CN116931530A - Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process - Google Patents
Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process Download PDFInfo
- Publication number
- CN116931530A CN116931530A CN202311188448.6A CN202311188448A CN116931530A CN 116931530 A CN116931530 A CN 116931530A CN 202311188448 A CN202311188448 A CN 202311188448A CN 116931530 A CN116931530 A CN 116931530A
- Authority
- CN
- China
- Prior art keywords
- production
- data
- quality
- production process
- steel rolling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 261
- 238000005096 rolling process Methods 0.000 title claims abstract description 90
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 79
- 239000010959 steel Substances 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000008859 change Effects 0.000 claims abstract description 68
- 238000009628 steelmaking Methods 0.000 claims abstract description 45
- 238000011958 production data acquisition Methods 0.000 claims abstract description 23
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 22
- 229910052742 iron Inorganic materials 0.000 claims abstract description 11
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 33
- 238000012216 screening Methods 0.000 claims description 23
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 238000013079 data visualisation Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- 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)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of production prediction, in particular to a dynamic prediction system and a dynamic prediction method for an ironmaking, steelmaking and steel rolling production process. The system comprises a production data acquisition unit, a production quality change trend acquisition unit, a performance change trend acquisition unit, a prediction result output unit and a prediction result selection unit; the production data acquisition unit is used for acquiring production data of iron making, steel making and steel rolling, extracting data of each production process and steel rolling quality data from the production data and establishing a production process database; the sensor equipment and the Internet of things connection module are installed on the production equipment, so that real-time acquisition and transmission of key parameters are realized, the real-time performance and the data accuracy of the production process are improved, the production quality change trend and the performance change trend are integrated, and then a prediction model of the production process is established, so that dynamic prediction and optimization of the production quality and the equipment performance are realized.
Description
Technical Field
The invention relates to the technical field of production prediction, in particular to a dynamic prediction system and a dynamic prediction method for an ironmaking, steelmaking and steel rolling production process.
Background
In the process of producing iron-steel-making steel-rolling, iron and steel are melted by adopting high temperature, when the production of the iron-steel-making steel-rolling is predicted by the temperature and the pressure in production equipment, but in the production process, after the equipment is used for a long time, the quality of steel rolling produced by the same production process parameter is gradually reduced by the temperature and the pressure in the production equipment in a high-temperature state, and the quality of the steel-making steel-rolling is predicted by only collecting the temperature and the pressure in the production equipment, so that the quality of the steel-rolling produced by the same production process parameter is not reduced, and the predicted result is deviated and the quality of enterprises cannot be adjusted in time.
Disclosure of Invention
The invention aims to provide a dynamic prediction system and a dynamic prediction method for an ironmaking, steelmaking and steel rolling production process, so as to solve the problems in the background technology.
In order to solve the technical problems, one of the purposes of the invention is to provide a dynamic prediction system for an iron-making steel-rolling production process, which comprises a production data acquisition unit, a production quality variation trend acquisition unit, a performance variation trend acquisition unit, a prediction result output unit and a prediction result selection unit;
the production data acquisition unit is used for acquiring production data of iron making, steel making and steel rolling, extracting data of each production process and steel rolling quality data from the production data and establishing a production process database;
the production quality change trend acquisition unit is used for screening the same parameters in the production process database established by the production data acquisition unit, acquiring production process data with the same process parameters and the maximum in the production process database, extracting steel rolling quality data corresponding to the maximum production process data, carrying out production quality analysis, and acquiring the change trend of the production quality;
the performance change trend acquisition unit is used for recording state data of the iron-making steel-rolling production equipment, screening out the same steel rolling quality data from a production process database established by the production data acquisition unit, extracting production process data corresponding to the same steel rolling quality data, and carrying out production performance analysis to acquire the performance change trend of the production equipment;
the prediction result output unit is used for establishing a dynamic prediction model according to the production quality change trend and the performance change trend acquired by the production quality change trend acquisition unit, acquiring the performance change trend of the production equipment, inputting the real-time recorded production data into the dynamic prediction model, and then respectively outputting two prediction results by the dynamic prediction model according to the two change trends;
and the prediction result selection unit is used for carrying out difference comparison on the two prediction results output by the prediction result output unit, if the comparison result shows that the prediction quality of the two prediction results is different, continuously monitoring the real-time production data, carrying out similarity matching on the production data and the two prediction results respectively, and displaying the prediction results with high similarity to a user as the finally selected prediction results.
As a further improvement of the technical scheme, the production data acquisition unit monitors various parameters in the production process in real time as production data by installing a temperature sensor, a pressure sensor, a flow sensor, a vibration sensor and the like in the iron-making steel-rolling production process.
As a further improvement of the technical scheme, the production data acquisition unit comprises a database establishment module;
the database building module is used for dividing the acquired life data according to three production steps of iron making, steel making and steel rolling, acquiring steel rolling quality data corresponding to each production data, and combining the divided production data with the steel rolling quality data to build a production process database.
As a further improvement of the technical scheme, the production quality variation trend acquisition unit comprises a same parameter screening module and a production quality analysis module;
the same parameter screening module is used for carrying out same parameter screening in the production process database established by the database establishing module, obtaining the production process data with the largest occurrence of the same parameters in the production process database, extracting steel rolling quality data corresponding to the maximum production process data and arranging according to the time period sequence;
the quality analysis module is used for carrying out production quality analysis on the steel rolling quality data arranged by the same parameter screening module, and obtaining the change trend of the production quality.
As a further improvement of the technical scheme, the performance change trend acquisition unit establishes an information transmission channel by using the Internet of things technology and ironmaking, steelmaking and steel rolling production equipment, and acquires state data of the ironmaking, steelmaking and steel rolling production equipment in real time.
As a further improvement of the present technical solution, the performance variation trend obtaining unit includes a production performance analysis module;
the production performance analysis module is used for screening the same steel rolling quality data in the production process database established by the database establishment module, and carrying out production performance analysis on the production process data respectively corresponding to the same steel rolling quality data to obtain the performance change trend of the production equipment under the condition of not changing parameters.
As a further improvement of the technical scheme, the prediction result output unit integrates the production quality change trend and the performance change trend which are respectively acquired by the quality analysis module and the production performance analysis module, and then a dynamic prediction model is established by a neural learning network method.
As a further improvement of the present technical solution, the prediction result selection unit includes a difference comparison module;
and the difference comparison module is used for comparing the difference between the two predicted results output by the predicted result output unit, if the comparison result shows that the predicted quality of the two predicted results is different, the real-time production data is continuously monitored, the production data is respectively subjected to similarity matching with the two predicted results, the predicted result with high similarity is used as the finally selected predicted result to be displayed to the user, otherwise, if the comparison result shows that the two predicted results are consistent, the predicted result is displayed to the user.
The second object of the present invention is to provide a dynamic prediction method for an ironmaking, steelmaking and steel rolling production process, comprising any one of the dynamic prediction systems for an ironmaking, steelmaking and steel rolling production process, including the following steps:
s1, acquiring production data through a production data acquisition unit to establish a production process database, and analyzing and acquiring the change trend of production quality and the change trend of equipment performance through the production process database by a production quality change trend acquisition unit and a performance change trend acquisition unit;
s2, a prediction result output unit establishes a dynamic prediction model through a production quality change trend acquisition unit and a performance change trend acquisition unit, and predicts the steel rolling production of iron making and steel making in real time.
Compared with the prior art, the invention has the beneficial effects that: the sensor equipment and the Internet of things connection module are installed on the production equipment, so that real-time acquisition and transmission of key parameters are realized, the real-time performance and the data accuracy of the production process are improved, the production quality change trend and the performance change trend are integrated, and then a prediction model of the production process is established, so that dynamic prediction and optimization of the production quality and the equipment performance are realized.
Drawings
Fig. 1 is a schematic diagram of the overall structure of the present invention.
The meaning of each reference sign in the figure is:
10. a production data acquisition unit; 20. a production quality variation trend acquisition unit; 30. a performance change trend acquisition unit; 40. a prediction result output unit; 50. and a prediction result selecting unit.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
as shown in fig. 1, one of the objects of the present invention is to provide a dynamic prediction system for an ironmaking, steelmaking and steel rolling production process, comprising a production data acquisition unit 10, a production quality variation trend acquisition unit 20, a performance variation trend acquisition unit 30, a prediction result output unit 40 and a prediction result selection unit 50;
the production data acquisition unit 10 is used for acquiring production data of ironmaking, steelmaking and steel rolling;
the production data acquisition unit 10 monitors various parameters in the production process in real time as production data by installing a temperature sensor, a pressure sensor, a flow sensor, a vibration sensor, etc. in the iron-making, steel-making and steel-rolling production process. The method comprises the following steps:
determining monitoring parameters: according to the characteristics of the iron-making steel-rolling production process, parameters to be monitored are determined, main influencing factors and key links are identified according to the characteristics of the production process, and the factors determine the product quality, the process efficiency and the energy consumption, for example, furnace temperature, gas flow, material components, temperature, pressure, flow and vibration factors play an important role in the steel-rolling quality;
selecting a sensor device: installing proper sensor equipment at corresponding positions according to the characteristics and requirements of the monitored parameters, and selecting proper sensor types, for example, a thermocouple, a temperature sensor or an infrared thermometer can be selected according to the temperature; the pressure may be selected from a pressure sensor or a pressure transmitter; the flow can select a flow sensor, and meanwhile, the measuring position of parameters needs to be considered, so that the sensor can accurately sense the corresponding physical quantity, for example, for temperature monitoring, the sensor can be arranged in a furnace and at other positions on a pipeline, which need to monitor the temperature, and factors such as temperature, humidity, corrosion resistance, environmental vibration resistance and the like are considered, and the sensor can be ensured to normally operate in the corresponding working environment;
sensor wiring and connection: connecting the sensor equipment with a data acquisition system to ensure that the sensor can normally receive and transmit monitoring data;
and (3) data acquisition: and the parameter values monitored by the sensor equipment are acquired in real time through the data acquisition system and recorded in a time sequence form.
Extracting data of each production process and steel rolling quality data from the production data and establishing a production process database;
the production data acquisition unit 10 comprises a database creation module;
the database building module is used for dividing the acquired life data according to three production steps of iron making, steel making and steel rolling, acquiring steel rolling quality data corresponding to each production data, and combining the divided production data with the steel rolling quality data to build a production process database. The method comprises the following steps:
data segmentation: dividing the obtained production data into corresponding production steps according to three production steps of steelmaking, ironmaking and steel rolling, grouping the data according to the similarity of the characteristics of the three steps of steelmaking, ironmaking and steel rolling, and classifying the data with the characteristics of similar temperature and pressure into steelmaking steps; for data with similar weight, carbon content characteristics, it can be classified as an ironmaking step; for data with similar pressure and speed characteristics, the data can be classified into steel rolling steps;
and (3) quality data association: correlating the segmented production data of each production step with corresponding steel rolling quality data to ensure that each production data has corresponding quality data, aligning the production data with the quality data through a time stamp, and ensuring that the production data and the quality data correspond in time;
data normalization and conversion: the data format conversion tool CSV, JSON, XML is used for converting the data into a target format, and meanwhile, the data of a plurality of data sources are integrated by using a data integration technology to form a unified data set, so that the unified data set has a unified data format and expression mode, and the subsequent database establishment and analysis are facilitated;
database establishment: a production process database is established based on the segmented production data and the associated steel quality data. The data may be stored in appropriate tables and fields using a relational database or a non-relational database;
data indexing and querying functions: an index is built into the production process database to enable quick retrieval and querying of specific production data and quality data. Meanwhile, a query function is added for the database, so that a user can conveniently query related data through various conditions;
data analysis and mining: by analyzing and mining the data of the production process database, the correlation and the dependency relationship between the production steps and the influence of the parameters on the quality are explored through correlation analysis and correlation rule mining technology. The correlation coefficient can be used for finding out the correlation between the production steps, and the Apriori algorithm is utilized for finding out the correlation rule between the parameters, so that valuable information and rules, such as the correlation between the production steps, the influence of the parameters on the quality and the like, are extracted;
visual display: and the data analysis result is displayed to a user in a visual form, such as a chart, a report and the like, so that the user can monitor and analyze the production process conveniently.
The production quality variation trend obtaining unit 20 is configured to perform the same parameter screening in the production process database established by the production data collecting unit 10, obtain the production process data with the largest same process parameter in the production process database, extract the steel rolling quality data corresponding to the largest production process data, and perform production quality analysis to obtain the variation trend of the production quality;
the production quality variation trend obtaining unit 20 includes the same parameter screening module and a production quality analysis module;
the same parameter screening module is used for carrying out same parameter screening in the production process database established by the database establishing module, obtaining the production process data with the largest occurrence of the same parameters in the production process database, extracting the steel rolling quality data corresponding to the maximum production process data and arranging according to the time period sequence; the method comprises the following steps:
data screening: parameter screening is carried out in a production process database, the same parameters to be analyzed are selected, and related production process data are obtained;
counting: counting the screened data, counting the occurrence times of each parameter value, and determining the parameter value with the largest occurrence;
and (3) data extraction: extracting corresponding production process data from a production process database according to the most-occurring parameter values, and acquiring corresponding steel rolling quality data;
data sorting: sequencing the extracted production process data and steel rolling quality data, and arranging according to a time period sequence so as to facilitate subsequent analysis and display;
data presentation: and displaying the sequenced production process data and the corresponding steel rolling quality data in a proper form, such as a table, a chart and the like, so that a user can clearly know the relevant time period and the corresponding quality data.
The quality analysis module is used for carrying out production quality analysis on the steel rolling quality data arranged by the same parameter screening module, and obtaining the change trend of the production quality. The formula is as follows:
;
wherein N represents the number of steel rolling quality data,values representing each rolling quality data point, +.>Mean value of data representing rolling quality,/->A summation symbol is represented for summing the differences for each data point.
The performance change trend acquisition unit 30 is used for recording state data of ironmaking, steelmaking and steel rolling production equipment;
the performance change trend acquiring unit 30 establishes an information transmission channel by using the internet of things technology and the ironmaking, steelmaking and steel rolling production equipment, and acquires state data of the ironmaking, steelmaking and steel rolling production equipment in real time. The method comprises the following steps:
and (3) data acquisition: and connecting the sensor equipment in the ironmaking, steelmaking and steel rolling production equipment to an Internet of things platform by using the Internet of things technology. Through the sensors, state data of the equipment can be acquired in real time;
and (3) data transmission: transmitting the state data acquired by the equipment to a cloud server or a data center through a wireless network by an Internet of things platform, so that the real-time performance and the safety of the data are ensured;
and (3) data processing: processing and analyzing the collected state data in a cloud server or a data center, wherein the processing and analyzing comprise operations such as data cleaning, feature extraction, pattern recognition and the like;
and (3) data storage: the processed and analyzed data is stored in a database for subsequent querying and use. The database table structure is designed according to the logical relationship and storage requirements of the data by using proper table structures and fields, the names, the fields and the field types of the tables are determined, and the relationship among the fields is established. For example, the method can divide parameters of different links in the production process, design a corresponding table structure, define appropriate fields for each table at the same time to store corresponding data, and the fields should be matched with the results of processing and analyzing the original data, including monitoring the values of the parameters, time stamps, process information and the like. If necessary, the field definition may be performed by using a data type, an index, a constraint, or the like, and the state data of each device may be stored in a time-series manner.
Then screening out the same steel rolling quality data from a production process database established by the production data acquisition unit 10, extracting production process data corresponding to the same steel rolling quality data, and carrying out production performance analysis to obtain the performance change trend of production equipment;
the performance variation trend acquisition unit 30 includes a production performance analysis module;
the production performance analysis module is used for screening the same steel rolling quality data in the production process database established by the database establishment module, and carrying out production performance analysis on the production process data respectively corresponding to the same steel rolling quality data to obtain the performance change trend of the production equipment under the condition of not changing parameters. The method comprises the following steps:
calculating performance indexes: calculating production efficiency, energy consumption and quality indexes of the extracted production process data according to the required performance indexes, wherein a ratio formula of yield to time can be used for calculating the production efficiency indexes; for the calculation of the energy consumption index, a ratio formula of energy consumption to yield can be used; for the calculation of the quality index, the quality of the same production process can be directly time-ordered;
and (3) analysis of change trend: according to the time sequence of the extracted production process data, calculating the performance change quantity or change rate between adjacent time points, and checking the change trend of the performance, such as increase, decrease or stability. This may be done by calculating the difference or percentage change.
The prediction result output unit 40 is configured to establish a dynamic prediction model according to the production quality variation trend obtained by the production quality variation trend obtaining unit 20 and the performance variation trend obtained by the performance variation trend obtaining unit 30, then input the real-time recording production data into the dynamic prediction model, and then the dynamic prediction model outputs two prediction results according to the two variation trends respectively; the method comprises the following steps:
data preparation: first, historical production data for modeling is prepared, including production quality data and corresponding production equipment status data. The accuracy and the integrity of data are ensured;
characteristic engineering: and processing the historical production data, and extracting and converting the characteristics. Selecting proper characteristics, such as the change trend of production quality, the change trend of the state of production equipment and other relevant characteristics;
and (3) establishing a model: according to the selected prediction problem, a dynamic prediction model is established by a neural learning network method;
recording production data in real time: inputting production data acquired in real time, including production quality data and production equipment state data, into an established dynamic prediction model;
and (3) outputting a prediction result: according to training and learning of the model, after real-time data is input, the model outputs two prediction results according to the quality change trend and the equipment performance change trend respectively.
The prediction result output unit 40 integrates the production quality variation trend and the performance variation trend respectively acquired by the quality analysis module and the production performance analysis module, and for quality data and performance data with time sequence attributes, the variation of quality and performance with time is known through time sequence analysis, the quality variation trend and the performance variation trend are integrated and displayed through data visualization and report output, the data visualization is performed by means of data visualization tools such as charts, curves, trend graphs and the like, the variation trend of quality and performance and the association situation thereof are intuitively displayed, and then a dynamic prediction model is established through a neural learning network method.
The prediction result selecting unit 50 is configured to compare the two prediction results output by the prediction result output unit 40, if the comparison result shows that the predicted quality of the two prediction results is different, monitor the real-time production data continuously, and match the production data with the two prediction results in similarity, and display the prediction result with high similarity to the user as the final selected prediction result.
The prediction result selection unit 50 includes a difference comparison module;
the difference comparison module is used for comparing the two prediction results output by the prediction result output unit 40, if the comparison result shows that the prediction quality of the two prediction results is different, the real-time production data is continuously monitored, the production data is respectively subjected to similarity matching with the two prediction results, the prediction result with high similarity is used as a final selected prediction result to be displayed to a user, otherwise, if the comparison result shows that the two prediction results are consistent, the prediction result is displayed to the user. The method comprises the following steps:
comparing the predicted result difference: and comparing the two prediction results to judge whether the quality predictions are consistent. Condition judgment can be used for judging whether similarity matching and final result selection are needed;
similarity matching: if the quality of the two predicted results is inconsistent, continuously monitoring the real-time production data, and respectively matching the production data with the similarity of the two predicted results;
similarity calculation: and calculating the similarity between the real-time production data and the predicted result by a proper similarity calculation method. The specific similarity calculation method can be selected according to actual conditions, such as cosine similarity, euclidean distance and the like;
similarity comparison: comparing the real-time production data with the similarity of the two prediction results, and selecting a prediction result with higher similarity;
final prediction result selection: and selecting a final prediction result to be displayed to a user according to the comparison result of the comparison and the similarity. If the two predicted results are consistent, the predicted results are directly displayed to the user; if the two predicted results are inconsistent, the predicted result with higher similarity is selected and displayed to the user.
The second object of the present invention is to provide a dynamic prediction method for an ironmaking, steelmaking and steel rolling production process, comprising any one of the above dynamic prediction systems for ironmaking, steelmaking and steel rolling production processes, including the steps of:
s1, acquiring production data through a production data acquisition unit 10 to establish a production process database, and analyzing and acquiring the production quality change trend and the equipment performance change trend through the production process database by a production quality change trend acquisition unit 20 and a performance change trend acquisition unit 30;
s2, a prediction result output unit 40 establishes a dynamic prediction model through a production quality change trend acquisition unit 20 and a performance change trend acquisition unit 30 to predict the iron-making steel rolling production in real time.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A dynamic prediction system for the production process of steel making and steel rolling in iron making is characterized in that: the device comprises a production data acquisition unit (10), a production quality variation trend acquisition unit (20), a performance variation trend acquisition unit (30), a prediction result output unit (40) and a prediction result selection unit (50);
the production data acquisition unit (10) is used for acquiring production data of iron making, steel making and steel rolling, extracting data of each production process and steel rolling quality data from the production data and establishing a production process database;
the production quality change trend acquisition unit (20) is used for carrying out the same parameter screening in a production process database established by the production data acquisition unit (10) to acquire production process data with the largest same process parameters in the production process database, extracting steel rolling quality data corresponding to the largest production process data, carrying out production quality analysis, and acquiring the change trend of the production quality;
the performance change trend acquisition unit (30) is used for recording state data of steel rolling production equipment for iron making and steel making, screening out the same steel rolling quality data in a production process database established by the production data acquisition unit (10), extracting production process data corresponding to the same steel rolling quality data, and carrying out production performance analysis to acquire the performance change trend of the production equipment;
the prediction result output unit (40) is used for establishing a dynamic prediction model according to the production quality change trend obtained by the production quality change trend obtaining unit (20) and the performance change trend obtained by the performance change trend obtaining unit (30), inputting real-time recording production data into the dynamic prediction model, and then respectively outputting two prediction results according to the two change trends by the dynamic prediction model;
the prediction result selecting unit (50) is used for performing difference comparison on the two prediction results output by the prediction result output unit (40), if the comparison results show that the prediction quality of the two prediction results is different, the real-time production data are continuously monitored, the production data are respectively subjected to similarity matching with the two prediction results, and the prediction results with high similarity are displayed to a user as the finally selected prediction results.
2. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 1, wherein: the production data acquisition unit (10) monitors various parameters in the production process in real time as production data by installing a temperature sensor, a pressure sensor, a flow sensor and a vibration sensor in the production process of iron making, steel making and steel rolling.
3. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 1, wherein: the production data acquisition unit (10) comprises a database establishment module;
the database building module is used for dividing the acquired life data according to three production steps of iron making, steel making and steel rolling, acquiring steel rolling quality data corresponding to each production data, and combining the divided production data with the steel rolling quality data to build a production process database.
4. A dynamic prediction system for ironmaking, steelmaking and steel rolling processes according to claim 3, characterized in that: the production quality change trend acquisition unit (20) comprises a same parameter screening module and a production quality analysis module;
the same parameter screening module is used for carrying out same parameter screening in the production process database established by the database establishing module, obtaining the production process data with the largest occurrence of the same parameters in the production process database, extracting steel rolling quality data corresponding to the maximum production process data and arranging according to the time period sequence;
the quality analysis module is used for carrying out production quality analysis on the steel rolling quality data arranged by the same parameter screening module, and obtaining the change trend of the production quality.
5. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 1, wherein: the performance change trend acquisition unit (30) establishes an information transmission channel by using the Internet of things technology and ironmaking, steelmaking and steel rolling production equipment, and acquires state data of the ironmaking, steelmaking and steel rolling production equipment in real time.
6. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 4, wherein: the performance variation trend acquisition unit (30) comprises a production performance analysis module;
the production performance analysis module is used for screening the same steel rolling quality data in the production process database established by the database establishment module, and carrying out production performance analysis on the production process data respectively corresponding to the same steel rolling quality data to obtain the performance change trend of the production equipment under the condition of not changing parameters.
7. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 6, wherein: the prediction result output unit (40) integrates the production quality change trend and the performance change trend which are respectively acquired by the quality analysis module and the production performance analysis module, and then establishes a dynamic prediction model through a neural learning network method.
8. The dynamic prediction system for ironmaking, steelmaking and steel rolling production process according to claim 1, wherein: the prediction result selection unit (50) comprises a difference comparison module;
the difference comparison module is used for comparing the difference between the two prediction results output by the prediction result output unit (40), if the comparison result shows that the prediction quality of the two prediction results is different, the real-time production data are continuously monitored, the production data are respectively subjected to similarity matching with the two prediction results, the prediction result with high similarity is used as a final selected prediction result to be displayed to a user, otherwise, if the comparison result shows that the two prediction results are consistent, the prediction result is displayed to the user.
9. A method for dynamically predicting the production process of steel making and steel making, comprising the dynamic prediction system for the production process of steel making and steel making, which is characterized in that: the method comprises the following steps:
s1, acquiring production data through a production data acquisition unit (10) to establish a production process database, and analyzing and acquiring the production quality change trend and the equipment performance change trend through the production process database by a production quality change trend acquisition unit (20) and a performance change trend acquisition unit (30);
s2, a prediction result output unit (40) establishes a dynamic prediction model through a production quality change trend acquisition unit (20) and a performance change trend acquisition unit (30) to predict the iron-making steel-rolling production in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311188448.6A CN116931530B (en) | 2023-09-15 | 2023-09-15 | Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311188448.6A CN116931530B (en) | 2023-09-15 | 2023-09-15 | Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116931530A true CN116931530A (en) | 2023-10-24 |
CN116931530B CN116931530B (en) | 2023-12-26 |
Family
ID=88389975
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311188448.6A Active CN116931530B (en) | 2023-09-15 | 2023-09-15 | Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116931530B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117420811A (en) * | 2023-12-19 | 2024-01-19 | 武汉佰思杰科技有限公司 | Production line quality monitoring method and system for automatic production |
CN117930786A (en) * | 2024-03-21 | 2024-04-26 | 山东星科智能科技股份有限公司 | Intelligent digital twin simulation system for steel production process |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN111210071A (en) * | 2020-01-03 | 2020-05-29 | 深圳前海微众银行股份有限公司 | Business object prediction method, device, equipment and readable storage medium |
CN112418522A (en) * | 2020-11-23 | 2021-02-26 | 重庆邮电大学 | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model |
CN113762329A (en) * | 2021-07-06 | 2021-12-07 | 山东钢铁股份有限公司 | Method and system for constructing state prediction model of large rolling mill |
CN114077924A (en) * | 2021-10-27 | 2022-02-22 | 国电南瑞科技股份有限公司 | Wind power prediction gale data enhancement method considering extreme gale weather |
US20220318714A1 (en) * | 2020-03-23 | 2022-10-06 | Dalian University Of Technology | Method for predicting oxygen load in iron and steel enterprises based on production plan |
CN116050678A (en) * | 2023-04-03 | 2023-05-02 | 江苏中科云控智能工业装备有限公司 | Die-casting product processing test system and method based on cloud computing |
CN116109012A (en) * | 2023-04-10 | 2023-05-12 | 张家港广大特材股份有限公司 | Special steel performance prediction method and system based on control parameters of refining furnace |
-
2023
- 2023-09-15 CN CN202311188448.6A patent/CN116931530B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN111210071A (en) * | 2020-01-03 | 2020-05-29 | 深圳前海微众银行股份有限公司 | Business object prediction method, device, equipment and readable storage medium |
US20220318714A1 (en) * | 2020-03-23 | 2022-10-06 | Dalian University Of Technology | Method for predicting oxygen load in iron and steel enterprises based on production plan |
CN112418522A (en) * | 2020-11-23 | 2021-02-26 | 重庆邮电大学 | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model |
CN113762329A (en) * | 2021-07-06 | 2021-12-07 | 山东钢铁股份有限公司 | Method and system for constructing state prediction model of large rolling mill |
CN114077924A (en) * | 2021-10-27 | 2022-02-22 | 国电南瑞科技股份有限公司 | Wind power prediction gale data enhancement method considering extreme gale weather |
CN116050678A (en) * | 2023-04-03 | 2023-05-02 | 江苏中科云控智能工业装备有限公司 | Die-casting product processing test system and method based on cloud computing |
CN116109012A (en) * | 2023-04-10 | 2023-05-12 | 张家港广大特材股份有限公司 | Special steel performance prediction method and system based on control parameters of refining furnace |
Non-Patent Citations (1)
Title |
---|
陈红生;郑忠;陈开;刘春阳;: "基于炉气分析的转炉冶炼过程仿真系统及应用", 冶金自动化, no. 03 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117420811A (en) * | 2023-12-19 | 2024-01-19 | 武汉佰思杰科技有限公司 | Production line quality monitoring method and system for automatic production |
CN117420811B (en) * | 2023-12-19 | 2024-03-08 | 武汉佰思杰科技有限公司 | Production line quality monitoring method and system for automatic production |
CN117930786A (en) * | 2024-03-21 | 2024-04-26 | 山东星科智能科技股份有限公司 | Intelligent digital twin simulation system for steel production process |
CN117930786B (en) * | 2024-03-21 | 2024-06-11 | 山东星科智能科技股份有限公司 | Intelligent digital twin simulation system for steel production process |
Also Published As
Publication number | Publication date |
---|---|
CN116931530B (en) | 2023-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116931530B (en) | Dynamic prediction system and dynamic prediction method for iron-making steel rolling production process | |
CN115276006B (en) | Load prediction method and system for power integration system | |
CN113255795A (en) | Equipment state monitoring method based on multi-index cluster analysis | |
CN111694877B (en) | Multi-element time series data search | |
CN107038505B (en) | Ore finding model prediction method based on machine learning | |
KR20190072652A (en) | Information processing apparatus and information processing method | |
CN115795380A (en) | Flue gas acid making data cleaning and optimizing method based on isolated forest and weighted random forest | |
CN116738866A (en) | Instant learning soft measurement modeling method based on time sequence feature extraction | |
CN117113006A (en) | Data management system and method for digital energy air compression station | |
CN115469585B (en) | Hydropower unit state monitoring method and system based on big data | |
CN116610105A (en) | Rolling mill mechanical operation fault monitoring method and system based on data fusion | |
CN113393169B (en) | Financial industry transaction system performance index analysis method based on big data technology | |
CN115987692A (en) | Safety protection system and method based on flow backtracking analysis | |
CN115935285A (en) | Multi-element time series anomaly detection method and system based on mask map neural network model | |
CN100371938C (en) | Quality design method under minute new aluminium sample | |
CN115438033A (en) | Digital twin operation and maintenance data quality inspection method | |
CN115221796A (en) | Cloud manufacturing mode-oriented process flow simulation method and system | |
CN111210147B (en) | Sintering process operation performance evaluation method and system based on time sequence feature extraction | |
CN114441463A (en) | Full-spectrum water quality data analysis method | |
CN106778848A (en) | A kind of Zn finery method for diagnosing faults based on multiclass Probit models | |
CN113312587A (en) | Sensor acquisition data missing value processing method based on ARIMA prediction and regression prediction | |
CN111210122B (en) | Parameter isolation-based sintering non-optimal operation performance reason tracing method and system | |
CN110956340A (en) | Engineering test detection data management early warning decision method | |
CN118092362B (en) | Method, device and equipment for analyzing abnormal reasons in sintering process | |
CN117574180B (en) | Fuel production and emission system data correlation control management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |