CN114004230A - Industrial control scheduling method and system for producing steel structure - Google Patents
Industrial control scheduling method and system for producing steel structure Download PDFInfo
- Publication number
- CN114004230A CN114004230A CN202111113835.4A CN202111113835A CN114004230A CN 114004230 A CN114004230 A CN 114004230A CN 202111113835 A CN202111113835 A CN 202111113835A CN 114004230 A CN114004230 A CN 114004230A
- Authority
- CN
- China
- Prior art keywords
- industrial control
- entity
- equipment
- additional information
- steel structure
- 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.)
- Granted
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 76
- 239000010959 steel Substances 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title abstract description 14
- 238000004519 manufacturing process Methods 0.000 claims abstract description 115
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 238000013507 mapping Methods 0.000 claims abstract description 4
- 238000010276 construction Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 7
- 238000012502 risk assessment Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims 4
- 239000013598 vector Substances 0.000 description 14
- 238000012549 training Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 3
- 238000003466 welding Methods 0.000 description 3
- 125000004432 carbon atom Chemical group C* 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses an industrial control scheduling method and system for producing a steel structure, which mainly comprise the following steps: extracting industrial control production parameters and additional information; adding labels to industrial control production parameters and additional information through a preset rule; defining an industrial control entity association framework; mapping industrial control production parameters, additional information and labels to an industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network; and matching the current steel structure production expectation to an industrial control entity associated network to generate an optimized industrial control mode. According to the method and the system, a standardized and structured industrial control entity associated network is established, and the industrial control entity associated network is matched according to the expectation of the current steel structure production operation, so that the automation level and efficiency of executing industrial control on steel structure equipment are improved.
Description
Technical Field
The invention relates to the technical field of steel structure production lines, in particular to an industrial control scheduling method and system for producing a steel structure.
Background
The steel structure is a heavy-load, large-span and light building structure formed by connecting steel materials such as steel plates, section steel, steel pipes, steel cables and the like by welding, riveting, bolts and the like. The steel structure is mainly applied to a plurality of fields such as industrial factory buildings, high-rise buildings, large public buildings, bridges, airport buildings, ocean platforms, power transmission towers and the like.
For the production and construction of steel structures, the steel structure production and construction method has more links, and relates to links such as material transportation, structure processing, structural part transportation, auxiliary part and accessory collocation, construction and the like. The equipment involved in each stage comprises: the steel member cutting, punching, welding and other operations are realized through the numerical control machine tool, the loading and unloading equipment, the transport vehicle, the hoisting equipment, the field assembly equipment such as a welding machine and the like, and the construction monitoring equipment such as an unmanned aerial vehicle and a ray detector for realizing engineering aerial survey. Because the quantity and the variety of the related equipment are more various, the processing and the operation modes are complex, and the processing, the transportation and the operation facing the nonstandard customized steel member occupy a certain proportion, the automation control difficulty of the related equipment is higher, namely, the industrial control link faces higher difficulty, and the related various equipment can be difficultly adapted to the characteristics of steel structure production, transportation and operation in each link of steel structure production and construction.
Disclosure of Invention
Objects of the invention
In view of the above problems, the present invention aims to provide an industrial control scheduling method and system for producing steel structures, which performs evaluation through the relationship between entities in an industrial control entity association network, deduces and obtains an optimized industrial control mode, thereby improving the automation level and efficiency of performing industrial control for steel structure-oriented equipment.
(II) technical scheme
As a first aspect of the invention, the invention discloses an industrial control scheduling method for producing a steel structure, which comprises the following steps:
extracting industrial control production parameters and additional information;
adding labels to the industrial control production parameters and the additional information through a preset rule;
defining an industrial control entity association framework;
mapping the industrial control production parameters, the additional information and the labels to the industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network;
and matching the current steel structure production expectation to the industrial control entity associated network to generate an optimized industrial control mode.
In a possible embodiment, the extracting the industrial control production parameters and the additional information specifically includes:
and extracting the industrial control production parameters and the additional information based on the historical records of processing, transportation and operation of each link of steel structure production.
In a possible embodiment, the industrial control production parameters and the additional information specifically include:
the industrial control production parameters comprise: instructions and parameters of a numerical control machine, loading and unloading equipment, a transport vehicle, hoisting equipment, field assembly equipment and construction monitoring equipment;
the additional information includes: working hours, cost, risk assessment, and accident recording.
In a possible embodiment, the tagging the industrial control production parameter and the additional information according to a predetermined rule specifically includes:
acquiring the characteristics of the industrial control production parameters and the additional information;
and grouping the industrial control production parameters and the additional information according to the characteristics, and adding attribute labels.
In a possible implementation manner, the defining an industrial control entity association framework specifically includes:
acquiring equipment, an instruction, an object and an additional factor, and determining an incidence relation among the equipment, the instruction, the object and the additional factor;
and defining an industrial control entity association framework based on the equipment, the instruction, the object, the additional factors and the association relation.
As a second aspect of the invention, the invention also discloses an industrial control scheduling system for producing the steel structure, which comprises:
the extraction module is used for extracting industrial control production parameters and additional information;
the adding module adds labels to the industrial control production parameters and the additional information according to a preset rule;
the definition module is used for defining an industrial control entity association framework;
the construction module maps the industrial control production parameters, the additional information and the labels to the industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network;
and the optimization module is used for matching the current steel structure production expectation to the industrial control entity associated network to generate an optimized industrial control mode.
In a possible implementation mode, the extraction module extracts the industrial control production parameters and the additional information based on historical records of processing, transportation and operation of all links of steel structure production.
In one possible embodiment, the industrial control production parameters include: instructions and parameters of a numerical control machine, loading and unloading equipment, a transport vehicle, hoisting equipment, field assembly equipment and construction monitoring equipment;
the additional information includes: working hours, cost, risk assessment, and accident recording.
In one possible embodiment, the adding module comprises an obtaining unit and a label unit;
the acquisition unit is used for acquiring the industrial control production parameters and the characteristics of the additional information;
and the label unit groups the industrial control production parameters and the additional information according to the characteristics and adds attribute labels.
In one possible embodiment, the definition module comprises an acquisition unit and a framework unit;
the acquisition unit is used for acquiring equipment, instructions, objects and additional factors and determining the incidence relation among the equipment, the instructions, the objects and the additional factors;
and the framework unit defines an industrial control entity association framework based on the equipment, the instruction, the object, the additional factors and the association relation.
(III) advantageous effects
The industrial control scheduling method and the industrial control scheduling system for producing the steel structure have the following beneficial effects: the standardized and structured industrial control entity associated network is established, the industrial control entity associated network is matched according to the expectation of the current steel structure production operation, a plurality of entities of the industrial control entity associated network are determined, evaluation can be executed through the relation among the entities in the associated network, and an optimized industrial control mode is obtained through derivation, so that the automation level and the efficiency of executing industrial control for steel structure equipment are improved.
Drawings
The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining and illustrating the present invention and should not be construed as limiting the scope of the present invention.
FIG. 1 is a flow chart of an industrial control scheduling method for producing a steel structure, which is disclosed by the invention;
FIG. 2 is a flow chart of the present disclosure for tagging industrial control production parameters and additional information via predetermined rules;
FIG. 3 is a flow chart of defining an industrial control entity association framework according to the present disclosure;
FIG. 4 is a schematic diagram of the BERT-BilSTM-CRF model disclosed in the present invention;
FIG. 5 is a block diagram of an industrial control scheduling system for producing steel structures.
Reference numerals: 010. an extraction module; 020. adding a module; 021. an acquisition unit; 022. a label unit; 030. a definition module; 031. a collection unit; 032. a frame unit; 040. building a module; 050. and an optimization module.
Detailed Description
In order to make the implementation objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention.
It should be noted that: in the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described are some embodiments of the present invention, not all embodiments, and features in embodiments and embodiments in the present application may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience in describing the present invention and for simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore, should not be taken as limiting the scope of the present invention.
A first embodiment of an industrial control scheduling method for producing a steel structure according to the present disclosure is described in detail below with reference to fig. 1 to 4. The embodiment is mainly applied to steel structure production, and the industrial control entity associated network is matched according to the expectation of the current steel structure production operation by constructing the standardized and structured industrial control entity associated network, so that the automation level and efficiency of executing industrial control for steel structure equipment are improved.
As shown in fig. 1 to 4, the present embodiment specifically includes the following steps:
and S100, extracting industrial control production parameters and additional information.
In step S100, industrial control production parameters and additional information thereof are extracted from historical records of processing, transportation and operation of steel structures in links of material transportation, structure processing, structural member transportation, auxiliary member and accessory collocation, construction and the like.
Further, before step S100, data of each link in the historical production and construction and in the different steel structure production and construction are stored, a historical database is generated, and industrial control production parameters and additional information are extracted from the historical database. The data in the historical database is updated occasionally as equipment is worn out, the process is updated and the raw materials are increased.
In one embodiment, the industrial control production parameters are instructions and parameters specifically directed to numerically controlled machine tools, handling equipment, transport vehicles, hoisting equipment, field assembly equipment, and construction monitoring equipment; the additional information is data such as man-hours, costs, risk assessment, accident records, etc. required in the steel structure production and construction.
And S200, adding labels to the industrial control production parameters and the additional information through a preset rule.
As shown in fig. 2, in step S200, the tagging of the industrial control production parameters and the additional information by the predetermined rule specifically includes:
s210, acquiring characteristics of industrial control production parameters and additional information;
and S220, grouping the industrial control production parameters and the additional information according to the characteristics, and adding an attribute label.
Specifically, the method comprises the steps of firstly obtaining characteristics of industrial control production parameters and additional information, such as the model and basic parameters of a numerical control machine, grouping the industrial control production parameters and the additional information according to the obtained characteristics, and adding attribute labels, wherein equipment type labels are added for equipment such as the numerical control machine, loading and unloading equipment, transport vehicles, hoisting equipment, field assembly equipment and construction monitoring equipment;
adding an instruction attribute tag to the industrial control execution instruction of the equipment;
adding an operation object label to an operation object of steel structure processing, transportation and operation;
additional factor labels are added for additional information such as labor hour, cost, risk, accident records, and the like.
In one implementation mode, an artificial intelligence analysis algorithm is utilized to add descriptive labels to industrial control production parameters and additional information, a subdivision clustering method is adopted to perform feature grouping on the descriptive labels, and after grouping, corresponding attribute labels are added to the same type of parameters or information. In the application, the label is added through an artificial intelligence analysis algorithm, and other common neural network algorithms and other modes can be used, so that the common algorithm or rule capable of adding the label to the industrial control production parameters and the additional information is within the protection scope of the embodiment of the application.
And S300, defining an industrial control entity association framework.
As shown in fig. 3, in step S300, defining the industrial control entity association framework specifically includes:
s310, collecting equipment, instructions, objects and additional factors, and determining incidence relations among the equipment, the instructions, the objects and the additional factors;
and S320, defining an industrial control entity association framework based on the equipment, the instruction, the object, the additional factors and the association relation.
Specifically, the industrial control entity association framework defines industrial control entities and association relations thereof, comprises equipment, instructions, objects and additional factors, and is constructed by adopting an industrial control knowledge graph which comprises a mode layer and a data layer, wherein the mode layer specifies concept bodies, attribute types and structural levels, the data layer stores entity data, triples are used as basic composition units, and the entity association framework of the industrial control entity knowledge graph is constructed by associating various data entities.
Further, the mode layer is constructed in a top-down mode, and a three-element framework of 'entity-relation-entity' or 'entity-attribute value' of an industrial control knowledge graph is set based on core elements of steel structure production industrial control, so that a concept design basis is provided for construction of a data layer, hierarchical relations, semantic relations and attribute relations among all ontologies are defined, and the mode layer is defined.
Further, the data layer is constructed in a bottom-up mode, from industrial control production parameters and additional information, according to attribute labels in the industrial control production parameters and the additional information, information such as entities, relations and attributes in steel structure production construction is obtained, triples of types of entity-relation-entity and entity-attribute value are filled, and the triples are associated with each other according to semantic relations.
And S400, mapping the industrial control production parameters, the additional information and the labels to an industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network.
In step S400, the entity extraction uses a named entity recognition model, because the named entity recognition algorithm has high labeling efficiency, but needs a large amount of data for training, and has relatively low accuracy, and the choice of the entity labeling algorithm is often determined according to the data situation and the work requirement, the BERT-blstm-CRF model is used for entity extraction, and is a named entity recognition model formed by combining a BERT pre-training language model and a bidirectional long-short term memory network-conditional random field model (blstm-CRF).
As shown in fig. 4, the BERT-BilSTM-CRF model is divided into three layers, the first BERT layer, and industrial control production parameters and additional information word vector features are extracted through a large amount of Chinese general linguistic data and a BERT general language model obtained through great computational training to obtain low-dimensional word vectors; the second layer is a BilSTM layer, based on the understanding of the pre-training layer to the industrial control production parameters and the vector characteristics of the additional information words, a large amount of marked industrial control production parameters and additional information entities are used for training the bidirectional long-short term memory network, according to the model training result, context semantic information is used for deducing and marking the entity sequence, and the weight is set through the attention mechanism for further screening the entity types; and the third layer is a CRF layer, and according to the corpus entity sequence output by the BilSTM layer, a probability model is used for predicting and outputting an optimal expression of sequence tags, so that automatic sequence labeling of the corpus is realized, and named entity identification is completed.
In one embodiment, the entity fusion is divided into two parts, namely entity alignment and entity matching, wherein the entity alignment refers to comparing and confirming the ontology concept and the hierarchy of the entity to be confirmed, if the similarity of the hierarchy and the concept is high, the ontology is considered to be aligned, and the entity matching refers to confirming the similarity degree of the two entities on the contents of entity names, entity relationships, attributes and the like.
Further, the entity fusion algorithm performs entity fusion to generate a data entity, including: comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
Further, semantic similarity of the two entities on the contents of entity names, hierarchical categories, attributes and the like is calculated, wherein a comprehensive similarity vector is obtained by synthesizing single attribute similarity, and whether entity redundancy exists or not is determined, wherein a calculation formula of the single attribute similarity is as follows:
in the above formula, the first and second carbon atoms are,
representing the similarity of some attribute m, A, of entity A, BmRepresenting a certain attribute m, B of an entity AmA certain attribute m, a representing an entity BiRepresents attribute AmWord frequency of participles biRepresents attribute BmThe word frequency of the participle, n represents the number of the participle.
Further, Am、BmThe total number of n participles in the semantic space is counted by the statistical attribute Am、BmWord frequency a of each participlei、biThe word frequency vector (i.e. the comprehensive similarity vector) is constructed, and the similarity of the two sentences is determined through vector cosine value calculation.
Further, the similarity ratio of the entities a and B is generated by calculating the ratio of the semantic similarity of the entities a and B to the number of the attributes, and the calculation formula is as follows:
in the above formula, SA，BRepresenting the similarity ratio of the entities A, B, S representing the number of attributes, SA，BBetween 0 and 1, with closer to 1 indicating two entity semantic faciesThe higher the similarity.
S500, matching the current steel structure production expectation to an industrial control entity associated network to generate an optimized industrial control mode.
In step S500, according to the expectation of the current steel structure production operation, matching the industrial control entity association network to generate an optimized industrial control mode, specifically including:
for the currently expected steel structure processing, transportation and operation, determining related equipment factors such as numerical control machines, loading and unloading equipment, transportation vehicles, hoisting equipment, field assembly equipment, construction monitoring equipment and the like, object factors such as materials, structural members, auxiliary members, accessories and the like, and at least one factor of instruction factors and additional factors to match with the industrial control entity association network, and determining a plurality of entities of the factors in the industrial control entity association network.
And further, performing evaluation through the relation between entities in the associated network, and deducing to obtain an optimized industrial control mode.
The following describes in detail with reference to fig. 4 to 5, and based on the same inventive concept, the embodiment of the present invention further provides a first embodiment of an industrial control scheduling system for producing a steel structure. The principle of the problem solved by the system is similar to that of the industrial control scheduling method for producing the steel structure, so the implementation of the system can refer to the implementation of the method, and repeated parts are not repeated.
The embodiment is mainly applied to steel structure production, and the industrial control entity associated network is matched according to the expectation of the current steel structure production operation by constructing the standardized and structured industrial control entity associated network, so that the automation level and efficiency of executing industrial control for steel structure equipment are improved.
As shown in fig. 5, the present embodiment mainly includes: an extraction module 010, an addition module 020, a definition module 030, a construction module 040 and an optimization module 050.
The extraction module 010 is used for extracting industrial control production parameters and additional information, and mainly extracts the industrial control production parameters and the additional information from historical records of processing, transportation and operation of steel structures in links such as material transportation, structure processing, structural member transportation, auxiliary member and accessory collocation, construction and the like.
Further, data of all links in the historical production and construction of different steel structures are stored, a historical record database is generated, and industrial control production parameters and additional information are extracted from the historical record database. The data in the historical database is updated occasionally as equipment is worn out, the process is updated and the raw materials are increased.
In one embodiment, the industrial control production parameters are instructions and parameters specifically directed to numerically controlled machine tools, handling equipment, transport vehicles, hoisting equipment, field assembly equipment, and construction monitoring equipment; the additional information is data such as man-hours, costs, risk assessment, accident records, etc. required in the steel structure production and construction.
The adding module 020 adds labels to the industrial control production parameters and the additional information through a preset rule, wherein the adding module 020 comprises an acquiring unit 021 and a label unit 022, and the acquiring unit 021 is used for acquiring characteristics of the industrial control production parameters and the additional information; the label unit 022 groups the industrial control production parameters and the additional information according to the characteristics, and adds an attribute label.
Specifically, the method comprises the steps of firstly obtaining characteristics of industrial control production parameters and additional information, such as the model and basic parameters of a numerical control machine, grouping the industrial control production parameters and the additional information according to the obtained characteristics, and adding attribute labels, wherein equipment type labels are added for equipment such as the numerical control machine, loading and unloading equipment, transport vehicles, hoisting equipment, field assembly equipment and construction monitoring equipment;
adding an instruction attribute tag to the industrial control execution instruction of the equipment;
adding an operation object label to an operation object of steel structure processing, transportation and operation;
additional factor labels are added for additional information such as labor hour, cost, risk, accident records, and the like.
In one implementation mode, an artificial intelligence analysis algorithm is utilized to add descriptive labels to industrial control production parameters and additional information, a subdivision clustering method is adopted to perform feature grouping on the descriptive labels, and after grouping, corresponding attribute labels are added to the same type of parameters or information.
The defining module 030 is configured to define an industrial control entity association framework, the defining module 030 includes an acquiring unit 031 and a framework unit 032, the acquiring unit 031 is configured to acquire a device, an instruction, an object, and an additional factor and determine an association relationship between the device, the instruction, the object, and the additional factor, and the framework unit 032 defines the industrial control entity association framework based on the device, the instruction, the object, the additional factor, and the association relationship.
Specifically, the industrial control entity association framework defines industrial control entities and association relations thereof, comprises equipment, instructions, objects and additional factors, and is constructed by adopting an industrial control knowledge graph which comprises a mode layer and a data layer, wherein the mode layer specifies concept bodies, attribute types and structural levels, the data layer stores entity data, triples are used as basic composition units, and the entity association framework of the industrial control entity knowledge graph is constructed by associating various data entities.
Further, the mode layer is constructed in a top-down mode, and a three-element framework of 'entity-relation-entity' or 'entity-attribute value' of an industrial control knowledge graph is set based on core elements of steel structure production industrial control, so that a concept design basis is provided for construction of a data layer, hierarchical relations, semantic relations and attribute relations among all ontologies are defined, and the mode layer is defined.
Further, the data layer is constructed in a bottom-up mode, from industrial control production parameters and additional information, according to attribute labels in the industrial control production parameters and the additional information, information such as entities, relations and attributes in steel structure production construction is obtained, triples of types of entity-relation-entity and entity-attribute value are filled, and the triples are associated with each other according to semantic relations.
The building module 040 maps the industrial control production parameters, the additional information and the labels to an industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network, wherein the entity extraction adopts a named entity recognition model, the named entity recognition algorithm is high in labeling efficiency, but needs a large amount of data for training and relatively low in accuracy, and the selection of the entity labeling algorithm is often determined according to data conditions and working requirements, so that the entity extraction is carried out by adopting a BERT-BilSTM-CRF model, and the BERT-BilSTM-CRF model is a named entity recognition model formed by combining a BERT pre-training language model and a two-way long-short-term memory network-conditional random field model (BilSTM-CRF).
As shown in fig. 4, the BERT-BilSTM-CRF model is divided into three layers, the first BERT layer, and industrial control production parameters and additional information word vector features are extracted through a large amount of Chinese general linguistic data and a BERT general language model obtained through great computational training to obtain low-dimensional word vectors; the second layer is a BilSTM layer, based on the understanding of the pre-training layer to the industrial control production parameters and the vector characteristics of the additional information words, a large amount of marked industrial control production parameters and additional information entities are used for training the bidirectional long-short term memory network, according to the model training result, context semantic information is used for deducing and marking the entity sequence, and the weight is set through the attention mechanism for further screening the entity types; and the third layer is a CRF layer, and according to the corpus entity sequence output by the BilSTM layer, a probability model is used for predicting and outputting an optimal expression of sequence tags, so that automatic sequence labeling of the corpus is realized, and named entity identification is completed.
In one embodiment, the entity fusion is divided into two parts, namely entity alignment and entity matching, wherein the entity alignment refers to comparing and confirming the ontology concept and the hierarchy of the entity to be confirmed, if the similarity of the hierarchy and the concept is high, the ontology is considered to be aligned, and the entity matching refers to confirming the similarity degree of the two entities on the contents of entity names, entity relationships, attributes and the like.
Further, the entity fusion algorithm performs entity fusion to generate a data entity, including: comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
Further, semantic similarity of the two entities on the contents of entity names, hierarchical categories, attributes and the like is calculated, wherein a comprehensive similarity vector is obtained by synthesizing single attribute similarity, and whether entity redundancy exists or not is determined, wherein a calculation formula of the single attribute similarity is as follows:
in the above formula, the first and second carbon atoms are,
representing the similarity of some attribute m, A, of entity A, BmRepresenting a certain attribute m, B of an entity AmA certain attribute m, a representing an entity BiRepresents attribute AmWord frequency of participles biRepresents attribute BmThe word frequency of the participle, n represents the number of the participle.
Further, Am、BmThe total number of n participles in the semantic space is counted by the statistical attribute Am、BmWord frequency a of each participlei、biThe word frequency vector (i.e. the comprehensive similarity vector) is constructed, and the similarity of the two sentences is determined through vector cosine value calculation.
Further, the similarity ratio of the entities a and B is generated by calculating the ratio of the semantic similarity of the entities a and B to the number of the attributes, and the calculation formula is as follows:
in the above formula, SA，BRepresenting the similarity ratio of the entities A, B, S representing the number of attributes, SA，BBetween 0 and 1, closer to 1 indicating a higher semantic similarity between the two entities.
And the optimization module 050 is used for matching the current steel structure production expectation to an industrial control entity associated network to generate an optimized industrial control mode. For the currently expected steel structure processing, transportation and operation, determining related equipment factors such as numerical control machines, loading and unloading equipment, transportation vehicles, hoisting equipment, field assembly equipment, construction monitoring equipment and the like, object factors such as materials, structural members, auxiliary members, accessories and the like, and at least one factor of instruction factors and additional factors to match with the industrial control entity association network, and determining a plurality of entities of the factors in the industrial control entity association network.
And further, performing evaluation through the relation between entities in the associated network, and deducing to obtain an optimized industrial control mode.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An industrial control scheduling method for producing a steel structure is characterized by comprising the following steps:
extracting industrial control production parameters and additional information;
adding labels to the industrial control production parameters and the additional information according to preset rules, and adding equipment type labels to numerical control machines, loading and unloading equipment, transport vehicles, hoisting equipment, field assembly equipment and construction monitoring equipment; adding an instruction attribute label to an industrial control execution instruction of the equipment; adding an operation object label to an operation object of steel structure processing, transportation and operation; adding additional factor labels for the working hours, cost, risks and accident records;
defining an industrial control entity association framework, and defining equipment, instructions, objects, additional factors and association relations of the equipment, the instructions, the objects and the additional factors;
mapping the industrial control production parameters, the additional information and the labels to an industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network, wherein the entity extraction adopts a BERT-BilSTM-CRF model to perform entity extraction, the BERT-BilSTM-CRF model comprises a BERT layer, a BilSTM layer and a CRF layer, the entity fusion comprises entity alignment and entity matching, the entity alignment refers to comparison and confirmation of the body concept and the level of an entity to be confirmed, and the entity matching refers to confirmation of the similarity degree of the two entities on the contents of entity names, entity relationships, attributes and the like;
and matching at least one factor in processing, transportation and operation expected by current steel structure production into the industrial control entity associated network, determining a plurality of entities in the industrial control entity associated network, and generating an optimized industrial control mode.
2. The industrial control scheduling method for producing the steel structure according to claim 1, wherein the extracting of industrial control production parameters and additional information specifically comprises:
and extracting the industrial control production parameters and the additional information based on the historical records of processing, transportation and operation of each link of steel structure production.
3. The industrial control scheduling method for producing the steel structure according to any one of claims 1 or 2, wherein the industrial control production parameters and the additional information specifically include:
the industrial control production parameters comprise: instructions and parameters of a numerical control machine, loading and unloading equipment, a transport vehicle, hoisting equipment, field assembly equipment and construction monitoring equipment;
the additional information includes: working hours, cost, risk assessment, and accident recording.
4. The industrial control scheduling method for producing the steel structure according to claim 1, wherein the tagging of the industrial control production parameters and the additional information through a predetermined rule specifically comprises:
acquiring the characteristics of the industrial control production parameters and the additional information;
and grouping the industrial control production parameters and the additional information according to the characteristics, and adding attribute labels.
5. The industrial control scheduling method for producing the steel structure according to claim 1, wherein the defining an industrial control entity association framework specifically comprises:
acquiring equipment, an instruction, an object and an additional factor, and determining an incidence relation among the equipment, the instruction, the object and the additional factor;
and defining an industrial control entity association framework based on the equipment, the instruction, the object, the additional factors and the association relation.
6. The utility model provides an industrial control dispatch system of production steel construction which characterized in that includes:
the extraction module is used for extracting industrial control production parameters and additional information;
the adding module adds labels to the industrial control production parameters and the additional information according to a preset rule, and adds equipment type labels to numerical control machines, loading and unloading equipment, transport vehicles, hoisting equipment, field assembly equipment and construction monitoring equipment; adding an instruction attribute label to an industrial control execution instruction of the equipment; adding an operation object label to an operation object of steel structure processing, transportation and operation; adding additional factor labels for the working hours, cost, risks and accident records; (ii) a
The definition module is used for defining an industrial control entity association framework, and defining equipment, instructions, objects, additional factors and association relations of the equipment, the instructions, the objects and the additional factors;
the building module maps the industrial control production parameters, the additional information and the labels to the industrial control entity association framework by utilizing entity extraction and entity fusion to obtain an industrial control entity association network, wherein the entity extraction adopts a BERT-BilSTM-CRF model to perform entity extraction, the BERT-BilSTM-CRF model comprises a BERT layer, a BilSTM layer and a CRF layer, the entity fusion comprises entity alignment and entity matching, the entity alignment refers to comparison and confirmation of the body concept and the hierarchy of the entity to be confirmed, and the entity matching refers to confirmation of the similarity degree of the two entities on the contents of entity names, entity relationships, attributes and the like;
and the optimization module is used for matching at least one factor of processing, transportation and operation expected by current steel structure production into the industrial control entity associated network, determining a plurality of entities in the industrial control entity associated network and generating an optimized industrial control mode.
7. The industrial control scheduling system for producing steel structures of claim 6, wherein the extraction module extracts the industrial control production parameters and the additional information based on historical records of processing, transportation and operation of each link of steel structure production.
8. An industrial control scheduling system for the production of steel structures according to any of claims 6 or 7, characterized in that said industrial control production parameters comprise: instructions and parameters of a numerical control machine, loading and unloading equipment, a transport vehicle, hoisting equipment, field assembly equipment and construction monitoring equipment;
the additional information includes: working hours, cost, risk assessment, and accident recording.
9. The industrial control dispatching system for producing the steel structure as claimed in claim 7, wherein the adding module comprises an obtaining unit and a labeling unit;
the acquisition unit is used for acquiring the industrial control production parameters and the characteristics of the additional information;
and the label unit groups the industrial control production parameters and the additional information according to the characteristics and adds attribute labels.
10. The industrial control scheduling system for producing the steel structure according to claim 7, wherein the definition module comprises an acquisition unit and a frame unit;
the acquisition unit is used for acquiring equipment, instructions, objects and additional factors and determining the incidence relation among the equipment, the instructions, the objects and the additional factors;
and the framework unit defines an industrial control entity association framework based on the equipment, the instruction, the object, the additional factors and the association relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111113835.4A CN114004230B (en) | 2021-09-23 | 2021-09-23 | Industrial control scheduling method and system for producing steel structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111113835.4A CN114004230B (en) | 2021-09-23 | 2021-09-23 | Industrial control scheduling method and system for producing steel structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114004230A true CN114004230A (en) | 2022-02-01 |
| CN114004230B CN114004230B (en) | 2022-07-05 |
Family
ID=79921896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111113835.4A Active CN114004230B (en) | 2021-09-23 | 2021-09-23 | Industrial control scheduling method and system for producing steel structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004230B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
| CN109902145A (en) * | 2019-01-18 | 2019-06-18 | 中国科学院信息工程研究所 | A kind of entity relationship joint abstracting method and system based on attention mechanism |
| CN110705272A (en) * | 2019-08-28 | 2020-01-17 | 昆明理工大学 | Named entity identification method for automobile engine fault diagnosis |
| CN110781683A (en) * | 2019-11-04 | 2020-02-11 | 河海大学 | Entity relation joint extraction method |
| CN110781682A (en) * | 2019-10-23 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Named entity recognition model training method, recognition method, device and electronic equipment |
| CN110851603A (en) * | 2019-11-13 | 2020-02-28 | 中国石油大学(华东) | Method for mining industrial accident recording text |
| CN111401058A (en) * | 2020-03-12 | 2020-07-10 | 广州大学 | Attribute value extraction method and device based on named entity recognition tool |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN111897968A (en) * | 2020-07-20 | 2020-11-06 | 国网浙江省电力有限公司嘉兴供电公司 | Industrial information security knowledge graph construction method and system |
| CN112149423A (en) * | 2020-10-16 | 2020-12-29 | 中国农业科学院农业信息研究所 | Corpus labeling method and system for domain-oriented entity relationship joint extraction |
| CN112468440A (en) * | 2020-10-28 | 2021-03-09 | 北京工业大学 | Knowledge graph-based industrial control system attack clue discovery system |
| CN112613314A (en) * | 2020-12-29 | 2021-04-06 | 国网江苏省电力有限公司信息通信分公司 | Electric power communication network knowledge graph construction method based on BERT model |
| CN113157940A (en) * | 2021-03-29 | 2021-07-23 | 上海融盈数据科技有限公司 | Knowledge fusion method of industry chain knowledge graph |
-
2021
- 2021-09-23 CN CN202111113835.4A patent/CN114004230B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109902145A (en) * | 2019-01-18 | 2019-06-18 | 中国科学院信息工程研究所 | A kind of entity relationship joint abstracting method and system based on attention mechanism |
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
| CN110705272A (en) * | 2019-08-28 | 2020-01-17 | 昆明理工大学 | Named entity identification method for automobile engine fault diagnosis |
| CN110781682A (en) * | 2019-10-23 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Named entity recognition model training method, recognition method, device and electronic equipment |
| CN110781683A (en) * | 2019-11-04 | 2020-02-11 | 河海大学 | Entity relation joint extraction method |
| CN110851603A (en) * | 2019-11-13 | 2020-02-28 | 中国石油大学(华东) | Method for mining industrial accident recording text |
| CN111401058A (en) * | 2020-03-12 | 2020-07-10 | 广州大学 | Attribute value extraction method and device based on named entity recognition tool |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN111897968A (en) * | 2020-07-20 | 2020-11-06 | 国网浙江省电力有限公司嘉兴供电公司 | Industrial information security knowledge graph construction method and system |
| CN112149423A (en) * | 2020-10-16 | 2020-12-29 | 中国农业科学院农业信息研究所 | Corpus labeling method and system for domain-oriented entity relationship joint extraction |
| CN112468440A (en) * | 2020-10-28 | 2021-03-09 | 北京工业大学 | Knowledge graph-based industrial control system attack clue discovery system |
| CN112613314A (en) * | 2020-12-29 | 2021-04-06 | 国网江苏省电力有限公司信息通信分公司 | Electric power communication network knowledge graph construction method based on BERT model |
| CN113157940A (en) * | 2021-03-29 | 2021-07-23 | 上海融盈数据科技有限公司 | Knowledge fusion method of industry chain knowledge graph |
Non-Patent Citations (2)
| Title |
|---|
| LIXIN TANG 等: "A review of planning and scheduling systems and methods for integrated steel production", 《EUROPEAN JOURNAL OF OPERATIONAL RESEARCH》 * |
| 张强: "基于型钢切割的机器人离线编程关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114004230B (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ke et al. | An intelligent design for remanufacturing method based on vector space model and case-based reasoning | |
| CN109902954B (en) | Flexible job shop dynamic scheduling method based on industrial big data | |
| CN117151222B (en) | Domain knowledge guided emergency case entity attribute and relation extraction method thereof, electronic equipment and storage medium | |
| Yıldızbaşı et al. | Performance evaluation of SMEs towards Industry 4.0 using fuzzy group decision making methods | |
| Yu et al. | Digital Twin-enabled and Knowledge-driven decision support for tunnel electromechanical equipment maintenance | |
| CN115238197A (en) | Expert thinking model-based field business auxiliary analysis method | |
| CN115907374A (en) | Intelligent dispatching method, device and equipment for vehicle of distribution center and storage medium | |
| CN114004230B (en) | Industrial control scheduling method and system for producing steel structure | |
| CN115934966A (en) | Automatic labeling method based on remote sensing image recommendation information | |
| CN110930024A (en) | Intelligent deep sea emergency situation analysis system and method based on Bayesian network | |
| CN116665305A (en) | Method and system for detecting worker behaviors based on computer vision and knowledge graph | |
| CN116069951A (en) | Construction worker safety knowledge extraction and knowledge graph construction method | |
| CN116450704A (en) | Automatic generation method and generation device of flow model | |
| CN113449526B (en) | Method and system for analyzing applicability of steel structure production scheduling strategy | |
| CN114064886B (en) | Mine project risk countermeasure recommending method and system based on deep learning | |
| CN114694098A (en) | Power grid infrastructure construction risk control method based on image recognition and knowledge graph | |
| CN118246776B (en) | Large-span bridge construction three-dimensional monitoring method | |
| CN118014306A (en) | Knowledge-graph-based unified characterization method for customized furniture plate processing data | |
| CN117435777B (en) | Automatic construction method and system for industrial chain map | |
| CN118296165B (en) | Method for constructing dynamic process knowledge base of production line and method for generating process scheme | |
| CN117764536B (en) | Innovative entrepreneur project auxiliary management system based on artificial intelligence | |
| Rao | Case-based reasoning (cbr) in condition monitoring & diagnostic engineering management (comadem): a literature survey | |
| Singh | Coding, Ranking and Optimum selection of Nanomaterials | |
| Jiang et al. | Human-in-Cognition Manufacturing-Loop (HCML): Framework and Technologies | |
| Duan et al. | Ontology-Based Knowledge Graph Construction and Application for Large Workpiece Forging |
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 |