Process identification method and system based on model features
By adopting a process identification method based on model features in ship manufacturing, reconstructing the manufacturing assembly structure tree and using classification algorithm models to generate process content, the problem of low process design efficiency in traditional technology is solved, and automated process definition and data link are realized The establishment of the company has improved the accuracy and efficiency of design and construction.
Patent Information
- Application Number
- CN202411021113.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-22
AI Technical Summary
In ship manufacturing, traditional model analysis technology cannot provide information on process methods, resulting in process designers needing to manually select and apply process knowledge, which is time-consuming and error-prone, and lacks the ability to map directly from model features to process methods.
The process identification method based on model features is adopted, and the manufacturing assembly structure tree is reconstructed, the geometric information and attribute information of the component model are extracted, and the classification algorithm model is used for classification recognition, and the manufacturing process content is generated and defined to realize the automated definition of the process.
It greatly shortens the design cycle, reduces manual intervention, improves the accuracy and efficiency of process identification and design, realizes the data link from the design end to the construction site, and improves the process quality.
Smart Images

Figure CN119004660A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of shipbuilding, and in particular, to a process identification method and system based on model features. Background Art
[0002] In traditional manufacturing, especially in the field of shipbuilding, model analysis technology mainly focuses on extracting geometric information, such as size, shape and position relationship, which is crucial for the preliminary stages of the design and manufacturing process. However, a significant limitation of this method is that it cannot provide information about the process method, that is, the specific steps and technologies required to transform the design into an actual product.
[0003] Shipbuilding is a complex process involving multiple processes, each of which may require different process methods and skills. Since the process knowledge between these processes is significantly different, there are huge challenges in process design, knowledge retrieval and matching. The lack of direct mapping capabilities from model features to process methods means that process designers need to manually select and apply appropriate process knowledge, which is time-consuming and error-prone. Therefore, studying the correlation between model features and process knowledge and developing automatic recognition technology based on this correlation are key technical issues that need to be urgently addressed in the current shipbuilding field. Summary of the invention
[0004] The purpose of this application is to provide a process identification method and system based on model features, which solves the problems of low efficiency of structural process design under the existing design model and inability to realize process intelligent design based on the process design model.
[0005] In order to achieve the above objectives, this application adopts the following technical solutions:
[0006] A process identification method based on model features comprises: reconstructing a manufacturing assembly structure tree based on a hull segment model to obtain a reconstructed manufacturing assembly structure tree; parsing the reconstructed manufacturing assembly structure tree and extracting geometric information and attribute information of all component models under the reconstructed manufacturing assembly structure tree; performing classification and identification using a classification algorithm model based on the extracted geometric information and attribute information of all component models and generating corresponding manufacturing process content; and defining the generated manufacturing process content in the corresponding component model.
[0007] In some embodiments, the reconstruction of the manufacturing assembly structure tree based on the hull section model includes: selecting a hull section model; identifying component model information of the hull section model; generating a hierarchical structure of the manufacturing assembly structure tree based on the identified component model information of the hull section model; classifying and reorganizing the identified component models, and assembling them to the corresponding level of the manufacturing assembly structure tree.
[0008] In some implementations, the component model information includes segmented space position, assembly base surface, and assembly type.
[0009] In some embodiments, the geometric information and attribute information of the component model are divided into at least cutting process elements, forming process elements and welding process elements.
[0010] In some embodiments, the cutting process elements include at least part type, category, flow direction, material, thickness, specification, model and joint direction; the forming process elements include at least part type, category, material, thickness, theoretical part height, theoretical part width, theoretical part length, weight, center of gravity, surface type, unfolded part length, unfolded part width, longest part length, curvature radius, ratio of plate thickness to curvature radius; the welding process elements include at least weld stage, joint form, whether it is the same panel, whether it is the main board, panel type, panel size, minimum panel thickness, part processing type, part type, part material, part category, weld length and welding position.
[0011] In some embodiments, based on the extracted geometric information and attribute information of all the component models, a classification algorithm model is used to perform classification and identification and generate corresponding manufacturing process information, including: converting the extracted geometric information and attribute information of all the component models into a standardized data format, calling the classification algorithm model to identify and match the corresponding manufacturing process type; and generating manufacturing process content based on the matching results.
[0012] In some embodiments, the generated manufacturing process content is defined in the corresponding component model, including: mapping the manufacturing process content to the corresponding component model; based on the mapping relationship between the manufacturing process content and the component model, defining the process content combination generated by the manufacturing process content in the corresponding component model.
[0013] The second aspect of the present application provides a process identification system based on model features, including: a reconstruction module, a parsing module, a matching module and a definition module; the reconstruction module is used to reconstruct the manufacturing assembly structure tree based on the hull section model to obtain a reconstructed manufacturing assembly structure tree; the parsing module is used to parse the reconstructed manufacturing assembly structure tree and extract the geometric information and attribute information of all component models under the reconstructed manufacturing assembly structure tree; the matching module is used to use a classification algorithm model to perform classification and identification and generate corresponding manufacturing process content based on the extracted geometric information and attribute information of all component models; the definition module is used to define the generated manufacturing process content in the corresponding component model.
[0014] A third aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program runs on a processor, the processor executes the identification method as described in the first aspect.
[0015] The fourth aspect of the present application provides an electronic device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, when the program stored in the memory is executed, the processor is used to execute the identification method described in the first aspect.
[0016] Compared with the prior art, the present invention has the following advantages:
[0017] The present application provides a process identification method and system based on model features, which realizes quantitative analysis of complex structural three-dimensional models to model geometric feature information by establishing a manufacturing structure relationship tree of structural parts, adopts machine learning methods to obtain the mapping relationship between geometric information, attribute information and manufacturing process methods, and realizes automatic definition of structural manufacturing processes based on the model manufacturing structure relationship tree of complex structures, thereby realizing process identification based on hull segment model features. The intelligent design of the present application not only greatly shortens the design cycle and reduces manual intervention, but also can self-optimize through continuous learning and practice, thereby improving the accuracy and efficiency of process identification and process design. The technical solution of the present application changes the problem of traditional reliance on the experience of process personnel for process operation, and at the same time realizes the direct transmission of the process from the design end to the construction site end based on the model, opening up the data link from design to construction and improving the process quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] 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.
[0019] Figure 1 A schematic flow chart of a process identification method based on model features according to an embodiment of the present application is shown;
[0020] Figure 2 A schematic diagram of the process of reconstructing the manufacturing assembly structure tree in an embodiment of the present application is shown;
[0021] Figure 3 A schematic diagram of a process for using a classification algorithm model to identify and generate manufacturing process content corresponding to a component model in an embodiment of the present application is shown.
[0022] Figure 4A structural schematic diagram of a process identification system based on model features according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0023] The technical solutions of the specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings. These implementation methods are only used to illustrate the present application, but not to limit the present application.
[0024] The term "and / or" in this application is a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In the present invention, the symbol " / " indicates that the associated objects are in an "or" relationship, for example, "A / B" means "A or B".
[0025] The terms "first" and "second" in the specification and claims of this application are used to distinguish different objects rather than to describe a specific order of the objects. For example, "first response message" and "second response message" are used to distinguish different response messages rather than to describe a specific order of the response messages.
[0026] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be considered as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0027] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc., and multiple elements refer to two or more elements, etc.
[0028] A process identification method and system based on model features of the present application are described in detail below in conjunction with the accompanying drawings.
[0029] Figure 1 FIG. 1 is a flow chart of a process identification method based on model features according to an embodiment of the present application. Figure 1 As shown, the process identification method based on model features of the present application includes:
[0030] Step S110, reconstruct the manufacturing assembly structure tree based on the hull segment model to obtain a reconstructed manufacturing assembly structure tree. Specifically, based on the artificial intelligence model, a hull segment model is selected from the design database. The hull segment model is the basis for subsequent analysis and reconstruction, and contains all the information of the hull segment. Then, the hull segment model is deeply analyzed using a pre-trained classification algorithm model. The classification algorithm model can identify the information of components and parts in the hull segment model through machine learning, including key features such as the type, location, material size, and material of the components.
[0031] After identifying the parts information in the hull segment model, a hierarchical structure of the manufacturing assembly structure tree is automatically generated using a machine learning algorithm. In one embodiment, the aforementioned automatically generated hierarchical structure may include two levels: large assembly and medium assembly. The aforementioned manufacturing assembly structure tree takes the segment as the root node, and organizes it into different levels according to the assembly relationship and logical relationship between the parts to reflect the assembly structure between the parts. The identified parts, such as parts and small groups, are classified and reorganized by machine learning, with the purpose of classifying parts and assemblies with similar characteristics or belonging to the same assembly unit together, and reorganizing them according to the hierarchical structure of the manufacturing assembly structure tree for subsequent assembly operations. The classified and reorganized small groups and parts are assembled to the corresponding level of the manufacturing assembly structure tree according to their assembly relationship and hierarchical structure, thus realizing the reconstruction of the manufacturing assembly structure tree. Each node in the manufacturing assembly structure tree represents a component, and each component corresponds to a digital part model.
[0032] In one embodiment, Figure 2 As shown, the process of reconstructing the manufacturing assembly structure tree may include: step S111, selecting the hull segment, and training the manufacturing assembly structure tree generation model through supervised learning according to the segment spatial position, assembly base surface, assembly type and other information, to realize the automatic generation of the manufacturing assembly structure tree and its assembly hierarchy.
[0033] Step S112, add the component model to the generated manufacturing assembly structure tree, search all the plate objects that meet the specific type under the segment through the machine learning model, and obtain the plate position matching the component position in the data. According to the information such as the plate position and component position, determine its uniqueness in the manufacturing assembly structure tree, and find its parent node. Add the matched structural parts such as plates and assemblies to the current assembly node to form a more complete assembly relationship.
[0034] Further, in step S113, the loose parts are processed. The aforementioned loose parts refer to parts that are relatively independent in the assembly process and do not directly belong to a specific assembly. According to the order of the loose parts in the assembly, the loose parts can be divided into segmented external loose parts and segmented internal loose parts. Through the interference between the segmented space and the loose parts calculation, and the use of the machine learning algorithm model to determine the loose parts node name corresponding to the common parent node, the loose parts node is searched or created under the selected segment node, and the loose parts are added to the current loose parts node, completing the reconstruction of the entire manufacturing assembly structure tree.
[0035] Step S120, based on the reconstructed manufacturing assembly structure tree, parse and extract the geometric information and attribute information of all the component models under the manufacturing assembly structure tree, and classify and structure the geometric information and attribute information. Specifically, based on the reconstructed manufacturing assembly structure tree, traverse all the component models under the entire manufacturing assembly structure tree, parse and extract the geometric information and attribute information of the component models. The geometric information includes the size and shape of the parts, and the attribute information includes the material type, heat treatment requirements, etc.
[0036] According to the different component model information that needs to be extracted for different manufacturing processes, the extracted information is classified, which is helpful for the subsequent intelligent identification and optimization of the process. For example, the cutting process pays more attention to the size and shape of the parts, and the welding process pays more attention to the weldability of the material and the form of the welded joint. The extracted and classified component model information may exist in various forms, such as text, numbers, images, etc. In order to facilitate subsequent processing and analysis, the extracted component model information is structured for intelligent identification of the process. For example, the extracted component model information can be converted into a standard format or data structure, and the association and index between the component model information can be established. The component model information after structured processing is easier to manage and use, which provides convenience for subsequent intelligent identification and optimization.
[0037] In one embodiment, the geometric information and attribute information of the aforementioned extracted component model are classified, which mainly includes cutting process elements, forming process elements, and welding process elements. Among them, the cutting process elements include part type, category, flow direction, material, thickness, specification, model joint direction, etc. The forming process elements include part type, category, material, thickness, theoretical part height, theoretical part width, theoretical part length, weight, center of gravity, surface type, unfolded part length, unfolded part width, maximum part length, curvature radius, ratio of plate thickness to curvature radius, etc. The welding process elements include weld stage, joint form, whether it is the same panel, whether it is the main board, panel type, panel size, minimum panel thickness, part processing type, part type, part material, part category, weld length and welding position, etc.
[0038] Step S130, select a suitable classification algorithm model according to the characteristics of the manufacturing process, and the classification algorithm model can be obtained based on machine learning algorithms such as decision trees, random forests, neural networks, etc. The classification algorithm model is trained in a supervised learning manner according to the geometric information and attribute information of all component models extracted in the above steps. After sufficient training, the classification algorithm model can automatically identify and generate suitable manufacturing process information according to the input component model geometric information and attribute information, such as structural cutting, forming, welding, etc.
[0039] In one embodiment, Figure 3 As shown, the steps of using the classification algorithm model to identify and generate the manufacturing process content corresponding to the component model include: step S131, converting the geometric information and attribute information of the component model extracted in the above step into a standardized data format. These data formats are designed for machine learning algorithms to ensure that the machine learning algorithm can accurately understand and process this information. The above-mentioned standardized data is used as input content, and the corresponding classification algorithm model is called for preliminary calculation, identification and matching for different manufacturing process types such as cutting, forming, and welding.
[0040] Preferably, the preliminary identification and matching results of the manufacturing process in the above steps can be reviewed and corrected. The above normalized data is subjected to human-computer interaction in the system, and the designer can review and correct the matching manufacturing process content, feed the matching results back to the machine learning algorithm model, participate in the iterative training of the machine learning algorithm model, and improve the accuracy of identifying and matching manufacturing processes.
[0041] Step S132, generates manufacturing process content according to the matching result or the corrected matching result, and the manufacturing process content includes the allowance, shrinkage, cutting equipment, cutting parameters, etc. corresponding to the cutting process, the forming process route, forming equipment selection, forming equipment processing instruction parameters, etc. corresponding to the forming process, the parts and assembly relationship, assembly method, assembly base, welding method, welding procedure, welding process parameters, welding work package, etc. corresponding to the welding process.
[0042] Step S140, the generated manufacturing process content is automatically defined in the corresponding component model by means of process combination. By defining it in the corresponding component model, the manufacturing process information is no longer an isolated text or data, but a part that is closely integrated with the component model. When you need to view or modify the process of a certain part, you only need to directly access its model to obtain complete information.
[0043] In one embodiment, the generated manufacturing process content is mapped to the corresponding component model. Specifically, the mapping association can be performed by ID. The mapping relationship ensures the accuracy and traceability of the manufacturing process information, which is convenient for the subsequent definition and identification of the manufacturing process. Based on the mapping relationship between the manufacturing process content and the component model in the above steps, the process content generated by the manufacturing process content is combined and defined in the corresponding component model to realize the batch and automated definition of the component process with the ship section as the object, which greatly improves the efficiency and accuracy of the process design. The defined component model is sent to the production site, and the on-site staff can realize the automatic execution of the process by extracting the manufacturing process content in the component model.
[0044] The second aspect of the present application provides a process identification system based on model features, such as Figure 2 As shown, it includes a reconstruction module, a parsing module, a matching module and a definition module. Among them, the reconstruction module is used to reconstruct the manufacturing assembly structure tree based on the hull segment model to obtain a reconstructed manufacturing assembly structure tree. The hull segment model is selected from the design database, and the hull segment model is analyzed using a pre-trained classification algorithm model to identify the information of the component model in the hull model. Then, the hierarchical structure of the manufacturing assembly structure tree is generated using a machine learning algorithm, and the identified component models are classified and reorganized by machine learning. The classified and reorganized component models are assembled to the corresponding level of the manufacturing assembly structure tree according to their assembly relationship and hierarchical structure, thereby realizing the reconstruction of the manufacturing assembly structure tree.
[0045] The parsing module is used to parse the reconstructed manufacturing assembly structure tree, extract the geometric information and attribute information of all component models under the manufacturing assembly structure tree, and classify and structure the geometric information and attribute information. The aforementioned geometric information and attribute information of the extracted component models are classified, which mainly includes cutting process element extraction, forming process element extraction, and welding process element extraction.
[0046] Among them, the cutting process extraction factors include part type, category, flow direction, material, thickness, specification, model joint direction, etc. Forming part type, category, material, thickness, theoretical part height, theoretical part width, theoretical part length, weight, center of gravity, surface type, unfolded part length, unfolded part width, part maximum length, curvature radius, plate thickness to curvature radius ratio, etc. Assembly and welding process factors include weld stage, joint form, whether it is the same panel, whether it is the main board, panel type, panel size, minimum panel thickness, part processing type, part type, part material, part category, weld length and welding position, etc.
[0047] The matching module is used to select a classification algorithm model for classification according to the characteristics of the manufacturing process, so as to identify and generate appropriate manufacturing process information. Specifically, the geometric information and attribute information of the component model extracted by the aforementioned parsing module are converted into a standardized data format, and the corresponding classification algorithm model is called for calculation, identification and matching for different manufacturing process types such as cutting, forming, and welding. Preferably, the preliminary identification and matching results of the manufacturing process can be reviewed and corrected.
[0048] The definition module is used to automatically define the generated manufacturing process content in the corresponding component model by means of process combination. The manufacturing process content is generated according to the matching result or the corrected matching result, and the generated manufacturing process content is mapped to the corresponding part model. Based on the mapping relationship between the manufacturing process content and the component model, the process content combination generated by the manufacturing process content is defined in the corresponding component model.
[0049] By defining it in the corresponding component model, the manufacturing process information is no longer an isolated text or data, but a part that is closely integrated with the component model. When you need to view or modify the process of a component, you only need to directly access its model to obtain complete information. The defined component model is sent to the production site, and the on-site staff can realize the automatic execution of the process by extracting the manufacturing process content in the component model.
[0050] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.
[0051] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.
[0052] The third aspect of the present application provides a computer-readable storage medium, on which a program of a process identification method based on model features is stored, so that the process identification method based on model features provided in the first aspect of the present application is executed. As for the aforementioned computer-readable storage medium, those skilled in the art can understand that the implementation example of the functions of the aforementioned system and each unit can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, it executes an implementation example including the functions of the aforementioned system and each unit. The aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM or optical disk.
[0053] The fourth aspect of the present application provides an electronic device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory. The electronic device may be a server. The electronic device comprises a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device comprises a non-volatile and / or volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the process identification function or step based on the model feature of the present application is implemented.
[0054] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.
Claims
1. A process identification method based on model features, characterized in that: include: Reconstruct the manufacturing assembly structure tree based on the hull segment model to obtain a reconstructed manufacturing assembly structure tree; Parse the reconstructed manufacturing assembly structure tree and extract the geometric information and attribute information of all component models under the reconstructed manufacturing assembly structure tree; According to the extracted geometric information and attribute information of all the component models, a classification algorithm model is used to perform classification and identification and generate corresponding manufacturing process content; The generated manufacturing process content is defined in the corresponding component model.
2. The process identification method based on model features according to claim 1, characterized in that: The reconstructing the manufacturing assembly structure tree based on the hull segment model includes: Identifying component model information of the hull section model; Based on the identified component model information of the hull segment model, generating a hierarchical structure of the manufacturing assembly structure tree; The identified component models are classified and reorganized, and assembled to the corresponding level of the manufacturing assembly structure tree.
3. The process identification method based on model features according to claim 2, characterized in that: The component model information includes segmented space position, assembly base surface and assembly type.
4. The process identification method based on model features according to claim 1, characterized in that: The geometric information and attribute information of the component model are at least divided into cutting process elements, forming process elements and welding process elements.
5. The process identification method based on model features according to claim 4, characterized in that: The cutting process elements shall at least include part type, category, flow direction, material, thickness, specification, model and joint direction; The forming process elements shall at least include part type, category, material, thickness, theoretical part height, theoretical part width, theoretical part length, weight, center of gravity, surface type, unfolded part length, unfolded part width, maximum part length, curvature radius, and ratio of plate thickness to curvature radius; The welding process elements include at least the welding stage, joint form, whether it is the same panel, whether it is the main panel, panel type, panel size, minimum panel thickness, part processing type, part type, part material, part category, weld length and welding position.
6. The process identification method based on model features according to claim 1, characterized in that: The method of using a classification algorithm model to classify and identify the extracted geometric information and attribute information of all component models and generate corresponding manufacturing process information includes: Convert the extracted geometric information and attribute information of all component models into a standardized data format, and call the classification algorithm model to identify and match the corresponding manufacturing process type; Generate manufacturing process content based on the matching results.
7. The process identification method based on model features according to claim 1, characterized in that: Defining the generated manufacturing process content in the corresponding component model includes: Mapping the manufacturing process content to the corresponding component model; Based on the mapping relationship between the manufacturing process content and the component model, the process content combination generated by the manufacturing process content is defined in the corresponding component model.
8. A process identification system based on model features, characterized in that: include: Reconstruction module, parsing module, matching module and definition module; The reconstruction module is used to reconstruct the manufacturing assembly structure tree based on the hull segment model to obtain a reconstructed manufacturing assembly structure tree; The parsing module is used to parse the reconstructed manufacturing assembly structure tree and extract the geometric information and attribute information of all component models under the reconstructed manufacturing assembly structure tree; The matching module is used to perform classification and identification based on the extracted geometric information and attribute information of all the component models using a classification algorithm model and generate corresponding manufacturing process content; The definition module is used to define the manufacturing process content to be generated in the corresponding component model.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program runs on a processor, the processor is enabled to execute the identification method according to any one of claims 1 to 7.
10. An electronic device, characterized in that: include: at least one memory for storing a program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the identification method according to any one of claims 1 to 7.
