CN117408427A - Novel continuous casting quality judging data analysis system - Google Patents
Novel continuous casting quality judging data analysis system Download PDFInfo
- Publication number
- CN117408427A CN117408427A CN202311442016.3A CN202311442016A CN117408427A CN 117408427 A CN117408427 A CN 117408427A CN 202311442016 A CN202311442016 A CN 202311442016A CN 117408427 A CN117408427 A CN 117408427A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- quality
- analysis
- continuous casting
- 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
- 238000009749 continuous casting Methods 0.000 title claims abstract description 64
- 238000007405 data analysis Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 169
- 230000008569 process Effects 0.000 claims abstract description 160
- 238000004458 analytical method Methods 0.000 claims abstract description 46
- 238000004519 manufacturing process Methods 0.000 claims abstract description 39
- 238000010223 real-time analysis Methods 0.000 claims abstract description 4
- 238000009826 distribution Methods 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000007547 defect Effects 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 238000013473 artificial intelligence Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 238000013386 optimize process Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims 1
- 238000005266 casting Methods 0.000 description 17
- 229910000831 Steel Inorganic materials 0.000 description 12
- 239000010959 steel Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 4
- 239000000047 product Substances 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 239000000498 cooling water Substances 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000004512 die casting Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 description 1
- 239000002826 coolant Substances 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000002436 steel type Substances 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 239000010936 titanium Substances 0.000 description 1
- 229910052719 titanium Inorganic materials 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
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
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a novel data analysis system for continuous casting quality judgment, which comprises a task issuing module, a data analysis module and a data analysis module, wherein the task issuing module is used for acquiring production plan information, generating corresponding plan tasks according to the production plan information and issuing the plan tasks to the system; the rule engine module is used for setting process rules and running a rule engine according to the set process rules; the quality analysis and statistics module is used for carrying out real-time analysis according to the process data obtained in real time to obtain the statistical data of the current quality; the online quality judging module is used for obtaining reasonable optimizing process parameters; according to the reasonable optimizing process parameters, the production line is adjusted; and the off-line data analysis module is used for performing off-line analysis statistics of the process data and updating the setting of the process rules. The novel continuous casting quality judging data analysis system can quickly and real-timely adjust the process parameters, ensure the production quality of the production line, and further update the strategy rules through offline analysis.
Description
Technical Field
The invention relates to a data analysis system, in particular to a system for analyzing product quality in a continuous casting process.
Background
Continuous casting, i.e. the abbreviation for continuous casting steel (Continuous Steel Casting). In the process of producing various steel products in a steel plant, there are generally two methods for solidifying and molding molten steel: conventional die casting and continuous casting processes. Compared with the traditional die casting method, the continuous casting technology has the remarkable advantages of greatly improving the metal yield and the casting blank quality, saving energy and the like. The continuous casting process flow mainly comprises the following steps: conveying the ladle filled with refined molten steel to a rotary table, and pouring the molten steel into a tundish after the rotary table rotates to a pouring position; the tundish distributes molten steel into each crystallizer through a water gap; the crystallizer rapidly solidifies and crystallizes molten steel into castings; and then the withdrawal and straightening machine and the crystallization vibration device act together to withdraw the casting in the crystallizer, and the casting is cut into slabs with a certain length after cooling and electromagnetic stirring.
In the prior art, effective determination of the quality of a slab output from a continuous casting process is still a relatively complex problem. In the existing method, the quality analysis and judgment are generally carried out in a manual field investigation mode, so that the cost is high and the accuracy is insufficient. Alternatively, a possible problem or defect of a particular process segment is detected or analyzed by acquiring process parameters of the particular process segment. This method does not consider global process flows and it is also difficult to accurately determine the quality of the final product. Or after the continuous casting slab is cut, restarting the continuous casting slab quality judging model, and judging the continuous casting slab quality according to the actually collected abnormal information in the continuous casting process. On one hand, the model adopted by the method is single; on the other hand, there is a certain hysteresis in the anomaly analysis and the anomaly information acquisition, and the anomaly information may not be complete or accurate, so that the accuracy and reliability of the final determination result may be affected.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a novel continuous casting quality judgment data analysis system which can acquire various process data in continuous casting in real time, predict and adjust the continuous casting quality and adjust and control the continuous casting quality.
The invention solves the technical problems by the following technical scheme: a novel data analysis system for continuous casting quality judgment is characterized by comprising,
the task issuing module is used for collecting production plan information, generating corresponding plan tasks according to the production plan information and issuing the plan tasks to the system;
the rule engine module is used for setting process rules and running a rule engine according to the set process rules;
the quality analysis and statistics module is used for carrying out real-time analysis according to the process data obtained in real time to obtain the statistical data of the current quality;
the online quality judging module is used for acquiring the planning task of the task issuing module, the statistical data of the current quality of the quality analysis and statistics module and the process data acquired in real time to obtain reasonable optimizing process parameters; according to the reasonable optimizing process parameters, the production line is adjusted; simultaneously feeding back the reasonably optimized technological parameters to an offline data analysis module;
and the offline data analysis module is used for carrying out offline analysis statistics on the process data and feeding back the result to the rule engine module for updating the setting of the process rule.
Preferably, the rule engine module comprises a rule engine setting module and a rule engine running module,
the rule engine setting module is used for setting process rules according to the technical characteristics of the continuous casting process and a continuous casting process knowledge base;
and the rule engine operation module is used for operating the rule engine according to the process rule.
Preferably, the online quality judging module comprises an artificial intelligent data predicting module, a processing module and a processing module, wherein the artificial intelligent data predicting module is used for adopting machine learning and deep learning as prediction engines, analyzing and predicting corresponding process parameters and process results according to process data acquired in real time, and carrying out reasonable optimizing on the process parameters through the process parameters and the process results; and/or
The mechanism model data prediction module is used for predicting and simulating data by adopting a mechanism model, predicting equipment states and process parameter effects according to process data acquired in real time, and further reasonably optimizing the process parameters.
Preferably, the system further comprises a data acquisition module, wherein the data acquisition module is used for acquiring various process data on the production line in real time.
Preferably, the system further comprises a communication module, wherein the communication module is connected with the data acquisition module, the online quality judgment module, the quality analysis statistics module and the offline data analysis module.
Preferably, the mass analysis statistics module further comprises,
the data cleaning and correcting unit is used for cleaning and correcting the process data acquired in real time;
and the data analysis and modeling unit is used for selecting and modeling the model aiming at the quality of each parameter.
Preferably, the artificial intelligence data prediction module is generated by using a BI-LSTM (BI-directional Long Short-Term Memory) network, and the data input by the artificial intelligence data prediction module includes process flow data, material data, defect distribution density when the output is defect-free or defect-free.
Preferably, the mechanism model data prediction module comprises,
a model forming unit for forming a prediction and calculation model of each parameter;
the calculation unit is used for carrying out data calculation and prediction according to the prediction and calculation model of each parameter to obtain a prediction result;
and the model verification and correction unit is used for comparing the model prediction result with data in the actual continuous casting process, verifying the accuracy and reliability of the model and correcting the model.
Preferably, the system further comprises a data display module, which is connected with the quality analysis and statistics module and the online quality judgment module and is used for outputting display data in real time.
Preferably, the off-line data analysis module comprises an analysis module and a verification module,
the analysis module is used for acquiring process data in real time according to each batch and reasonably optimizing the process parameters and storing the process parameters in a database in the form of historical data;
the verification module is used for verifying whether the models in the quality analysis and statistics module and the online quality judgment module are valid or not.
The invention has the positive progress effects that: according to the novel continuous casting quality judging data analysis system, a task issuing module is utilized to make a planning task, a rule engine module is utilized to make a process rule, a quality analysis statistics module is utilized to conduct current quality statistics analysis, an online quality judging module is utilized to obtain reasonably optimized process parameters, and the process data are adjusted according to the process parameters, so that real-time adjustment and correction of a continuous casting production line are controlled; and the offline data analysis module is used for carrying out offline analysis statistics on the process data and feeding back the result to the rule engine module for updating the setting of the process rule so that the subsequent continuous casting can be produced by using the optimized strategy rule. The novel data analysis system for judging the continuous casting quality can quickly and real-timely adjust the process parameters, ensure the production quality of a production line, and further update the strategy rules through offline analysis.
Drawings
FIG. 1 is a schematic block diagram of a data analysis system for novel continuous casting quality determination provided by an embodiment of the present invention;
fig. 2 is a schematic block diagram of another data analysis system for continuous casting quality determination according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated by means of the following examples, which are not intended to limit the scope of the invention.
The data analysis system for judging the quality of the novel continuous casting according to the embodiment of the invention, as shown in figure 1, comprises,
the task issuing module 1 is used for collecting production plan information, generating corresponding plan tasks according to the production plan information and issuing the plan tasks to the system;
the rule engine module 2 is used for setting process rules and running a rule engine according to the set process rules;
the quality analysis and statistics module 3 is used for acquiring process data in real time and analyzing the process data in real time to obtain the current quality statistical data;
the online quality judging module 4 is used for acquiring the planning task of the task issuing module, the statistical data of the current quality of the quality analysis and statistics module and the process data acquired in real time to obtain reasonable optimized process parameters; according to the reasonable optimizing process parameters, the production line is adjusted; and simultaneously feeding back the reasonably optimized process parameters to an offline data analysis module.
And the offline data analysis module 5 is used for performing offline analysis statistics of the process data and feeding back the result to the rule engine module for updating the setting of the process rule.
Specifically, the task publishing module 1 can obtain production plan information collected by continuous casting production lines L2 and L3 and the MES system, and generate a corresponding plan task according to the collected production plan information. And issued to the system, so that the system can track the current production state and blank state in real time. Meanwhile, the task issuing module 1 also comprises a manufacturing standard in the MES system, and can provide a corresponding manufacturing standard value for the system, and the unified manufacturing standard judgment is carried out on the basis of the manufacturing standard value.
Preferably, the production plan information comprises casting time information, casting time events, furnace time information, furnace opening time, final casting time and the like, and the plan tasks are issued to the system in a packaged mode. The manufacturing criteria specifically include process parameter manufacturing criteria in the manufacturing process, such as: upper and lower limits of pull rate, upper and lower limits of ladle molten steel temperature, upper and lower limits of crystallizer liquid level fluctuation, and the like.
The rule engine module 2 is configured to set a process rule, and perform operation of a rule engine according to the set process rule. Specifically, as shown in fig. 2, includes a rule engine setting module 21 and a rule engine running module 22,
the rule engine setting module 21 is configured to set a process rule according to the technical characteristics of the continuous casting process and a knowledge base of the continuous casting process; specifically, the process rule can be set through a visual graphical interface, and corresponding rules can be modified online and offline in real time, so that a good setting function is provided for a background operation rule engine. And specific setting rules such as that the pulling speed exceeds a certain number value, and performing rule alarm, such as that the weight of molten steel in the ladle is lower than 25 tons. The continuous casting process technical characteristics and the continuous casting process knowledge base are preset continuous casting process technical characteristics and continuous casting process knowledge base, can be adjusted according to experience and requirements, and can also be used for different production lines.
The rule engine operation module 22 performs operation of the rule engine through the set process rules, the rule engine performs real-time engine operation in the background, and meanwhile, corresponding process parameter configuration is performed through various configuration files, and the process rules are judged and operated according to various steel types in real time through configuration of various configuration files. In the real-time judging process, partial information with quality deviation can be analyzed in time, and meanwhile, data information can be recorded and stored, so that the whole quality scheme is analyzed and recorded very effectively.
And the quality analysis and statistics module 3 is used for carrying out real-time analysis according to the process data acquired in real time to obtain the current quality statistical data. The process data is a series of process parameters and other effect data, such as water quantity, temperature, speed and the like, which are acquired by the production line in the real-time processing process, and the process parameters can be adjusted and some parameters for controlling the production effect of the production line, such as parameters of materials, set processing time, set processing temperature and the like.
The quality analysis and statistics module 3 comprises a data cleaning and correction unit 31 for cleaning and correcting process data acquired in real time; preferably, the method is used for cleaning and correcting the collected data, such as parameters of secondary cooling water distribution, crystallizer liquid level, crystallizer temperature and the like, so as to ensure the accuracy and reliability of the data.
In particular, the data cleansing and correction, including but not limited to,
removing abnormal values: in the data, there may be some outliers that may have an impact on the accuracy of the model. Therefore, it is necessary to detect and remove abnormal values from data, and to identify and process the abnormal values by a method such as a box diagram or a scatter diagram.
Data deletion processing: in practical applications, data loss often occurs. For missing data, interpolation, deletion, or the like may be used to process, for example, filling in missing values by linear interpolation, polynomial interpolation, or the like.
And (3) data smoothing: in continuous casting quality determination and cutting optimization, there may be some noise or fluctuations in the data. Noise and fluctuations of the data can be reduced by data smoothing, for example by moving average or exponential average.
Data normalization: before model training, the data needs to be normalized, for example, by a method such as Z-score normalization or min-max normalization.
Data correction: in continuous casting quality determination and cutting optimization, some data errors or measurement deviations may exist. These errors and deviations can be eliminated by data correction, for example by regression analysis or fitting curves.
A data analysis and modeling unit 32 for each parameterSelecting and modeling a model by quality, specifically analyzing and modeling the cleaned and corrected data to obtain the relation among various technological parameters in the continuous casting process, and establishing a correlation prediction model 。 And then, only the process data acquired in real time is input, and the statistical data of the current quality can be output.
Of course, the data analysis and modeling unit 32 of the mass analysis statistics module may further include a model verification and optimization unit 321 for comparing the established model with actual data, verifying accuracy and reliability of the model, and performing optimization and updating.
As another alternative implementation manner, the quality analysis statistics module 3 may further perform multidimensional analysis on the process data according to various data analysis graphs, data fitting graphs and data distribution graphs, so as to obtain the statistics of the current quality. Specifically, at least any one of the following patterns may be employed.
The temperature map is drawn by recording the temperature distribution condition in the continuous casting process. Analyzing the temperature map can help identify possible temperature gradients and temperature changes, and further evaluate the quality and heat conduction of the cast slab.
A histogram is a graphical representation that visualizes the frequency distribution of a particular indicator, such as the rate of continuous casting, the flow of cooling water, etc. By analyzing the histogram, the existing frequency distribution mode can be identified, and the stability and reliability of the casting blank quality can be judged.
A scatter plot is a graph used to show the relationship between two variables, typically for the correlation between two related variables during continuous casting, such as the relationship between casting speed and casting quality. By analyzing the scatter plot, correlations between variables can be identified and adjusted accordingly to optimize casting quality.
Box plot, which is a graph for visualizing the distribution of continuous variables. The box plot can identify statistical information such as median, maximum, minimum, quartile, etc. of the variables. By analyzing the box line diagram, the distribution condition of variables in the continuous casting process can be determined, and the rationality and stability of quality indexes can be judged.
Thermodynamic diagrams are diagrams used to show density and can be used to represent the surface temperature and surface quality distribution of a cast slab. By analyzing the thermodynamic diagram, the temperature distribution and the surface quality distribution of the casting blank can be determined, so that possible problems in the casting process can be judged and corresponding adjustment can be performed to optimize the quality.
The online quality judging module 4 acquires the planning task of the task issuing module, the statistical data of the current quality of the quality analysis and statistics module and the process data acquired in real time, and obtains reasonably optimized process parameters; adjusting the process data according to the optimized process parameters; simultaneously feeding back the reasonably optimized process parameters to an offline data analysis module;
preferably, the process data analysis and verification results include process parameters, process results, equipment status and process parameter effects; the online quality determination module includes an artificial intelligence data prediction module 41 and a mechanism model data prediction module 42.
The artificial intelligence data prediction module 41 is configured to perform corresponding artificial intelligence data prediction by using machine learning and deep learning as prediction engines, analyze and predict corresponding process parameters and process results according to process data acquired in real time, and perform reasonable optimization of the process parameters according to the process parameters and the process results.
Preferably, the artificial intelligence data prediction module 41 uses BI-LSTM (BI-directional Long Short-Term Memory) network for generation, and the data input by the artificial intelligence data prediction module, that is, the process data acquired in real time, includes process flow data, material data, and defect distribution density when there is no defect.
More preferably, the process flow data input uses Cooling scrap added (coolant addition), ladle treatment time (bale processing time), slab width, steel temperature in tundish (mold inner plate billet temperature);
the material data is input by AI content deviation from target value (AI value under the target value), AI content in non-metallic inclusions (nonmetallic AI value), total AI content (integral AI value), si content (silicon value), ti content (titanium value) and N pickup during casting (nitrogen value in the casting process);
the output is:
with no defects (classifiers), for example outputs 0 and 1,0 indicating no defects, 1 indicating defects,
defect distribution density (Regression) the defect distribution density under slab casting length is performed by the predicted value.
The reasonable optimizing mode is to perform the reasonable optimizing of the parameters in a mode of large coefficient arrangement with large similarity among the calculation process parameters.
The mechanism model data prediction module 42 is configured to predict and simulate data by using a mechanism model, predict a device state and a process parameter effect according to process data obtained in real time, and further reasonably optimize a process parameter.
The module mainly uses a mechanism model to predict and simulate data, the mechanism model is used for simulating the data, meanwhile, the module prediction of the data is performed in a numerical simulation calculation mode aiming at mathematical modeling of various process sections, and the state and process parameter effect of equipment are predicted in a real-time data simulation mode to predict the data of the mechanism model.
Preferably, the mechanism model data prediction module includes a model forming unit 421 for forming a prediction and calculation model of each parameter;
a calculating unit 422, configured to calculate and predict data according to the prediction and calculation model of each parameter, so as to obtain a prediction result;
the model verification and correction unit 423 compares the model prediction result with data in the actual continuous casting process, verifies the accuracy and reliability of the model, and corrects the model.
The online quality judging module 4 analyzes and predicts corresponding process parameters and process results according to the process data acquired in real time through the artificial intelligence data predicting module 41, performs reasonable optimizing of the process parameters through the process parameters and the process results, and/or predicts equipment states and process parameter effects according to the process data acquired in real time through the mechanism model data predicting module 42, and performs reasonable optimizing of the process parameters according to the predicted equipment states and the process parameter effects. The artificial intelligent poetry prediction module 41 and the mechanism model data prediction module 42 may have only one of them, or may have both of them, mainly through an online quality judgment module, it is able to obtain reasonably optimized process parameters; and adjusting the production line according to the reasonably optimized technological parameters, so as to obtain the continuous casting product with optimal quality.
The offline data analysis module 5 comprises an analysis module 51 and a verification module 52.
The analysis module 51 is configured to store the process data obtained in real time and the process parameters after rational optimization in a database in the form of historical data according to the process data related to each batch; the historical data may include: data range, process data, inspection method, slab information, quality anomaly class, similarity statistical method, similarity statistical distribution diagram, etc.
The verification module 52 is configured to verify whether the models in the quality analysis statistics module 3 and the online quality determination module 4 are valid.
The novel continuous casting quality judging data analysis system of the embodiment further comprises a data acquisition module 6, wherein the data acquisition module is used for acquiring various process data on a production line in real time, is connected with the quality analysis statistics module 3, the online quality judging module 4 and the offline data analysis module 5, and is used for transmitting the acquired real-time process data to each module for subsequent data processing and analysis.
Of course, the system can also comprise a communication module 7 which is connected with the data acquisition module 6, the quality analysis statistics module 3, the online quality judgment module 4 and the offline data analysis module 5. Preferably, the data on the production line is collected by the PLC and then enters the online quality judging module through TCP/IP and OPCUA protocols.
The novel continuous casting quality judging data analysis system of the embodiment further comprises a data display module 8, wherein the data display module is connected with the quality analysis and statistics module and the online quality judging module and is used for outputting display data in real time. The real-time process data in the process flow can be displayed through the data display module.
According to the novel continuous casting quality judging data analysis system, a task issuing module is utilized to make a planning task, a rule engine module is utilized to make a process rule, a quality analysis and statistics module is utilized to conduct statistics of current quality, an online quality judging module is utilized to obtain reasonably optimized process parameters, and the process data are adjusted according to the process parameters, so that real-time adjustment and correction of a continuous casting production line are controlled; and the offline data analysis module is used for carrying out offline analysis statistics on the process data and feeding back the result to the rule engine module for updating the setting of the process rule so that the subsequent continuous casting can be produced by using the optimized strategy rule.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.
Claims (10)
1. A novel data analysis system for continuous casting quality judgment is characterized by comprising,
the task issuing module is used for collecting production plan information, generating corresponding plan tasks according to the production plan information and issuing the plan tasks to the system;
the rule engine module is used for setting process rules and running a rule engine according to the set process rules;
the quality analysis and statistics module is used for carrying out real-time analysis according to the process data obtained in real time to obtain the statistical data of the current quality;
the online quality judging module is used for acquiring the planning task of the task issuing module, the statistical data of the current quality of the quality analysis statistical module and the process data acquired in real time to obtain reasonable optimized process parameters; according to the reasonable optimizing process parameters, the production line is adjusted; simultaneously feeding back the reasonably optimized technological parameters to an offline data analysis module;
and the offline data analysis module is used for carrying out offline analysis statistics on the process data and feeding back the result to the rule engine module for updating the setting of the process rule.
2. The data analysis system for determining the quality of continuous casting according to claim 1, wherein the rule engine module comprises a rule engine setting module and a rule engine running module,
the rule engine setting module is used for setting process rules according to the technical characteristics of the continuous casting process and a continuous casting process knowledge base;
and the rule engine operation module is used for operating the rule engine according to the process rule.
3. The data analysis system for novel continuous casting quality determination according to claim 1, wherein the on-line quality determination module comprises,
the artificial intelligent data prediction module is used for adopting machine learning and deep learning as prediction engines, analyzing and predicting corresponding process parameters and process results according to the process data acquired in real time, and carrying out reasonable optimization on the process parameters through the process parameters and the process results; and/or
The mechanism model data prediction module is used for predicting and simulating data by adopting a mechanism model, predicting equipment states and process parameter effects according to process data acquired in real time, and further reasonably optimizing the process parameters.
4. The data analysis system for determining the quality of continuous casting according to claim 1, further comprising a data acquisition module for acquiring various process data on a production line in real time.
5. The data analysis system for determining the quality of a novel continuous casting according to claim 4, further comprising a communication module, wherein the communication module is connected with the data acquisition module, the on-line quality determination module, the quality analysis statistics module and the off-line data analysis module.
6. The data analysis system for determining the quality of a novel continuous casting according to claim 1, wherein the quality analysis statistical module further comprises,
the data cleaning and correcting unit is used for cleaning and correcting the process data acquired in real time;
and the data analysis and modeling unit is used for selecting and modeling the model aiming at the quality of each parameter.
7. The data analysis system for determining the quality of a new continuous casting according to claim 3, wherein the artificial intelligence data prediction module is generated by using a BI-LSTM (BI-directionalLong Short-Term Memory) network, and the data input by the artificial intelligence data prediction module includes process flow data and material data, and the output is defect-free and defect distribution density when defective.
8. The data analysis system for novel continuous casting quality judgment according to claim 3, wherein the mechanism model data prediction module comprises,
a model forming unit for forming a prediction and calculation model of each parameter;
the calculation unit is used for carrying out data calculation and prediction according to the prediction and calculation model of each parameter to obtain a prediction result;
and the model verification and correction unit is used for comparing the model prediction result with data in the actual continuous casting process, verifying the accuracy and reliability of the model and correcting the model.
9. The data analysis system for determining the quality of the continuous casting according to claim 1, further comprising a data display module connected to both the quality analysis and statistics module and the online quality determination module for outputting display data in real time.
10. The data analysis system for determining the quality of a novel continuous casting according to claim 1, wherein the off-line data analysis module comprises an analysis module and a verification module,
the analysis module is used for acquiring process data in real time according to each batch, and reasonably optimizing analysis and verification results of the process data and storing the results in a database in a form of historical data;
and the verification module is used for verifying whether the models in the quality analysis and statistics module and the online quality judgment module are valid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311442016.3A CN117408427A (en) | 2023-10-31 | 2023-10-31 | Novel continuous casting quality judging data analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311442016.3A CN117408427A (en) | 2023-10-31 | 2023-10-31 | Novel continuous casting quality judging data analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117408427A true CN117408427A (en) | 2024-01-16 |
Family
ID=89488767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311442016.3A Pending CN117408427A (en) | 2023-10-31 | 2023-10-31 | Novel continuous casting quality judging data analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117408427A (en) |
-
2023
- 2023-10-31 CN CN202311442016.3A patent/CN117408427A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1428598B1 (en) | Method and online system for monitoring continuous caster start-up operation and predicting start cast breakouts | |
| CN108256260A (en) | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine | |
| CN106735029B (en) | A method of strand production process parameters are accurately positioned to strand and are sliced | |
| CN103100678A (en) | Online control system and method of influencing parameters of continuous casting defects | |
| Knyazev et al. | Automated system of control and diagnostics of cast-steel defects in the mass production | |
| CN112418538A (en) | Continuous casting billet inclusion prediction method based on random forest classification | |
| CN116307289B (en) | Textile processing procedure parameter detection and prediction method, system and storage medium | |
| CN102426622A (en) | Adaptive variable-speed drawing simulation method for production of single-crystal blade | |
| CN115283649B (en) | Mold temperature closed-loop control method and system in wheel casting process | |
| CN114985697B (en) | Crystallizer liquid level fluctuation monitoring method and system | |
| Zhou et al. | Application of time series data anomaly detection based on deep learning in continuous casting process | |
| Hahn et al. | Autonomous optimization of casting processes and designs | |
| CN111651729A (en) | Method for predicting blockage of secondary cooling water nozzle in continuous casting | |
| CN114266286A (en) | Online detection method and device for welding process information | |
| CN117408427A (en) | Novel continuous casting quality judging data analysis system | |
| CN116703254B (en) | Production information management system for mechanical parts of die | |
| CN106694863A (en) | Molten steel pouring control method and device | |
| CN116179840A (en) | Laser surface heat treatment temperature monitoring control system and control method | |
| JP2022014435A (en) | Method and device for estimating surface defect of steel raw material, method and device for supporting determination of specification of steel raw material production, and production method of steel raw material | |
| CN117171936A (en) | Slab quality prediction method for extracting real-time characteristic value of crystallizer based on defect mechanism | |
| NL2030465B1 (en) | Continuous casting slab quality predicting method based on extreme learning machine | |
| SV | DEVELOPMENT OF AUTOMATED CONTROL SYSTEM FOR CONTINUOUS CASTING. | |
| CN112775404B (en) | Method for predicting temperature of straightening section of continuous casting square billet | |
| CN117840392A (en) | Electromagnetic stirring control method and system | |
| JPH09314299A (en) | Method for controlling slab width in continuous casting equipment |
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 |