into the rule reasoning model; if the molding equipment data and process relationship data are obtained, then the process ends; if the molding equipment data and process relationship data are not obtained, then proceed to the next step;

[0037] S44, inputting the extracted curved plate data into the curved plate process reasoning model, and then determining the molding equipment data and process relationship data through machine learning training;

[0038] S45, adding the extracted curved plate data and the finally confirmed forming equipment data and process relationship data into the training data set, and updating and training the curved plate process reasoning model.

[0039] In an implementable solution, the method for generating a ship curved plate forming process based on a knowledge graph further includes:

[0040] S5, binding the forming equipment data and process relationship data obtained in step S4 to the curved plate model, and storing them in a curved plate model process database;

[0041] S6. Determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and send it out.

[0042] In an implementable solution, the curved plate data at least includes a curved plate number, a curved plate name and curved plate attribute information, and the curved plate attribute information at least includes curved plate material information, thickness information, curved surface type information, curved plate length information, curved plate height information, curvature radius information, and plate thickness curvature radius ratio information;

[0043] The molding equipment data at least includes the molding equipment number, the molding equipment name and the molding equipment attribute information, and the molding equipment attribute information at least includes various standard parameters of the equipment;

[0044] The process relationship data at least includes the process relationship name, the curved plate number, the forming equipment number, and also includes the processing parameters involved in the forming of the curved plate by the forming equipment.

[0045] In the second aspect, a ship curved plate forming process generation system based on a knowledge graph is also provided, including a building module, an acquisition module, a storage module, a request module and a reasoning module;

[0046] The establishment module is used to establish a knowledge graph library of curved plate forming process; the knowledge graph library of curved plate forming process includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data;

[0047] The acquisition module is used to traverse the curved plate models in the design model, acquire the curved plate data of all curved plates and store them in a curved plate model information library;

[0048] The storage module is used to store at least a knowledge graph library of curved plate forming process and a curved plate model information library;

[0049] The request module is used to determine the curved plate that needs to be formed and to establish a forming process reasoning request for the current curved plate;

[0050] The reasoning module is used to respond to the curved plate forming process reasoning request, extract the curved plate data of the current curved plate from the curved plate model information library, and obtain the forming equipment data and process relationship data corresponding to the current curved plate based on the curved plate forming process knowledge graph library.

[0051] In an implementable solution, the ship curved plate forming process generation system based on the knowledge graph also includes an output module, a sorting module, and a task issuing module;

[0052] The output module is used to send out the inferred molding equipment data and process relationship data;

[0053] The sorting module is used to receive the molding equipment data and process relationship data sent by the output module, and bind the molding equipment data and process relationship data with the curved plate model, and store them in a curved plate model process database; the curved plate model process database is stored in the storage module;

[0054] The task issuing module is used to determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and issue it.

[0055] Compared with the prior art, the beneficial effects of this application include at least:

[0056] The ship curved plate forming process generation method based on the knowledge graph of the present application solves the information island problem between the design content and the design object based on the constructed curved plate forming process knowledge graph library, and realizes the tight coupling of the curved plate data with the forming equipment data and the process relationship data. And based on the forming process reasoning request, with the known curved plate data and through the curved plate forming process knowledge graph library, the corresponding forming equipment data and process relationship data can be automatically inferred, which improves the design efficiency of the curved plate forming process 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 curved plate forming process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original design of the curved plate forming process based on empirical data, and help to obtain relatively more accurate forming equipment data and process relationship data, which is beneficial to improve the subsequent curved plate forming quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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.

[0058] Figure 1 It is a flowchart of a first method for generating a ship curved plate forming process based on a knowledge graph according to an embodiment of the present application;

[0059] Figure 2 It is a flow chart of a second method for generating a ship curved plate forming process based on a knowledge graph according to an embodiment of the present application;

[0060] Figure 3 A schematic diagram of a reasoning process based on a rule-based reasoning model according to an embodiment of the present application;

[0061] Figure 4 It is a structural schematic diagram of a ship curved plate forming process generation system based on a knowledge graph according to an embodiment of the present application;

[0062] Figure 5 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0063] 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.

[0064] 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.

[0065] like Figure 1 As shown, the present application first provides a method for generating a ship curved plate forming process based on a knowledge graph, comprising:

[0066] S1. Establish a knowledge graph library of curved plate forming process; the knowledge graph library of curved plate forming process includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data;

[0067] S2, traversing the curved plate models in the design model, obtaining the curved plate data of all the curved plates and storing them in a curved plate model information library;

[0068] S3, determining the curved plate that needs to be formed, and establishing a forming process reasoning request for the current curved plate;

[0069] S4. In response to the curved plate forming process reasoning request, the curved plate data of the current curved plate is extracted from the curved plate model information library, and the forming equipment data and process relationship data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library.

[0070] The ship curved plate forming process generation method based on the knowledge graph of the present application solves the information island problem between the design content and the design object based on the constructed curved plate forming process knowledge graph library, and realizes the tight coupling of the curved plate data with the forming equipment data and the process relationship data. And based on the forming process reasoning request, with the known curved plate data and through the curved plate forming process knowledge graph library, the corresponding forming equipment data and process relationship data can be automatically inferred, which improves the design efficiency of the curved plate forming process 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 curved plate forming process knowledge graph library, can overcome the problems of low efficiency and low accuracy of the original design of the curved plate forming process based on empirical data, and help to obtain relatively more accurate forming equipment data and process relationship data, which is beneficial to improve the subsequent curved plate forming quality.

[0071] At the same time, the previous experience-based design of the curved plate forming process may also lead to redundancy of the forming process knowledge. The method of this application can improve the reusability and ease of use of the curved plate forming process knowledge and establish a theoretical model guarantee.

[0072] In one embodiment, the curved plate data may at least include the curved plate number, the curved plate name and the curved plate attribute information, etc. The curved plate attribute information may at least include the curved plate material information, thickness information, surface type information, curved plate length information, curved plate height information, curvature radius information, plate thickness curvature radius ratio information, etc.

[0073] In one embodiment, the molding equipment data may at least include the molding equipment number, the molding equipment name and the molding equipment attribute information, and the molding equipment attribute information at least includes various standard parameters of the equipment, such as the purpose or type of equipment, maximum processing thickness, rolling gap, pressing force, etc.

[0074] In one embodiment, the process relationship data may include at least the process relationship name, the curved plate number, the molding equipment number, and also the processing parameters involved in the curved plate molding by the molding equipment, such as the priority and processing parameters of the equipment used.

[0075] In one embodiment, in step S1, the step of establishing a knowledge graph library of curved plate forming process includes:

[0076] S11. Construct a model layer of the knowledge graph library of the curved plate forming process; the curved plate data and the forming equipment data are stored in the entity type data format, and the process relationship data are stored in the relationship type data format; the curved plate and the forming equipment are collectively referred to as entities;

[0077] The entity type data format is:

[0078] Entity_i={E-ID, E-Name, E-Attributes1, E-Attributes2,…};

[0079] Among them, Entity_i represents the i-th entity data;

[0080] E-ID is the bending plate number or molding equipment number, which specifies the unique identification of the entity in the world;

[0081] E-Name represents the name of the curved plate or the name of the forming equipment;

[0082] E-Attributes represent the attribute information of the curved plate or forming equipment;

[0083] The relationship type data format is:

[0084] Relationship_i={R-ID, R-Name, E-IDi, E-IDj, R-Attributes1, R-Attributes2,…}

[0085] Among them, Relationship_i represents the i-th process relationship data

[0086] R-ID is the process relationship number, which specifies the unique identifier of the process relationship in the world;

[0087] R-Name is the process relationship name;

[0088] E-IDi and E-IDj are the numbers of the two entities associated with this relationship, and the direction of the relationship is defined as from entity E-IDi to entity E-IDj;

[0089] R-Attributei represents the attribute information of the relationship;

[0090] S12. Constructing the data layer of the knowledge graph library of the curved plate forming process; including:

[0091] Based on the historical knowledge of curved plate forming process, the curved plate data, forming equipment data and process relationship data are extracted, and each data is stored in the data format of the model layer;

[0092] S13. Construct a curved plate process case library in the curved plate forming process knowledge graph library; take the curved plate data, forming equipment data and process relationship data extracted for a curved plate forming process knowledge in step S12 as a curved plate process case, and store it in the curved plate process case library.

[0093] To more clearly explain entity type data and relationship type data, the following examples are provided.

[0094] For example, a curved plate has a curved plate number of 001, a curved plate name of curved plate A, and curved plate attribute information including material of steel plate, thickness of 10 mm, size of 2000 mm × 1000 mm, and curvature radius of 500 mm. Then the entity type data of this curved plate can be expressed as: Entity_1 = {001, curved plate A, material = steel plate, thickness = 10 mm, size = 2000 mm × 1000 mm, curvature radius = 500 mm}.

[0095] For another example, the molding equipment number of a molding equipment is 002, the molding equipment name is three-core roller, and the molding equipment attribute information includes: the equipment type is rolling equipment, the maximum processing thickness is 12mm, the rolling gap is 5mm, and the pressing force is 100kN. Then the entity type data of this molding equipment can be expressed as: Entity_2 = {002, three-core roller, equipment type = rolling equipment, maximum processing thickness = 12mm, rolling gap = 5mm, pressing force = 100kN}.

[0096] For another example, in a process relationship data, the process relationship number is 101, the process relationship name is "suitable processing equipment level and parameters", the entity of the associated entity is curved plate A and three-core roller, and the attribute information of the relationship is that among the equipment suitable for processing curved plate A, the priority of the three-core roller is high, and the roller gap is 5mm. Then the process relationship data can be expressed as Relationship_1 = {101, suitable processing equipment level and parameters, 001, 002, priority = high, roller gap = 5mm}.

[0097] In one embodiment, in step S1, the step of establishing a knowledge graph library of curved plate forming process may further include:

[0098] S14. Establish a rule-based reasoning model and store it in the knowledge graph library of the curved plate forming process. The rule-based reasoning model uses the process relationship data in the knowledge graph library of the curved plate forming process as a parameter basis, and transforms the previous process of manually determining the curved plate forming process into a process of automatically searching for corresponding forming equipment data and process relationship data from the curved plate data.

[0099] In one embodiment, in step S1, the step of establishing a knowledge graph library of curved plate forming process may further include:

[0100] S15. Using the curved plate data extracted in step S12 as input and the forming equipment data and process relationship data as output, a training data set is constructed, and a curved plate process reasoning model is obtained through training using a machine learning method, and the model is stored in a curved plate forming process knowledge graph library.

[0101] In one embodiment, in step S4, in response to the curved plate forming process reasoning request, the steps of extracting the curved plate data of the current curved plate from the curved plate model information library, and obtaining the forming equipment data and process relationship data corresponding to the current curved plate based on the curved plate forming process knowledge graph library may include:

[0102] S41, in response to the curved plate forming process reasoning request, extracting the curved plate data of the current curved plate from the curved plate model information library;

[0103] S42, based on the curved plate data, searching in the curved plate process case library whether there is a similar curved plate process case; if there is a similar case, extracting the molding equipment data and process relationship data of the similar curved plate process case, verifying and confirming the molding equipment data and process relationship data to obtain the finalized molding equipment data and process relationship data, and storing the current curved plate data and the corresponding molding equipment data and process relationship data as a new curved plate process case in the curved plate process case library to increase the content of process knowledge and improve the scope of application and accuracy of subsequent reasoning; if there is no similar case, proceeding to the next step;

[0104] S43, see Figure 3 The schematic diagram of the rule reasoning process shown in the figure takes the extracted curved plate data as the parameter basis and inputs it into the rule reasoning model; if the molding equipment data and process relationship data are obtained, the process ends; if the molding equipment data and process relationship data are not obtained (i.e., there is no reasoning result), the next step is carried out;

[0105] S44, inputting the extracted curved plate data into the curved plate process reasoning model, and then determining the molding equipment data and process relationship data through machine learning training;

[0106] S45. Add the extracted curved plate data and the final confirmed forming equipment data and process relationship data into the training data set, and update the curved plate process reasoning model for training. This not only increases the amount of process knowledge content, but also improves the reuse rate of process knowledge through updated training to improve reasoning accuracy.

[0107] The above steps, based on standardized data and established standardized reasoning models, realize standardized reasoning of the forming equipment data and process relationship data corresponding to the curved plate, eliminate the influence of human experience errors as much as possible, improve the efficiency and accuracy of deduction, and increase the probability of successful reasoning and the comprehensiveness of coping with reasoning situations.

[0108] In one embodiment, the ship curved plate forming process generation method may further include:

[0109] S5, binding the forming equipment data and process relationship data obtained in step S4 to the curved plate model, and storing them in a curved plate model process database;

[0110] S6. Determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and send it out.

[0111] like Figure 4As shown, the present application provides a ship curved plate forming process generation system based on a knowledge graph, including a building module 10, an acquisition module 20, a storage module 30, a request module 40 and a reasoning module 50;

[0112] The establishment module 11 is used to establish a knowledge graph library of the curved plate forming process; the knowledge graph library of the curved plate forming process includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data;

[0113] The acquisition module 20 is used to traverse the curved plate models in the design model, acquire the curved plate data of all the curved plates and store them in a curved plate model information library;

[0114] The storage module 30 is at least used to store a curved plate forming process knowledge graph library and a curved plate model information library;

[0115] The request module 40 is used to determine the curved plate that needs to be formed and establish a forming process reasoning request for the current curved plate;

[0116] The reasoning module 50 is used to respond to the curved plate forming process reasoning request, extract the curved plate data of the current curved plate from the curved plate model information library, and obtain the forming equipment data and process relationship data corresponding to the current curved plate based on the curved plate forming process knowledge graph library.

[0117] In one embodiment, if Figure 4 As shown, the ship curved plate forming process generation system based on the knowledge graph may also include an output module 60, a sorting module 70, and a task issuing module 80;

[0118] The output module 60 is used to send out the inferred molding equipment data and process relationship data;

[0119] The sorting module 70 is used to receive the molding equipment data and process relationship data sent by the output module 60, and bind the molding equipment data and process relationship data with the curved plate model, and store them in a curved plate model process database; the curved plate model process database is stored in the storage module 30;

[0120] The task issuing module 80 is used to determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and issue it.

[0121] Corresponding to the above method embodiment, Figure 5 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.

[0122] 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 method for generating a ship curved plate forming process based on a knowledge graph.

[0123] 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 curved plate forming process generation method based on the knowledge graph are implemented.

[0124] 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.

[0125] Corresponding to the above method embodiments, the present application also provides a computer program product. When the instructions in the computer program product are executed by a processor, the steps shown in the embodiment of the method for generating a ship curved plate forming process based on a knowledge graph are implemented.

[0126] 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 method for generating a ship curved plate forming process based on a knowledge graph, characterized in that: include: S1. Establish a knowledge graph library of curved plate forming process; The curved plate forming process knowledge graph library includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data; S2, traversing the curved plate models in the design model, obtaining the curved plate data of all the curved plates and storing them in a curved plate model information library; S3, determining the curved plate that needs to be formed, and establishing a forming process reasoning request for the current curved plate; S4. In response to the curved plate forming process reasoning request, the curved plate data of the current curved plate is extracted from the curved plate model information library, and the forming equipment data and process relationship data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library.

2. The method for generating a ship curved plate forming process based on a knowledge graph according to claim 1, characterized in that: In step S1, the steps of establishing a knowledge graph library of curved plate forming process include: S11. Construct a model layer of the knowledge graph library of the curved plate forming process; the curved plate data and the forming equipment data are stored in the entity type data format, and the process relationship data is stored in the relationship type data format; the curved plate and the forming equipment are collectively referred to as entities; The entity type data format is: Entity_i={E-ID, E-Name, E-Attributes1, E-Attributes2,…}; Among them, Entity_i represents the i-th entity data; E-ID is the bending plate number or molding equipment number, which specifies the unique identification of the entity in the world; E-Name represents the name of the curved plate or the name of the forming equipment; E-Attributes represent the attribute information of the curved plate or forming equipment; The relationship type data format is: Relationship_i={R-ID, R-Name, E-IDi, E-IDj, R-Attributes1, R-Attributes2,…} Among them, Relationship_i represents the i-th process relationship data R-ID is the process relationship number, which specifies the unique identifier of the process relationship in the world; R-Name is the process relationship name; E-IDi and E-IDj are the numbers of the two entities associated with this relationship, and the direction of the relationship is defined as from entity E-IDi to entity E-IDj; R-Attributei represents the attribute information of the relationship; S12. Constructing the data layer of the knowledge graph library of the curved plate forming process; including: Based on the historical knowledge of curved plate forming process, the curved plate data, forming equipment data and process relationship data are extracted, and each data is stored in the data format of the model layer; S13. Construct a curved plate process case library in the curved plate forming process knowledge graph library; take the curved plate data, forming equipment data and process relationship data extracted for a curved plate forming process knowledge in step S12 as a curved plate process case, and store it in the curved plate process case library.

3. The method for generating a ship curved plate forming process based on a knowledge graph according to claim 2, characterized in that: In step S1, the step of establishing a knowledge graph library of curved plate forming process also includes: S14. Establish a rule-based reasoning model and store it in the curved plate forming process knowledge graph library; the rule-based reasoning model uses the process relationship data in the curved plate forming process knowledge graph library as a parameter basis, and transforms the previous process of manually determining the curved plate forming process into a process of automatically searching for corresponding forming equipment data and process relationship data from the curved plate data.

4. The method for generating a ship curved plate forming process based on a knowledge graph according to claim 3 is characterized in that: In step S1, the step of establishing a knowledge graph library of curved plate forming process also includes: S15. Using the curved plate data extracted in step S12 as input and the forming equipment data and process relationship data as output, a training data set is constructed, and a curved plate process reasoning model is obtained through training using a machine learning method, and the model is stored in a curved plate forming process knowledge graph library.

5. The method for generating a ship curved plate forming process based on a knowledge graph according to claim 4 is characterized in that: In step S4, in response to the curved plate forming process reasoning request, the curved plate data of the current curved plate is extracted from the curved plate model information library, and the forming equipment data and process relationship data corresponding to the current curved plate are obtained based on the curved plate forming process knowledge graph library, including: S41, in response to the curved plate forming process reasoning request, extracting the curved plate data of the current curved plate from the curved plate model information library; S42, based on the curved plate data, searching in the curved plate process case library whether there is a similar curved plate process case; if there is a similar case, extracting the molding equipment data and process relationship data of the similar curved plate process case, verifying and confirming the molding equipment data and process relationship data to obtain the finalized molding equipment data and process relationship data, and storing the current curved plate data and the corresponding molding equipment data and process relationship data as a new curved plate process case in the curved plate process case library; if there is no similar case, proceeding to the next step; S43, using the extracted curved plate data as a parameter basis, inputting it into the rule reasoning model; if the molding equipment data and process relationship data are obtained, then the process ends; if the molding equipment data and process relationship data are not obtained, then proceed to the next step; S44, inputting the extracted curved plate data into the curved plate process reasoning model, and then determining the molding equipment data and process relationship data through machine learning training; S45, adding the extracted curved plate data and the finally confirmed forming equipment data and process relationship data into the training data set, and updating and training the curved plate process reasoning model.

6. The method for generating a ship curved plate forming process based on a knowledge graph according to claim 1, characterized in that: Also includes: S5, binding the forming equipment data and process relationship data obtained in step S4 to the curved plate model, and storing them in a curved plate model process database; S6. Determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and send it out.

7. The method for generating a ship curved plate forming process based on a knowledge graph according to any one of claims 1 to 6, characterized in that: The curved plate data at least includes the curved plate number, the curved plate name and the curved plate attribute information, and the curved plate attribute information at least includes the curved plate material information, thickness information, curved surface type information, curved plate length information, curved plate height information, curvature radius information, and plate thickness curvature radius ratio information; The molding equipment data at least includes the molding equipment number, the molding equipment name and the molding equipment attribute information, and the molding equipment attribute information at least includes various standard parameters of the equipment; The process relationship data at least includes a process relationship name, a curved plate number, a molding equipment number, and also includes processing parameters involved in the molding of the curved plate by the molding equipment.

8. A ship curved plate forming process generation 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 (11) is used to establish a knowledge graph library of curved plate forming process; the knowledge graph library of curved plate forming process includes curved plate data and forming equipment data, and also includes process relationship data set between the curved plate data and the forming equipment data; The acquisition module (20) is used to traverse the curved plate models in the design model, acquire the curved plate data of all curved plates and store them in a curved plate model information library; The storage module (30) is used to store at least a curved plate forming process knowledge graph library and a curved plate model information library; The request module (40) is used to determine the curved plate that needs to be formed and to establish a forming process reasoning request for the current curved plate; The reasoning module (50) is used to respond to the curved plate forming process reasoning request, extract the curved plate data of the current curved plate from the curved plate model information library, and obtain the forming equipment data and process relationship data corresponding to the current curved plate based on the curved plate forming process knowledge graph library.

9. The ship curved plate forming process generation system based on knowledge graph according to claim 8 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 molding equipment data and process relationship data; The sorting module (70) is used to receive the molding equipment data and process relationship data sent by the output module (60), bind the molding equipment data and process relationship data with the curved plate model, and store them in a curved plate model process database; the curved plate model process database is stored in the storage module (30); The task issuing module (80) is used to determine all the curved plates to be processed, extract the forming equipment data and process relationship data bound to the current curved plate model from the curved plate model process database, form a curved plate forming process task package and issue it.

Images