A method and device for supporting reconfiguration of a complex product manufacturing process model

Abstract

The present disclosure provides a method and device for supporting complex product manufacturing process model reconstruction. A user can input manufacturing process reconstruction requirements according to a language structure specified by a manufacturing process reconstruction template, including production units, manufacturing activities to be added, manufacturing targets and manufacturing constraints; the method parses the reconstruction requirements according to a manufacturing process reconstruction dictionary, performs information extraction and element matching in a manufacturing process model library according to the production units and the manufacturing activities to be added, obtains a preliminary manufacturing process model scheme, and optimizes the preliminary manufacturing process model scheme according to the manufacturing targets and the manufacturing constraints to reconstruct a final manufacturing process scheme, thereby realizing model-driven adaptive and reconfigurable manufacturing process functions. The present disclosure can realize rapid generation of complex product manufacturing process models, and improve the efficiency and quality of product design.

Description

Technical Field

[0001] This invention relates to the fields of systems engineering and computer technology, and specifically to a method and apparatus for supporting the reconstruction of complex product manufacturing process models. Background Technology

[0002] As product complexity increases, so do manufacturing processes. Model-based Systems Engineering (MBSE) supports the formalization, modeling, design, analysis, and verification of the product manufacturing process through models, providing solutions to address the manufacturing challenges of complex systems. Typically, to handle different product models or different batches of the same model, different manufacturing process models need to be designed to meet manufacturing requirements. This process involves the refactoring of manufacturing process models. Traditional methods for refactoring manufacturing process models mainly rely on human experience and manual configuration, which suffers from inefficiency and error-proneness. An automated method is needed to achieve adaptive refactoring of manufacturing process models to improve refactoring efficiency and accuracy.

[0003] Automated adaptive reconfiguration methods can efficiently reconfigure and optimize manufacturing processes by leveraging advanced algorithms and technologies, combined with artificial intelligence and algorithm optimization, thereby rapidly responding to product changes and manufacturing needs.

[0004] CN202011214559.6 discloses a system and method for the automatic generation and self-improvement of dynamic flexible processes. This method decomposes each node in a process into tasks and data, establishing task models and data models. The task models and data models are then linked to form upstream and downstream relationships between tasks. The position of each node in the task model within the process is determined by the generation and use of data, thereby automatically generating the process. When the input and output nodes of the task model nodes change, the process automatically changes, achieving model-based dynamic process construction and self-improvement.

[0005] The method includes the following steps: S1: Obtain the top-level task; based on multiple task model nodes in the task model module, select at least one task model node related to the top-level task; and determine the task instance node after task decomposition in the task decomposition module; S2: Based on multiple data model nodes in the data model module, establish a complete data instance node in the data storage module; S3: Based on the input-output relationships between multiple task model nodes and multiple data model nodes defined in the task data relationship module, determine the input-output relationships between the task instance node and multiple data model nodes, and determine the input-output relationships between the task instance node and the complete data instance node; S4: Based on the input-output relationships between the task instance node and the complete data instance node, obtain the execution order between the task instance nodes. Although this method solves the problem of automatic process generation to some extent, it still has the following main drawbacks in terms of manufacturing process refactoring:

[0006] 1. Lack of intelligent optimization and adaptive capabilities

[0007] Existing technologies rely primarily on predefined relationships between tasks and data models during process generation and self-improvement, lacking intelligent optimization and adaptive mechanisms. Because no optimization algorithms are introduced, the generated process may not be the optimal solution and cannot meet the optimal requirements of manufacturing goals.

[0008] 2. Insufficient user input processing capabilities

[0009] Existing methods primarily generate processes through task decomposition and data model association, but their ability to handle user input requirements is relatively limited. For complex manufacturing process refactoring needs, the system struggles to accurately understand and parse them, resulting in generated process models that fail to fully meet actual manufacturing requirements. This limitation significantly reduces the system's usability and user experience.

[0010] 3. Lack of support for model reconstruction of heterogeneous manufacturing process models.

[0011] In existing technologies, manufacturing process model reconstruction is usually only applicable to manufacturing process models in a specific modeling language, and it is difficult to support manufacturing process models in other modeling languages. However, manufacturing process models can be constructed using various modeling languages ​​such as SysML, UML, and BPMN. The semantic and syntactic heterogeneity between different modeling languages ​​limits the current technology's support for the reconstruction of heterogeneous manufacturing process models. Summary of the Invention

[0012] In view of this, the present invention provides a method and apparatus for supporting the reconstruction of complex product manufacturing process models, which can construct manufacturing processes according to user needs and solve for the optimal model solution through optimization algorithms, thereby realizing the rapid generation of complex product manufacturing process models and improving the efficiency and quality of product design.

[0013] To solve the above-mentioned technical problems, the present invention is implemented as follows.

[0014] A method for supporting the refactoring of complex product manufacturing process models includes:

[0015] Step S1: Build a manufacturing process model library, define the manufacturing process refactoring dictionary and manufacturing process refactoring requirement template;

[0016] The manufacturing process model library includes the production units involved in the basic manufacturing process and the manufacturing activities they perform, as well as the execution order between the manufacturing activities;

[0017] The manufacturing process refactoring requirement template is constructed based on the manufacturing process refactoring dictionary and specifies the sentence structure of the manufacturing process model refactoring requirement text, including the production unit selection template, manufacturing activity addition template, manufacturing target template, and manufacturing constraint template.

[0018] Step S2: Based on the manufacturing process refactoring requirement template, input the manufacturing process model refactoring requirement text; based on the manufacturing process refactoring dictionary, parse the manufacturing process refactoring requirements, including production units, new manufacturing activities, manufacturing goals, and manufacturing constraints.

[0019] Step S3: Based on the production unit and new manufacturing activity analyzed in step S2, match them in the manufacturing process model library, extract the manufacturing activities that the production unit needs to perform, as well as the production unit information, all manufacturing activity information and execution order, and generate a preliminary manufacturing process model scheme.

[0020] Step S4: Based on the manufacturing objectives and constraints analyzed in Step S2, perform multi-objective optimization on the manufacturing activities in the preliminary manufacturing process model scheme to reconstruct the final manufacturing process scheme.

[0021] Preferably, step S4 uses the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) for multi-objective optimization.

[0022] Preferably, in step S4, when performing multi-objective optimization, each manufacturing activity in the preliminary manufacturing process model scheme is used as a node to construct a node set; by randomly sampling from the node set, a subset of nodes is generated as an initial population; based on the resolved manufacturing objectives and manufacturing constraints, each node in the node set is adaptively selected or discarded to obtain the optimal solution set.

[0023] Preferably, in step 1, the manufacturing process model library is constructed based on a manufacturing process meta-model library built using the multi-architecture modeling language KARMA; the meta-models included in the manufacturing process meta-model library are:

[0024] The primitive model includes: a manufacturing process primitive model, used to describe the manufacturing process;

[0025] The object metamodel includes: production unit object metamodel, manufacturing activity object metamodel, start object metamodel, and end object metamodel; the production unit object metamodel is used to describe the production units in the manufacturing process and their related characteristics, including name attribute; the manufacturing activity object metamodel is used to describe the manufacturing activities in the manufacturing process and their related characteristics, including name attribute, time attribute, cost attribute, and resource consumption rate attribute.

[0026] Relational meta-models include: control flow relational meta-models, which are used to describe the sequential relationship between two manufacturing activities.

[0027] Preferably, the manufacturing process model library constructed in step S1 includes:

[0028] The production unit includes: purchasing department, quality inspection department, production planning department, warehousing department, production workers, assembly workers, surface treatment workers, equipment maintenance workers, packaging workers, logistics department, and data analysts;

[0029] Manufacturing activities include: purchasing raw materials (constructed in the Purchasing Department); accepting materials, conducting quality inspections during production, performing product testing, and inspecting final products (constructed in the Quality Inspection Department); formulating production plans and assigning production tasks (constructed in the Production Planning Department); managing raw material inventory, distributing materials to the production line, and storing finished products (constructed in the Warehousing Department); pre-processing materials and manufacturing parts (constructed in the Production Workers' Objects); assembling products (constructed in the Assembly Workers' Objects); surface treatment and painting (constructed in the Surface Treatment Workers' Objects); daily equipment inspection, preventative maintenance, and equipment failure repair (constructed in the Equipment Maintenance Workers' Objects); packaging finished products (constructed in the Packaging Workers' Objects); arranging transportation (constructed in the Logistics Department's Objects); and analyzing production data (constructed in the Data Analyst's Objects). Manufacturing activities also include: start objects and end objects.

[0030] After the manufacturing activities are constructed, the control flow relation meta-model is used to connect the manufacturing activities in the required order to form the basic manufacturing process.

[0031] Preferably, the manufacturing process refactoring dictionary includes {new manufacturing process model: new model}, {shall: shall}, {contain: contain}, {add: add}, {add: add}, {name: name}, {is: is}, {production activity: object}, {max: max}, {more than: more than}, {more than: more than}, {rather than: rather than}, {rather than: rather than}, {manufacturing process model, model}.

[0032] Preferably, the manufacturing process reengineering requirement template is specifically as follows:

[0033] The production unit selection template is as follows:<new model> <shall> <contain>…,…,…,;

[0034] The template for the manufacturing activity is as follows: ... <shall> <add> <name> <is> … <object>;

[0035] The manufacturing target template is: <model> … <max min>;

[0036] The manufacturing constraint template is: ... <shall> <add> <name> <is> … <object>.

[0037] Preferably, in step S3, generating the preliminary manufacturing process model scheme includes: manufacturing process model data conversion and generation and display of the preliminary manufacturing process scheme.

[0038] The steps of manufacturing process model data conversion are to convert the extracted data that needs to be displayed into form data;

[0039] The steps for generating and displaying the preliminary manufacturing process plan involve presenting the converted form data in a tabular format.

[0040] Preferably, the production unit objects and manufacturing activity objects in the manufacturing process model library also include the position and size of the object nodes on the layout;

[0041] When reconstructing the final manufacturing process scheme as described in step S4, the manufacturing activities and production units are matched in the manufacturing process model library according to the optimization scheme. The positions and sizes of these manufacturing activities and production units are obtained and provided to the modeling tool to display icons of each object on the modeling canvas for users to view and modify.

[0042] The present invention also provides an apparatus for supporting the reconstruction of complex product manufacturing process models, comprising: a manufacturing process meta-model library construction unit, a manufacturing process model library construction unit, and a manufacturing process model reconstruction unit;

[0043] The manufacturing process meta-model library construction unit is used to build a manufacturing process meta-model library using the multi-architecture modeling language KARMA.

[0044] The manufacturing process model library construction unit is used to construct a manufacturing process model library based on the manufacturing process meta-model library; the manufacturing process model library includes the production units involved in the basic manufacturing process and the manufacturing activities they perform, as well as the execution order between the manufacturing activities;

[0045] The manufacturing process model reconstruction unit includes an analysis module, a preliminary scheme generation module, an optimization module, and a reconstruction module;

[0046] The parsing module is used to receive the manufacturing process model reconstruction requirement text organized according to the statement structure provided by the manufacturing process reconstruction requirement template; and to parse the manufacturing process reconstruction requirement according to the manufacturing process reconstruction dictionary, including production unit, new manufacturing activity, manufacturing target, and manufacturing constraint.

[0047] The manufacturing process refactoring requirement template is constructed based on the terminology provided by the manufacturing process refactoring dictionary, and includes a production unit selection template, a manufacturing activity addition template, a manufacturing target template, and a manufacturing constraint template.

[0048] The preliminary scheme generation module is used to match the production unit and new manufacturing activities parsed by the parsing module in the manufacturing process model library, extract the manufacturing activities that the production unit needs to perform, as well as the production unit information, all manufacturing activity information and execution order, and generate a preliminary manufacturing process model scheme.

[0049] The optimization module is used to perform multi-objective optimization of the manufacturing activities in the preliminary manufacturing process model scheme based on the manufacturing objectives and manufacturing constraints analyzed by the analysis module.

[0050] The reconstruction module is used to reconstruct the final manufacturing process scheme based on the multi-objective optimization results of the optimization module.

[0051] Beneficial effects:

[0052] (1) Standardized manufacturing process reengineering requirements expression methods

[0053] Existing manufacturing process construction and reconfiguration technologies typically rely on human experience and manual configuration, which is time-consuming, error-prone, and unable to quickly respond to the changing demands of complex battlefield environments. This invention provides a standardized expression method by defining a manufacturing process reconfiguration dictionary and a manufacturing process reconfiguration requirement template. Through word segmentation, part-of-speech tagging, and sentence processing technologies, it can accurately parse the user's textual requirements, significantly improving the efficiency and accuracy of manufacturing process reconfiguration.

[0054] (2) Manufacturing process optimization based on multi-objective optimization algorithm

[0055] Existing manufacturing process optimization methods typically only orchestrate manufacturing activities by matching data and prioritizing the relationships between manufacturing activities and their order of execution within the manufacturing process model. This approach lacks systematic algorithmic support and struggles to meet the demands of manufacturing process model reconstruction in complex scenarios. This invention, after obtaining a preliminary manufacturing process model, further optimizes the manufacturing activities within the model using manufacturing objectives and constraints obtained from the manufacturing process reconstruction requirement template. This generates an optimal set of manufacturing activities, significantly improving optimization efficiency and effectiveness.

[0056] (3) Model reconstruction of heterogeneous manufacturing process model

[0057] In model-based systems engineering, manufacturing process models can be constructed using BPMN, SysML, UML, or domain-specific modeling languages. The semantic and syntactic heterogeneity between different modeling languages ​​means that existing technologies can only support the reconstruction of manufacturing process models within a specific modeling language. This invention constructs manufacturing process models based on the multi-architecture modeling language KARMA. Since KARMA can support a unified expression of various heterogeneous manufacturing processes, this invention can also support the reconstruction of heterogeneous manufacturing process models.

[0058] (4) In a preferred embodiment, the information of production unit objects and manufacturing activity objects in the manufacturing process model library also includes the position and size of the object nodes on the layout, so that the newly generated demand model is not inaccessible due to problems such as position confusion, thereby improving the readability of the model. Attached Figure Description

[0059] Figure 1 A flowchart illustrating the method for reconstructing complex product manufacturing process models provided by this invention;

[0060] Figure 2 A schematic diagram of the method framework for supporting the reconstruction of complex product manufacturing process models provided by this invention;

[0061] Figure 3 A schematic diagram of the device structure for supporting the reconstruction of complex product manufacturing process models provided by the present invention. Detailed Implementation

[0062] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0063] like Figure 1 and Figure 2 As shown, this invention proposes a method for supporting the reconstruction of complex product manufacturing process models, comprising the following steps:

[0064] Step S1: Construct a meta-model library for the manufacturing process.

[0065] First, a domain-specific metamodel library is constructed based on the multi-architecture modeling language KARMA. This library includes six metamodels (graph, object, relation, vertex, attribute, and role). The relationships between these six metamodels are as follows: the graph metamodel includes the object metamodel and the relation metamodel; the object metamodel contains the attribute metamodel and the vertex metamodel; the relation metamodel contains the attribute metamodel, and both ends of it are bound to the role metamodel; the vertex metamodel exists dependent on the object metamodel; the attribute metamodel serves as an attribute of both the object metamodel and the relation metamodel; and the role metamodel is bound to both ends of the relation metamodel.

[0066] This invention constructs a specific domain meta-model library for manufacturing process model reconstruction, which is a manufacturing process meta-model library. Its six meta-models are as follows:

[0067] (1) The primitive model includes:

[0068] The manufacturing process primitive model is used to construct the manufacturing process model and describe the manufacturing process. This manufacturing process primitive model is configured as follows:

[0069] The configuration object metamodel includes: production unit object metamodel, manufacturing activity object metamodel, start object metamodel, and end object metamodel;

[0070] The configuration relation metamodel includes: the control flow relation metamodel;

[0071] The configuration attribute metamodel includes: None.

[0072] The starting point of the configuration control flow relation metamodel can be connected to the production unit object metamodel, the manufacturing activity object metamodel, and the start object metamodel; the ending point of the configuration control flow relation metamodel can be connected to the production unit object metamodel, the manufacturing activity object metamodel, and the end object metamodel.

[0073] (2) The object meta-model includes:

[0074] • Production Unit Object Metamodel: Used to describe production units and their related characteristics in the manufacturing process; configured with a "rounded rectangle" style; the configuration attribute metamodel includes: name attribute metamodel.

[0075] Type; Configure color as "default";

[0076] • Manufacturing Activity Metamodel: Used to describe manufacturing activities and their related characteristics in the manufacturing process; configured with a "rounded rectangle" style; the configuration attribute metamodel includes: name attribute metamodel.

[0077] Type, time attribute metamodel, cost attribute metamodel, resource consumption rate attribute metamodel; configured color is "default";

[0078] • Start Object Metamodel: Used to describe the starting node of the manufacturing process; configured style is "rounded rectangle"; configured attribute metamodel includes: none; configured color is "default";

[0079] • End Object Metamodel: Used to describe the end node of the manufacturing process; configured with the style "rounded corners".

[0080] "Shape"; Configuration attribute metamodel includes: None; Configuration color is "default".

[0081] (3) The relational meta-model includes:

[0082] • Control flow relationship metamodel: used to describe the sequential relationship between two manufacturing activities; the beginning of the control flow relationship is bound to the previous manufacturing activity, and the end of the control flow relationship is bound to the next manufacturing activity; configuration attribute metamodel includes: none; configure the beginning role as the control flow beginning role metamodel; configure the end role as the control flow end role metamodel, and configure the style as "bold line";

[0083] (4) The attribute metamodel includes:

[0084] • Name attribute metamodel: Used to describe the name of the object production unit object metamodel and the manufacturing activity object metamodel. The attribute value type is configured as String and the unit is configured as "none".

[0085] • Time attribute metamodel: Used to describe the time consumed by the metamodel of the manufacturing activity object. The attribute value type is configured as Int, and the attribute value unit is configured as "hour".

[0086] • Cost attribute meta-model: Used to describe the cost consumed by the meta-model of manufacturing activity objects. The attribute value type is configured as Int, and the attribute value unit is configured as "yuan".

[0087] ●Resource Consumption Rate Attribute Metamodel: Used to describe the percentage of resources consumed by the metamodel of the manufacturing activity object. The attribute value type is configured as Int, and the attribute value unit is configured as "%".

[0088] (5) The point element model is absent;

[0089] (6) The character metamodel includes:

[0090] • Control Flow Starter Role Metamodel: Used to bind the starter of the control flow and configure the control flow starter role.

[0091] The direction of the color element model is "start" and the style is "arrow".

[0092] • Control Flow Terminal Role Metamodel: Used to bind terminals to the control flow and configure the control flow terminal role.

[0093] The color element model is oriented as "terminal" and has a "diamond" pattern.

[0094] Step S2: Define the manufacturing process refactoring dictionary.

[0095] The purpose of defining a manufacturing process refactoring dictionary is to provide the ability to identify technical terms in manufacturing process refactoring requirements, which helps to accurately match and understand the information in the text of manufacturing process refactoring requirements. The definition of each word in the dictionary includes two parts: word content and part of speech. The dictionary definition format is {word: part of speech}. The manufacturing process refactoring dictionary defined in this invention includes: {new manufacturing process model: new model}, {shall: shall}, {contain: contain}, {add: add}, {add: add}, {name: name}, {is: is}, {object: object}, {max: max}, {morethan: more than}, {more than: more than}, {rather than: rather than}, {rather than: rather than}, {manufacturing process model, model}.

[0096] Step S3: Define the manufacturing process refactoring requirement template.

[0097] The purpose of defining manufacturing process refactoring requirement templates is to provide specific statement templates, allowing users to input manufacturing process model refactoring requirements based on the corresponding templates. Manufacturing process refactoring requirement templates mainly include: production cell selection templates, manufacturing activity addition templates, manufacturing target templates, and manufacturing constraint templates.

[0098] Production Unit Selection Template: This template allows users to input structured statements. The template is created based on the parts of speech of words provided by the dictionary.<new model> <shall> <contain>…,…,…, Based on this statement, an example of a structured statement that the user can input is: The new manufacturing process model should include manufacturing workers, technicians, quality inspectors, manufacturing managers, and maintenance personnel. The manufacturing process model reconstruction device of the present invention can process this statement using NLP (Natural Language Processing) technology, and obtain the corresponding production unit objects and their executed manufacturing activities from the manufacturing process model library constructed in step S4, as part of the new manufacturing process model.

[0099] Manufacturing Activity Addition Template: Users have defined the manufacturing activities that production units need to perform in the manufacturing process model library. However, in a new manufacturing process model, some production units may need to perform additional manufacturing activities that are not present in the library. This template allows users to input structured statements, and it is created based on parts of speech:… <shall> <add> <name> <is> … <object>Users can input structured statements, such as: "Technicians should add a production activity named 'Equipment Maintenance'." The manufacturing process model refactoring device can use NLP (Natural Language Processing) technology to process this statement and add corresponding manufacturing activities to the production units specified in the statement, obtaining a preliminary manufacturing process model scheme to meet the needs of the new manufacturing process.

[0100] Manufacturing target template and manufacturing constraint template: Based on the preliminary manufacturing process model, it is necessary to define optimization targets and constraints to help users generate a manufacturing process model after algorithm processing.

[0101] The purpose of creating target templates is to allow users to input structured sentences; the templates are created based on parts of speech. <model> … <max>For example: The manufacturing process model has the lowest resource consumption rate and the lowest cost. The manufacturing process model reconstruction device can use NLP (Natural Language Processing) technology to process this statement and convert it into the optimization objective of the mathematical model in the algorithm.

[0102] The purpose of creating constraint templates is to allow users to input structured statements. The templates are created based on parts of speech. <model>…<rather than / more than> …For example: if the manufacturing process model's time is less than or equal to 100 hours, and its cost is less than or equal to 300,000 yuan. The manufacturing process model reconstruction device can use NLP (Natural Language Processing) technology to process this statement and convert it into constraints for the mathematical model in the algorithm. After algorithmic processing, the optimal manufacturing process solution is obtained, helping users quickly build new manufacturing process models.

[0103] Step S4: Construct a manufacturing process model library, which includes production cell construction (constructing the production cells involved in the manufacturing process model and their attribute values), manufacturing activity construction (constructing the manufacturing activities executed by each production cell in the manufacturing process model and their attribute values), and the topological relationships between manufacturing activities (sequential relationships, parallel relationships, etc.). This manufacturing process model library provides a basic process model. If the actual requirements are larger than this model, additional templates can be added through manufacturing activities.

[0104] The production unit objects include: purchasing department, quality inspection department, production planning department, warehousing department, production workers, assembly workers, surface treatment workers, equipment maintenance workers, packaging workers, logistics department, and data analysts.

[0105] Create a manufacturing activity object within the purchasing department: Purchasing Raw Materials (name attribute value: Purchasing Raw Materials, time attribute value: 10 hours, cost attribute value: 10,000 yuan, resource consumption rate attribute value: 3.5%).

[0106] Within the Quality Inspection Department, construct the following manufacturing activity objects: Material Acceptance (Name attribute: Material Acceptance; Time attribute: 1 hour; Cost attribute: 1000 yuan; Resource Consumption Rate attribute: 0.5%), In-Process Quality Inspection (Name attribute: In-Process Quality Inspection; Time attribute: 10 hours; Cost attribute: 10000 yuan; Resource Consumption Rate attribute: 2.5%), Product Testing (Name attribute: Product Testing; Time attribute: 5 hours; Cost attribute: 2000 yuan; Resource Consumption Rate attribute: 0.5%), and Final Product Inspection (Name attribute: Final Product Inspection; Time attribute: 6 hours; Cost attribute: 10000 yuan; Resource Consumption Rate attribute: 1.5%).

[0107] In the Production Planning Department object, construct the following manufacturing activity objects: Create a production plan (name attribute value: Create Production Plan; time attribute value: 8 hours; cost attribute value: 20,000 yuan; resource consumption rate attribute value: 2.5%), and arrange production tasks (name attribute value: Arrange Production Task; time attribute value: 5 hours; cost attribute value: 10,000 yuan; resource consumption rate attribute value: 3.5%).

[0108] Within the Warehouse Department, construct the following manufacturing activity objects: Manage Raw Material Inventory (Name attribute: Manage Raw Material Inventory; Time attribute: 10 hours; Cost attribute: 20,000 yuan; Resource Consumption Rate attribute: 1.5%), Material Delivery to Production Line (Name attribute: Material Delivery to Production Line; Time attribute: 8 hours; Cost attribute: 10,000 yuan; Resource Consumption Rate attribute: 0.5%), Store Finished Goods (Name attribute: Store Finished Goods; Time attribute: 12 hours; Cost attribute: 20,000 yuan; Resource Consumption Rate attribute: 1.5%), and Store Finished Goods (Name attribute: Prepare for Product Shipment; Time attribute: 8 hours; Cost attribute: 15,000 yuan; Resource Consumption Rate attribute: 0.5%).

[0109] Within the production worker object, construct manufacturing activity objects: Pre-processing materials (name attribute value: Pre-processing materials; time attribute value: 8 hours; cost attribute value: 13,000 yuan; resource consumption rate attribute value: 2.5%) and Part manufacturing (name attribute value: Part manufacturing; time attribute value: 35 hours; cost attribute value: 1,200,000 yuan; resource consumption rate attribute value: 35%). Within the assembly worker object, construct manufacturing activity objects: Assembled products (name attribute value: Assembled products; time attribute value: 20 hours; cost attribute value: 1,000,000 yuan; resource consumption rate attribute value: 28%).

[0110] Within the Surface Treatment Worker object, construct the manufacturing activity objects: Surface Treatment and Coating (Name attribute: Surface Treatment and Coating; Time attribute: 15 hours; Cost attribute: 900,000 yuan; Resource Consumption Rate attribute: 18%). Within the Equipment Maintenance Worker object, construct the manufacturing activity objects: Routine Equipment Inspection (Name attribute: Routine Equipment Inspection; Time attribute: 6 hours; Cost attribute: 90,000 yuan; Resource Consumption Rate attribute: 7%), Preventive Maintenance (Name attribute: Equipment Maintenance Worker; Time attribute: 6 hours; Cost attribute: 90,000 yuan; Resource Consumption Rate attribute: 7%), and Equipment Failure Repair (Name attribute: Equipment Failure Repair; Time attribute: 8 hours; Cost attribute: 60,000 yuan; Resource Consumption Rate attribute: 3%).

[0111] In the Packaging Worker object, create a Manufacturing Activity object: Packaging Finished Product (Name attribute: Packaging Finished Product, Time attribute: 18 hours, Cost attribute: 1,000,000 yuan, Resource Consumption Rate attribute: 15%). In the Logistics Department object, create a Manufacturing Activity object: Arrange Transportation (Name attribute: Arrange Transportation, Time attribute: 10 hours, Cost attribute: 20,000 yuan, Resource Consumption Rate attribute: 0.6%).

[0112] Construct a manufacturing activity object within the data analyst object: Analyze production data (name attribute value is Analyze production data, time attribute value is 2 hours, cost attribute value is 3000 yuan, resource consumption rate attribute value is 0.2%).

[0113] The manufacturing activity objects also include: the start object and the end object.

[0114] After constructing the manufacturing activities, a control flow relation meta-model is used to connect the manufacturing activities in a certain order to form a manufacturing process model. For example, the manufacturing activities can be connected in the following order: Start, purchase raw materials, accept materials, formulate production plans, arrange production tasks, manage raw material inventory, deliver materials to the production line, pre-treat materials, manufacture parts, assemble products, surface treatment and painting, quality inspection during production, conduct product testing, routine equipment inspection, preventive maintenance, equipment failure repair, final product inspection, package finished products, store finished products, prepare for product shipment, arrange transportation, record production data, analyze production data, end.

[0115] The constructed manufacturing process model will serve as the optimization space in subsequent algorithms.

[0116] Step S5: The user inputs the textual expression of the manufacturing process model reconstruction requirements according to the four statement templates specified in the manufacturing process reconstruction requirement template, and processes the manufacturing process reconstruction requirement statement on the textual expression.

[0117] The purpose of manufacturing process refactoring requirement statement processing is to process the textual expression of manufacturing process refactoring requirements input by users, and obtain identifiable requirement information as input for manufacturing process refactoring. Statement processing mainly includes word segmentation, part-of-speech tagging, chunking, and information extraction.

[0118] For example, the textual expression of the manufacturing process reengineering requirements input in this case includes:

[0119] The requirements for selecting production units are as follows: The new manufacturing process model should include purchasing, quality inspection, production planning, warehousing, production workers, assembly workers, surface treatment workers, equipment maintenance workers, packaging workers, logistics, and data analysts.

[0120] The increased demand for manufacturing activities is as follows: Production workers should add a manufacturing activity named "Pre-treatment Materials";

[0121] The manufacturing objectives are: to achieve the lowest resource utilization rate and the lowest cost in the manufacturing process model.

[0122] The manufacturing constraint requirement is that the manufacturing process model time is less than or equal to 350 hours.

[0123] Word segmentation and part-of-speech tagging: This step first removes punctuation and stop words from the manufacturing process refactoring requirement statements to facilitate subsequent word segmentation, part-of-speech tagging, and statement processing; then, in conjunction with the manufacturing process refactoring dictionary, rule-based word segmentation is used and the segmentation results are tagged with parts of speech to facilitate a better understanding of the text content.

[0124] The part-of-speech tagging results in this case are:

[0125] <new model> <shall> <contain>Purchasing Department, Quality Inspection Department, Production Planning Department, Warehousing Department, Production Workers, Assembly Workers, Surface Treatment Workers, Equipment Maintenance Workers, Packaging Workers, Logistics Department, Data Analysts

[0126] Production workers <shall> <add> <name> <is>Pretreatment materials <object>，

[0127] <model>resource utilization rate <min>cost <min> ，

[0128] <model>time<rather than / more than> 350

[0129] Segmentation: The purpose of this step is to segment the word segmentation results into blocks based on the four types of templates in the manufacturing process reconstruction requirement template library, and to divide the manufacturing process reconstruction requirements into independent information blocks.

[0130] In this case, information blocks can be identified based on the part-of-speech structure of the requirements template for manufacturing process refactoring. For example, based on... <model>…<rather than / more than> …, can be seen from " <model>The information blocks "time" and "350" are extracted from the text "time <rather than / more than> 350", and it is determined that the two information belong to manufacturing constraint information.

[0131] Information extraction: based on the block result, the information required for model reconstruction is extracted, and the types of information include four categories: production unit information, manufacturing activity addition information, manufacturing target information, and manufacturing constraint information. The purpose of this step is to extract the information required for model reconstruction, which will be input into the manufacturing process model reconstruction device.

[0132] The production unit information in this case is: {purchase department, quality inspection department, production planning department, warehouse department, production workers, assembly workers, surface treatment workers, equipment maintenance workers, packaging workers, logistics department, data analysts}, manufacturing activity addition information is: {production workers, pre-processing materials}, manufacturing target information is {resource utilization rate, minimum; cost, minimum}, and manufacturing constraint information is: {time, less than or equal to, 350}.

[0133] Step S6: match manufacturing process model data and generate a preliminary manufacturing process scheme.

[0134] (1) The purpose of matching manufacturing process data is to match the corresponding production unit and its executed manufacturing activities from the manufacturing process model library based on the extracted production unit information and added manufacturing activity information. Model data matching mainly includes production unit data matching and added manufacturing activity data matching.

[0135] Production unit data matching: the purpose of this step is to obtain relevant production unit data such as name, parameter value, location, size, etc. from the manufacturing process model library based on production unit information.

[0136] Manufacturing activity data matching: the purpose of this step is to obtain relevant manufacturing activity data executed by the production unit and added manufacturing activities, including name, parameter type, parameter name, parameter value, location, size, etc. from the manufacturing process model library based on added manufacturing activity information.

[0137] (2) The purpose of generating a preliminary manufacturing process is to convert the matched production unit and manufacturing activity data into a structured form that can be edited, such as production unit, manufacturing activity name, attribute name, and attribute value, to facilitate users to modify or delete manufacturing activities according to actual manufacturing requirements, where modification includes changing manufacturing activity attribute values. Preliminary manufacturing process scheme generation includes manufacturing process model data conversion, preliminary manufacturing process scheme generation and display.

[0138] Manufacturing process model data conversion: The purpose of this step is to convert the matched manufacturing process model data into form data. The conversion only converts the model data that needs to be displayed, such as the position of the object model, the size of the object model, and the name of the object model, parameter name, parameter value, etc.

[0139] Preliminary manufacturing process scheme generation and display: The purpose of this step is to display the converted data after the model data conversion, thereby providing a user interface or carrier for modification scheme. The preliminary manufacturing process scheme is mainly displayed in the form of a table to show the relevant data of each manufacturing activity attribute.

[0140] Step S7: Algorithm processing. The manufacturing process model provides an optimization space for algorithm optimization. The purpose of algorithm processing is to optimize and solve the preliminary manufacturing process scheme based on the modified preliminary manufacturing process scheme, manufacturing target information and manufacturing constraint information, thereby obtaining a model scheme that meets the user's needs and providing a basis for subsequent manufacturing process model generation. The algorithm used in the algorithm processing process is NSGA-II: Non-dominated Sorting Genetic Algorithm II, which is a genetic algorithm for solving multi-objective optimization problems. The algorithm process regards each manufacturing activity in the manufacturing process model as a node, and all manufacturing activities in the model constitute a node set. Based on the manufacturing target and manufacturing constraint, a mathematical model is constructed to adaptively select each node in the node set, and finally obtain an optimal solution set.

[0141] The target in this case is to minimize the total resource utilization rate value of all manufacturing activities in the manufacturing process model and the total cost value of all manufacturing activities in the manufacturing process model. The constraint is that the total time value of all manufacturing activities in the manufacturing process model is less than or equal to 350 hours.

[0142] The main steps of the NSGA-II algorithm are as follows:

[0143] a) Set the objective function and constraint condition: Convert the manufacturing target information and manufacturing constraint information into the objective function and constraint condition in the mathematical model to provide a basis for the subsequent optimization process.

[0144] b) Initialize the population: Randomly generate a set of node subsets from the node set as the initial population. Set the number of iterations. Here, the manufacturing activity set is used as the base set, and a group of individuals is obtained by randomly selecting some manufacturing activities from the base set. The initial population is composed of different selections. The original node set also needs to be a population. In this way, it can be finally known which manufacturing activities can not participate in the manufacturing process.

[0145] c) Evaluation, non-dominated sorting and crowdedness calculation: First, the objective function of each node subset in the initial population is calculated to measure the performance of each node subset. Then, the node subsets in the population are sorted according to the non-dominated relationship. Finally, crowdedness calculation is performed, and the crowdedness of each non-dominated layer of node subsets is calculated.

[0146] d) Selection, crossover and mutation: First, the individuals (a set of node subsets) of the next generation population are selected, and the node subsets with larger crowdedness are selected to maintain the diversity of the population. Then, crossover and mutation are performed on the selected individuals (node subsets) to generate new offspring individuals (node subsets).

[0147] e) Merge and new population generation: The node subsets selected, crossed and mutated are combined into a new population.

[0148] f) Iteration and optimal solution generation: iterate the process of c) to e) until the number of iterations is met, output the final non-dominated sorting result, and obtain the optimal node set.

[0149] g) Determine the manufacturing activity node: Based on the optimal node set, the optimal manufacturing activity set is mapped.

[0150] Step S8: Generate the final manufacturing process model.

[0151] The purpose of generating the final manufacturing process model is to match the production unit and manufacturing activity data in the manufacturing process model library based on the optimal node set obtained by algorithm processing, and finally obtain the manufacturing activity process model that meets the demand. Model data generation mainly includes demand model data acquisition and new demand model generation.

[0152] Manufacturing process model data processing: The purpose of this step is to match the manufacturing activities and production units in the existing manufacturing process model library based on the optimal node set obtained by algorithm processing, and obtain all data of these manufacturing activities and production units, including model position and size, etc., so that the newly generated demand model can be viewed without position confusion and other problems, and the readability of the model is improved.

[0153] Manufacturing process model generation: The purpose of this step is to process the obtained manufacturing process model data, such as updating the ID of the existing production unit and manufacturing activity data, adding new manufacturing activity data, etc., to generate the final manufacturing process model data, so that the modeling tool can directly view or modify the manufacturing process model through parsing the manufacturing process model data on the modeling canvas.

[0154] The final manufacturing process model includes the following production unit objects: Purchasing Department, Quality Inspection Department, Production Planning Department, Warehousing Department, Production Workers, Assembly Workers, Surface Treatment Workers, Equipment Maintenance Workers, Packaging Workers, Logistics Department, and Data Analyst. Manufacturing activities include: Purchasing raw materials, pre-treating materials, accepting materials, developing production plans, assigning production tasks, managing raw material inventory, distributing materials to the production line, pre-treating materials, manufacturing parts, assembling products, surface treatment and painting, quality inspection during production, product testing, preventative maintenance, equipment failure repair, final product inspection, packaging finished products, storing finished products, preparing for product shipment, and arranging transportation. The activities of analyzing and recording production data, and routine equipment inspections were removed because they did not meet the optimal solution.

[0155] Based on the above method, the present invention also provides an apparatus for supporting the reconstruction of complex product manufacturing process models, such as... Figure 3 As shown, the application layer of this device includes: a manufacturing process meta-model library construction unit, a manufacturing process model library construction unit, and a manufacturing process model reconstruction unit.

[0156] The Manufacturing Process Meta-Model Library Building Unit is used to build a manufacturing process meta-model library using the multi-architecture modeling language KARMA.

[0157] A manufacturing process model library construction unit is used to construct a manufacturing process model library based on a manufacturing process meta-model library; the manufacturing process model library includes the production units involved in the basic manufacturing process and the manufacturing activities they perform, as well as the execution order between the manufacturing activities;

[0158] The manufacturing process model reconstruction unit includes an analysis module, a preliminary solution generation module, an optimization module, and a reconstruction module;

[0159] The parsing module receives the manufacturing process model reconstruction requirement text organized according to the statement structure provided by the manufacturing process reconstruction requirement template; and parses the manufacturing process reconstruction requirements according to the manufacturing process reconstruction dictionary, including production units, new manufacturing activities, manufacturing goals, and manufacturing constraints.

[0160] The manufacturing process refactoring requirement template is constructed based on the terminology provided by the manufacturing process refactoring dictionary, and includes a production unit selection template, a manufacturing activity addition template, a manufacturing target template, and a manufacturing constraint template.

[0161] The preliminary solution generation module is used to match the production units and new manufacturing activities parsed by the parsing module in the manufacturing process model library, extract the manufacturing activities that the production units need to perform, as well as the production unit information, all manufacturing activity information and execution order, and generate a preliminary manufacturing process model solution.

[0162] The optimization module is used to perform multi-objective optimization of the manufacturing activities in the preliminary manufacturing process model scheme based on the manufacturing objectives and constraints analyzed by the analysis module.

[0163] The reconstruction module is used to reconstruct the final manufacturing process scheme based on the multi-objective optimization results of the optimization module.

[0164] In summary, this invention allows users to input manufacturing process reconstruction requirements, such as manufacturing process specifications, based on a constructed manufacturing process model library and following structured templates. The system then extracts information and matches elements based on the input manufacturing process reconstruction requirements to obtain a preliminary manufacturing process model solution. Finally, a multi-objective optimization algorithm is used to weigh and optimize the early requirements justification process, reconstructing the final manufacturing process solution and realizing a model-driven, adaptive, and reconfigurable manufacturing process function.

[0165] The specific embodiments described above only illustrate the design principles of the present invention. The shapes and names of the components in this description may differ and are not limited. Therefore, those skilled in the art can modify or make equivalent substitutions to the technical solutions described in the foregoing embodiments; and these modifications and substitutions do not depart from the inventive spirit and technical solutions of the present invention, and should all fall within the protection scope of the present invention.< / model> < / model> < / model> < / min> < / min> < / model> < / object> < / is> < / name> < / add> < / shall> < / contain> < / shall> < / model> < / max> < / model> < / object> < / is> < / name> < / add> < / shall> < / contain> < / shall> < / object> < / is> < / name> < / add> < / shall> < / max> < / model> < / object> < / is> < / name> < / add> < / shall> < / contain> < / shall>

Claims

1. A method for supporting the reconstruction of complex product manufacturing process models, characterized in that, include: Step S1: Construct a manufacturing process model library based on the manufacturing process meta-model library built on the multi-architecture modeling language KARMA, and define the manufacturing process refactoring dictionary and manufacturing process refactoring requirement template; The manufacturing process model library includes the production units involved in the basic manufacturing process and the manufacturing activities they perform, as well as the execution order between the manufacturing activities; The manufacturing process refactoring requirement template is constructed based on the manufacturing process refactoring dictionary and specifies the sentence structure of the manufacturing process model refactoring requirement text, including the production unit selection template, manufacturing activity addition template, manufacturing target template, and manufacturing constraint template. Step S2: Based on the manufacturing process refactoring requirement template, input the manufacturing process model refactoring requirement text; based on the manufacturing process refactoring dictionary, parse the manufacturing process refactoring requirements, including production units, new manufacturing activities, manufacturing goals, and manufacturing constraints. Step S3: Based on the production unit and new manufacturing activity analyzed in step S2, match them in the manufacturing process model library, extract the manufacturing activities that the production unit needs to perform, as well as the production unit information, all manufacturing activity information and execution order, and generate a preliminary manufacturing process model scheme. Step S4: Based on the manufacturing objectives and constraints analyzed in Step S2, perform multi-objective optimization on the manufacturing activities in the preliminary manufacturing process model scheme to reconstruct the final manufacturing process scheme.

2. The method as described in claim 1, characterized in that, Step S4 employs a non-dominated sorting genetic algorithm II for multi-objective optimization.

3. The method as described in claim 1 or 2, characterized in that, In step S4, when performing multi-objective optimization, each manufacturing activity in the preliminary manufacturing process model is used as a node to construct a node set. By randomly sampling from the node set, a subset of nodes is generated as the initial population. Based on the resolved manufacturing objectives and constraints, each node in the node set is adaptively selected to obtain the optimal solution set.

4. The method as described in claim 1, characterized in that, In step 1, the meta-models included in the manufacturing process meta-model library are: The primitive model includes: a manufacturing process primitive model, used to describe the manufacturing process; The object metamodel includes: production unit object metamodel, manufacturing activity object metamodel, start object metamodel, and end object metamodel; the production unit object metamodel is used to describe the production units in the manufacturing process and their related characteristics, including name attribute; the manufacturing activity object metamodel is used to describe the manufacturing activities in the manufacturing process and their related characteristics, including name attribute, time attribute, cost attribute, and resource consumption rate attribute. Relational meta-models include: control flow relational meta-models, which are used to describe the sequential relationship between two manufacturing activities.

5. The method as described in claim 4, characterized in that, The manufacturing process model library constructed in step S1 includes: The production unit includes: purchasing department, quality inspection department, production planning department, warehousing department, production workers, assembly workers, surface treatment workers, equipment maintenance workers, packaging workers, logistics department, and data analysts; Manufacturing activities include: purchasing raw materials (constructed in the Purchasing Department); accepting materials, conducting quality inspections during production, performing product testing, and inspecting final products (constructed in the Quality Inspection Department); formulating production plans and assigning production tasks (constructed in the Production Planning Department); managing raw material inventory, distributing materials to the production line, and storing finished products (constructed in the Warehousing Department); pre-processing materials and manufacturing parts (constructed in the Production Workers' Objects); assembling products (constructed in the Assembly Workers' Objects); surface treatment and painting (constructed in the Surface Treatment Workers' Objects); daily equipment inspection, preventative maintenance, and equipment failure repair (constructed in the Equipment Maintenance Workers' Objects); packaging finished products (constructed in the Packaging Workers' Objects); arranging transportation (constructed in the Logistics Department's Objects); and analyzing production data (constructed in the Data Analyst's Objects). Manufacturing activities also include: start objects and end objects. After the manufacturing activities are constructed, the control flow relation meta-model is used to connect the manufacturing activities in the required order to form the basic manufacturing process.

6. The method as described in claim 1, characterized in that, The manufacturing process refactoring dictionary includes {new manufacturing process model: new model}, {shall: shall}, {contain: contain}, {add: add}, {add: add}, {name: name}, {is: is}, {production activity: object}, {max: max}, {more than: more than}, {more than: morethan}, {rather than: rather than}, {less than: rather than}, and {manufacturing process model, model}.

7. The method as described in claim 1, characterized in that, The specific template for manufacturing process reengineering requirements is as follows: The production unit selection template is as follows:<new model> <shall> <contain> …，…，…；< / contain> < / shall> The template for the manufacturing activity is as follows: ... <shall> <add> <name> <is> … <object>； The manufacturing target template is: <model> … <max min> ；< / max> < / model> The manufacturing constraint template is: ... <shall> <add> <name> <is> … <object>。 8. The method as described in claim 1, characterized in that, In step S3, generating the preliminary manufacturing process model scheme includes: manufacturing process model data conversion and generation and display of the preliminary manufacturing process scheme. The steps of manufacturing process model data conversion are to convert the extracted data that needs to be displayed into form data; The steps for generating and displaying the preliminary manufacturing process plan involve presenting the converted form data in a tabular format.

9. The method as described in claim 1, characterized in that, The production unit objects and manufacturing activity objects in the manufacturing process model library also include the position and size of the object nodes on the layout; When reconstructing the final manufacturing process scheme as described in step S4, the manufacturing activities and production units are matched in the manufacturing process model library according to the optimization scheme. The positions and sizes of these manufacturing activities and production units are obtained and provided to the modeling tool to display icons of each object on the modeling canvas for users to view and modify.

10. An apparatus for supporting the reconstruction of complex product manufacturing process models, characterized in that, include: Manufacturing process meta-model library construction unit, manufacturing process model library construction unit, manufacturing process model reconstruction unit; The manufacturing process meta-model library construction unit is used to build a manufacturing process meta-model library using the multi-architecture modeling language KARMA. The manufacturing process model library construction unit is used to construct a manufacturing process model library based on the manufacturing process meta-model library; the manufacturing process model library includes the production units involved in the basic manufacturing process and the manufacturing activities they perform, as well as the execution order between the manufacturing activities; The manufacturing process model reconstruction unit includes an analysis module, a preliminary scheme generation module, an optimization module, and a reconstruction module; The parsing module is used to receive the manufacturing process model reconstruction requirement text organized according to the statement structure provided by the manufacturing process reconstruction requirement template; and to parse the manufacturing process reconstruction requirement according to the manufacturing process reconstruction dictionary, including production unit, new manufacturing activity, manufacturing target, and manufacturing constraint. The manufacturing process refactoring requirement template is constructed based on the terminology provided by the manufacturing process refactoring dictionary, and includes a production unit selection template, a manufacturing activity addition template, a manufacturing target template, and a manufacturing constraint template. The preliminary scheme generation module is used to match the production unit and new manufacturing activities parsed by the parsing module in the manufacturing process model library, extract the manufacturing activities that the production unit needs to perform, as well as the production unit information, all manufacturing activity information and execution order, and generate a preliminary manufacturing process model scheme. The optimization module is used to perform multi-objective optimization of the manufacturing activities in the preliminary manufacturing process model scheme based on the manufacturing objectives and manufacturing constraints analyzed by the analysis module. The reconstruction module is used to reconstruct the final manufacturing process scheme based on the multi-objective optimization results of the optimization module. < / object> < / is> < / name> < / add> < / shall> < / object> < / is> < / name> < / add> < / shall>

Images