CN115062918A - Slab quality tracing method based on rule engine and event reporting - Google Patents
Slab quality tracing method based on rule engine and event reporting Download PDFInfo
- Publication number
- CN115062918A CN115062918A CN202210564093.5A CN202210564093A CN115062918A CN 115062918 A CN115062918 A CN 115062918A CN 202210564093 A CN202210564093 A CN 202210564093A CN 115062918 A CN115062918 A CN 115062918A
- Authority
- CN
- China
- Prior art keywords
- event
- quality
- rule
- events
- production
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004519 manufacturing process Methods 0.000 claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000012423 maintenance Methods 0.000 claims abstract description 10
- 239000002893 slag Substances 0.000 claims description 14
- 230000007547 defect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000009749 continuous casting Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims description 2
- 239000010959 steel Substances 0.000 claims description 2
- 238000007664 blowing Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000007654 immersion Methods 0.000 description 4
- 238000007599 discharging Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Primary Health Care (AREA)
- General Factory Administration (AREA)
Abstract
A slab quality tracing method based on a rule engine and event reporting belongs to the technical field of slab quality tracing. Firstly, a knowledge map is built according to experience knowledge and an event in production, then a rule is built according to abnormal production parameters, the quality problem, the furnace number and the blank number are input after data are obtained, a rule engine can match parameters violating the rule, the event is issued to maintenance personnel for processing, and after the event is reported, the map and an event chain can be updated to obtain the reason causing the quality problem. Has the advantages that: and the rule engine and the event report are cooperated to realize the tracing of the slab quality, so that the tracing efficiency is improved. And calculating the probability of the event chain by using the frequency, and providing a certain reference value for decision making.
Description
Technical Field
The invention belongs to the technical field of slab quality tracing, particularly provides a slab quality tracing method based on a rule engine and event reporting, and mainly provides a method for tracing the slab quality by combining a knowledge graph, the rule engine and the event reporting.
Background
In the production process of the slab, parameter abnormity and event abnormity can cause certain influence on the quality of the slab. In the prior plate blank quality tracing, when a certain batch of plate blanks have problems, special technical personnel are required to analyze according to production data in a production flow, the problems of cross-process analysis and data redundancy exist at the moment, and the efficiency and the accuracy of quality tracing can be greatly reduced. How to realize the tracing of slab quality faces a great challenge.
Disclosure of Invention
The invention aims to provide a slab quality tracing method based on a rule engine and event reporting, and solves the problems of cross-process analysis, data redundancy and the like. The knowledge graph, the rule engine and the event report are combined to realize the tracing function, and the probability of the event chain is provided for providing a reference decision, so that the utilization rate of experience knowledge can be effectively improved, the quality tracing efficiency is improved, and the quality tracing is more comprehensive and accurate.
The invention comprises the following steps:
step one, establishing a knowledge graph
Firstly, an ontology and a relation are abstracted according to events in slab production, and the ontology is regular, abnormal events, quality events and quality defects. The rules determine the abnormal events, which are one of the quality events that have a conductive relationship with each other and that cause the quality defect. And then, an ontology example and a relation example of the knowledge graph are constructed by combining the production conditions of the ontology and the slab. Each instance of the body is an event in production, and the entities of quality defects, such as surface longitudinal cracks, surface slag inclusions, etc. The entities of quality events are submerged nozzle damage, low pull rates, etc. And constructing corresponding entities, wherein each entity has a corresponding ontology model, and then establishing specific relations for the entities according to the relations among the ontologies. The weight of the relation is expressed by frequency, and the calculation formula of the frequency is
n AB Representing the number of times event A causes event B to occur, n B Indicating the number of occurrences of event B.
Step two, establishing rules and acquiring data
In order to realize dynamic configuration of a rule engine, the invention establishes a process table and a process parameter table, wherein the process table comprises a process number, a process name and a process attribute, the process attribute table comprises the process name, the process parameter name and the parameter attribute, and the added rule is as follows: rule names, rule processes, process parameters of rules, rule descriptions, and rules result in results. The process parameters in the rule description must be consistent with the names of the selected parameters, and the rule description can use +, -,' and/four operators and the logical operators <, >, <, &, |. The configured rules are stored in MySQL. And establishing different data information tables for different processes to store data in production, wherein the data information tables comprise furnace numbers, blank numbers and process parameter names in the process parameter tables. The data acquisition is to fill in the specific data of the process in the production according to the process data information table. For example, the converter work order table contains the furnace number, the process parameters of converter blowing-in times, the weight of the returning water and the like, and the continuous casting work order table contains the furnace number, the billet number, the process parameters of the drawing speed, the temperature of the tundish molten steel and the like.
Three-step tracing of slab quality problems
When the quality tracing is carried out, the quality problem, the furnace number and the slab number of the slab are input, corresponding Cypher sentences are generated, a knowledge graph is searched, and all possible paths are found out. If the production parameters of the furnace number or the blank number on the path meet certain rules, the path is reserved, and if the production parameters do not meet the rules, the path is deleted. Meanwhile, the records of the query, the triggered rules and the abnormal production data are stored in MySQL, and the abnormal data caused by the non-rules are issued to maintenance personnel. The event chain causing the quality problem of the slab is shown in the form of a graph and an event chain, which shows the probability of its occurrence. The frequency is used to calculate the probability of the occurrence of a chain of events, assuming that an event is only related to events to which it is directly connected, the calculation formula is as follows:
P(A|C)=P(A|B)×P(B|C)
p (a | C) represents the probability of occurrence of a if C occurs, P (a | B) represents the probability of occurrence of a if B occurs, and P (B | C) represents the probability of occurrence of B if C occurs.
Step four, reporting the event to realize dynamic updating
When a quality problem arises, an event that may cause the quality problem is issued to a serviceman. The maintenance personnel checks and reports the issued events, and if the events do not occur, the event chain causing the quality problem is cancelled; and when the event occurs, the event chain causing the quality problem is reserved, so that the query record is updated, and finally the real path causing the slab quality problem is obtained.
The invention has the advantages that:
1, the rule engine and the event report cooperate to realize the tracing of the slab quality and improve the tracing efficiency.
And 2, calculating the probability of the event chain by using the frequency, and providing a certain reference value for decision making.
Drawings
Fig. 1 is a flow chart of a slab quality tracing method.
FIG. 2 is an example diagram of a knowledge graph constructed from empirical knowledge.
FIG. 3 is a path tracing flow diagram.
Fig. 4 is a probability analysis diagram.
FIG. 5 is an event processing module flow diagram.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the accompanying drawings and specific examples.
The method for tracing the quality of the slabs comprises the following specific steps as shown in fig. 1:
step one, establishing a knowledge graph
Ontology rules, anomaly events, quality events, and quality defects. The rules determine the abnormal events, which are one of the quality events that have a conductive relationship with each other and that cause the quality defect. Constructing a body example and a relation example of a knowledge graph based on a body model, wherein the blockage of an immersion type closing-up side hole belongs to the damage of an immersion type water gap, so that slag is clamped on the surface; the unclean ladle belongs to the problem of slag falling of a ladle, so that slag is included on the surface; when the pulling speed is more than 0.8m/min and less than 1.1m/min, the problem of low pulling speed is solved, slag is included on the surface, and the relationship weight between entities is expressed by frequency. The constructed knowledge graph is shown in FIG. 2.
Step two, establishing rules and acquiring data
In order to realize dynamic configuration of a rule engine, the invention establishes a process table and a process parameter table, wherein the process table comprises a process number, a process name and a process attribute, the process attribute table comprises the process name, the process parameter name and the parameter attribute, and the added rule is as follows: rule names, rule processes, process parameters of rules, rule descriptions, and rules result in results. An example of a rule is that the pull rate is greater than 0.8m/min and less than 1.1m/min, the rule procedure is continuous casting, the rule parameter is pullingSpeed, and the rule is described as pullingSpeed >0.8& & pullingSpeed <1.1, which results in a low pull rate, and the rule is stored in MySQL. And filling specific data of the working procedure in the production according to a working procedure data information table, wherein the furnace number is 16101204, the billet number is 16304664022Z and the specific value of the drawing speed is 0.9.
Step three, tracing to the source of the quality problem of the plate blank
When quality tracing is carried out, the quality problem, the furnace number and the slab number of the slab are input, corresponding Cypher sentences are generated, knowledge maps are searched, and all possible paths are found out. If the production parameters on the path meet certain rules, the path is retained, and if the production parameters do not meet the rules, the path is deleted. Meanwhile, the records of the query, the triggered rules and the abnormal production data are stored in MySQL, and the abnormal data caused by the non-rules are issued to maintenance personnel. The event chain causing the quality problem of the slab is shown in the form of a graph and an event chain, which shows the probability of its occurrence. The path tracing flow chart is shown in fig. 3. FIG. 4 is a probability analysis diagram of a method. When surface slag inclusion occurs on the slab with the slab number of 16304664022Z, the source tracing page inputs the surface slag inclusion, the slab number of 16304664022Z and the furnace number of 16101204, the pulling speed is 0.9m/min at the moment, and the path is reserved if the rule is met. The events of the blockage of the immersed closing-up side hole and the slag falling of the ladle are sent to maintenance personnel, and the probability of surface slag inclusion caused by the blockage of the immersed closing-up side hole can be calculated to be 1.08% by combining the graph 2 and the graph 4.
Step four, reporting the event to realize dynamic updating
When a quality problem arises, an event that may cause the quality problem is issued to a serviceman. The maintenance personnel checks and reports the issued events, and if the events do not occur, the event chain causing the quality problem is cancelled; events occur and the chain of events leading to the quality problem is preserved, so that the query record is updated, and finally a real path causing the slab quality problem is obtained, and the event processing is shown in fig. 5. And (4) the maintenance personnel check whether the events of the blockage of the immersion type closing-in side hole and the slag discharging of the ladle occur or not, and update the event chain in the query record after detecting that the blockage of the immersion type closing-in side hole does not occur and the slag discharging of the ladle occurs. Only low pulling rates will eventually remain, resulting in both surface slag entrapment and ladle unclean surface slag entrapment.
Claims (1)
1. A slab quality tracing method based on a rule engine and event reporting is characterized in that,
step one, establishing a knowledge graph
Abstracting an ontology and a relation according to events in slab production, wherein the ontology has rules, abnormal events, quality events and quality defects; the rule determines an abnormal event, the abnormal event belongs to one of quality events, the quality events have a conduction relation, and the quality events can cause quality defects; then, an ontology example and a relation example of the knowledge graph are constructed by combining the production conditions of the ontology and the slab; each entity example is an event in production, the entity of the quality defect comprises surface longitudinal cracks and surface slag inclusion, the entity of the quality event comprises submerged nozzle damage and low pulling speed, a corresponding entity is constructed, each entity has a corresponding entity model, then a specific relation is established for the entities according to the relation between the entities, the weight of the relation is expressed by frequency, and the calculation formula of the frequency is as follows:
n AB representing the number of times event A caused event B to occur, n B Represents the number of occurrences of event B;
step two, establishing rules and acquiring data
In order to enable the rule engine to realize dynamic configuration, a process table and a process parameter table are established, the process table comprises process numbers, process names and process attributes, the process attribute table comprises the process names, the process parameter names and the parameter attributes, and the added rule is as follows: rule name, rule procedure, procedure parameters of the rule, rule description and rule leading result; the process parameters in the rule description are required to be consistent with the names of the selected parameters, and the rule description uses +, -,' operators and <, >, <, &, | logical operators; the configured rule can be stored in MySQL; establishing different data information tables for different processes to store data in production, wherein the data information tables comprise furnace numbers, blank numbers and process parameter names in a process parameter table, and the data acquisition is to fill specific data of the processes in the production according to the process data information table, wherein the specific data comprise the furnace numbers, the process parameters of converter blowing times and the weight of returning water in the converter process table, the furnace numbers and the blank numbers in the continuous casting process table, the process parameters of pulling speed and the temperature of tundish molten steel;
three-step tracing of slab quality problems
When quality tracing is carried out, the quality problem, the furnace number and the blank number of the plate blank are input, corresponding Cypher sentences are generated, a knowledge graph is searched, and all possible paths are found out; when the production parameters of the furnace number or the blank number on the path meet certain rules, the path is reserved, and when the production parameters do not meet the rules, the path is deleted; meanwhile, the records of the query, the triggered rules and the abnormal production data are stored in MySQL, and the abnormal data caused by the non-rules are issued to maintenance personnel; event chains causing quality problems of slabs are displayed in the form of graphs and event chains, and the event chains can display the occurrence probability of the event chains; the frequency is used to calculate the probability of the occurrence of a chain of events, assuming that an event is only related to events to which it is directly connected, the calculation formula is as follows:
P(A|C)=P(A|B)×P(B|C)
p (A | C) represents the probability of occurrence of A if C occurs, P (A | B) represents the probability of occurrence of A if B occurs, and P (B | C) represents the probability of occurrence of B if C occurs;
step four, reporting the event to realize dynamic updating
When the quality problem occurs, events which possibly cause the quality problem are issued to maintenance personnel; the maintenance personnel checks and reports the issued events, and if the events do not occur, the event chain causing the quality problem is cancelled; and when the event occurs, the event chain causing the quality problem is reserved, so that the query record is updated, and finally the real path causing the slab quality problem is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210564093.5A CN115062918A (en) | 2022-05-23 | 2022-05-23 | Slab quality tracing method based on rule engine and event reporting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210564093.5A CN115062918A (en) | 2022-05-23 | 2022-05-23 | Slab quality tracing method based on rule engine and event reporting |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115062918A true CN115062918A (en) | 2022-09-16 |
Family
ID=83198469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210564093.5A Pending CN115062918A (en) | 2022-05-23 | 2022-05-23 | Slab quality tracing method based on rule engine and event reporting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115062918A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115577120A (en) * | 2022-10-09 | 2023-01-06 | 华院计算技术(上海)股份有限公司 | Digital human interaction method and device for continuous casting production and computing equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100280977A1 (en) * | 2009-04-30 | 2010-11-04 | Exprentis, Inc. | System, Program, and Method for Representation, Utilization, and Maintenance of Regulatory Knowledge |
WO2021057202A1 (en) * | 2019-09-25 | 2021-04-01 | 北京国双科技有限公司 | Method and apparatus for processing judgement result |
CN113420157A (en) * | 2021-05-27 | 2021-09-21 | 冶金自动化研究设计院 | Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph |
CN113487211A (en) * | 2021-07-20 | 2021-10-08 | 华东理工大学 | Nuclear power equipment quality tracing method and system, computer equipment and medium |
-
2022
- 2022-05-23 CN CN202210564093.5A patent/CN115062918A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100280977A1 (en) * | 2009-04-30 | 2010-11-04 | Exprentis, Inc. | System, Program, and Method for Representation, Utilization, and Maintenance of Regulatory Knowledge |
WO2021057202A1 (en) * | 2019-09-25 | 2021-04-01 | 北京国双科技有限公司 | Method and apparatus for processing judgement result |
CN113420157A (en) * | 2021-05-27 | 2021-09-21 | 冶金自动化研究设计院 | Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph |
CN113487211A (en) * | 2021-07-20 | 2021-10-08 | 华东理工大学 | Nuclear power equipment quality tracing method and system, computer equipment and medium |
Non-Patent Citations (1)
Title |
---|
马刚;李楠;郭叶鹏;: "基于企业质量问题知识图谱的构建及应用", 仪器仪表用户, no. 06, 7 June 2020 (2020-06-07) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115577120A (en) * | 2022-10-09 | 2023-01-06 | 华院计算技术(上海)股份有限公司 | Digital human interaction method and device for continuous casting production and computing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115062918A (en) | Slab quality tracing method based on rule engine and event reporting | |
CN113420157A (en) | Steel product surface longitudinal crack defect traceability analysis method based on knowledge graph | |
Sithole et al. | Process knowledge for improving quality in sand casting foundries: A literature review | |
CN111091546B (en) | Railway wagon coupler tail frame breaking fault identification method | |
CN110991916A (en) | Casting blank quality judgment system and method | |
CN114985697B (en) | Crystallizer liquid level fluctuation monitoring method and system | |
JP2018156346A5 (en) | ||
Zhou et al. | Application of time series data anomaly detection based on deep learning in continuous casting process | |
CN113947333A (en) | Wisdom subway red line protection management system based on multisource information fusion technique | |
Feng et al. | Endpoint temperature prediction of molten steel in RH using improved case-based reasoning | |
CN115106499A (en) | Crystallizer liquid level abnormal fluctuation distinguishing method and system | |
CN116319858A (en) | Intelligent ship Internet of things data operation and maintenance monitoring method and system | |
CN113634728A (en) | Real-time determination method and display method for mixing rate of continuous casting actual mixed casting fixed-length casting blank | |
CN114626673A (en) | Continuous casting billet quality forecasting method based on Bayesian network | |
Ansari et al. | An Intelligent Logic-Based Mold Breakout Prediction System Algorithm for the Continuous Casting Process of Steel: A Novel Study | |
CN117132064A (en) | Liquid crystal display produces line operation management system based on thing networking | |
CN114757277A (en) | Rail transit signal system alarm method, device, electronic equipment and storage medium | |
CN115941746A (en) | AI-based intelligent early warning system for high-risk area of oil and gas pipeline | |
CN114969364B (en) | Knowledge graph construction method for enterprise production material tracking system | |
CN113592816A (en) | Machine vision-based online steel ladle cleanliness rating method | |
Androsenko et al. | Determining the quality of continuous casting from billet caster | |
CN116618597A (en) | Continuous casting cutting optimization method and system based on mixed integer programming | |
CN115041653B (en) | Continuous casting performance generation method, device, equipment and computer storage medium | |
CN114781762B (en) | Equipment fault prediction method based on life consumption | |
Camisani-Calzolari, FR*, Craig, IK* & Pistorius | Quality prediction in continuous casting of stainless steel slabs |
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 |