CN117355852A - Knowledge-based assembly process planning method, device and system - Google Patents
Knowledge-based assembly process planning method, device and system Download PDFInfo
- Publication number
- CN117355852A CN117355852A CN202180098306.3A CN202180098306A CN117355852A CN 117355852 A CN117355852 A CN 117355852A CN 202180098306 A CN202180098306 A CN 202180098306A CN 117355852 A CN117355852 A CN 117355852A
- Authority
- CN
- China
- Prior art keywords
- historical
- product
- cbs
- materials
- assembly
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 114
- 238000013461 design Methods 0.000 claims abstract description 162
- 239000000463 material Substances 0.000 claims abstract description 158
- 238000000429 assembly Methods 0.000 claims description 32
- 238000005259 measurement Methods 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 230000000712 assembly Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 3
- 239000000047 product Substances 0.000 description 162
- 238000010586 diagram Methods 0.000 description 13
- 238000013459 approach Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 6
- 238000004026 adhesive bonding Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- RVCKCEDKBVEEHL-UHFFFAOYSA-N 2,3,4,5,6-pentachlorobenzyl alcohol Chemical compound OCC1=C(Cl)C(Cl)=C(Cl)C(Cl)=C1Cl RVCKCEDKBVEEHL-UHFFFAOYSA-N 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 241001463014 Chazara briseis Species 0.000 description 1
- 238000009411 base construction Methods 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a knowledge-based assembly process planning method, which comprises the following steps: s1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database; s2, calling the historical assembly plans corresponding to the similar historical design bill of materials from a database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans; s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed in the step S2 in the historical assembly line, and reconstructing the work station into the product assembly line. The invention has the advantages of convenient use, high efficiency and intelligence.
Description
The present invention relates to the field of digitization, and in particular, to a knowledge-based assembly process planning method, apparatus, and system.
In the 4.0 era of industry, many manufacturing facilities are facing increasing customer-customized needs. How to cope with such changing demands quickly by providing flow planning and resource planning accordingly is a decisive issue.
Traditionally, production line planning has been performed manually by engineers using their judgment and experience. Some factories define standard flow procedures as a starting point to cover the customized services of a particular product family.
The above prior art solutions are highly dependent on human expertise and are error-prone and labor-intensive. For complex products, the number of possible assembly sequences can be large and even the most skilled engineers will be disadvantaged in finding the best possible sequence. In addition, the above solution cannot utilize a large amount of accumulated historical flow planning data of the historical customization needs, which may result in waste of information resources.
For example, the prior art provides a hierarchical approach to assembly sequence planning of connectors. Specifically, the principle is to generate a hierarchy of connector structures from a CAD model, then hierarchically decompose the hierarchy of connectors, retrieve similar connector structures in a database and refer to their assembly plans, and finally merge the assembly plans of the patch panel structure nodes from top to bottom. The limitation of this approach is that when retrieving similar connector structures in the database, the retrieval history reference data needs to retrieve the same parts with the same names and only the topological similarities are aligned and not quantitatively compared.
For another example, the prior art also provides a pattern similarity approach to compare assembly patterns of two production lines, as opposed to a connector structure hierarchy approach. In particular, connection information between elements and/or sub-assemblies that assemble the edges of a graphic is described in principle. The graph similarity algorithm for similar assembly search includes graph matching (topology) and similarity testing (quantitative). A limitation of this approach is that the assembly pattern has more nodes than the connector level approach, and pattern matching may require more computation.
Disclosure of Invention
The first aspect of the invention provides a knowledge-based assembly process planning method, comprising the following steps: s1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database; s2, calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans; s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed in the step S2 in the historical assembly line, and reconstructing the work station into a product assembly line.
Further, the step S1 further includes the following steps: s11, receiving a product design bill of materials, analyzing a data structure of the product design bill of materials based on a topology model template, acquiring knowledge information in the product design bill, and generating a topology model instance based on the topology model template; s22, a historical design bill of materials is called in a database, and the product design bill of materials and the historical design bill of materials are respectively converted into a product CBS map and a historical CBS map; s23, according to the product CBS map, matching the historical CBS maps, when the product CBS map is matched with the plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the plurality of historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement so as to select a similar CBS map with the minimum index difference from the plurality of historical CBS maps.
Further, the step S23 is characterized by further comprising the steps of: and (3) hierarchically matching historical CBS maps according to the product CBS maps, when one part of the product CBS maps are matched with a plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement, deconstructing the matched and unmatched parts in the product CBS maps, continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched, and when the product CBS maps are left to be unmatched, invoking standard CBS map nodes in a database to execute matching on the node.
Further, the nodes of the topology model comprise various types of entities, the entities comprise assemblies, sub-assemblies, parts and connectors, and the nodes of the CBS map are the connectors and a plurality of assemblies, sub-assemblies, parts and connectors connected with the connectors.
Further, the step S22 further includes the following steps: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
Further, the database stores a design bill of materials, a standard CBS map, a historical assembly plan, a topology model template and a historical assembly line.
A second aspect of the present invention provides a knowledge-based assembly process planning system comprising: a processor; and a memory coupled with the processor, the memory having instructions stored therein that, when executed by the processor, cause the electronic device to perform actions comprising: s1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database; s2, calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans; s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed by the action S2 in the historical assembly line, and reconstructing the work station into a product assembly line.
Further, the action S1 further includes the following steps: s11, receiving a product design bill of materials, analyzing a data structure of the product design bill of materials based on a topology model template, acquiring knowledge information in the product design bill, and generating a topology model instance based on the topology model template; s22, a historical design bill of materials is called in a database, and the product design bill of materials and the historical design bill of materials are respectively converted into a product CBS map and a historical CBS map; s23, according to the product CBS map, matching the historical CBS maps, when the product CBS map is matched with the plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the plurality of historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement so as to select a similar CBS map with the minimum index difference from the plurality of historical CBS maps.
Further, the act S23 further includes: and (3) hierarchically matching historical CBS maps according to the product CBS maps, when one part of the product CBS maps are matched with a plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement, deconstructing the matched and unmatched parts in the product CBS maps, continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched, and when the product CBS maps are left to be unmatched, retrieving standard CBS map nodes in a database to execute matching on the node.
Further, the nodes of the topology model comprise various types of entities, the entities comprise assemblies, sub-assemblies, parts and connectors, and the nodes of the CBS map are the connectors and a plurality of assemblies, sub-assemblies, parts and connectors connected with the connectors.
Further, the step S22 further includes the following steps: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
Further, the database stores a design bill of materials, a standard CBS map, a historical assembly plan, a topology model template and a historical assembly line.
A third aspect of the present invention provides a knowledge-based assembly process planning apparatus, wherein the knowledge-based assembly process planning apparatus further comprises: a similarity retrieval device which receives a product design bill of materials, acquires knowledge information in the product design bill and generates a topology model instance based on a topology model template, matches a historical design bill of materials similar to the design bill of materials of the product in a database; the assembly plan generating device is used for calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes irrelevant to the historical design bill of materials in the historical assembly plans and corresponding process steps, and reconstructing the nodes into the product assembly plan; and the assembly line generating device is used for calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work stations corresponding to the process steps removed by the assembly plan generating device in the historical assembly line and reconstructing the work stations into the product assembly line.
A fourth aspect of the invention provides a computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions which, when executed, cause at least one processor to perform a method according to the first aspect of the invention.
A fifth aspect of the invention provides a computer readable medium having stored thereon computer executable instructions which when executed cause at least one processor to perform a method according to the first aspect of the invention.
The semantic map is used as a carrier for describing an assembly body, an assembly line and assembly planning, the description capability is strong, the understanding is easy, the inference rule is easy to apply, and the naming of the entity is not limited, so that the knowledge-based assembly process planning device provided by the invention is convenient to use.
Moreover, the present invention combines topological and quantitative ways to perform a graph similarity measurement, wherein the ontology comparison is the first coarse filtering and the quantitative similarity measurement is the precise filtering further based on the first coarse filtering, thus reducing the computational effort. The quantitative measurement increases the accuracy of the similarity comparison and increases the accuracy of the recommendation over a pure topology comparison. Therefore, the invention is more efficient and accurate.
In addition, knowledge in the database is accumulated as history data for a long time, so that the recommending ability is increased, and the invention is more intelligent and self-evolutionary.
FIG. 1 is a schematic diagram of a topology model according to one particular embodiment of the invention;
FIG. 2 is a schematic diagram of the relationship between topological models of products and processes according to one embodiment of the present invention;
FIG. 3 is a schematic illustration of a recommended assembly plan and assembly line in a product design bill of materials, according to one embodiment of the invention;
FIG. 4 is a schematic diagram of a knowledge-based assembly process planning system in accordance with a particular embodiment of the invention;
FIG. 5 is a schematic diagram of converting a design bill of materials into a CBS structure in accordance with one embodiment of the present invention;
FIG. 6 is a database data diagram according to one embodiment of the invention;
FIG. 7 is a schematic diagram of a product design bill of materials conversion to a CBS structure in accordance with yet another embodiment of the present invention;
FIG. 8 is a schematic diagram of a historical design bill of materials according to yet another embodiment of the invention;
FIG. 9 is a schematic diagram of hierarchical deconstructment and graph matching in accordance with a specific embodiment of the present invention;
FIG. 10 is a schematic diagram of similarity comparison according to one embodiment of the present invention.
The following describes specific embodiments of the present invention with reference to the drawings.
The present invention provides a knowledge-based assembly process planning (assembly process planning) method, apparatus and system that reduces reliance on human expertise and increases planning quality and efficiency. The invention greatly reduces the calculation amount of database retrieval, provides a knowledge expression mode, and is more convenient for knowledge base construction. In addition, the invention realizes quantitative similarity measurement through rich geometric attributes.
When carrying out the assembly process planning with the present invention, it is important that the product structure and relationship between the elements, rather than the overall shape of the assembly model. Wherein the similar connections conform to similar assembly process steps. That is, the two fittings may not be very related and have similar assembly processes even though their all visual profiles are not very identical.
For manufacturers who typically have custom requests, they may have a large number of custom product historical assembly plans accumulated. Some of these products are of the same product type, with only some of the parts differing in their appearance, including part count, materials, and trim. For example, some electronic control cabinets including doors include glass windows, some have pure metal doors, some have 10 internal switches, and some have only 8 internal switches. Therefore, efficiency and accuracy would be greatly improved if such historical data could be used as a reference for new assembly process planning for new customer needs.
The first aspect of the invention provides a knowledge-based assembly process planning method.
Fig. 4 is a schematic diagram of the architecture of a knowledge-based assembly process planning system in accordance with a particular embodiment of the invention. The knowledge-based assembly process planning system 200 includes a similarity retrieval device 210, an assembly plan generation device 220, and an assembly line generation device 230. Wherein the similarity retrieval means 210 is for decomposing the product design bill of materials Q based on new customer requirements and performing retrieval on the knowledge database KD (Knowledge Database) using the product design bill of materials Q. Specifically, the similarity retrieval means 210 includes history extraction means 211, map structure construction means 212, and similarity measurement means 213. The assembly plan generating means 220 includes plan extracting means 221, node replacing means 222, and assembly plan constructing means 223. The assembly line generating device 230 includes a rule extracting device 231, a workstation adding and removing device 232, and an assembly line constructing device 233.
First, step S1 is executed, where the similarity retrieving device 210 receives a product design bill of materials, obtains knowledge information in the product design bill, generates a topology model instance based on a topology model template, and matches a historical design bill of materials similar to the design bill of materials of the product in a database.
When a new product order is received, the product designer typically provides a CAD model, along with its design bill of materials (EBOM, engineering Bill of Materials). The design bill of materials should have all parts, sub-assemblies (sub-assemblies), layered structures (hierarchical structures) and connections between the above parts.
The topology model (Ontology model) of the assembly structure is generated and stored in a Knowledge Base (knowledgebase), which accords with the ISO10303 standard. The ISO10303 standard 44 section provides some limited assembly design representation (assembly design representations) that captures assembly structure and dynamic joint information (kinematic joint information) during the design process. Specifically, the assembly model establishes a neutral representation of the product assembly (neutral representation), which includes multiple sets of components. In this model, the complete product is referred to as an "assembly", the lowest level of non-separable components in the assembly being referred to as "parts", two or more of the parts being assembled together as a "sub-assembly". The model focuses on the level of the product, as well as the location and orientation between parts.
As shown in fig. 1, the topology model 100 includes product and its assembly related concepts, parts, sub-assemblies, and connectors (connectors). Wherein the connector type corresponds to a particular assembly operation (assembly operation). The relationship between the concepts described above, the data property (property) of each concept is described as an attribute (attributes). Specifically, the topology model 100 includes an assembly body, a sub-assembly body 1, a sub-assembly body 2, a sub-assembly body 3, a sub-assembly body 4, a sub-assembly body 5, a part 1, a part 2, a part 3, and a part 4. The circles of fig. 1 represent the relationship between the above-described components.
FIG. 2 is a schematic diagram of the relationship between topological models of products and processes according to one embodiment of the present invention. As shown in fig. 2, a portion 310 of the topology model of the product includes assemblies, parts, sub-assemblies, connectors, and connectors. Wherein the parts and the sub-assemblies are connected by a connecting piece. The connecting piece comprises glue bonding, bolting, press fitting and snap fitting. Process 320 includes assembly operations including glue bonding operations, bolting operations, press-fitting operations, and snap-fitting operations. Wherein, the above-mentioned technology and connecting piece are in one-to-one correspondence, and the relation between technology and connecting piece is used. Specifically, the "glue bonding operation" uses "glue bonding", the "bolt operation" uses "bolting", the "press-fitting operation" uses "press-fitting", and the "snap-fitting operation" uses "snap-fitting".
Specifically, each design bill of materials information is described as an RDF or LGP map, which conforms to the topology model shown in fig. 2. The present invention attempts to find an assembly that is similar to the new customized assembly and creates a new assembly plan by modifying the assembly plan for the similar historical assembly.
Specifically, step S1 includes sub-step S11, sub-step S12, and sub-step S13.
In sub-step S11, the history extraction means 211 receives the product design bill of materials, analyzes the data structure of the product design bill of materials based on the topology model template, acquires knowledge information in the product design bill and generates a topology model instance based on the topology model template. Specifically, the history extraction means 211 is for retrieving a history design bill of materials, which is described by an RDF map or an LGP map, in a map database. If the patterns in the database are classified by product category, the history extraction means 211 need only perform a search in that category, since the products involved in the product design bill of materials are considered to belong to a certain category. Otherwise, all of the design bill of materials maps would need to be retrieved in the entire database. Wherein the profile search is identified in an application program interface in a profile database.
FIG. 3 is a schematic diagram of a recommended assembly plan and assembly line in a product design bill of materials, according to one embodiment of the invention. As shown in fig. 3, in the product design bill of materials G1, node a is an assembly, node B is a part, node c is a sub-assembly, and c1, c2, and c3 are parts or connectors. The topology model of the product and the product design bill of materials G1 are sent to the similarity retrieval means 210, and the similarity retrieval means 210 inquires from the database D a history design bill of materials similar to the design bill of materials of the product.
Wherein the database KD comprises a historical design bill of materials, an assembly plan and an assembly line. In the linked assembly plan map, the P1, P2, and P3 nodes are process step nodes, and the material nodes are connected to process nodes, which represent materials that can be consumed or manufactured in the process. Preferably, the material nodes are material flow (material flow) nodes. In addition to materials, process nodes also have some data values to describe their properties, such as process time and process name. In addition, in the linked assembly line graph, WS nodes represent workstations, and connections between WS nodes represent the sequence of process steps that occur at the workstations. Each WS node has some data values to describe its properties such as height, width, length, cost, workstation name and workstation number, etc.
In sub-step S22, the map structure construction means 212 retrieves the historical design bill of materials in the database KD, converting the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map, respectively. The step S22 further includes the steps of: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
Further, the nodes of the topology model comprise various types of entities, the entities comprise assemblies, sub-assemblies, parts and connectors, and the nodes of the CBS map are the connectors and a plurality of assemblies, sub-assemblies, parts and connectors connected with the connectors.
Specifically, the map Structure building device 212 is used to convert RDF or LPG maps in the product design bill of materials and the historical design bill of materials in the database into a CBS (Connector-Based Structure) map for short. Wherein, based on the connector structure described as a C [ P1, P2 … … Pn ] format, C represents the connector name, P1, P2 … … Pn represents the part or sub-assembly to which the connector C is connected. The connector and its parts or subassemblies can be named by the designer under any name desired. If more than one connector of the same type, the invention combines them into a connector group, denoted by (C1, C2 … … Cn) [ P1, P2 … … Pn ]. For example, 4 screws are required to secure a lid and box.
Illustratively, as shown in FIG. 5, the design bill of materials 410 may be a product design bill of materials or a historical design bill of materials. The design bill of materials 410 includes sub-assembly B, connector S1, connector R2, part N1, part N2, sub-assembly N3, sub-assembly N4, part N5, and part N6, all of which are denoted as nodes. The map structure building device 212 converts the product design bill of materials 410 into a CBS map 420. For example, part N1 is a leg, connector S1 is a screw, part N2 is a table, and part N1, connector S1, and part N2 are nodes in design bill of materials 410, but are converted to a node S1[ N1, N2] in CBS map 420. Similarly, in CBS map 420, connector B, sub-assembly B, and part N are converted to nodes B [ B, N ], connector R1, sub-assembly N3, and sub-assembly N4 are converted to nodes R1[ N3, N4], and connector R2, part N5, and part N6 are converted to nodes R2[ N5, N6].
According to the invention, the nodes such as the product, the assembly, the part, the sub-assembly and the connecting piece in the design bill of materials are converted into the form of the connecting piece and the connecting parts thereof in the CBS map, so that the number of the nodes is reduced, and the calculated amount is also reduced.
In sub-step S23, the similarity measurement means 213 matches the historical CBS patterns according to the product CBS patterns, and calculates index differences between nodes corresponding to the product CBS patterns and the historical CBS patterns, respectively, by the euclidean algorithm to perform similarity measurement when the product CBS patterns match the historical CBS patterns, so as to select a similar CBS pattern having the smallest index difference among the historical CBS patterns.
Specifically, the step S23 further includes the steps of: and (3) hierarchically matching historical CBS maps according to the product CBS maps, when one part of the product CBS maps are matched with a plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement, deconstructing the matched and unmatched parts in the product CBS maps, continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched, and when the product CBS maps are left to be unmatched, invoking standard CBS map nodes in a database to execute matching on the node.
Wherein the similarity measurement means 213 is configured to perform a hierarchical graph similarity measurement using a graph similarity algorithm, wherein the graph similarity algorithm comprises 2 incremental steps: a pattern matching step and a similarity measuring step.
The principle of pattern matching of the present invention is described below. The pattern matching uses the VF2 pattern isomorphism algorithm (VF 2 graph isomorphism algorithm), plus semantics to query the historical design material inventory patterns with similar topologies. When the graph isomorphism algorithm is executed, the node type is assigned to serve as an input attribute for the algorithm. The same connector nodes need not be under the same name at this time, they can also be identified as identical. Since semantically they are of the same type as in the topology model, they are of the same type of connection.
The hierarchical principle of pattern matching is as follows. If the query cannot find a match in the historical database once based on the connector structure map, a hierarchical structure is required and a search is performed for the match.
In one embodiment of the invention, the product design bill of materials map and the historical design bill of materials map (historical EBOM graph) in the database are not able to determine isomorphism by comparing their connector structure based maps. Assuming that the query CBS map cannot be matched to the historical CBS map, the comparison needs to be performed recursively as shown in the deconstructed and map.
For each structure, the pattern may be changed into two parts by removing the connectors of the upper layer nodes and other parts of the pattern. For each part, a matching map or sub-map is retrieved in two databases. Some known CBS structures and their assembly plans are stored in a standard database. The history database stores sub-assembly level or product level CBS structures and their plans. If similar structures are found, the assembly plans they now exist can be extracted to serve as starting points for the assembly process plan for the product.
If there are still some CBD nodes after the lowest level of structure that cannot be matched in the database, common sense rules (heurisc rules) can be executed to infer the assembly features from the basic geometric features, and then infer the assembly operation from the assembly features (assembly operations). The common sense rules can be combined in a topology model of the SWRL language and driven with a reasoner (reasoner). Illustratively, the reasoner includes Pellet or Hermit, or the like. If it is difficult to generate rules from human experience, a CBS that cannot be matched is performed manually, which does not affect the workflow of the overall system.
Specifically, in one embodiment, as shown in FIG. 7, a new customer order requires assembly An assembly as described in the product design bill of materials 510. Wherein the product design bill of materials 510 includes the following nodes: assembly, bolt, box base, backplate, HMI interface, bolt, shell assembly, PCBA, bolt, front assembly, PCBA1, PCBA2, card slot, PCB, LCD and nut. Thus, the product design bill of materials 510 described above is converted into a product CBS map 520, wherein the product CBS map 520 comprises the following nodes: first node N 11 Bolt [ box base, back plate]Second node N 12 Bolt [ HMI interface, housing assembly]Third node N 13 Bolt [ PCBA, PCBA]Fourth node N 14 Card slot [ PCBA1, PCBA2]Fifth node N 15 Bolted [ PCB, LCD ]]。
At this time, as shown in fig. 8, a historical CBS map 530 is stored in the database KD, which includes a plurality of nodes: first node N 21 Bolt [ PCBA1, front assembly body]Second node N 22 Bolted [ PCB, LCD ]]Third node N 23 Glue bonding [ slice, frame ]]。
As shown in FIG. 9, a first attempt is made to perform a first round of matching the product CBS map 520 to a first node N of the historical CBS map 530 11 Specifically, a first node N of the product CBS map 520 11 And a first node N of the historical CBS map 530 21 Is well matched, and none are well matched, so deconstructing the product CBS map 520 is performed to obtain a first node N 11 And a second node N 12 Second node N 12 Third node N 13 Second node N 14 And (5) disassembling. Then a second round of matching is performed on the unmatched portion, matching with the historical CBS map 530 to a node second node N 12 Specifically, a second node N of the product CBS map 520 12 And a first node N of the historical CBS map 530 21 Well matched, none of the others are well matched, so deconstructing the product CBS map 520 is performed to form a second node N 12 And a second node N 12 Third node N 13 Second node N 14 And (5) disassembling. Then, a third round of matching is performed on the unmatched portion, and two nodes are matched with the historical CBS map 530: third node N 13 And a fifth node N 15 . Wherein the third node N of the product CBS map 520 13 And a fifth node N 15 First nodes N respectively matched with the historical CBS map 530 21 And a second node N 22 . Wherein the matching is matched with the historical CBS map in the database KD, and a single node fourth node N is remained 14 And not matched.
Further, the matching of the present invention to a single node typically calls for standard CBS map nodes in the database, which are single nodes. As shown in FIG. 9, the database includes a standard CBS map node N 33 、N 34 And N 35 . Finally, in the present embodiment, a single node fourth node N 14 Node N of standard CBS map is matched 33 。
The similarity measurement principle is that if more than one match is found, the components inside the CBS node need to perform further comparisons in number. FIG. 10 is a schematic diagram of a similarity comparison of product CBS map 610 to two historical CBS maps 620 and 630, according to one embodiment of the invention. Specifically, product CBS map 610 includes three nodes, D [ B, K, E ], s [ K1, K2, K3] and B [ E1, E2], respectively. The two historical CBS maps 620 and 630 are structurally similar to the product CBS map 610, wherein the historical CBS map 620 includes three nodes S1[ N1, N2], R1[ N3, N4] and R2[ N5, N6], and the historical CBS map 630 includes three nodes d [ x, y ], S2[ t1, t2] and p [ k1, k2]. Wherein nodes B, N in the historical CBS map 620 are not matched.
To compare which of the historical CBS maps 620 and 630 is more similar to and matches the product CBS map 610, index differences between the corresponding nodes need to be computed by the euclidean algorithm. For example, it is necessary to compare the index differences between the nodes D [ B, K, E ] and the nodes S1[ N1, N2] and D [ x, y ] respectively, and the index differences between the nodes S [ K1, K2, K3] and the nodes R1[ N3, N4] and S2[ t1, t2] respectively. Optionally, the index includes model number, feature, size, mass, material, and the like.
Illustratively, part B and part N1 can calculate the distance between the two by the following algorithm:
where Xi is an index, a and b are two corresponding parts, and i is a natural number.
Then, step S2 is executed, where the history extracting means 211 retrieves the history assembly plan corresponding to the similar history design bill of materials from the database, the node replacing means 222 replaces the node in the history assembly plan with the node corresponding to the product design bill of materials, and the assembly plan forming means 223 removes the node in the history assembly plan, which is not related to the history design bill of materials, and the corresponding process steps thereof, and reconstructs the node into the product assembly plan. The assembly plan generation means 220 is used to generate assembly plans for new products, wherein matched CBS map structures can be derived from different assemblies, so that there can be more than one assembly plan that can be referenced. Therefore, it is first necessary to extract those assembly plans for which the CBS patterns of the product are well matched, then remove the unmatched portions of those assembly plans, and finally replace the parts and subassemblies for the matched portions of the parts/subassemblies of the product design bill of materials, and then merge the process portions in the materials of the product design bill of materials in a hierarchical relationship.
The assembly line generating device 230 is used to generate assembly lines for new products, where more than one assembly line can be referenced, so that the assembly lines are first extracted with matched parts, then the workstations that do not have matched parts or redundant process steps are removed, and then the workstations are combined in a preferential relationship in the process steps. As shown in fig. 3, in the present embodiment, the history bill of materials matched in step S1 is G2, which includes nodes A, B, C, D, E, c1, c2, c3, and E1, and the history assembly plan corresponding to the history bill of materials G2 is SP1. Wherein the historical assembly plan includes process steps P1, P2, and P3, the process steps P1 and P2 being performed prior to the process step P3. The flow before process step P1 is described by node E1, the flow after process step P1 is described by node E, the flow after process step P2 is described by node a, the flow after process step P3 is described by node a, the flow before process step P2 is described by nodes C1, C2, C3, the flow after process step P2 is described by node C, the flow before process step P2 is described by node E, B, C, and the flow after process step P2 is described by node a. Thus, the product assembly plan SP2 is obtained after the removal of the irrelevant nodes E1 and E and their relevant process steps.
Finally, step S3 is executed, the rule extraction device 231 retrieves the corresponding historical assembly line corresponding to the corresponding historical assembly plan from the database, the workstation adding and removing device 232 removes the workstation corresponding to the process step removed in step S2 in the historical assembly line, and the assembly line forming device 233 reconstructs the assembly line into a product assembly line. As shown in fig. 3, the corresponding historical assembly line for the corresponding historical assembly plan SP1 is SL1, wherein the assembly line includes workstations for each process step of the assembly plan. Specifically, process step P1 is performed at workstation WS1, process step P2 is performed at workstation WS2, and process step P3 is performed at workstation WS3, such that history assembly line SL1 includes workstations WS1, WS2, and WS2, wherein workstations WS1 and WS2 perform process steps P1 and P2, respectively, before workstation WS3 performs process step P3. Thus, the product assembly line SP3 is obtained after the work station WS1 corresponding to the process step P1 removed in step S2 is removed.
Further, the database stores a design bill of materials, a standard CBS map, a historical assembly plan, a topology model template and a historical assembly line. As shown in fig. 6, the standard CBS map is a node N33 that includes a card slot that includes a box and a board. Therefore, the assembly plan SP3 generated for the standard CBS map by the present invention includes a process step P, which is a clamping process. The flow of material before the process step P is performed is described by nodes N41 and N42, and the flow of material after the process step P is performed is described by node N43, wherein node N41 is a "box with a slot", node N42 is a "plate", and node N43 is a "box with a plate clamped.
In addition, the invention also comprises the following steps: the generated product design bill of materials, product assembly plan, and product assembly line are stored in the database.
A second aspect of the present invention provides a knowledge-based assembly process planning system comprising: a processor; and a memory coupled with the processor, the memory having instructions stored therein that, when executed by the processor, cause the electronic device to perform actions comprising: s1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database; s2, calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans; s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed by the action S2 in the historical assembly line, and reconstructing the work station into a product assembly line.
Further, the action S1 further includes the following steps: s11, receiving a product design bill of materials, analyzing a data structure of the product design bill of materials based on a topology model template, acquiring knowledge information in the product design bill, and generating a topology model instance based on the topology model template; s22, a historical design bill of materials is called in a database, and the product design bill of materials and the historical design bill of materials are respectively converted into a product CBS map and a historical CBS map; s23, according to the product CBS map, matching the historical CBS maps, when the product CBS map is matched with the plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the plurality of historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement so as to select a similar CBS map with the minimum index difference from the plurality of historical CBS maps.
Further, the act S23 further includes: and (3) hierarchically matching historical CBS maps according to the product CBS maps, when one part of the product CBS maps are matched with a plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement, deconstructing the matched and unmatched parts in the product CBS maps, continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched, and when the product CBS maps are left to be unmatched, invoking standard CBS map nodes in a database to execute matching on the node.
Further, the nodes of the topology model comprise various types of entities, the entities comprise assemblies, sub-assemblies, parts and connectors, and the nodes of the CBS map are the connectors and a plurality of assemblies, sub-assemblies, parts and connectors connected with the connectors.
Further, the step S22 further includes the following steps: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
Further, the database stores a design bill of materials, a standard CBS map, a historical assembly plan, a topology model template and a historical assembly line.
A third aspect of the present invention provides a knowledge-based assembly process planning apparatus, wherein the knowledge-based assembly process planning apparatus further comprises: a similarity retrieval device which receives a product design bill of materials, acquires knowledge information in the product design bill and generates a topology model instance based on a topology model template, matches a historical design bill of materials similar to the design bill of materials of the product in a database; the assembly plan generating device is used for calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes irrelevant to the historical design bill of materials in the historical assembly plans and corresponding process steps, and reconstructing the nodes into the product assembly plan; and the assembly line generating device is used for calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed by the assembly plan generating device in the historical assembly line and reconstructing the work station into the product assembly line.
A fourth aspect of the invention provides a computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions which, when executed, cause at least one processor to perform a method according to the first aspect of the invention.
A fifth aspect of the invention provides a computer readable medium having stored thereon computer executable instructions which when executed cause at least one processor to perform a method according to the first aspect of the invention.
The semantic map is used as a carrier for describing an assembly body, an assembly line and assembly planning, the description capability is strong, the understanding is easy, the inference rule is easy to apply, and the naming of the entity is not limited, so that the knowledge-based assembly process planning device provided by the invention is convenient to use.
Moreover, the present invention combines topological and quantitative ways to perform a graph similarity measurement, wherein the ontology comparison is the first coarse filtering and the quantitative similarity measurement is the precise filtering further based on the first coarse filtering, thus reducing the computational effort. The quantitative measurement increases the accuracy of the similarity comparison and increases the accuracy of the recommendation over a pure topology comparison. Therefore, the invention is more efficient and accurate.
In addition, knowledge in the database is accumulated as history data for a long time, so that the recommending ability is increased, and the invention is more intelligent and self-evolutionary.
While the present invention has been described in detail through the foregoing description of the preferred embodiment, it should be understood that the foregoing description is not to be considered as limiting the invention. Many modifications and substitutions of the present invention will become apparent to those of ordinary skill in the art upon reading the foregoing. Accordingly, the scope of the invention should be limited only by the attached claims. Furthermore, any reference signs in the claims shall not be construed as limiting the claim concerned; the word "comprising" does not exclude the presence of other elements or steps than those listed in any claim or the specification; the terms "first," "second," and the like are used merely to denote a name, and do not denote any particular order.
Claims (15)
- The knowledge-based assembly process planning method comprises the following steps:s1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database;S2, calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans;s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed in the step S2 in the historical assembly line, and reconstructing the work station into a product assembly line.
- The knowledge-based assembly process planning method according to claim 1, wherein the step S1 further comprises the steps of:s11, receiving a product design bill of materials, analyzing a data structure of the product design bill of materials based on a topology model template, acquiring knowledge information in the product design bill, and generating a topology model instance based on the topology model template;s22, a historical design bill of materials is called in a database, and the product design bill of materials and the historical design bill of materials are respectively converted into a product CBS map and a historical CBS map;S23, according to the product CBS map, matching the historical CBS maps, when the product CBS map is matched with the plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the plurality of historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement so as to select a similar CBS map with the minimum index difference from the plurality of historical CBS maps.
- The knowledge-based assembly process planning method according to claim 2, wherein the step S23 further comprises the steps of:hierarchically matching historical CBS maps according to the product CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through Euclidean algorithm to execute similarity measurement when one part of the product CBS maps are matched with the historical CBS maps, deconstructing the matched and unmatched parts in the product CBS maps and continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched,and when one node is not matched with the CBS map of the product, calling the standard CBS map node in the database to perform matching on the node.
- The knowledge-based assembly process planning method according to claim 2, wherein the nodes of the topology model comprise various types of entities, the entities comprise assemblies, sub-assemblies, parts and connectors, and the nodes of the CBS map are connectors and a plurality of assemblies, sub-assemblies, parts and connectors connected with the connectors.
- The knowledge-based assembly process planning method according to claim 2, wherein said step S22 further comprises the steps of: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
- The knowledge-based assembly process planning method of claim 1, wherein the database stores a design bill of materials, a standard CBS map, a historical assembly plan, a topology model template, a historical assembly line.
- A knowledge-based assembly process planning system comprising:a processor; anda memory coupled with the processor, the memory having instructions stored therein that, when executed by the processor, cause the electronic device to perform actions comprising:S1, receiving a product design bill of materials, acquiring knowledge information in the product design bill, generating a topology model instance based on a topology model template, and matching a historical design bill of materials similar to the design bill of materials of the product in a database;s2, calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes in the historical assembly plans which are not related to the historical design bill of materials and corresponding process steps, and reconstructing the nodes into the product assembly plans;s3, calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work station corresponding to the process step removed by the action S2 in the historical assembly line, and reconstructing the work station into a product assembly line.
- The knowledge-based assembly process planning system of claim 7, wherein the act S1 further comprises the steps of:s11, receiving a product design bill of materials, analyzing a data structure of the product design bill of materials based on a topology model template, acquiring knowledge information in the product design bill, and generating a topology model instance based on the topology model template;S22, a historical design bill of materials is called in a database, and the product design bill of materials and the historical design bill of materials are respectively converted into a product CBS map and a historical CBS map;s23, according to the product CBS map, matching the historical CBS maps, when the product CBS map is matched with the plurality of historical CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the plurality of historical CBS maps respectively through a Euclidean algorithm to execute similarity measurement so as to select a similar CBS map with the minimum index difference from the plurality of historical CBS maps.
- The knowledge-based assembly process planning system of claim 8, wherein the act S23 further comprises:hierarchically matching historical CBS maps according to the product CBS maps, calculating index differences between nodes corresponding to the product CBS maps and the historical CBS maps respectively through Euclidean algorithm to execute similarity measurement when one part of the product CBS maps are matched with the historical CBS maps, deconstructing the matched and unmatched parts in the product CBS maps and continuing to execute matching and similarity measurement on the unmatched parts of the product CBS maps until the product CBS maps are completely matched or one node is left unmatched,And when one node is not matched with the CBS map of the product, calling the standard CBS map node in the database to perform matching on the node.
- The knowledge-based assembly process planning system of claim 8, wherein the nodes of the topology model comprise various types of entities including assemblies, sub-assemblies, parts, and connectors, and the nodes of the CBS map are connectors and a plurality of assemblies, sub-assemblies, parts, and connectors connected thereto.
- The knowledge-based assembly process planning system of claim 8, wherein said step S22 further comprises the steps of: and converting the nodes of the topology model into the nodes of the CBS map to convert the product design bill of materials and the historical design bill of materials into a product CBS map and a historical CBS map respectively.
- The knowledge-based assembly process planning system of claim 7, wherein the database stores a list of design materials, a standard CBS map, a historical assembly plan, a topology model template, a historical assembly line.
- Knowledge-based assembly process planning apparatus, characterized in that the knowledge-based assembly process planning apparatus further comprises:A similarity retrieval device which receives a product design bill of materials, acquires knowledge information in the product design bill and generates a topology model instance based on a topology model template, matches a historical design bill of materials similar to the design bill of materials of the product in a database;the assembly plan generating device is used for calling the historical assembly plans corresponding to the similar historical design bill of materials from the database, replacing nodes in the historical assembly plans with nodes corresponding to the product design bill of materials, removing nodes irrelevant to the historical design bill of materials in the historical assembly plans and corresponding process steps, and reconstructing the nodes into the product assembly plan;and the assembly line generating device is used for calling the corresponding historical assembly line of the corresponding historical assembly plan from the database, removing the work stations corresponding to the process steps removed by the assembly plan generating device in the historical assembly line and reconstructing the work stations into the product assembly line.
- A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform the method of any one of claims 1 to 7.
- A computer readable medium having stored thereon computer executable instructions which when executed cause at least one processor to perform the method according to any of claims 1 to 7.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/097439 WO2022252061A1 (en) | 2021-05-31 | 2021-05-31 | Knowledge-based assembly process planning method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117355852A true CN117355852A (en) | 2024-01-05 |
Family
ID=84322616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202180098306.3A Pending CN117355852A (en) | 2021-05-31 | 2021-05-31 | Knowledge-based assembly process planning method, device and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117355852A (en) |
| WO (1) | WO2022252061A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116187738B (en) * | 2023-04-27 | 2023-08-29 | 中建科技集团有限公司 | Automatic generation method of work package based on execution sequence and position distribution |
| CN117270832B (en) * | 2023-11-22 | 2024-02-13 | 卡奥斯工业智能研究院(青岛)有限公司 | Machine instruction generation method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110870B (en) * | 2019-06-05 | 2022-03-22 | 厦门邑通软件科技有限公司 | Intelligent equipment fault monitoring method based on event map technology |
| CN110866317B (en) * | 2019-11-23 | 2023-06-30 | 广东科龙模具有限公司 | Design tool kit reconstruction method based on product history information and design behavior analysis |
| CN111191821B (en) * | 2019-12-17 | 2023-07-25 | 东华大学 | Knowledge graph driving-based equipment resource allocation optimization method |
| CN111444351B (en) * | 2020-03-24 | 2023-09-12 | 清华苏州环境创新研究院 | Knowledge graph construction method and device in industrial process field |
| CN111930956B (en) * | 2020-06-17 | 2023-05-30 | 西安交通大学 | Multi-innovation method recommendation and flow driving integrated system adopting knowledge graph |
-
2021
- 2021-05-31 WO PCT/CN2021/097439 patent/WO2022252061A1/en active Application Filing
- 2021-05-31 CN CN202180098306.3A patent/CN117355852A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022252061A1 (en) | 2022-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Semantic hyper-graph-based knowledge representation architecture for complex product development | |
| Khoo et al. | Framework of a fuzzy quality function deployment system | |
| Du et al. | Graph grammar based product family modeling | |
| CN104899242B (en) | Design of Mechanical Product two dimension knowledge method for pushing based on design idea | |
| Tay et al. | Product modeling for conceptual design support | |
| CN104636478A (en) | Information query method and device | |
| Tseng et al. | A variant approach to product definition by recognizing functional requirement patterns | |
| CN102004767A (en) | Abstract service logic-based interactive semantic Web service dynamic combination method | |
| Froeschl | Metadata management in statistical information processing: a unified framework for metadata-based processing of statistical data aggregates | |
| CN117355852A (en) | Knowledge-based assembly process planning method, device and system | |
| CN105808853B (en) | A kind of ontological construction management of Engineering Oriented application and ontology data automatic obtaining method | |
| CN104699719A (en) | Semantization method of Internet of things terminal equipment | |
| Shen et al. | Dynamic knowledge modeling and fusion method for custom apparel production process based on knowledge graph | |
| CN113742368A (en) | Data blood relationship analysis method | |
| CN116301755A (en) | Automatic batch flow data marking framework construction method based on directed calculation graph | |
| CN111144123B (en) | Industrial Internet identification analysis data dictionary construction method | |
| Bao et al. | A node2vec-based graph embedding approach for unified assembly process information modeling and workstep execution time prediction | |
| CN113722564A (en) | Visualization method and device for energy and material supply chain based on space map convolution | |
| CN114270282A (en) | System for generating an integral digital twin | |
| Jiang et al. | Construction of substation engineering design knowledge graph based on “ontology seven-step method” | |
| Unterdechler et al. | Identifying repeating patterns in IEC 61499 systems using Feature-Based embeddings | |
| CN109508410A (en) | A kind of industrial service parametrization configuration searching algorithm | |
| White et al. | Variant generation of software-defined mechatronic systems in model-based systems engineering | |
| Amira et al. | An extension of protégé for an automatic fuzzy-ontology building using clustering and FCA | |
| Jia et al. | The research on representation and processing of process knowledge based on object-oriented modeling |
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 |