CN113420157A - Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph - Google Patents

Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph Download PDF

Info

Publication number
CN113420157A
CN113420157A CN202110584742.3A CN202110584742A CN113420157A CN 113420157 A CN113420157 A CN 113420157A CN 202110584742 A CN202110584742 A CN 202110584742A CN 113420157 A CN113420157 A CN 113420157A
Authority
CN
China
Prior art keywords
quality
steel product
model
longitudinal crack
converter
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
Application number
CN202110584742.3A
Other languages
Chinese (zh)
Inventor
张云贵
刘自恒
李卓卿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Automation Research and Design Institute of Metallurgical Industry
Original Assignee
Automation Research and Design Institute of Metallurgical Industry
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Automation Research and Design Institute of Metallurgical Industry filed Critical Automation Research and Design Institute of Metallurgical Industry
Priority to CN202110584742.3A priority Critical patent/CN113420157A/en
Publication of CN113420157A publication Critical patent/CN113420157A/en
Pending legal-status Critical Current

Links

Images

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
    • 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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Animal Behavior & Ethology (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Factory Administration (AREA)

Abstract

A method for analyzing the traceability of surface longitudinal crack defects of steel products based on a knowledge graph belongs to the technical field of steel product quality tracing. The method comprises the steps of adopting a top-down knowledge map construction route, carrying out knowledge combing by means of industry experts in the aspect of longitudinal crack defects on the surface of the steel product, designing a body of the traceability knowledge map of the longitudinal crack defects on the surface of the steel product, and establishing an entity and a relation of the knowledge map by combining actual data of enterprises to construct a cross-process traceability knowledge map of the longitudinal crack defects on the surface of the steel product. The method has the advantages that the knowledge graph visualization technology is used for representing the transmission relation between the quality defects and the quality events of the whole process, the limitation of the process is broken, and the cross-process traceability analysis of the longitudinal crack defects on the surface of the steel product is realized.

Description

Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph
Technical Field
The invention belongs to the technical field of quality tracing of steel products, and particularly relates to a knowledge graph-based method for tracing and analyzing surface longitudinal crack defects of steel products.
Technical Field
In the original tracing of the quality defect of the surface longitudinal crack of the steel product, the whole production flow of the steel product with the quality defect of the surface longitudinal crack is obtained through the correlation of specific fields or product ID in a relational database, and then the source tracing is carried out through corresponding data analysis. The technical personnel need to clearly know the complex association relationship among the data tables and the meaning and the association influence of each production parameter recorded in the data tables. However, the cause of the formation of the surface longitudinal crack defect is complex, and the influence of other quality events without parameter record and the transmission effect of the quality events among all the processes due to heredity and relevance are ignored to a certain extent by analyzing the data.
Disclosure of Invention
The invention aims to provide a method for analyzing the traceability of the surface longitudinal crack defects of steel products based on an intellectual map, which describes the relationship between quality events occurring in the steel production process and the final surface longitudinal crack defects of the steel products by using a graph mode, and is more reasonable and more flexible instead of simply describing the relationship by using a relational database table. The field association of the table structure in the original relational database is replaced by a graph mode, a steel product quality defect cause knowledge graph is constructed by means of expert knowledge from top to bottom, the expert knowledge is normalized through an ontology, and the expert knowledge is precipitated. The knowledge graph visualization technology is used for representing the transmission relation between the quality defects and the quality events of the whole process, so that the limitation of the process is broken, and the cross-process traceability analysis of the longitudinal crack defects on the surface of the steel product is realized.
The method adopts a top-down knowledge map construction route, carries out knowledge carding by means of industry experts in the aspect of longitudinal crack defects on the surface of the steel product, designs a body of the traceability knowledge map of the longitudinal crack defects on the surface of the steel product, and creates entities and relations of the knowledge map by combining actual data of enterprises to construct the traceability knowledge map of the longitudinal crack defects on the surface of the steel product across processes. The method specifically comprises the following steps:
(1) constructing a source tracing knowledge map body of the surface longitudinal crack defects of the steel product based on expert experience knowledge;
(2) based on the ontology and the actual production condition, constructing an entity example and a relation example to form a traceability knowledge map of the surface longitudinal crack defects of the steel product: the example corresponding to the model in the knowledge graph body is a specific event which can occur in the process of processing and producing the steel product. For example: entities corresponding to the quality event model are working steps of steel products in the production process, such as 'converter slag tapping', 'converter reblowing' in the converter process, and 'LF argon static blowing time inconsistency' in the LF refining process; the entity corresponding to the abnormal event model is an abnormal situation which may occur in each process step (quality event entity), such as "excessive converter tapping temperature drop", "2 times of converter reblowing" and the like which may occur in a converter process. And (3) building entities, wherein each entity corresponds to a certain ontology model, and then establishing specific relations among the entities for all the entities according to the relations among the ontology models.
(3) According to the established knowledge graph entity network, the possible cause path of the surface longitudinal crack quality defect of the steel product is searched: inputting quality defects of steel products, such as surface longitudinal cracks, acquiring all entity nodes and relations pointing to the surface longitudinal crack nodes to form a map network with the surface longitudinal crack nodes as the center. And then inputting screening conditions according to actual conditions, performing attribute filtration on entity types and relationship types appearing in the network, and acquiring a cause path possibly causing surface longitudinal crack defects. For example, when a billet number of a product steel product with a surface longitudinal crack defect is input, a processing procedure for processing the billet number steel is obtained, and all cause paths which may cause the surface longitudinal crack in the processing procedure of the billet number steel product are screened.
(4) And analyzing by combining actual production data and events based on the searched possible paths, and reasoning out the real cause of the quality defect: according to the blank number of the steel product with the quality defect, on one hand, all processing procedures of the blank number product and abnormal events possibly occurring in the processing procedures are obtained, and then a production process parameter model and a judgment rule which can cause the abnormal events are obtained; on the other hand, the actual production parameters of the steel product are obtained from the production process database of the enterprise and are matched with the judgment rule, so that the path of the quality defect caused by the unmatched production rule is obtained. For example, the billet number of the steel product with the surface longitudinal crack defect is 200900011, the surface longitudinal crack is selected from the quality defects, and the billet number is input 20092300011, obtaining the product through systematic retrieval, wherein in the production process of the product, in the working procedure processing link of a converter with the furnace number of 20092301, the temperature drop is overlarge in the tapping process of the converter, and T isEnd point temperature-TTemperature of baleThe temperature is 73 ℃ and is 65 ℃ higher than the critical value of the judging rule endpoint, so that the surface longitudinal crack defect occurs. Therefore, the analysis is output (decision rule { rule description: "at converter tapping, T)End point temperature-TTemperature of bale≥ 65 ℃ ", rule id: 10}) ->(parameter: [ "T [) parameterEnd point temperature”,”TTemperature of bale”]Metadata { converter monitoring sensor database } }) ->(abnormal event name: converter tapping temperature drop is too large; occurrence position: all casting blanks produced by the converter, belonging to equipment: converter equipment name; belonging to procedure: converter)>(quality event name: converter tapping temperature drop, belonging to the process: converter->(quality defect) (defect name: "surface longitudinal crack", belonging to the process: "continuous casting") the cause path;
generating a cross-process cause key path for the longitudinal crack defects on the surface of the steel product through attribute filtering, and outputting a specific quality event chain; meanwhile, a steel product quality defect traceability key path flow chart is established based on experience probability and data drive, the cause probability of each possible traceability path is quantitatively analyzed, and support is provided for quality decision.
The traceability analysis knowledge graph of the longitudinal crack defects on the surface of the steel product comprises five knowledge graph ontology models and interrelations. The specific ontology model is as follows:
quality defect model: refers to the quality defect event which can occur in the steel product, such as the defect of 'surface longitudinal crack'. The quality defect ontology model comprises two attributes of a defect name and a process to which the defect name belongs. The out-of-relationship "produce" points to the failed product model, with the relationship being weighted. Certain quality defects can cause product failure of steel products in the product using process, and the weight is the influence degree of the product defects on the product failure.
Quality event model: refers to the process events in the steel product processing process. The quality event ontology model comprises two attributes of a quality event name and a process to which the quality event belongs. The relation 'result' points to a quality defect model, the relation is accompanied by a weight, a certain quality event in the process of processing the steel product can cause the appearance of a certain quality defect, and the weight refers to the influence degree on the quality defect; the relation "conduct" points to the relation, the relation is accompanied by a weight, each process is composed of a plurality of quality events, the quality events in different processes have mutual influence, and the weight refers to the influence degree between different quality events.
An abnormal event model: refers to the abnormal situation that may occur in a certain quality event in the process of processing steel products. The abnormal event model comprises four attributes of the name, the occurrence position, the equipment and the process of the abnormal event, and the relation of 'belonging' to the pointing quality event model.
Parameter model: the method refers to an influence parameter for judging whether an abnormal event occurs in the process of processing the steel product. The judgment rule model comprises two attributes of parameter names and metadata, and the output relation points to the abnormal event. Metadata attributes record information such as the location of the parameter in the database table and the access method or interface. There are cases where a plurality of parameters jointly determine the occurrence of an abnormal event.
Judging a rule model: refers to the decision rule of the corresponding parameter. The judgment rule model comprises two attributes of rule description and rule ID, and the relationship points to the parameter model. The rule ID is the serial number of a rule in the rule base.
Drawings
FIG. 1 is a body model diagram of a knowledge map for tracing analysis of quality defects of longitudinal cracks on the surface of a steel product.
FIG. 2 is a knowledge graph entity node and relationship graph constructed based on a knowledge graph ontology model.
Detailed Description
The technical solution of the present invention will be described in more detail below with reference to the accompanying drawings:
the method of the invention is based on a knowledge graph. A knowledge graph is essentially a semantic network in which nodes represent entities or concepts and edges represent various semantic relationships between entities/concepts. Each model in the knowledge graph ontology is a concept in an abstract meaning, and entity nodes corresponding to the ontology models are the appearance of the ontology concept in reality.
The method adopts a top-down mode to construct the source-tracing analysis knowledge graph of the longitudinal crack defects on the surface of the steel product, so that the ontology model of the knowledge graph and the relation between the models need to be designed and defined. And summarizing cross-process causes and related quality events of the surface longitudinal crack defects of the steel products by using experts in the related field, and establishing an ontology and defining a relation between the ontologies in a manual modeling mode.
The traceability knowledge map body of the longitudinal crack defects on the surface of the steel product comprises a quality defect model, a quality event model, an abnormal event model, a parameter model, a judgment rule model, a failure product model, a solution model and relations among the models. The model specific information has been detailed in the summary of the invention.
And after the knowledge map ontology model is designed, constructing a cross-process steel product surface longitudinal crack defect traceability knowledge map based on the ontology model and in combination with a data source in a steel enterprise production database. As shown in fig. 2.
The following describes embodiments by way of a specific example:
the quality defect model refers to a quality defect event which can occur in a steel product, and a corresponding entity node can be established (a: quality defect { defect name: "surface longitudinal crack", belonging to the procedure: "continuous casting");
in the production of steel products, the steel products undergo a series of processing steps and steps. The quality event model refers to process events that are passed through during the process. The corresponding quality event entity node (b: { quality event name: "crystallizer liquid level does not meet", belonging process: "converter") can be established, and meanwhile, according to the knowledge graph body model, the relationship of (b) - > (a) exists, and the influence degree relationship weight is 0.6. Because different process steps exist in the same process and the represented quality events also have mutual influence, the method can establish a quality event entity node (c: { quality event name: 'single casting blank pulling speed fluctuation', belonging to the process: 'continuous casting'), and has (c) - > (a) according to the body model relation, and the relation weight is 0.4; meanwhile, according to the actual production link sequence of the steel product, the relation weight is 0.4, wherein the relation is (c) - > (b).
In the process of processing steel products, abnormal conditions may occur in a certain quality event. Therefore, an abnormal event entity node (d: an abnormal event { the name of the abnormal event: '0 < the pulling speed fluctuation < 0.1 m/min', 'all casting blanks produced by the furnace', the equipment, the continuous casting machine and the process are established), and according to the body model relationship, the relationship (d) - > (c) exists, and the influence weight is 0.2.
The influencing parameters of whether the abnormal event occurs are the actual pulling speed maximum value and the pulling speed minimum value, so that the parameters (e: parameter name:
Figure RE-GDA0003212099910000061
metadata { continuous casting machine monitoring sensor database } } according to the ontology model relationship, the existence (e) ->(d)。
The rule decision model refers to a decision rule of parameters corresponding to the occurrence of an abnormal event, so that for parameters related to the entity node (e), a corresponding rule is used for deciding the entity node (f: decision rule { rule description: "during continuous casting, for a single casting blank, pulling fluctuation of a continuous casting machine is between 0.1m/min and 0.25m/min,
Figure RE-GDA0003212099910000062
rule id: 88}) in combination with (f) ->(e)。
All data related to the entity nodes are derived from the actual situation of the iron and steel enterprises in the actual production and processing process, and the data source is mainly semi-structured data. And establishing the steel enterprise data into a CSV format semi-structured data table based on the knowledge graph ontology model and the relation rule. And compiling scripts to extract knowledge, selectively extracting fields in the CSV table into attributes and access relations of entity nodes, and performing knowledge mapping on the entity attributes after information extraction and the defined body attributes to complete the construction of the iron product surface longitudinal crack defect traceability knowledge map. Wherein, the number of the quality defect entity nodes is 1, the number of the quality event entity nodes is 59, the number of the abnormal event entity nodes is 119, the number of the parameter entity nodes is 60, and the number of the judgment rule instances is 93.
And establishing an abstract relation between a Cypher graph database query language and actual use requirements for the constructed tracing knowledge graph of the surface longitudinal crack defects of the steel product.
And (3) carrying out product traceability analysis on the product with the surface longitudinal crack defect by means of a knowledge graph:
firstly, the billet number of the steel product with the surface longitudinal crack defect is obtained, so that the processing steps of the billet number product and the production parameters in the corresponding processing equipment monitoring sensor are known.
Taking the steel product with the product blank number of "200900011" as an example, the converter process number of "20092301" and the production process parameters of the product are obtained. And then, performing attribute filtering in the knowledge graph, and filtering out quality events belonging to the converter process, abnormal events belonging to the converter process and related parameters. This resulted in all the causative paths of surface longitudinal crack defects associated with the "200900011" billet product. And finally, analyzing, and matching the production process parameters of the '20092301' furnace number with the production rules to which the parameter entity nodes belong. If the determination rule is not satisfied, it means that the corresponding production process parameter is abnormal in the production process, and finally the surface longitudinal crack defect is caused to appear. And deducing a real cause causing the defect, and outputting a cause path pointing to the surface longitudinal crack defect entity node from the entity node of the judgment rule so as to provide support for quality decision.

Claims (2)

1. A method for analyzing the traceability of surface longitudinal crack defects of steel products based on a knowledge graph is characterized by comprising the following steps:
(1) constructing a source tracing knowledge map body of the surface longitudinal crack defects of the steel product based on expert experience knowledge;
(2) based on the ontology and the actual production condition, constructing an entity example and a relation example to form a traceability knowledge map of the surface longitudinal crack defects of the steel product: the example corresponding to the model in the knowledge graph body is a specific event which can occur in the process of processing and producing the steel product. For example: the entity corresponding to the quality event model is the working steps of the steel product in the production process, and comprises converter slag tapping, converter supplementary blowing and LF argon static blowing time in an LF refining process which are not consistent; the entity corresponding to the abnormal event model is an abnormal condition which may occur to the quality event entity in each process step, and comprises 'the excessive reduction of the tapping temperature of the converter' and 'the 2 times of additional blowing of the converter' which may occur to the converter process; building entities, wherein each entity corresponds to a certain ontology model, and then building specific relations among the entities for all the entities according to the relations among the ontology models;
(3) according to the established knowledge graph entity network, the possible cause path of the surface longitudinal crack quality defect of the steel product is searched: inputting quality defects of the steel product, such as surface longitudinal cracks, acquiring all entity nodes and relations pointing to the surface longitudinal crack nodes to form a map network taking the surface longitudinal crack nodes as a center; then inputting screening conditions according to actual conditions, performing attribute filtration on entity types and relationship types appearing in the network, and acquiring a cause path possibly causing surface longitudinal crack defects; inputting the blank number of the product steel product with the surface longitudinal crack defect, and obtaining a processing procedure for processing the blank number steel, thereby screening all cause paths which can cause the surface longitudinal crack in the processing procedure of the blank number steel product.
(4) And analyzing by combining actual production data and events based on the searched possible paths, and reasoning out the real cause of the quality defect: according to the blank number of the steel product with the quality defect, on one hand, all processing procedures of the blank number product and abnormal events possibly occurring in the processing procedures are obtained, and then a production process parameter model and a judgment rule which can cause the abnormal events are obtained; on the other hand, the actual production parameters of the steel product are obtained from the production process database of the enterprise and are matched with the judgment rule, so that a path of the quality defect caused by the unmatched production rule is obtained; selecting surface stringers in quality defectsCracks are obtained through systematic retrieval, and in the production process of the product, in the working procedure processing link of the converter, the temperature drop in the tapping process of the converter is overlarge, and T isEnd point temperature-TTemperature of baleThe temperature is 73 ℃ and is 65 ℃ higher than the critical value of the judging rule end point, so that the surface longitudinal crack defect occurs; output after analysis (decision rule { rule description: "at tapping of converter, TEnd point temperature-TTemperature of bale≥ 65 ℃ ", rule id: 10}) ->(parameter: [ "T [) parameterEnd point temperature”,”TTemperature of bale”]Metadata { converter monitoring sensor database } }) ->(abnormal event name: converter tapping temperature drop is too large; occurrence position: all casting blanks produced by the converter, belonging to equipment: converter equipment name; belonging to procedure: converter)>(quality event name: converter tapping temperature drop, belonging to the process: converter->(quality defect) (defect name: "surface longitudinal crack", belonging to the process: "continuous casting") the cause path;
generating a cross-process cause key path for the longitudinal crack defects on the surface of the steel product through attribute filtering, and outputting a specific quality event chain; meanwhile, a steel product quality defect traceability key path flow chart is established based on experience probability and data drive, the cause probability of each possible traceability path is quantitatively analyzed, and support is provided for quality decision.
2. The method for analyzing the traceability of the surface longitudinal crack defects of the steel product based on the knowledge graph according to claim 1,
the traceability analysis knowledge graph of the longitudinal crack defects on the surface of the steel product comprises five knowledge graph ontology models and interrelations. The specific ontology model is as follows:
quality defect model: the method comprises the following steps that quality defect events which can occur in steel products are referred to, surface longitudinal cracks are referred to, a quality defect body model comprises two attributes of a defect name and a process which the quality defect body model belongs to, a relation of generation points to a failure product model, and a weight is attached to the relation; certain quality defects can cause product failure of steel products in the product using process, and the weight is the influence degree of the product defects on the product failure;
quality event model: refers to the process events in the steel product processing process. The quality event ontology model comprises two attributes of a quality event name and a process to which the quality event name belongs; the relation 'result' points to a quality defect model, the relation is accompanied by a weight, a certain quality event in the process of processing the steel product can cause the appearance of a certain quality defect, and the weight refers to the influence degree on the quality defect; the relation "conduction" points to the relation, the relation is accompanied by a weight, each process consists of a plurality of quality events, the quality events in different processes have mutual influence, and the weight refers to the influence degree among different quality events;
an abnormal event model: the method refers to abnormal conditions which may occur in a certain quality event in the process of processing the steel products; the abnormal event model comprises four attributes of the name, the occurrence position, the equipment and the process of the abnormal event, and the relation of belonging to the pointing quality event model is shown;
parameter model: the method comprises the steps of judging whether an abnormal event occurs in the process of processing the steel product or not according to an influence parameter, judging whether a rule model comprises two attributes of a parameter name and metadata, and enabling a relation to point to the abnormal event; metadata attributes record information such as the location of the parameter in the database table and the access method or interface. The situation that a plurality of parameters jointly determine the generation of an abnormal event exists;
judging a rule model: and the judgment rule model comprises two attributes of rule description and rule ID, the relationship points to the parameter model, and the rule ID is the serial number of a rule in the rule base.
CN202110584742.3A 2021-05-27 2021-05-27 Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph Pending CN113420157A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110584742.3A CN113420157A (en) 2021-05-27 2021-05-27 Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110584742.3A CN113420157A (en) 2021-05-27 2021-05-27 Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph

Publications (1)

Publication Number Publication Date
CN113420157A true CN113420157A (en) 2021-09-21

Family

ID=77713137

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110584742.3A Pending CN113420157A (en) 2021-05-27 2021-05-27 Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph

Country Status (1)

Country Link
CN (1) CN113420157A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114324368A (en) * 2022-03-10 2022-04-12 广东祥利科技有限公司 Modified plastic production detection method and system based on mechanical vision detection
CN114881474A (en) * 2022-05-09 2022-08-09 山东大学 Tire full life cycle quality tracing method and system based on knowledge graph
CN114943415A (en) * 2022-04-15 2022-08-26 上海波士内智能科技有限公司 Metal welding defect root cause analysis method based on knowledge graph
CN114969364A (en) * 2022-05-23 2022-08-30 冶金自动化研究设计院有限公司 Knowledge graph construction method of enterprise production material tracking system
CN115062918A (en) * 2022-05-23 2022-09-16 冶金自动化研究设计院有限公司 Slab quality tracing method based on rule engine and event reporting
CN115345434A (en) * 2022-07-15 2022-11-15 华院计算技术(上海)股份有限公司 Improved dynamic data mining method and device for continuous casting quality judgment model
CN116523039A (en) * 2023-04-26 2023-08-01 华院计算技术(上海)股份有限公司 Continuous casting knowledge graph generation method and device, storage medium and terminal

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114324368A (en) * 2022-03-10 2022-04-12 广东祥利科技有限公司 Modified plastic production detection method and system based on mechanical vision detection
CN114324368B (en) * 2022-03-10 2022-07-29 广东祥利科技有限公司 Modified plastic production detection method and system based on mechanical vision detection
CN114943415A (en) * 2022-04-15 2022-08-26 上海波士内智能科技有限公司 Metal welding defect root cause analysis method based on knowledge graph
CN114881474A (en) * 2022-05-09 2022-08-09 山东大学 Tire full life cycle quality tracing method and system based on knowledge graph
CN114969364A (en) * 2022-05-23 2022-08-30 冶金自动化研究设计院有限公司 Knowledge graph construction method of enterprise production material tracking system
CN115062918A (en) * 2022-05-23 2022-09-16 冶金自动化研究设计院有限公司 Slab quality tracing method based on rule engine and event reporting
CN114969364B (en) * 2022-05-23 2024-05-31 冶金自动化研究设计院有限公司 Knowledge graph construction method for enterprise production material tracking system
CN115345434A (en) * 2022-07-15 2022-11-15 华院计算技术(上海)股份有限公司 Improved dynamic data mining method and device for continuous casting quality judgment model
CN116523039A (en) * 2023-04-26 2023-08-01 华院计算技术(上海)股份有限公司 Continuous casting knowledge graph generation method and device, storage medium and terminal
CN116523039B (en) * 2023-04-26 2024-02-09 华院计算技术(上海)股份有限公司 Continuous casting knowledge graph generation method and device, storage medium and terminal

Similar Documents

Publication Publication Date Title
CN113420157A (en) Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph
Ghosh et al. Data mining driven DMAIC framework for improving foundry quality–a case study
CN112612902A (en) Knowledge graph construction method and device for power grid main device
CN105160038B (en) Data analysis method and system based on audit database
US11380087B2 (en) Data analyzing device
CN111209472B (en) Railway accident fault association and accident fault cause analysis method and system
CN103226743B (en) Aircraft equipment technology maturity based on TRL assesses information processing method
JP2018156346A5 (en)
US20210004721A1 (en) Inspection system, discrimination system, and learning data generation device
CN114626673A (en) Continuous casting billet quality forecasting method based on Bayesian network
JP6244274B2 (en) Correlation rule analysis apparatus and correlation rule analysis method
CN117316409A (en) Hospital information management method and system based on big data
CN106056300A (en) Crisscrossed mixed resource allocation rule mining method
CN113837554B (en) Multi-mode key information matching-based food safety risk identification method and system
CN115878599A (en) Sewage industry data cleaning method
US20230376795A1 (en) Device, computing platform and method of analyzing log files of an industrial plant
CN112035905B (en) Self-learning three-dimensional modeling method and system
Sullivan et al. A systematic literature review of changeability in engineering systems along the life cycle
Bertrand et al. A novel multi-perspective trace clustering technique for IoT-enhanced processes: a case study in smart manufacturing
US20200257926A1 (en) Data Analyzing Device
Ambrósio et al. WIP: Prov-SE-O: A provenance ontology to support scientists in scientific experimentation process
Okoye et al. Semantic process mining towards discovery and enhancement of learning model analysis
KR102331047B1 (en) Method and System for creating and managing the relation based document
JP7349383B2 (en) Characteristic analysis system and method
CN117009586A (en) Continuous casting billet quality tracing method based on decision tree and knowledge graph

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