CN117573880A - Rolling process data element model and data space construction method and system - Google Patents
Rolling process data element model and data space construction method and system Download PDFInfo
- Publication number
- CN117573880A CN117573880A CN202311433609.3A CN202311433609A CN117573880A CN 117573880 A CN117573880 A CN 117573880A CN 202311433609 A CN202311433609 A CN 202311433609A CN 117573880 A CN117573880 A CN 117573880A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- rolling process
- constructing
- metadata
- 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
- 238000005096 rolling process Methods 0.000 title claims abstract description 188
- 238000010276 construction Methods 0.000 title claims abstract description 57
- 238000004519 manufacturing process Methods 0.000 claims abstract description 58
- 238000013499 data model Methods 0.000 claims abstract description 54
- 238000004458 analytical method Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 27
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 19
- 238000013523 data management Methods 0.000 claims abstract description 19
- 239000010959 steel Substances 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 80
- 230000008569 process Effects 0.000 claims description 53
- 239000008280 blood Substances 0.000 claims description 20
- 210000004369 blood Anatomy 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 abstract description 22
- 238000006243 chemical reaction Methods 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000003860 storage Methods 0.000 abstract description 7
- 238000013500 data storage Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 abstract 1
- 239000010410 layer Substances 0.000 description 75
- 238000005098 hot rolling Methods 0.000 description 13
- 239000000047 product Substances 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 239000011159 matrix material Substances 0.000 description 7
- 239000013598 vector Substances 0.000 description 7
- 238000013506 data mapping Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 230000015654 memory Effects 0.000 description 6
- 230000003068 static effect Effects 0.000 description 6
- 238000001816 cooling Methods 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000003556 assay Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000012407 engineering method Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012800 visualization Methods 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
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a rolling process data element model and a data space construction method and a system, which relate to the technical field of industrial process data management and comprise the following steps: performing data analysis on the obtained strip steel hot continuous rolling process data to determine the class of rolling process metadata, providing a six-dimensional data model on the basis of a data unified modeling technology, and constructing a rolling process metadata structure model according to the relation between the class and the data; constructing an ontology model according to the data relationship and the related attributes to complete a data entity association network model; tracking information of each link such as data generation, data storage, data processing and display and the like based on metadata through data blood-edge analysis, and realizing data tracing and data query; and finally, constructing a knowledge graph of the data relationship and the attribute of the rolling process, and managing various metadata in the database to finish the construction of the data space of the rolling process. The invention realizes the tasks of conversion, storage, management, inquiry, analysis and the like of multi-source heterogeneous data for complex product manufacturing process data.
Description
Technical Field
The invention relates to the technical field of industrial process rolling data management, in particular to a rolling process data meta-model and data space construction method and system.
Background
The hot continuous rolling process of the strip steel is a steel production process with complex mechanism, huge scale, high efficiency and multiple working procedures, and is a typical complex flow industry. The production line mainly comprises a heating furnace, a rough rolling unit, a heat output roller way, flying shears, a finishing mill unit, a laminar cooling and coiling unit and the like. And the data of the hot continuous rolling process of the strip steel is uniformly managed, so that operators can know the data of the production process. In order to meet the requirement of unified management of multi-source heterogeneous data in the rolling process, a metadata structure model of a complex product manufacturing process is built to realize multi-level structuring, semi-structuring, unstructured data conversion and information unified description, how to build a data space to describe objects in an industrial application scene, and complex processes and knowledge of the rolling industry are mapped, so that the data can be clearly and accurately expressed.
In the industrial field, rolling process data are gradually changed from byproducts of the rolling process into strategic resources bringing new values to metallurgical enterprises and supply chain links, become key elements for improving productivity, competitiveness and innovation of rolling manufacturing industry, and aiming at the characteristics of multiscale, multilevel, difficult unification of forms and the like of multisource heterogeneous data in the rolling process, a metadata structure model is constructed by utilizing technical metadata, process metadata and business metadata. In the industrial manufacturing process data description, "metadata" refers to structured data describing characteristics of an information bearing entity, metadata management is generally defined as "description information of information resources", and in the context of multi-source heterogeneous data in a rolling process, metadata in the present invention refers to description data of all information integrated into a data warehouse by a source system.
Regarding the related technology of metadata management, related research on management of description of data resources is focused in China at present, and the management method is mainly applied to a distributed metadata management system for managing metadata information (picture size, time and position information) related to face pictures in a distributed scene, or corresponding management is carried out on a file system through related information describing organization architecture, and metadata management of massive network data information can be realized with low cost and high efficiency by applying metadata information; meanwhile, related research on metadata is carried out abroad by a metadata management software platform CKAN, and organizations of each country realize overall management on public data resources through the well-known free open source platform, so that sharing, identification, release and repeated utilization of open data are promoted, and the platform identifies data information through a special description key value pair, thereby realizing metadata management on the data resources. Metadata may provide a unified description mechanism and operation model for data of different sources and different structures, but is not itself representative of a substantial object, but plays a critical role in the data ETL process. Therefore, the object is described by means of a metadata model during the hot strip rolling process to construct a rolling process data space.
In order to solve the existing problems in the current data management process, the iDM data model for uniformly describing heterogeneous data is provided by the data space technology in 2005, so that the difficulty in the current data management field is solved, heterogeneous data can be effectively managed, the method relates to one-system data types such as extensible markup language (XML, extensible Markup Language) data, catalogues, documents and the like, and a resource view is constructed to describe the data space, so that entities are associated with a file system; the method mainly solves the problem of continuously changing heterogeneous data in a data space by a follow-up researcher aiming at an implementation prototype System (SEMEX) of a personal data management system, represents multi-source heterogeneous data and the relation between the multi-source heterogeneous data through triples, and establishes a user view by utilizing a graph model so as to manage the heterogeneous multi-source data; the following scholars, through analyzing the deficiency of the traditional data model and further researching, put forward a correlation model (COSNA) based on the context semantics of the perception entity, consider the semantic relation between data from multiple dimensions, measure the dynamic change of the data through the time dimension, add the context information to the description item of the entity, and provide an effective and convenient means for managing the related data about a certain theme.
The data space technology has many researches on the aspects of data models, data integration, data indexing, query methods and the like at present, but the research results are less due to the fact that the starting time is relatively late, and the application of the digital space technology based on the meta model to the field of industrial processes is still a worth exploring direction.
Disclosure of Invention
The invention provides a rolling process data element model and a data space construction method and system, which solve the problems that in the prior art, because the starting time is late, the research result is less, and the digital space technology based on the element model needs to be explored and applied to the industrial process field direction.
In order to solve the above-mentioned purpose, the technical scheme provided by the invention is as follows: a rolling process data element model and a data space construction method are characterized by comprising the following steps:
s1, acquiring process data of hot continuous rolling of strip steel;
s2, constructing a rolling process data space overall architecture;
s3, constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data element class relation;
s4, constructing an ontology model according to the data element relation and the related attribute, and extracting a rolling process triplet through a BiLSTM-CRF model and dependency syntax analysis to construct a data entity association network model;
S5, constructing and analyzing data blood edges based on metadata, and tracing data by utilizing a graph database according to each logic entity associated network model;
s6, constructing a knowledge graph of the data relationship and the attribute of the rolling process, forming a global view of the metadata of the manufacturing process of the complex product, and completing the construction of the data space of the rolling process.
Preferably, in step S1, process data of hot continuous rolling of the strip steel is obtained, including:
determining a data source type;
and acquiring process data of hot continuous rolling of the strip steel based on the data source type.
Preferably, in step S2, the rolling process data space overall architecture comprises:
the system comprises a user login unit, a source data importing unit, a meta model-ontology model unit, a data management module, a data query unit and a knowledge graph unit.
Preferably, in step S3, building an integrated metadata model based on the relationship between the class and the data includes:
designing a data metadata model for manufacturing a rolling process of a four-layer meta-model structure from bottom to top, and dividing the model into an example layer, a model layer, a meta-model layer and a meta-model layer;
constructing a six-dimensional data model based on the big data metadata model, and constructing a comprehensive rolling process metadata structure model according to a rolling process data dictionary;
According to the management and service flow of the rolling process data, constructing metadata systems with various functions and with which metadata are associated to form the rolling process data.
Preferably, a data metadata model of a rolling process for manufacturing a four-layer meta-model structure is designed from bottom to top, the model is divided into an instance layer, a model layer, a meta-model layer and a meta-model layer, and the method comprises the following steps:
abstract the rolling whole-flow physical system to construct a series of classes with higher universality for representing specific examples;
constructing a meta model layer based on the network ontology language; constructing a meta model layer based on the resource description framework; constructing a model layer based on the extensible markup language; the instance layer is built based on the hypertext markup language.
Preferably, in step S3, the six-dimensional data model includes:
based on the RDF knowledge description method, a six-dimensional data model is constructed by combining a four-layer meta-model structure, wherein the six-dimensional data model comprises: time domain data, space domain data, entity object domain data, relationship domain data, attributes, and attribute values.
Preferably, an ontology model is constructed according to the data element class relation and the related attribute, a rolling process triplet is extracted through BiLSTM-CRF model and dependency syntax analysis, and a data entity association network model is constructed, comprising:
Presetting a standard concept of rolling process data, establishing attribute association between data information, describing constraint relation of concept attributes, and establishing a unified ontology model of the rolling process data;
acquiring rolling industry knowledge, and extracting entities and relations by adopting a BiLSTM-CRF model and dependency syntactic analysis to acquire triples;
describing the conceptual model by using ontology knowledge, and constructing an ontology model by using Prot e software;
and importing the ontology model and the triples into a graph database Neo4j, and constructing a rolling process data entity association network model.
Preferably, in step S5, data blood edges are constructed and parsed based on metadata, and data tracing is performed by using a graph database according to each logical entity association network model, including:
constructing a dependency relationship analysis model, an influence analysis model and a data processing model according to the six-dimensional data model and the corresponding space-time correlation model;
analyzing the data blood edges according to the dependency analysis model, the influence analysis model and the data processing model;
acquiring data information described by a six-dimensional data model, and constructing a four-dimensional traceability model based on data blood-lineage analysis to perform data traceability;
and constructing a data mapping relation between input data items and output data items, obtaining a relation link of the data mapping to realize the construction of a data tracing model, and carrying out data tracing based on a graph database.
Preferably, in step S6, a knowledge graph of the data relationship and attribute of the rolling process is constructed, so as to form a global view of metadata of the manufacturing process of the complex product, and the construction of the data space of the rolling process is completed, including:
constructing a knowledge graph based on the process data entity association network model to obtain metadata attributes and association relations;
and visualizing the knowledge graph to form a global view of the manufacturing process data, and constructing a data space.
The system is used for the rolling process data meta-model and the data space construction method, and comprises the following steps:
the data acquisition module is used for acquiring process data of hot continuous rolling of the strip steel;
the overall construction module is used for constructing a rolling process data space overall architecture;
the data model construction module is used for constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data element class relation;
the data entity association module is used for constructing an ontology model according to the data element class relation and the related attribute, extracting a rolling process triplet through BiLSTM-CRF model and dependency syntactic analysis, and constructing a data entity association network model;
The data tracing module is used for constructing and analyzing data blood edges based on metadata and tracing data by utilizing the graph database according to the association network model of each logic entity;
and the data space construction module is used for constructing knowledge graphs of data relations and attributes in the rolling process, forming a metadata global view of the manufacturing process of the complex product and completing the data space construction of the rolling process.
In one aspect, an electronic device is provided, the electronic device including a processor and a memory, the memory storing at least one instruction, the at least one instruction loaded and executed by the processor to implement the rolling process data meta-model and the data space construction method described above.
In one aspect, a computer readable storage medium having stored therein at least one instruction loaded and executed by a processor to implement the rolling process data meta-model and data space construction method described above is provided.
Compared with the prior art, the technical scheme has at least the following beneficial effects:
according to the scheme, the rolling process data space overall architecture is constructed, and a unified description model based on metadata is provided on the basis of researching unified modeling technology of big data in a manufacturing process according to the multi-source heterogeneous characteristics of the big data in the manufacturing process: the six-dimensional data model develops a data management tool oriented to the metadata structure model aiming at the characteristic of multi-source heterogeneous process data, and performs standardized description on data of various stages such as design, development, production, manufacturing, test assay, operation and maintenance of the manufacturing process.
The metadata-based data blood edge analysis construction method is characterized in that definition and abstraction are carried out on a data processing flow of a heterogeneous data processing component and diversified data conversion solutions, the multi-source heterogeneous data processing flow is abstracted into an association relation between entities based on a meta model, information of each link such as data generation, data storage, data processing and presentation is tracked through data blood edge analysis, and application verification is carried out through data tracing and data query.
And uniformly managing various metadata in the database to form a global view of the metadata in the manufacturing process of the complex product, and completing the construction of the data space in the rolling process.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a rolling process data meta-model and a data space construction method provided by an embodiment of the invention;
FIG. 2 is an industrial flow chart of a rolling process provided by an embodiment of the present invention;
FIG. 3 is a diagram of the overall architecture of a rolling process data space provided by an embodiment of the present invention;
FIG. 4 is a diagram of a six-dimensional data meta-model provided by an embodiment of the present invention;
FIG. 5 is a diagram of an exemplary knowledge description provided by an embodiment of the invention;
FIG. 6 is a diagram of a rolling process metadata structure model provided by an embodiment of the present invention;
FIG. 7 is a metadata hierarchy model diagram of rolling data provided by an embodiment of the present invention;
FIG. 8 is a flow chart of a seven-step method of building an ontology provided by an embodiment of the present invention;
FIG. 9 is a diagram of a Bi LSTM-CRF model provided by an embodiment of the present invention;
FIG. 10 is a block diagram of a rolling process data meta-model and data space construction system provided by an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Aiming at the problem that a path tracking control method which has three advantages of effectively processing the constraint influence of a system, effectively utilizing the front reference path information, having good instantaneity and the like is lacked in the prior art, the invention provides a rolling process data meta-model and data space construction method and system.
As shown in fig. 1, the embodiment of the invention provides a rolling process data element model and a data space construction method, which can be realized by electronic equipment. The rolling process data element model and data space construction method flow chart shown in fig. 1, the processing flow of the method can comprise the following steps:
s101, acquiring process data of hot continuous rolling of strip steel;
in a possible implementation manner, in step S101, obtaining process data of hot continuous rolling of strip steel includes:
determining a data source type;
and acquiring process data of hot continuous rolling of the strip steel based on the data source type.
In a possible implementation, the data sources are of multiple types: the hot rolling equipment data mainly comprises static data, dynamic data, configuration data and the like, wherein the hot rolling equipment static data describes relevant static characteristics of hot rolling equipment, and comprises equipment names, equipment models, equipment codes, equipment manufacturers, equipment production dates, installation positions, geometric dimensions and the like; the hot rolling equipment dynamic data comprises heating furnace equipment dynamic data, rough rolling equipment dynamic data, finish rolling equipment dynamic data, laminar cooling and coiling service equipment dynamic data and the like; the hot rolling equipment configuration data refers to configuration items in the process of collecting and accessing hot rolling equipment and equipment quantity;
In a possible embodiment, there are several methods of acquiring data: the hot rolling industrial process has different data acquisition channels, different storage formats and differences of metadata items, so that the data is difficult to coordinate and apply;
in a possible implementation, the data does not have a unified management format: the format of the rolling process data is inconsistent, the digitalized definition and unified description of the whole life cycle products, processes and resources are not available, and the management, inquiry and data retrieval cannot be realized in a unified mode.
In one possible embodiment, the process data may be collected from a hot strip mill industrial site as the raw data set. As shown in FIG. 2, the production line mainly comprises a heating furnace, a roughing mill group, a heat output roller way, a flying shear, a finishing mill group, a laminar cooling and coiling group and the like. The process data comprise static data, dynamic data and configuration data, wherein the static data of the hot rolling equipment describe relevant static characteristics of the hot rolling equipment, including equipment names, equipment models, equipment codes, equipment manufacturers, equipment production dates, installation positions, geometric dimensions and the like; the hot rolling equipment dynamic data comprises heating furnace equipment dynamic data, rough rolling equipment dynamic data, finish rolling equipment dynamic data, laminar cooling and coiling service equipment dynamic data and the like; the hot rolling equipment configuration data refers to configuration items in the process of collecting and accessing hot rolling equipment and equipment quantity, and the association relationship among various attribute data is complex, and the hot rolling equipment configuration data has obvious process characteristics and data characteristics.
S102, constructing a rolling process data space overall architecture; as shown in fig. 3.
In a possible embodiment, in step S102, the rolling process data space overall architecture includes:
user login unit: the data space system requires password verification to ensure the safety of the system when a user of the system logs in, and the user login module can enter a front page of the whole rolling data system to operate and use the corresponding functions of the system after successful login by comparing with staff information stored in a database;
source data importing unit: the rolling process data sources are different and the structures are different, the module is used for importing multi-source heterogeneous rolling process data into a database corresponding to a data space, dividing the data format and preprocessing the imported data so as to form data space resources;
meta-model-ontology model unit: the meta model prescribes the form and structure of various metadata of rolling process data, and is the basis of metadata management construction. The module carries out metadata structure description on rolling process data, a rolling process data model is constructed according to data division of an industrial data dictionary (industrial internet platform industrial equipment data dictionary), and integrated management of the data is realized through model mapping;
And a data management module: the part is mainly used for realizing the management operation of an administrator on data, and the data space constructed based on metadata can facilitate the administrator to realize the work of changing, deleting, exporting and the like of the data;
a data query unit: and a data query module: the data space system can help staff to perform data query through source data, so that detailed information related to the data is clear, data tracing and association relation query are convenient to perform, and compared with a traditional data management technology, the data space technology using metadata can rapidly locate the data and check corresponding attribute information of the data, and data management efficiency is improved;
knowledge graph unit: the data is preprocessed to determine the variable relation, the entity relation attribute triplet is extracted based on the knowledge of the rolling process, the knowledge graph of the rolling process data variable is constructed, the index of the metadata variable association relation is realized through single-layer and multi-layer inquiry of the entity relation, and the tasks of adding, deleting, managing and the like of the entity, the relation and the attribute can be performed.
S103, constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data element class relation;
In a possible implementation, in step S103, building an integrated metadata model based on a relationship between a class and data includes:
designing a data metadata model for manufacturing a rolling process of a four-layer meta-model structure from bottom to top, and dividing the model into an example layer, a model layer, a meta-model layer and a meta-model layer;
constructing a six-dimensional data model based on the big data metadata model, and constructing a comprehensive rolling process metadata structure model according to a rolling process data dictionary;
according to the management and service flow of the rolling process data, constructing metadata systems with various functions and with which metadata are associated to form the rolling process data.
In a possible implementation manner, a data metadata model of a rolling process for manufacturing a four-layer meta-model structure is designed from bottom to top, and the model is divided into an instance layer, a model layer, a meta-model layer and a meta-model layer, which comprises the following steps:
abstract the rolling whole-flow physical system to construct a series of classes with higher universality for representing specific examples;
constructing a meta model layer based on the network ontology language; constructing a meta model layer based on the resource description framework; constructing a model layer based on the extensible markup language; the instance layer is built based on the hypertext markup language.
In a possible implementation, the meta-modeling process adopts a bottom-up design from concrete to abstract implementation, and the meta-modeling is generally divided into four layers and is in a pyramid structure.
In a possible implementation, classes with a high universality are built as much as possible when the object is highly summarized. If the class is required to be expanded, a new class is established in a mode of aggregation, inheritance and the like, and the original class is not required to be modified;
constructing a meta model layer based on a network ontology language, wherein the meta model layer comprises basic model structure components, mainly including classes, attributes, relations and the like abstracted from rolling process data;
constructing a meta model layer based on a resource description framework, wherein the meta model layer mainly comprises classes and attributes corresponding to files generated or used in a rolling process and space-time correlation among different models;
constructing a model layer based on an extensible markup language, wherein the model layer is used for describing a specific service model and comprises various data models, relation models and the like in the rolling process;
an instance layer is built based on the hypertext markup language, including objects and data, for description of specific operational objects and specific data generated thereby during the rolling process.
In a feasible implementation mode, a unified description model-six-dimensional data model based on metadata is provided aiming at the characteristic of manufacturing big data multi-source isomerism.
In a possible embodiment, in step S103, the six-dimensional data model includes:
the method for describing the triple (main body, attribute and attribute value) knowledge based on RDF (Uniform resource description framework, resource Description Framework) is combined with a four-layer meta-model structure to construct a six-dimensional data model, wherein the six-dimensional data model comprises the following steps: time domain data, space domain data, entity object domain data, relationship domain data, attributes, and attribute values. Denoted M.fwdarw. (T, S, I, R, P, V), the model structure is shown in FIG. 4. Taking the knowledge description of the finishing mill process and the attribute outlet thickness thereof as an example, as shown in fig. 5, through the description of the unified data model structure, the mutual conversion of structured and unstructured data and the unified information description are finally realized.
In a possible implementation, to provide better data service for users, a standard set of rolling process data information description expression schemes is further researched and established, and a comprehensive rolling process metadata structure model is established, as shown in fig. 6, so that data information can be circulated and shared among various systems. The rolling process metadata structure model includes description of data source and data description, description of data owner and data sequence, etc., description of data processing information, description of data quality, description of data conversion method, etc. On one hand, metadata can describe the related information such as occurrence form, data format, access condition and address, management information, etc. in detail and accurately; on the other hand, it can also provide a consistent data view for data management, facilitating unified data management and data service operations.
In a possible embodiment, as the life cycle of the rolling process data progresses, there is a different expansion at different life cycle stages on the basis of sharing one core metadata. The metadata structure model is constructed by utilizing metadata, the rolling process metadata system is divided into technical metadata, management metadata and service metadata according to application scenes according to rolling process data management and service flow, and metadata with various functions are mutually related to form the rolling process data metadata system as shown in fig. 7.
S104, constructing an ontology model according to the data element class relation and the related attribute, and extracting a rolling process triplet through a BiLSTM-CRF model and dependency syntax analysis to construct a data entity associated network model;
in a feasible implementation mode, as many as thousands of process control variables and performance indexes are involved in the rolling production process, and according to the characteristics of multi-level, multi-scale and difficult-to-unify form of rolling process data, each model layer corresponds to different information description formats and example characteristics respectively. The data associations in the data space are entity level associations.
In a possible implementation manner, in step S104, an ontology model is constructed according to the data element class relationship and the related attribute, and a data entity association network model is constructed by using a Bi lstm-CRF (Bi-directional Long Short-Term Memory-Conditional random field) model and dependency syntax analysis extraction rolling process triples, including:
Based on unified modeling of production process data of an ontology, presetting a canonical concept of rolling process data, establishing attribute association between data information, describing constraint relation of concept attributes, and establishing a unified ontology model of the rolling process data.
In a possible implementation manner, the development domain ontology is constructed based on a top layer ontology, and a construction ontology flow is shown in fig. 8, and is constructed by adopting a seven-step method:
according to the characteristics of the whole flow data in the rolling process, determining the category of the building body mainly comprises related information of a heating furnace, a roughing mill group, a heat output roller way, a flying shear, a finishing mill group, a laminar cooling and coiling group;
the built body is analyzed and checked to determine whether the built body can be reused, and the workload can be reduced on the one hand by multiplexing the body, and the interactive function between different systems and different sub-modules can be realized;
the term standardization is combined with the steel rolling industry process data dictionary, letter abbreviation standards and the like to determine important terms;
defining class of rolling process data and class grade;
defining terms for describing relationships between concepts (classes) and the classes, respectively defining attributes of the classes in the rolling process data and the relationships;
Classifying the resource attributes, and performing classification operation before creating an instance because of the differences of types, values and the like among different resource attributes;
an instance is created.
In a feasible implementation mode, obtaining rolling industry knowledge, and extracting entities and relations by adopting a BiLSTM-CRF model and dependency syntactic analysis to obtain triples;
as shown in FIG. 9, the BiLSTM-CRF model is mainly composed of an input layer, biLSTM layers and CRF layers, wherein the input layer is mainly character features, and words are embedded into a vector sequence x, x= { x 1 ,x 2 ,...x n-1 ,x n },x i The representative meaning is the input vector of the i-th word, the characteristic of the sequence character, such as part-of-speech characteristic, front and back words, can be defined by a characteristic engineering method, the input model is subjected to characteristic extraction, then CRF layer classification decision is utilized, and the relationship between the entities is analyzed based on dependency syntax.
The input layer serves as a base layer of the BiLSTM-CRF model, and is mainly used for mapping the input vectors of the individual characters or words from an embedded matrix to a low-dimensional dense vector by random initialization.
Inputting the word vector sequence obtained by the input layer into the BiLSTM layer to obtain the forward hidden layer sequence respectivelyAnd the backward hidden layer sequence- >Handle->And->Obtaining the final complete hidden layer sequence according to position integration>To obtain the hidden layer sequence (h) 1 ,h 2 ,…,h t )∈R t*m . Then the sequence is accessed into a linear layer, mapping is carried out from n dimension to k dimension, vector dimension and label set length are respectively corresponding, and mapping is carried out to obtain a Chinese character matrix p= (p) 1 ,p 2 ,…,p t )∈R t*k (k represents the standard tab number) to obtain the score marking the current position;
and taking the CRF as the outermost layer of the model, normalizing the feature matrix by a Softmat function in the BiLSTM layer, and judging the information marking according to the probability value when the value of each line of the feature matrix is equal to the probability of the label. Classifying and labeling the feature matrix P output by the BiLSTM layer through the CRF layer, and performing P ij Meaning of representation is the ith word in the jth label by inputting the sequence x= { x 1 ,x 2 ,…,x n-1 ,x n The label sequence y= { y corresponding to the same 1 ,y 2 ,…,y n-1 ,y n Combining the state transition matrix of CRF, the condition that the label of the BSTM-CFR model to statement x is a y score can be obtained, and the following formula is obtained:
wherein the method comprises the steps ofRepresenting adjacent state transition matrix scores in the CRF layer. />Representing the output vector score of the BiLST model, the probability formula for obtaining the BLSTM-CRF model after normalizing the score s (x, y) is as follows:
wherein Y (x) represents all possible labeling sequences, and finally, the prediction process of the model selects a prediction formula labeled by using a maximum likelihood estimation function as follows:
In a possible embodiment, the conceptual model is described using ontology knowledge, and the ontology model is built by Prot g software. The method specifically comprises the following steps:
establishing a class, namely establishing a class of rolling process data according to the element number model and the extracted entity;
establishing the attribute of the entity object, and determining the entity object according to the rolling process;
establishing an entity, and determining a corresponding entity according to related variables in the rolling process;
and constructing the association relationship among the entities, and determining the entity relationship according to the extracted triplet knowledge and the variable relativity.
In a possible implementation mode, the ontology model and the triples are imported into a map database Neo4j, and a rolling process data entity association network model is built.
S105, constructing and analyzing data blood edges based on metadata, and tracing data by utilizing a graph database according to each logic entity associated network model;
in a possible implementation manner, in step S105, constructing and analyzing a data blood edge based on metadata, and performing data tracing by using a graph database according to each logical entity association network model, including:
constructing a dependency relationship analysis model, an influence analysis model and a data processing model according to the six-dimensional data model and the corresponding space-time correlation model;
Analyzing the data blood edges according to the dependency analysis model, the influence analysis model and the data processing model;
acquiring data information described by a six-dimensional data model, and constructing a four-dimensional traceability model based on data blood-lineage analysis to perform data traceability;
and constructing a data mapping relation between input data items and output data items, obtaining a relation link of the data mapping to realize the construction of a data tracing model, and carrying out data tracing based on a graph database.
In one possible implementation, the data lineage construction principle includes:
the set of transformations in the data processing flow is noted as:
TS (Transformation Set) ＝ {T 1 ,..,T w ,..,T n } (4)
wherein T is w Denoted as data conversion node, the data processing flow is denoted as:
TS(I)＝O (5)
where I is the initial set of input data items and O is the final set of output data items, with each specific transformation expressed as:
T w (I w )＝ O w (6)
and the mapping set obtained by conversion analysis is recorded as:
M (Map)＝ {M 1 ,..,M w ...,M n } (7)
wherein M is w A single conversion mapping process is represented, but temporary input and output data items are denoted as D ' and temporary input and output data item sets are denoted as I ', O ' at the time of conversion, so that related data maps may be generated such as:
{Di`→Do，Di→Do` ，Di`→Do`，Di→Do } (8)。
s106, constructing a knowledge graph of the data relationship and the attribute of the rolling process, forming a global view of the metadata of the manufacturing process of the complex product, and completing the construction of the data space of the rolling process.
In a possible implementation manner, in step S106, a knowledge graph of the data relationship and attribute of the rolling process is constructed, a global view of metadata of the manufacturing process of the complex product is formed, and the construction of the data space of the rolling process is completed, including:
constructing a knowledge graph based on the process data entity association network model to obtain metadata attributes and association relations;
and visualizing the knowledge graph to form a global view of the manufacturing process data, and constructing a data space.
In a feasible implementation mode, a rolling process database model is constructed to uniformly manage process data, so that a rolling process meta-model and a data space device are realized and the rolling process meta-model and the data space device are applied to data tracing and data query;
adding and deleting functions of data management are added to realize the treatment of process data;
in one possible implementation, a data space system is designed and implemented based on a B/S architecture;
designing a rolling process metadata base based on unified metadata standards;
completing data unified description through data preprocessing, source data importing, meta modeling and ontology modeling processes, and constructing an ontology model by adopting a network ontology language (OWL, web Ontology Language) for description;
forming an entity association network model based on the data relationship attribute, importing the entity association network model into a Neo4j graph database, performing blood-margin analysis based on metadata to form a complex product manufacturing process data global view, and realizing the functions of visualization and search query;
And finishing a data space device for the multi-source heterogeneous rolling process data and realizing data service management.
In the embodiment of the invention, a rolling process data space overall architecture is constructed, and a unified description model based on metadata is provided on the basis of researching unified modeling technology of big data in a manufacturing process aiming at the multi-source heterogeneous characteristics of the big data in the manufacturing process: the six-dimensional data model develops a data management tool oriented to the metadata structure model aiming at the characteristic of multi-source heterogeneous process data, and performs standardized description on data of various stages such as design, development, production, manufacturing, test assay, operation and maintenance of the manufacturing process.
The metadata-based data blood edge analysis construction method is characterized in that definition and abstraction are carried out on a data processing flow of a heterogeneous data processing component and diversified data conversion solutions, the multi-source heterogeneous data processing flow is abstracted into an association relation between entities based on a meta model, information of each link such as data generation, data storage, data processing and presentation is tracked through data blood edge analysis, and application verification is carried out through data tracing and data query.
And uniformly managing various metadata in the database to form a global view of the metadata in the manufacturing process of the complex product, and completing the construction of the data space in the rolling process.
Fig. 10 is a schematic diagram of a rolling process data meta-model and data space construction system according to the present invention, the system 200 is used for the rolling process data meta-model and data space construction method described above, and the system 200 includes:
the data acquisition module 210 is used for acquiring process data of hot continuous rolling of the strip steel;
an overall construction module 220 for constructing a rolling process data space overall architecture;
a data model construction module 230 for constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data element class relation;
the data entity association module 240 is configured to construct an ontology model according to the data element class relationship and the related attribute, extract a rolling process triplet through the BiLSTM-CRF model and the dependency syntax analysis, and construct a data entity association network model;
the data tracing module 250 is configured to construct and parse data blood edges based on metadata, and perform data tracing by using a graph database according to each logic entity association network model;
the data space construction module 260 is configured to construct a knowledge graph of data relationships and attributes in a rolling process, form a global view of metadata in a manufacturing process of a complex product, and complete the construction of the data space in the rolling process.
Preferably, the data acquisition module 210 is configured to determine a data source type;
and acquiring process data of hot continuous rolling of the strip steel based on the data source type.
Preferably, the overall construction module 220 is used for a user login unit, a source data import unit, a meta model-ontology model unit, a data management module, a data query unit and a knowledge graph unit.
Preferably, the data model construction module 230 is configured to design a data metadata model of a rolling process for manufacturing a four-layer meta-model structure from bottom to top, and divide the model into an instance layer, a model layer, a meta-model layer and a meta-model layer;
constructing a six-dimensional data model based on the big data metadata model, and constructing a comprehensive rolling process metadata structure model according to a rolling process data dictionary;
according to the management and service flow of the rolling process data, constructing metadata systems with various functions and with which metadata are associated to form the rolling process data.
Preferably, a data metadata model of a rolling process for manufacturing a four-layer meta-model structure is designed from bottom to top, the model is divided into an instance layer, a model layer, a meta-model layer and a meta-model layer, and the method comprises the following steps:
abstract the rolling whole-flow physical system to construct a series of classes with higher universality for representing specific examples;
Constructing a meta model layer based on the network ontology language; constructing a meta model layer based on the resource description framework; constructing a model layer based on the extensible markup language; the instance layer is built based on the hypertext markup language.
Preferably, the six-dimensional data model comprises:
based on the RDF knowledge description method, a six-dimensional data model is constructed by combining a four-layer meta-model structure, wherein the six-dimensional data model comprises: time domain data, space domain data, entity object domain data, relationship domain data, attributes, and attribute values.
Preferably, the data entity association module 240 is configured to include:
presetting a standard concept of rolling process data, establishing attribute association between data information, describing constraint relation of concept attributes, and establishing a unified ontology model of the rolling process data;
acquiring rolling industry knowledge, and extracting entities and relations by adopting a BiLSTM-CRF model and dependency syntactic analysis to acquire triples;
describing the conceptual model by using ontology knowledge, and constructing an ontology model by using Prot e software;
and importing the ontology model and the triples into a graph database Neo4j, and constructing a rolling process data entity association network model.
Preferably, the data tracing module 250 is configured to construct a dependency analysis model, an influence analysis model and a data processing model according to the six-dimensional data model and the corresponding space-time correlation model;
Analyzing the data blood edges according to the dependency analysis model, the influence analysis model and the data processing model;
acquiring data information described by a six-dimensional data model, and constructing a four-dimensional traceability model based on data blood-lineage analysis to perform data traceability;
and constructing a data mapping relation between input data items and output data items, obtaining a relation link of the data mapping to realize the construction of a data tracing model, and carrying out data tracing based on a graph database.
Preferably, the data space construction module 260 is configured to construct a knowledge graph based on the process data entity association network model, so as to obtain metadata attributes and association relationships;
and visualizing the knowledge graph to form a global view of the manufacturing process data, and constructing a data space.
In the embodiment of the invention, a rolling process data space overall architecture is constructed, and a unified description model based on metadata is provided on the basis of researching unified modeling technology of big data in a manufacturing process aiming at the multi-source heterogeneous characteristics of the big data in the manufacturing process: the six-dimensional data model develops a data management tool oriented to the metadata structure model aiming at the characteristic of multi-source heterogeneous process data, and performs standardized description on data of various stages such as design, development, production, manufacturing, test assay, operation and maintenance of the manufacturing process.
The metadata-based data blood edge analysis construction method is characterized in that definition and abstraction are carried out on a data processing flow of a heterogeneous data processing component and diversified data conversion solutions, the multi-source heterogeneous data processing flow is abstracted into an association relation between entities based on a meta model, information of each link such as data generation, data storage, data processing and presentation is tracked through data blood edge analysis, and application verification is carried out through data tracing and data query.
And uniformly managing various metadata in the database to form a global view of the metadata in the manufacturing process of the complex product, and completing the construction of the data space in the rolling process.
Fig. 11 is a schematic structural diagram of an electronic device 300 according to an embodiment of the present invention, where the electronic device 300 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 301 and one or more memories 302, where at least one instruction is stored in the memories 302, and the at least one instruction is loaded and executed by the processors 301 to implement the following steps of a rolling process data meta-model and a data space construction method:
S1, acquiring process data of hot continuous rolling of strip steel;
s2, constructing a rolling process data space overall architecture;
s3, constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data element class relation;
s4, constructing an ontology model according to the data element relation and the related attribute, and extracting a rolling process triplet through a BiLSTM-CRF model and dependency syntax analysis to construct a data entity association network model;
s5, constructing and analyzing data blood edges based on metadata, and tracing data by utilizing a graph database according to each logic entity associated network model;
s6, constructing a knowledge graph of the data relationship and the attribute of the rolling process, forming a global view of the metadata of the manufacturing process of the complex product, and completing the construction of the data space of the rolling process.
In an exemplary embodiment, a computer readable storage medium, such as a memory comprising instructions executable by a processor in a terminal to perform the rolling process data meta-model and the data space construction method described above is also provided. For example, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Claims (10)
1. A rolling process data element model and a data space construction method are characterized in that the method comprises the following steps:
s1, acquiring process data of hot continuous rolling of strip steel;
s2, constructing a rolling process data space overall architecture;
s3, constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data meta-class relation;
s4, constructing an ontology model according to the data element relation and the related attribute, and extracting a rolling process triplet through a BiLSTM-CRF model and dependency syntax analysis to construct a data entity association network model;
s5, constructing and analyzing data blood edges based on metadata, and tracing data by utilizing a graph database according to each logic entity associated network model;
S6, constructing a knowledge graph of the data relationship and the attribute of the rolling process, forming a global view of the metadata of the manufacturing process of the complex product, and completing the construction of the data space of the rolling process.
2. The method according to claim 1, wherein in the step S1, the process data of hot continuous rolling of the strip steel is obtained, including:
determining a data source type;
and acquiring the process data of hot continuous rolling of the strip steel based on the data source type.
3. The method according to claim 2, wherein in step S2, the rolling process data space overall architecture comprises:
the system comprises a user login unit, a source data importing unit, a meta model-ontology model unit, a data management module, a data query unit and a knowledge graph unit.
4. A method according to claim 3, wherein in step S3, building an integrated metadata model based on the relationship between the class and the data comprises:
designing a rolling process data metadata model of a pyramid four-layer meta-model structure from bottom to top, and dividing the model into an instance layer, a model layer, a meta-model layer and a meta-model layer;
constructing a six-dimensional data model based on the big data metadata model, and constructing a comprehensive rolling process metadata model according to a rolling process data dictionary;
And constructing metadata with different functions by combining the six-dimensional data model and the rolling process metadata model according to the rolling process data management and service flow, and forming a metadata system of the rolling process data by associating the metadata with each other.
5. The method of claim 4, wherein the bottom-up design of the rolling process data metadata model for manufacturing the four-layer meta-model structure divides the rolling process data metadata model into an instance layer, a model layer, a meta-model layer, and a meta-model layer, comprising:
abstract data of an instance in a rolling full-flow physical system to construct classification, wherein the classification represents a specific instance;
constructing a meta model layer based on the network ontology language; constructing a meta model layer based on the resource description framework; constructing a model layer based on the extensible markup language; the instance layer is built based on the hypertext markup language.
6. The method according to claim 5, wherein in the step S3, the six-dimensional data model includes:
based on an RDF knowledge description method, a six-dimensional data model is constructed by combining a four-layer meta-model structure, wherein the six-dimensional data model comprises: time domain data, space domain data, entity object domain data, relationship domain data, attributes, and attribute values.
7. The method of claim 6, wherein constructing the ontology model from the data element class relationships and the related attributes, extracting the rolling process triples through the BiLSTM-CRF model and the dependency syntax analysis, and constructing the data entity association network model, comprises:
presetting a standard concept of rolling process data, establishing attribute association between data information, describing constraint relation of concept attributes, and establishing a unified ontology model of the rolling process data;
acquiring rolling industry knowledge, and extracting entities and relations by adopting a BiLSTM-CRF model and dependency syntactic analysis to acquire triples;
describing the conceptual model by using ontology knowledge, and constructing an ontology model by using Prot e software;
and importing the ontology model and the triples into a map database Neo4j to build a rolling process data entity association network model.
8. The method according to claim 7, wherein in the step S5, the step of constructing and analyzing the data blood edges based on the metadata, and performing the data tracing by using the graph database according to each logical entity association network model includes:
constructing a dependency relationship analysis model, an influence analysis model and a data processing model according to the six-dimensional data model and the corresponding space-time correlation model;
Analyzing the data blood margin according to the dependency analysis model, the influence analysis model and the data processing model;
and acquiring data information described by the six-dimensional data model, constructing a four-dimensional traceability model based on data blood-margin analysis, and carrying out data traceability based on a graph database.
9. The method according to claim 8, wherein in step S6, a knowledge graph of the data relationships and attributes of the rolling process is constructed, a global view of the metadata of the complex product manufacturing process is formed, and the rolling process data space construction is completed, including:
constructing a knowledge graph based on the process data entity association network model to obtain metadata attributes and association relations;
and visualizing the knowledge graph to form a global view of the manufacturing process data, and managing various metadata in a database to complete the construction of a rolling process data space.
10. A rolling process data meta-model and data space construction system for a rolling process data meta-model and data space construction method according to any one of claims 1-9, said system comprising:
the data acquisition module is used for acquiring process data of hot continuous rolling of the strip steel;
The overall construction module is used for constructing a rolling process data space overall architecture;
the data model construction module is used for constructing a six-dimensional data model; analyzing the process data based on the six-dimensional data model to obtain a class of the process data; constructing a metadata structure model based on the relation between the class and the data to obtain a data meta-class relation;
the data entity association module is used for constructing an ontology model according to the data element class relation and the related attribute, extracting a rolling process triplet through BiLSTM-CRF model and dependency syntactic analysis, and constructing a data entity association network model;
the data tracing module is used for constructing and analyzing data blood edges based on metadata and tracing data by utilizing the graph database according to the association network model of each logic entity;
and the data space construction module is used for constructing knowledge graphs of data relations and attributes in the rolling process, forming a metadata global view of the manufacturing process of the complex product and completing the data space construction of the rolling process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311433609.3A CN117573880A (en) | 2023-10-31 | 2023-10-31 | Rolling process data element model and data space construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311433609.3A CN117573880A (en) | 2023-10-31 | 2023-10-31 | Rolling process data element model and data space construction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117573880A true CN117573880A (en) | 2024-02-20 |
Family
ID=89883399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311433609.3A Pending CN117573880A (en) | 2023-10-31 | 2023-10-31 | Rolling process data element model and data space construction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117573880A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892817A (en) * | 2024-03-15 | 2024-04-16 | 南方科技大学 | Knowledge graph construction method based on manufacturing full life cycle data |
-
2023
- 2023-10-31 CN CN202311433609.3A patent/CN117573880A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892817A (en) * | 2024-03-15 | 2024-04-16 | 南方科技大学 | Knowledge graph construction method based on manufacturing full life cycle data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Vysotska et al. | Web Content Support Method in Electronic Business Systems. | |
| Soibelman et al. | Management and analysis of unstructured construction data types | |
| Hsu | Content-based text mining technique for retrieval of CAD documents | |
| Yang et al. | Research on enterprise risk knowledge graph based on multi-source data fusion | |
| CN102609512A (en) | System and method for heterogeneous information mining and visual analysis | |
| CN103425740A (en) | IOT (Internet Of Things) faced material information retrieval method based on semantic clustering | |
| CN117573880A (en) | Rolling process data element model and data space construction method and system | |
| Shakhovska et al. | Big Data Model" Entity and Features" | |
| CN115221337A (en) | Data weaving processing method and device, electronic equipment and readable storage medium | |
| Mhammedi et al. | Heterogeneous integration of big data using semantic web technologies | |
| Jiang et al. | Research on BIM-based Construction Domain Text Information Management. | |
| Li et al. | Application research of machine learning method based on distributed cluster in information retrieval | |
| KR102096328B1 (en) | Platform for providing high value-added intelligent research information based on prescriptive analysis and a method thereof | |
| Shi et al. | [Retracted] Research on Fast Recommendation Algorithm of Library Personalized Information Based on Density Clustering | |
| Zhang et al. | A knowledge reuse-based computer-aided fixture design framework | |
| Bova et al. | Multi-level ontological model of big data processing | |
| CN113901077A (en) | Method and system for producing entity object label, storage medium and electronic equipment | |
| Fawei et al. | An Adaptable Ontology for Easy and Efficient University Data Management in Niger Delta University | |
| Hirchoua et al. | Topic hierarchies for knowledge capitalization using hierarchical Dirichlet processes in big data context | |
| Tang | [Retracted] Analysis of English Multitext Reading Comprehension Model Based on Deep Belief Neural Network | |
| Wyskwarski | Business intelligence-publication analysis using the R language | |
| CN115687623B (en) | Industrial digital twin data space construction method and system | |
| Hakeem | A framework for combining software patterns with semantic web for unstructured data analysis | |
| Haddad et al. | Machine learning analytics-based distributed frameworks: a survey | |
| Mangat et al. | Relevance of data mining techniques in real life |
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 |