CN117745152B - AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system - Google Patents
AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system Download PDFInfo
- Publication number
- CN117745152B CN117745152B CN202410153231.XA CN202410153231A CN117745152B CN 117745152 B CN117745152 B CN 117745152B CN 202410153231 A CN202410153231 A CN 202410153231A CN 117745152 B CN117745152 B CN 117745152B
- Authority
- CN
- China
- Prior art keywords
- product
- production
- stage
- factory
- plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004519 manufacturing process Methods 0.000 claims abstract description 258
- 238000012545 processing Methods 0.000 claims description 26
- 238000013461 design Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 238000003908 quality control method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000016507 interphase Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 238000012430 stability testing Methods 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an industrial automatic modeling method and system based on AIGC, comprising the following steps: determining product information of a product to be produced based on the production order; determining a plurality of product phases of a product to be produced based on the product category; selecting a plurality of groups of production factories from a factory database based on the product stage; the production factories respectively correspond to a plurality of product stages, and each production factory at least comprises one factory for completing the production content of the corresponding product stage; selecting at least one factory from each group of production factories as a stage production factory for completing production content of a corresponding product stage based on the product information; each stage production factory is an independent factory; acquiring production parameters of a production factory in a plurality of stages, and constructing a virtual factory based on the production parameters; coordinating a plurality of said stage production plants to produce products jointly by controlling the virtual plants; so as to reduce the production time and improve the yield.
Description
Technical Field
The invention relates to the technical field of factory production control, in particular to an industrial automatic modeling method and system based on AIGC.
Background
Cloud manufacturing is a manufacturing mode based on cloud computing and Internet of things technology, manufacturing industry and information technologies such as cloud computing, big data, internet of things and the like are organically combined, and sharing, coordination and intelligent management of manufacturing resources are achieved. In the cloud manufacturing mode, manufacturing enterprises can acquire required manufacturing resources, technologies and services through the cloud platform, and flexible production and supply chain management is achieved. Cloud manufacturing achieves sharing and cooperative utilization of manufacturing resources, including equipment, tools, manpower, knowledge, information and the like, through a cloud platform. The manufacturing enterprises can acquire required resources through the cloud platform, so that the cost is reduced, the efficiency is improved, and market demand changes are flexibly dealt with. The cloud manufacturing supports customized production requirements, and can rapidly adjust production lines and production flows according to customer requirements, so that small-batch and diversified production is realized. However, since cloud manufacturing often requires multiple factories to jointly produce products, the multiple factories often lack effective coordination control when producing products, so that the final products are greatly different from the demands of customers, and the problem of low time-consuming yield is caused. In addition, there are a number of unreasonable choices for the plant.
In view of the above, the application provides an industrial automatic modeling method and system based on AIGC (artificial intelligence generation content), which realizes the joint control of a cloud platform on factories for processing products by modeling a plurality of factories, reduces the production time and improves the yield.
Disclosure of Invention
The invention aims to provide an industrial automatic modeling method based on AIGC, which comprises the following steps: determining product information of a product to be produced based on the production order; the product information comprises product category, customer information, time information and demand information; determining a plurality of product stages of the product to be produced based on the product category; selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of groups of production factories respectively correspond to the plurality of product stages, and each group of production factories at least comprises one factory for completing the production content of the corresponding product stage; selecting at least one factory from each group of production factories as a stage production factory for completing production content of a corresponding product stage based on the product information; each stage production factory is an independent factory; obtaining production parameters of a plurality of production factories at the stage, and constructing a virtual factory based on the production parameters; by controlling the virtual factory, a plurality of the stage production factories are coordinated to jointly produce a product.
Further, the product stage includes a design stage, a production stage, and an acceptance stage.
Further, the selecting a plurality of groups of production factories from a factory database based on the product stage includes: respectively extracting the characteristics of each factory on the cloud platform, and normalizing the characteristics to obtain factory characteristics; assigning weights to the elements in the factory features based on the class correlation to obtain a first factory feature; classifying factories of the cloud platform based on the first factory features to obtain a plurality of first factory sets corresponding to product categories; selecting a target factory set from a plurality of first factory sets based on the class of the product to be produced; assigning weights to the elements of the plant features in the target plant set based on the stage correlation to obtain second plant features; and classifying the target factory set based on the second factory characteristics to obtain a plurality of production factory groups corresponding to the product stages.
Further, classifying factories of the cloud platform through a first k nearest neighbor algorithm; the k value of the first k nearest neighbor algorithm is obtained through cross verification; the distance between the first factory feature and the adjacent factory feature is smaller than a first preset distance; classifying the target factory set by a second k-nearest neighbor algorithm; the k value of the second k nearest neighbor algorithm is obtained through cross verification; the second factory feature is less than a second predetermined distance from its immediate neighbors.
Further, the expression of the first preset distance is:
;
wherein, Representing a first preset distance; /(I)Representing the aggregate variable; /(I)Representing a total number of the first set of plants; /(I)AndRespectively representing first plant characteristic variables in different first plant sets; /(I)And/>Respectively representing the total number of first factory features within the different first factory sets; /(I)Represents the/>First plant set of/>A first factory feature; /(I)Represents the/>First plant set of/>A first factory feature; /(I)Representing the minimum value of the absolute value;
The expression of the second preset distance is:
;
wherein, Representing a second preset distance; /(I)Representing a plant group variable; /(I)Representing the total number of groups of phase plants; /(I)AndRespectively representing second plant characteristic variables in different stage plant groups; /(I)And/>Respectively representing the total number of second plant features in the different stage plant groups; /(I)Represents the/>Within the individual phase plant group/>A second factory feature; represents the/> Within the individual phase plant group/>A second factory feature; /(I)Representing the minimum value taking the absolute value.
Further, the selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the product information includes: constructing a factory selection objective function; the plant selection objective function is related to a plant address; constructing a factory selection constraint condition; the factory selection constraint conditions comprise a construction period constraint and a transportation constraint; and solving the plant selection objective function based on the plant selection constraint condition to obtain a transportation route between a plant for producing the product in each product stage and each product stage.
Further, the expression of the plant selection objective function is:
;
wherein D represents the transport distance along the product phase from the first stage production plant group to the last stage production plant group; min represents the minimum value; Representing product phase variables; q represents the total number of product stages for producing the product; representing the total number of stage production plants for completing the e-1 th product stage; /(I) Representing a total number of phase production plants for completing the e-th product phase; /(I)Representing a stage production plant variable for completing the e-1 th product stage; /(I)A phase production factory variable representing a phase for completing an e-th product phase; /(I)Representing a distance between a stage production factory for completing the e-1 th product stage and a stage production factory for completing the e-1 th product stage; /(I)The value is 0 or 1, when the value is 1, the factories in the front and rear stages have a sequential processing relationship, and when the value is 0, the factories in the front and rear stages have no sequential processing relationship.
Further, the expression of the construction period constraint is:
;
wherein, Representing product phase variables; q represents the total number of product stages for producing the product; /(I)Representing the production time of the e-th product stage; /(I)Representing the transport time; /(I)Representing the production period of the product.
Further, the expression of the transport constraint is:
;
;
wherein, Representing product phase variables; /(I)Representing the total number of stage production plants for completing the e-1 th product stage; /(I)Representing a total number of phase production plants for completing the e-th product phase; /(I)Representing a stage production plant variable for completing the e-1 th product stage; /(I)A phase production factory variable representing a phase for completing an e-th product phase; Representing the distance of the stage production plant for completing the e-1 th product stage from the stage production plant for completing the e-1 th product stage.
The invention also provides an industrial automatic modeling system based on AIGC, which comprises a product information determining module, a product stage determining module, a generating factory determining module, a stage production factory determining module, a virtual factory building module and a control module; the product information determining module is used for determining product information of a product to be produced based on the production order; the product information comprises product category, customer information, time information and demand information; the product stage determining module is used for determining a plurality of product stages of the product to be produced based on the product category; the generating factory determining module is used for selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of groups of production factories respectively correspond to the plurality of product stages, and each group of production factories at least comprises one factory for completing the production content of the corresponding product stage; the stage production factory determining module is used for selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the client information; each stage production factory is an independent factory; the virtual factory building module is used for obtaining production parameters of a plurality of production factories in the stage and building a virtual factory based on the production parameters; the control module is used for controlling the virtual factory and coordinating a plurality of the stage production factories to jointly produce products.
The technical scheme of the embodiment of the invention has at least the following advantages and beneficial effects:
the factories on the cloud platform are classified to obtain the target factory set, and then the target factory set is classified to obtain the production factory set, so that the grouping accuracy of the production factory set can be improved, and the interference is reduced.
By using the first and second factory features smaller than the first and second preset thresholds as neighbors, noise data can be reduced and classification accuracy can be improved.
The transportation route between factories and product stages for producing products in each stage is determined through the factory selection constraint conditions and the factory selection objective function, so that production time can be minimized under the condition of meeting production requirements, and the conditions of error coordination or product transportation error between factories due to excessive factories can be avoided, thereby further improving production efficiency.
Drawings
FIG. 1 is an exemplary flow chart of an industrial automation modeling method based on AIGC provided in accordance with some embodiments of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
FIG. 1 is an exemplary flow chart of an industrial automation modeling method based on AIGC provided in accordance with some embodiments of the invention. As shown in fig. 1, the process 100 includes the following:
Step 110, determining product information of a product to be produced based on the production order.
A production order may refer to an order in which a customer entrusts production of a certain product. The product to be produced refers to the product that the customer entrusts to produce. The products to be produced can be of various kinds, for example, foods, daily necessities, clothing, electronic products, paper products, and the like. Product information may refer to information in a production order regarding a product to be produced. For example, the product information may include product category, customer information, time information, demand information, and the like. The product category may refer to information related to the category of the product. For example, the product categories may include production flows, processing techniques, production conditions, and the like. Customer information may refer to information related to a customer. For example, the customer information may include time of order, time of delivery, customer address, customer level, customer contact details, and the like. The demand information may refer to a user's demand for a product to be produced. For example, demand information may include production budget, product usage, product size, product functionality, parameter requirements, and the like. Different products can have different requirements, taking a packaging box as an example: the demand information may include size, color, font content, picture content, printing accuracy, use, style, budget, and the like. Taking a power amplifier as an example: the demand information may include amplifier size, amplification factor, signal to noise ratio, operating environment, etc.
Step 120, determining a plurality of product phases of the product to be produced based on the product category. The product phase refers to the multiple phases of producing a product. For example, the product phase may include a design phase, a production phase, and an acceptance phase.
In some embodiments, a production flow of a product to be produced may be obtained; the production flow comprises a plurality of production sub-flows; inputting the multiple production sub-flows and the product stages into a semantic model, and matching the multiple production sub-flows to the multiple product stages of the product by the model to obtain the production content of the product in each product stage.
Taking a package as an example, the production sub-process of the package may include design, material selection and preparation, printing, cutting and trimming, folding and forming, bonding and assembly, and quality control; the production sub-process of the design stage after matching comprises design, material selection and preparation; the production sub-process of the production stage comprises printing, cutting and clipping, folding and forming, bonding and assembling; the production sub-process of the acceptance phase includes quality control.
Taking a power amplifier as an example, the production sub-process of the power amplifier comprises design development, prototype fabrication, design modification and optimization, production preparation, component purchase, circuit board manufacture, circuit board assembly, post-welding treatment, test and debugging, aging and stability test, packaging and final assembly and final quality control. The production sub-flow of the design stage after matching comprises design development, prototype making, design modification and optimization; the production sub-process of the production stage comprises production preparation, component purchase, circuit board manufacture, circuit board assembly and post-welding treatment; the production sub-process of the acceptance phase includes testing and debugging, burn-in and stability testing, packaging and final assembly and final quality control.
Step 130, selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of production factories respectively correspond to the plurality of product stages, and each production factory comprises at least one factory for completing the production content of the corresponding product stage. Wherein, based on the product stage, selecting a plurality of groups of production factories from a factory database comprises:
respectively extracting the characteristics of each factory on the cloud platform, and normalizing the characteristics to obtain factory characteristics; factory features include factory type, product type, equipment number, factory address, etc.
Assigning weights to the elements in the factory features based on the class correlation to obtain a first factory feature; the class relativity refers to the degree of relatedness of the element and the product class, and the higher the relatedness is, the higher the weight is, and the lower the weight is, otherwise.
And classifying factories of the cloud platform based on the first factory features to obtain a plurality of first factory sets corresponding to the product categories. For example, factories are classified into a food factory set, a daily necessities factory set, a clothing factory set, an electronic product factory set, a paper product factory set, and the like.
And selecting a target factory set from a plurality of first factory sets based on the class of the product to be produced. For example, if the product to be produced is a package, the paper product plant is set as the target plant. For another example, if the product to be produced is a power amplifier, the electronic product factory set is taken as the target factory set.
In some embodiments, the factories of the cloud platform may be classified by a first k-nearest neighbor algorithm; the k value of the first k nearest neighbor algorithm is obtained through cross verification; the first factory feature is less than a first preset distance from its neighbors. The expression of the first preset distance is:
;
wherein, Representing a first preset distance; /(I)Representing the aggregate variable; /(I)Representing a total number of the first set of plants; /(I)AndRespectively representing first plant characteristic variables in different first plant sets; /(I)And/>Respectively representing the total number of first factory features within the different first factory sets; /(I)Represents the/>First plant set of/>A first factory feature; /(I)Represents the/>First plant set of/>A first factory feature; /(I)Representing the minimum value taking the absolute value.
Assigning weights to the elements of the plant features in the target plant set based on the stage correlation to obtain second plant features; the stage relativity refers to the relativity of elements and the production stage of the product; the correlation degree is high and the weight is high, otherwise, the correlation degree is low.
And classifying the target factory set based on the second factory characteristics to obtain a plurality of production factory groups corresponding to the product stages. For example, a production factory set for completing a design phase, a production factory set for completing a production phase, and a production factory set for completing an acceptance phase.
In some embodiments, the target set of plants may be classified by a second k-nearest neighbor algorithm; the k value of the second k nearest neighbor algorithm is obtained through cross verification; the second factory feature is less than a second predetermined distance from its immediate neighbors. The expression of the second preset distance is:
;
wherein, Representing a second preset distance; /(I)Representing a plant group variable; /(I)Representing the total number of groups of phase plants; /(I)AndRespectively representing second plant characteristic variables in different stage plant groups; /(I)And/>Respectively representing the total number of second plant features in the different stage plant groups; /(I)Represents the/>Within the individual phase plant group/>A second factory feature; represents the/> Within the individual phase plant group/>A second factory feature; /(I)Representing the minimum value taking the absolute value.
Step 140, selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the product information; the stage production plants include a design stage plant, a production stage plant, and an acceptance stage plant; each stage production plant is an independent plant.
In some embodiments, a multi-stage production plant may be selected based on the plant's address, including:
constructing a factory selection objective function; the plant selection objective function is related to a plant address; the expression of the plant selection objective function is as follows:
;
wherein D represents the transport distance along the product phase from the first stage production plant group to the last stage production plant group; min represents the minimum value; Representing product phase variables; q represents the total number of product stages for producing the product; representing the total number of stage production plants for completing the e-1 th product stage; /(I) Representing a total number of phase production plants for completing the e-th product phase; /(I)Representing a stage production plant variable for completing the e-1 th product stage; /(I)A phase production factory variable representing a phase for completing an e-th product phase; /(I)Representing a distance between a stage production factory for completing the e-1 th product stage and a stage production factory for completing the e-1 th product stage; /(I)The value is 0 or 1, when the value is 1, the factories in the front and rear stages have a sequential processing relationship, and when the value is 0, the factories in the front and rear stages have no sequential processing relationship.
Constructing a factory selection constraint condition; the factory selection constraint conditions comprise a construction period constraint and a transportation constraint; the expression of the construction period constraint is as follows:
;
wherein, Representing product phase variables; q represents the total number of product stages for producing the product; /(I)Representing the production time of the e-th product stage; /(I)Representing the transport time; /(I)Representing the production period of the product.
And solving the plant selection objective function based on the plant selection constraint condition to obtain a transportation route between a plant for producing the product in each product stage and each product stage.
The expression of the transport constraint is:
;
;
wherein, Representing product phase variables; /(I)Representing the total number of stage production plants for completing the e-1 th product stage; /(I)Representing a total number of phase production plants for completing the e-th product phase; /(I)Representing a stage production plant variable for completing the e-1 th product stage; /(I)A phase production factory variable representing a phase for completing an e-th product phase; Representing the distance of the stage production plant for completing the e-1 th product stage from the stage production plant for completing the e-1 th product stage.
Step 150, obtaining production parameters of a plurality of the stage production factories, and constructing a virtual factory based on the production parameters.
The production parameters include the detailed specifications of the equipment within the production plant, the operating parameters of the equipment, the performance data of the equipment, the workflow of the product to be produced, the line configuration of the plant and the material handling process.
In some embodiments, building a virtual factory based on production parameters includes:
Production parameters of a stage production factory of each product stage are respectively obtained, and the production parameters are uploaded to a cloud database to obtain stage parameters; for example, the stage parameters may include the speed at which each stage production plant completes one current stage product, the distance from the previous stage plant to transport the previous stage product to the plant, the number of product processes per stage production plant, and the like.
Constructing a stage virtual factory on the cloud platform based on the stage parameters; the phase virtual factory refers to a virtual factory for completing production content of a corresponding phase.
And associating the stage production factories in the same product stage to obtain the stage virtual parameters. The stage virtual parameter is used to represent the processing conditions of the stage virtual factory. The stage virtual parameters may include stage process time, stage process product quantity, and the like. The stage processing time is the starting time of processing the first product to the ending time of processing the last product in the production stage factory of the product stage; the start time and the end time may be the same production stage factory or different production stages. The number of products processed by the production plant at each of the product stages is the total number of products to be produced.
And associating the stage virtual factories of different stages to obtain the inter-stage virtual parameters. The inter-phase virtual parameters are used to represent the relationship between the phase virtual factories of different product phases. The inter-stage virtual parameters may include coincident processing time and stage product parameters, etc. The overlapping processing time refers to the time when the product is processed at the same time as the processing at the previous stage and the two processing are simultaneously performed at the current time, and is called overlapping time. The stage product parameters refer to parameters of the product generated in the current stage for subsequent processing.
Linkage control logic is added between the stage virtual factories, and sub-linkage control logic is added in the stage virtual factories. The coordinated control logic refers to control logic that coordinates the process states of the virtual plant at the stage. For example, the start processing time and the end processing time of the production factory at each stage are controlled to process other products at the time of processing the present product. The sub-linkage control logic refers to logic for coordinating the processing state of the production plant at the stage of coordination. For example, the number of products processed by each stage production plant is controlled, the processing time of the stage production plant is coordinated so that the processing time of the stage is minimized, and the like.
Step 160, coordinating a plurality of the stage production plants to jointly produce the product by controlling the virtual plants. For example, the cloud platform issues linkage control logic or sub-linkage control logic to adjust the processing state of each factory production, so as to change the production progress of the product.
The invention also provides an industrial automatic modeling system based on AIGC. The system includes a product information determination module, a product phase determination module, a generation plant determination module, a phase production plant determination module, a virtual plant construction module, and a control module.
The product information determining module is used for determining product information of a product to be produced based on the production order; the product information includes product category, customer information, time information, and demand information.
The product stage determining module is used for determining a plurality of product stages of the product to be produced based on the product category.
The generating factory determining module is used for selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of production factories respectively correspond to the plurality of product stages, and each production factory comprises at least one factory for completing the production content of the corresponding product stage.
The stage production factory determining module is used for selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the client information; each stage production plant is an independent plant.
The virtual factory building module is used for obtaining production parameters of a plurality of the stage production factories and building the virtual factories based on the production parameters.
The control module is used for controlling the virtual factory and coordinating the production factories in a plurality of stages to jointly produce products.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An industrial automation modeling method based on AIGC, comprising:
Determining product information of a product to be produced based on the production order; the product information comprises product category, customer information, time information and demand information;
Determining a plurality of product stages of the product to be produced based on the product category;
Selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of groups of production factories respectively correspond to the plurality of product stages, and each group of production factories at least comprises one factory for completing the production content of the corresponding product stage;
Selecting at least one factory from each group of production factories as a stage production factory for completing production content of a corresponding product stage based on the product information; each stage production plant is an independent plant, comprising:
constructing a factory selection objective function; the plant selection objective function is related to a plant address; the expression of the plant selection objective function is as follows:
;
Wherein D represents the transport distance along the product phase from the first stage production plant group to the last stage production plant group; Representing the minimum value;/( Representing product phase variables; /(I)Representing the total number of product stages in which the product is produced; Representation for completing the/> The total number of stage production plants for each product stage; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>Stage production factory variables for individual product stages; Representation for completing the/> Stage production factory variables for individual product stages; /(I)Representation for completing the/>Stage production plant and completion of the product stageThe distance of the stage production plant for each product stage; /(I)The value is 0 or 1, when the value is 1, the factories in the front and rear stages have a sequential processing relationship, and when the value is 0, the factories in the front and rear stages have no sequential processing relationship;
constructing a factory selection constraint condition; the factory selection constraint conditions comprise a construction period constraint and a transportation constraint; the expression of the construction period constraint is as follows:
;
wherein, Representing product phase variables; /(I)Representing the total number of product stages in which the product is produced; /(I)Represents the/>Production time of individual product stages; /(I)Representing the transport time; /(I)Representing the production period of the product;
the expression of the transport constraint is:
;
;
wherein, Representing product phase variables; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>Stage production factory variables for individual product stages; /(I)Representation for completing the/>Stage production factory variables for individual product stages; Representation for completing the/> Stage production plant and completion of the product stageThe distance of the stage production plant for each product stage;
Solving the plant selection objective function based on the plant selection constraint condition to obtain a transportation route between a plant for carrying out product production in each product stage and each product stage;
Obtaining production parameters of a plurality of production factories at the stage, and constructing a virtual factory based on the production parameters;
by controlling the virtual factory, a plurality of the stage production factories are coordinated to jointly produce a product.
2. The AIGC-based industrial automation modeling method of claim 1, wherein the product phase includes a design phase, a production phase, and an acceptance phase.
3. The AIGC-based industrial automation modeling method of claim 1, wherein the selecting a plurality of sets of production plants from a plant database based on the product phase includes:
Respectively extracting the characteristics of each factory on the cloud platform, and normalizing the characteristics to obtain factory characteristics;
Assigning weights to the elements in the factory features based on the class correlation to obtain a first factory feature;
Classifying factories of the cloud platform based on the first factory features to obtain a plurality of first factory sets corresponding to product categories;
selecting a target factory set from a plurality of first factory sets based on the class of the product to be produced;
assigning weights to the elements of the plant features in the target plant set based on the stage correlation to obtain second plant features;
and classifying the target factory set based on the second factory characteristics to obtain a plurality of production factory groups corresponding to the product stages.
4. A AIGC-based industrial automation modeling method according to claim 3, characterised in that the factories of the cloud platform are classified by a first k-nearest neighbor algorithm; the k value of the first k nearest neighbor algorithm is obtained through cross verification; the distance between the first factory feature and the adjacent factory feature is smaller than a first preset distance;
classifying the target factory set by a second k-nearest neighbor algorithm; the k value of the second k nearest neighbor algorithm is obtained through cross verification; the second factory feature is less than a second predetermined distance from its immediate neighbors.
5. The AIGC-based industrial automation modeling method of claim 4, wherein the first preset distance is expressed as:
;
wherein, Representing a first preset distance; /(I)Representing the aggregate variable; /(I)Representing a total number of the first set of plants; /(I)And/>Respectively representing first plant characteristic variables in different first plant sets; /(I)And/>Respectively representing the total number of first factory features within the different first factory sets; /(I)Represents the/>First plant set of/>A first factory feature; represents the/> First plant set of/>A first factory feature; /(I)Representing the minimum value of the absolute value;
The expression of the second preset distance is:
;
wherein, Representing a second preset distance; /(I)Representing a plant group variable; /(I)Representing the total number of groups of phase plants; /(I)And/>Respectively representing second plant characteristic variables in different stage plant groups; /(I)And/>Respectively representing the total number of second plant features in the different stage plant groups; /(I)Represents the/>Within the individual phase plant group/>A second factory feature; represents the/> Within the individual phase plant group/>A second factory feature; /(I)Representing the minimum value taking the absolute value.
6. An industrial automatic modeling system based on AIGC is characterized by comprising a product information determining module, a product stage determining module, a generating factory determining module, a stage production factory determining module, a virtual factory building module and a control module;
the product information determining module is used for determining product information of a product to be produced based on the production order; the product information comprises product category, customer information, time information and demand information;
The product stage determining module is used for determining a plurality of product stages of the product to be produced based on the product category;
The generating factory determining module is used for selecting a plurality of groups of production factories from a factory database based on the product stage; the plurality of groups of production factories respectively correspond to the plurality of product stages, and each group of production factories at least comprises one factory for completing the production content of the corresponding product stage;
The stage production factory determining module is used for selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the product information; each stage production factory is an independent factory; the selecting at least one factory from each group of production factories as a stage production factory for completing the production content of the corresponding product stage based on the product information comprises:
constructing a factory selection objective function; the plant selection objective function is related to a plant address; the expression of the plant selection objective function is as follows:
;
Wherein D represents the transport distance along the product phase from the first stage production plant group to the last stage production plant group; Representing the minimum value;/( Representing product phase variables; /(I)Representing the total number of product stages in which the product is produced; Representation for completing the/> The total number of stage production plants for each product stage; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>Stage production factory variables for individual product stages; Representation for completing the/> Stage production factory variables for individual product stages; /(I)Representation for completing the/>Stage production plant and completion of the product stageThe distance of the stage production plant for each product stage; /(I)The value is 0 or 1, when the value is 1, the factories in the front and rear stages have a sequential processing relationship, and when the value is 0, the factories in the front and rear stages have no sequential processing relationship;
constructing a factory selection constraint condition; the factory selection constraint conditions comprise a construction period constraint and a transportation constraint; the expression of the construction period constraint is as follows:
;
wherein, Representing product phase variables; /(I)Representing the total number of product stages in which the product is produced; /(I)Represents the/>Production time of individual product stages; /(I)Representing the transport time; /(I)Representing the production period of the product;
the expression of the transport constraint is:
;
;
wherein, Representing product phase variables; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>The total number of stage production plants for each product stage; /(I)Representation for completing the/>Stage production factory variables for individual product stages; /(I)Representation for completing the/>Stage production factory variables for individual product stages; Representation for completing the/> Stage production plant and completion of the product stageThe distance of the stage production plant for each product stage;
Solving the plant selection objective function based on the plant selection constraint condition to obtain a transportation route between a plant for carrying out product production in each product stage and each product stage;
The virtual factory building module is used for obtaining production parameters of a plurality of production factories in the stage and building a virtual factory based on the production parameters;
the control module is used for controlling the virtual factory and coordinating a plurality of the stage production factories to jointly produce products.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410153231.XA CN117745152B (en) | 2024-02-04 | 2024-02-04 | AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410153231.XA CN117745152B (en) | 2024-02-04 | 2024-02-04 | AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117745152A CN117745152A (en) | 2024-03-22 |
CN117745152B true CN117745152B (en) | 2024-04-19 |
Family
ID=90278003
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410153231.XA Active CN117745152B (en) | 2024-02-04 | 2024-02-04 | AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117745152B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015535123A (en) * | 2012-12-19 | 2015-12-07 | グーグル インコーポレイテッド | Selecting content items based on geoposition samples |
CN106030624A (en) * | 2013-12-06 | 2016-10-12 | 邓白氏公司 | Method and system for collecting data on businesses via mobile and geolocation communications |
CN109559039A (en) * | 2018-11-29 | 2019-04-02 | 贵州航天云网科技有限公司 | A kind of virtual factory business cooperation system based on the twin technology of number |
CN115641097A (en) * | 2022-12-23 | 2023-01-24 | 深圳市仕瑞达自动化设备有限公司 | Non-standard machining collaborative manufacturing management method and system based on cloud platform |
CN116957177A (en) * | 2023-07-26 | 2023-10-27 | 陕西科技大学 | Flexible workshop production line planning method, system, equipment and medium |
CN117035364A (en) * | 2023-09-11 | 2023-11-10 | 哈尔滨工业大学 | Distributed heterogeneous flow shop scheduling method based on improved mixed cause algorithm |
CN117132181A (en) * | 2023-08-21 | 2023-11-28 | 北京工业大学 | Distributed flexible production and transportation cooperative scheduling method |
-
2024
- 2024-02-04 CN CN202410153231.XA patent/CN117745152B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015535123A (en) * | 2012-12-19 | 2015-12-07 | グーグル インコーポレイテッド | Selecting content items based on geoposition samples |
CN106030624A (en) * | 2013-12-06 | 2016-10-12 | 邓白氏公司 | Method and system for collecting data on businesses via mobile and geolocation communications |
CN109559039A (en) * | 2018-11-29 | 2019-04-02 | 贵州航天云网科技有限公司 | A kind of virtual factory business cooperation system based on the twin technology of number |
CN115641097A (en) * | 2022-12-23 | 2023-01-24 | 深圳市仕瑞达自动化设备有限公司 | Non-standard machining collaborative manufacturing management method and system based on cloud platform |
CN116957177A (en) * | 2023-07-26 | 2023-10-27 | 陕西科技大学 | Flexible workshop production line planning method, system, equipment and medium |
CN117132181A (en) * | 2023-08-21 | 2023-11-28 | 北京工业大学 | Distributed flexible production and transportation cooperative scheduling method |
CN117035364A (en) * | 2023-09-11 | 2023-11-10 | 哈尔滨工业大学 | Distributed heterogeneous flow shop scheduling method based on improved mixed cause algorithm |
Non-Patent Citations (1)
Title |
---|
面向工业互联网的可编程虚拟网络平台构建方法与实现;王子琛;《中国优秀硕士学位论文全文数据库》;20231115(第11期);I139-248 * |
Also Published As
Publication number | Publication date |
---|---|
CN117745152A (en) | 2024-03-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Towill | Forridge-Principles of good practice in material flow | |
Grubbström | Modelling production opportunities—an historical overview | |
CN104636871B (en) | A kind of control method of the single phase multi-product batch processing based on data | |
CN108805623B (en) | Supply prediction method for fast-selling products | |
CN107146039B (en) | Multi-target cooperative control customized mixed-flow assembly production method and device | |
CN109782714A (en) | Virtual electronic intelligence manufacture plant control system and its control method | |
CN111489180A (en) | Reference information generation method, system and device | |
CN108510154A (en) | A kind of Internet of Things cognitive method towards Furniture Flexible Production | |
KR102574244B1 (en) | A method and apparatus for generating future demand forecast data based on attention mechanism | |
Monostori et al. | Hybrid, AI-and simulation-supported optimisation of process chains and production plants | |
CN112070326A (en) | Multi-target production order allocation device and multi-target production order allocation method | |
CN117745152B (en) | AIGC-based industrial automatic modeling method and AIGC-based industrial automatic modeling system | |
Singh et al. | Multi-step short-term electric load forecasting using 2D convolutional neural networks | |
Edghill et al. | The use of system dynamics in manufacturing systems engineering | |
CN110675055A (en) | Automatic production line modeling and layout planning method and system | |
CN109683555A (en) | A kind of furniture design production system | |
CN106056435A (en) | Design model sharing system in cloud manufacturing environment | |
CN107942926A (en) | Parameter self modification method/system, readable storage medium storing program for executing and the equipment of the small trade mark | |
Karlsson et al. | Online knowledge extraction and preference guided multi-objective optimization in manufacturing | |
CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
CN112712239B (en) | Industrial Internet based collaborative manufacturing system and control method | |
CN115719194A (en) | Big data prediction based material purchasing method and system | |
CN110047001A (en) | A kind of futures data artificial intelligence analysis method and system | |
Mörzinger et al. | A modular, holistic optimization approach for industrial appliances | |
CN113052426A (en) | Machining cost calculation method and system based on mechanical parts |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |