CN116186936A - Method, system, equipment and medium for determining continuous casting process parameters - Google Patents
Method, system, equipment and medium for determining continuous casting process parameters Download PDFInfo
- Publication number
- CN116186936A CN116186936A CN202310187762.6A CN202310187762A CN116186936A CN 116186936 A CN116186936 A CN 116186936A CN 202310187762 A CN202310187762 A CN 202310187762A CN 116186936 A CN116186936 A CN 116186936A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting process
- parameters
- correlation coefficient
- process parameters
- 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
- 238000000034 method Methods 0.000 title claims abstract description 485
- 238000009749 continuous casting Methods 0.000 title claims abstract description 212
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 238000013210 evaluation model Methods 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000009826 distribution Methods 0.000 claims description 42
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 17
- 238000010998 test method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 7
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 230000001351 cycling effect Effects 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 26
- 238000004422 calculation algorithm Methods 0.000 description 20
- 239000002893 slag Substances 0.000 description 18
- 238000005457 optimization Methods 0.000 description 17
- 230000000694 effects Effects 0.000 description 15
- 229910000831 Steel Inorganic materials 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 239000007788 liquid Substances 0.000 description 11
- 239000010959 steel Substances 0.000 description 11
- XKRFYHLGVUSROY-UHFFFAOYSA-N Argon Chemical compound [Ar] XKRFYHLGVUSROY-UHFFFAOYSA-N 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 6
- 230000004907 flux Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 239000007921 spray Substances 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000005096 rolling process Methods 0.000 description 5
- 229910052786 argon Inorganic materials 0.000 description 4
- 238000005266 casting Methods 0.000 description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 4
- 239000010931 gold Substances 0.000 description 4
- 229910052737 gold Inorganic materials 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000012300 Sequence Analysis Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 239000000498 cooling water Substances 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 230000005499 meniscus Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000004540 process dynamic Methods 0.000 description 2
- 239000002436 steel type Substances 0.000 description 2
- 238000004781 supercooling Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Factory Administration (AREA)
- Continuous Casting (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for determining continuous casting process parameters, wherein the method for determining the continuous casting process parameters comprises the following steps: acquiring continuous casting process data; the continuous casting process data comprises a plurality of continuous casting process parameters; calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine, and screening out a target process parameter from continuous casting process data according to the correlation coefficient; and circularly inputting the target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value. According to the invention, the continuous casting process parameters most relevant to the production quality of the continuous casting machine can be screened out by calculating the correlation coefficient of the continuous casting process parameters, so that only the continuous casting process parameters more relevant are scored and adjusted; the continuous casting process parameters are circularly input into the model for scoring, so that the scoring of the adjusted continuous casting process parameters can be continuously obtained, and the accurate adjustment of the continuous casting process parameters is realized.
Description
Technical Field
The application relates to the technical field of steel casting, in particular to a method, a system, equipment and a medium for determining continuous casting process parameters.
Background
Since the fifties of the twentieth century, a production process of continuous casting, which is a process of directly casting liquid molten steel into a shaped steel product by a continuous casting machine, has been applied in steel plants, and compared with the traditional casting-before-rolling process, the production time is greatly shortened, and the working efficiency is improved. In order to obtain good quality of steel produced by manufacturing different kinds of steel, parameters of a continuous casting machine need to be adjusted, however, parameters affecting the quality of steel in the continuous casting machine are numerous, and it is difficult to achieve an excellent production state of the continuous casting machine by adjusting the parameters of the continuous casting machine only empirically. In the prior art, some methods for automatically adjusting process parameters exist, see patent document with application number 201811470948.8, and the prior art realizes off-line optimization of high latitude data based on a GA-LS-SVM off-line optimization mode, but is not applicable to the off-line optimization of massive cross data, and is not applicable to quality judgment scenes under continuous casting process; or referring to the patent document with the application number of 20190139402.2, the optimal point is selected by adopting comparative analysis, and meanwhile, related data mining is carried out aiming at work under multiple modes, but the optimal point searching and optimizing can not be rapidly positioned under the conditions of multiple dimensions of process data and large data quantity, and meanwhile, the method is not applicable to scenes aiming at quality pre-judgment in continuous casting.
Therefore, the prior art can not quickly and accurately adjust the numerical value of the continuous casting process parameter to the optimal value in the continuous casting process field, so that the production quality of the continuous casting machine can not be fully exerted.
Disclosure of Invention
The invention aims to overcome the defect that effective continuous casting process parameters cannot be rapidly and accurately screened in the prior art, and provides a method, a system, equipment and a medium for determining the continuous casting process parameters.
The invention solves the technical problems by the following technical scheme:
in a first aspect, a method for determining a continuous casting process parameter is provided, the determining method comprising:
acquiring continuous casting process data; the continuous casting process data comprises a plurality of continuous casting process parameters;
calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine, and screening out a target process parameter from the continuous casting process data according to the correlation coefficient;
and circularly inputting the target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value.
Preferably, the determining method trains to obtain the evaluation model through the following steps:
acquiring historical process parameters and corresponding historical process evaluation scores;
taking the historical process parameters as input, taking the historical process evaluation scores as output to train a preset model, and generating the evaluation model;
the preset model comprises at least one of a linear model, an LSTM network model and a random forest model.
Preferably, the step of calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine comprises;
checking whether the continuous casting process parameters meet normal distribution;
when normal distribution is met, calculating a Pearson correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a card method test method aiming at the Pearson correlation coefficient;
and when the normal distribution is not met, calculating a Spearman correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting the card method test method aiming at the Spearman correlation coefficient.
Preferably, the method comprises the steps of,
the continuous casting process data comprises a first process rule, and before the step of circularly inputting the target process parameters into a pre-trained evaluation model, the continuous casting process data further comprises:
determining target process parameters and corresponding process evaluation scores which do not accord with the first process rule as invalid data;
generating a second process rule according to the invalid data;
the target process parameter is adjusted based on the first process rule and the second process rule.
In a second aspect, a system for determining parameters of a continuous casting process is provided, the system comprising:
the first acquisition module is used for acquiring continuous casting process data; the continuous casting process data comprises a plurality of continuous casting process parameters;
the screening module is used for calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine and screening target process parameters from the continuous casting process data according to the correlation coefficient;
and the adjusting module is used for circularly inputting the target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value.
Preferably, the determining system trains to obtain the evaluation model through the following modules, including:
the second acquisition module is used for acquiring the historical process parameters and the corresponding historical process evaluation scores;
the input module is used for taking the historical process parameters as input, taking the historical process evaluation scores as output and training a preset model, and generating the evaluation model; the preset model comprises at least one of a linear model, an LSTM network model and a random forest model.
Preferably, the screening module includes:
the testing unit is used for testing whether the continuous casting process parameters meet normal distribution; when the normal distribution is satisfied, the first computing unit is called, and when the normal distribution is not satisfied, the second computing unit is called;
the first calculation unit is used for calculating a Pearson correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a card method test method aiming at the Pearson correlation coefficient;
the second calculating unit is used for calculating a Spearman correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting the card method test method aiming at the Spearman correlation coefficient.
Preferably, the continuous casting process data includes a first process rule, and the determining system further includes:
a judging module, configured to judge that the target process parameter and the corresponding process evaluation score do not conform to the first process rule are invalid data;
the generation module is used for generating a second process rule according to the invalid data;
and the adjusting module is used for adjusting the target process parameters based on the first process rule and the second process rule.
In a third aspect, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and configured to run on the processor, where the processor implements the method for determining parameters of a continuous casting process according to the present invention when executing the computer program.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of determining a continuous casting process parameter of the present invention.
On the basis of conforming to the common knowledge in the field, the above preferred conditions can be arbitrarily combined to obtain the preferred examples of the invention.
The invention has the positive progress effects that: the continuous casting process parameters which are most relevant to the production quality of the continuous casting machine can be screened out by calculating the correlation coefficient of the continuous casting process parameters, so that the more relevant continuous casting process parameters are only scored and adjusted, the calculation time can be saved, and the requirement of quickly adjusting the continuous casting machine process parameters is met; the continuous casting process parameters are circularly input into the model for scoring, so that the scoring of the adjusted continuous casting process parameters can be continuously obtained until the scoring is higher than a preset threshold value, thereby realizing accurate adjustment of the continuous casting process parameters and fully playing the production quality of the continuous casting machine.
Drawings
Fig. 1 is a flowchart of a method for determining parameters of a continuous casting process according to embodiment 1 of the present invention.
Fig. 2 is a schematic flow chart of the evaluation model training of the determination method of continuous casting process parameters provided in embodiment 1 of the present invention.
Fig. 3 is a flow chart of the method for determining continuous casting process parameters according to embodiment 2 of the present invention.
Fig. 4 is a schematic structural diagram of a system for determining parameters of continuous casting process according to embodiment 3 of the present invention.
Fig. 5 is a schematic structural diagram of a system for determining parameters of continuous casting process according to embodiment 4 of the present invention.
Fig. 6 is a schematic structural diagram of an electronic device according to embodiment 5 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.
Example 1
The embodiment provides a method for determining continuous casting process parameters. Referring to fig. 1, the method includes the steps of:
s1, acquiring continuous casting process data; the continuous casting process data includes a plurality of continuous casting process parameters.
The continuous casting process data comprises process quality rules of a continuous casting offline part, and the process quality rules of the part are as follows: constant argon and constant speed calculation rules (calculation method between chi square variation and constant rule inspection), crystallizer heat flux density calculation rules (relationship between surface longitudinal crack and heat flux density), nozzle spray water quantity calculation rules (relationship between nozzle spray water quantity under two cold areas), sensitivity of steel grade and surface longitudinal crack (relationship between steel grade and calculated crack sensitivity), liquid level distribution and calculation of slag and meniscus distribution (calculated liquid level distribution and slag distribution calculation relationship), and the like.
A plurality of preferred process quality rules and process quality parameters can be extracted from the total process quality rules in a mode of model calculation and the like.
The quality parameters of part of the process are as follows:
the parameters of slag inclusion component correlation parameters after slag rolling, slag inclusion distribution correlation parameters of slag inclusion types, slag structure correlation parameters, low superheat degree and FEMS optimization correlation parameters, superheat degree data correlation parameters, supercooling data correlation parameters, argon gas quantity, casting speed, drawing speed, crystallizer liquid level, heat flux density, spray water quantity, steel types, surface longitudinal crack coefficients, liquid level distribution, slag rolling, slag and the like.
The above process quality parameters or combinations of process quality parameters and their corresponding specific values are collectively referred to herein as continuous casting process parameters, and when the continuous casting machine sets the continuous casting process parameters, they affect the quality of the product produced by the continuous casting machine, and it is obviously difficult to adjust them by experience only to achieve the optimal state of the quality of the product produced by them, so that the assistance of the model is required to perform accurate and rapid adjustment.
S2, checking a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine, and screening out a target process parameter from continuous casting process data according to the correlation coefficient;
because of the numerous process quality parameters, many process quality parameters do not have a great influence on the production quality of the continuous casting machine, and therefore, process quality parameters with high correlation need to be extracted from the numerous process quality parameters. Specifically:
calculating whether the continuous casting process parameters meet normal distribution;
the continuous casting process parameters mainly comprise 2, 3 and 4 process quality parameters, and a plurality of process quality parameters are taken as one continuous casting process parameter to calculate a correlation coefficient because part of process quality parameters need to be cooperated with other process quality parameters to have related influence on the production quality of the continuous casting machine.
Whether the continuous casting process parameters meet the normal distribution is calculated, and mainly whether the historical data of the process quality parameters corresponding to the continuous casting process parameters meet the normal distribution is calculated.
The invention adopts a time window, and when the continuous casting process parameters comprise a plurality of process quality parameters, the time intervals among the process quality parameters can also influence the correlation coefficient of the process quality parameters in some cases, so that the correlation coefficient of each continuous casting process parameter under different time intervals is calculated, and then the highest correlation coefficient and the corresponding interval are output.
And when the normal distribution is met, calculating the Pearson correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a card method test method aiming at the Pearson correlation coefficient. Specifically:
under the condition that the data has normal distribution, calculating Pearson correlation coefficients of continuous casting process parameters, when the continuous casting process parameters comprise a plurality of process quality parameters, calculating Pearson correlation coefficients in different time intervals, then automatically matching, calculating and optimizing the continuous casting process parameters, checking normal and scatter diagrams through normal diagrams, extracting a plurality of continuous casting process parameters with highest correlation coefficients in the parameter automatic optimizing process, and calculating the correlation coefficients by adopting a card method aiming at the Pearson correlation coefficients.
After the Pearson correlation coefficient is calculated, the correlation coefficient can be calculated by a card method, and the correlation coefficient of the continuous casting process parameters is further tested, so that a plurality of continuous casting process parameters with the highest correlation coefficient are extracted as target process parameters.
And when the normal distribution is not satisfied, calculating a Spearman correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a chi-square test method aiming at the Spearman correlation coefficient. Specifically:
in the case where the data does not satisfy the normal distribution, spearman correlation coefficient analysis is automatically added, and when the continuous casting process parameter contains a plurality of process quality parameters, pearson correlation coefficients in different time intervals can be calculated. And then carrying out automatic matching calculation optimizing on the continuous casting process parameters, checking a normalization and a scatter diagram through a normalization diagram, extracting a plurality of continuous casting process parameters with highest correlation coefficients in the parameter automatic optimizing process, and calculating the correlation coefficients by adopting a card method checking method aiming at the Spearman correlation coefficients.
After the Spearman correlation coefficient is calculated, the correlation coefficient can be calculated by a card method, and the correlation coefficient of the continuous casting process parameters is further tested, so that a plurality of continuous casting process parameters with the highest correlation coefficient are extracted as target process parameters.
In step S3, the target process parameters are circularly input into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value.
Firstly, training an evaluation model is needed, referring to fig. 2, the specific training process is as follows:
s201, acquiring historical process parameters and corresponding historical process evaluation scores.
The historical process parameter is a historical value of the target process parameter, and the historical process evaluation score is a process evaluation score corresponding to the historical value of the target process parameter.
S202, taking the historical process parameters as input, taking the historical process evaluation scores as output, training a preset model, and generating an evaluation model.
The preset model includes at least one of a linear model, an LSTM network model, and a random forest model.
The self-adaptive model after training is used for off-line prediction of data, predicts what level the working state of the current continuous casting unit is, carries out process scoring aiming at each target process parameter in a targeted manner, and comprehensively carries out evaluation and scoring of the continuous casting unit in the process to obtain comprehensive digital scoring under the working state of the current continuous casting unit so as to achieve the digital evaluation effect of the unit.
Taking the drawing speed process parameters as examples: 1.1-1.8 process parameters, wherein the score of 1.5 is 10,1.6, the score of 1.4 is 9,1.7, the score of 1.3 is 8 …, and the like, the pull rate process with the optimal process parameter of 1.5m/s and the pull rate process with the worst process parameter of 0.7m/s are determined, so that a pull rate process parameter evaluation system is formed. Meanwhile, the system can be adjusted timely according to the actual process production condition.
Based on the process evaluation score, the optimization adjustment work of parameters is carried out on several target process parameters (such as pulling speed, crystallizer liquid level adjustment, secondary cooling water distribution and the like) of the system in a targeted manner, the process is optimized through the self-adaptive optimization adjustment of each round, so that the optimal production effect in the process is achieved, the efficiency of the quality slab is effectively improved, the parameter optimization effect of a gold slab is achieved, the parameters of the gold slab can be dynamically adjusted to an optimal level in real time, and the optimal stable operation of production is achieved.
After the parameters are adjusted, the parameters are sent to the L1 through communication to carry out process dynamic adjustment of the unit, so that the operation effect of the optimal mode of the industrial brain process is realized.
According to the embodiment, the continuous casting process parameters which are most relevant to the production quality of the continuous casting machine can be screened out by calculating the correlation coefficient of the continuous casting process parameters, so that the more relevant continuous casting process parameters are only scored and adjusted, the calculation time can be saved, and the requirement of quickly adjusting the continuous casting machine process parameters is met; the continuous casting process parameters are circularly input into the model for scoring, so that the scoring of the adjusted continuous casting process parameters can be continuously obtained until the scoring is higher than a preset threshold value, thereby realizing accurate adjustment of the continuous casting process parameters and fully playing the production quality of the continuous casting machine.
Example 2
On the basis of embodiment 1, this embodiment provides a method for determining continuous casting process parameters.
Before step S3, adjusting the target process parameters based on rules, and then circularly inputting the continuously adjusted target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value. Referring to fig. 3, specifically:
when the continuous casting process data includes the first process rule, the determining method further includes:
s203, taking the target process parameters and the corresponding process evaluation scores which do not accord with the first process rule as invalid data.
S204, generating a second process rule based on the invalid data.
And training a preset model by taking invalid data conforming to the second process rule and historical data of the target process parameter as the historical process parameter.
The method for verifying whether the process rule is met is as follows: and carrying out time sequence analysis and actual off-line analysis statistical graph display by calculating data meeting Pearson and Spearman statistics and Kendall correlation coefficient data meeting process rule consistency comparison analysis, and carrying out verification of process rule conditions under the existing process rule conditions based on the statistical data.
The method of generating the new process rules is as follows: and the data of Kendall correlation coefficients are adopted, but the data of Pearson and Spearman statistics and the data of process rule consistency comparison analysis are met, the data of the data are subjected to corresponding graphic display through time sequence data analysis and offline data analysis, and the corresponding process rules are extracted through time sequence data analysis.
Because the cleaned data of each round has corresponding process rules, strategic adjustment of target process parameters is performed through recognition of data patterns, and dynamic adjustment of a quality prediction algorithm is performed through a pattern recognition mode of the strategic algorithm. In order to ensure the accuracy of the quality prediction algorithm and the quality of the algorithm, a dynamic algorithm model monitoring module is introduced to provide dynamic monitoring of an algorithm model, and when the accuracy of the quality prediction algorithm is reduced and the calculated quality of the quality prediction algorithm is reduced, corresponding algorithm adjustment is carried out to ensure the accurate operation of the quality of the algorithm.
And training an evaluation model by using the historical process parameters conforming to the process rules and the corresponding historical process evaluation scores.
S205, adjusting target process parameters based on the first process rule and the second process rule.
As new process rules can be continuously extracted from the target process parameters, the target process parameters can be adjusted through the process rules, so that the effect of accurately and quickly adjusting the target process parameters is achieved, the parameters are quickly adjusted, and the production quality of the continuous casting machine is improved.
In the final quality slab processing stage, the surface inspection process is detected through the surface inspection equipment and the like, then the process rule is adjusted in real time in a process reverse tracing mode, and the process reverse parameter optimization and optimization are carried out in a process decision tree mode in the reverse tracing process, so that the aim of decision parameter optimization is fulfilled. And optimizing continuous casting process parameters to finally realize a quality closed loop effect.
According to the method, the data of the training evaluation model are verified through the process rules, the training accuracy of the evaluation model is guaranteed, and the target process parameters are adjusted through the process rules, so that the effect of accurately and quickly adjusting the target process parameters is achieved, the parameters are quickly adjusted, and the production quality of the continuous casting machine is improved.
Example 3
The embodiment provides a system for determining continuous casting process parameters. Referring to fig. 4, the determination system includes a first acquisition module 1, a screening module 2, an adjustment module 3, a second acquisition module 4, and an input module 5, and the screening module 2 further includes a verification unit 21, a first calculation unit 22, and a second calculation unit 23.
The first acquisition module 1 is used for acquiring continuous casting process data; the continuous casting process data includes a plurality of continuous casting process parameters.
The continuous casting process data comprises process quality rules of a continuous casting offline part, and the process quality rules of the part are as follows: constant argon and constant speed calculation rules (calculation method between chi square variation and constant rule inspection), crystallizer heat flux density calculation rules (relationship between surface longitudinal crack and heat flux density), nozzle spray water quantity calculation rules (relationship between nozzle spray water quantity under two cold areas), sensitivity of steel grade and surface longitudinal crack (relationship between steel grade and calculated crack sensitivity), liquid level distribution and calculation of slag and meniscus distribution (calculated liquid level distribution and slag distribution calculation relationship), and the like.
A plurality of preferred process quality rules and process quality parameters can be extracted from the total process quality rules in a mode of model calculation and the like.
The quality parameters of part of the process are as follows:
the parameters of slag inclusion component correlation parameters after slag rolling, slag inclusion distribution correlation parameters of slag inclusion types, slag structure correlation parameters, low superheat degree and FEMS optimization correlation parameters, superheat degree data correlation parameters, supercooling data correlation parameters, argon gas quantity, casting speed, drawing speed, crystallizer liquid level, heat flux density, spray water quantity, steel types, surface longitudinal crack coefficients, liquid level distribution, slag rolling, slag and the like.
The above process quality parameters or combinations of process quality parameters and their corresponding specific values are collectively referred to herein as continuous casting process parameters, and when the continuous casting machine sets the continuous casting process parameters, they affect the quality of the product produced by the continuous casting machine, and it is obviously difficult to adjust them by experience only to achieve the optimal state of the quality of the product produced by them, so that the assistance of the model is required to perform accurate and rapid adjustment.
The screening module 2 is used for calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine, and screening target process parameters from continuous casting process data according to the correlation coefficient;
because of the numerous process quality parameters, many process quality parameters do not have a great influence on the production quality of the continuous casting machine, and therefore, process quality parameters with high correlation need to be extracted from the numerous process quality parameters. Specifically:
the checking unit 21 is used for checking whether the continuous casting process parameter satisfies the normal distribution, and when the normal distribution is satisfied, the first calculating unit 22 is called, and when the normal distribution is not satisfied, the second calculating unit 23 is called.
The continuous casting process parameters mainly comprise 2, 3 and 4 process quality parameters, and a plurality of process quality parameters are taken as one continuous casting process parameter to calculate a correlation coefficient because part of process quality parameters need to be cooperated with other process quality parameters to have related influence on the production quality of the continuous casting machine.
Whether the continuous casting process parameters meet the normal distribution is calculated, and mainly whether the historical data of the process quality parameters corresponding to the continuous casting process parameters meet the normal distribution is calculated.
The invention adopts a time window, and when the continuous casting process parameters comprise a plurality of process quality parameters, the time intervals among the process quality parameters can also influence the correlation coefficient of the process quality parameters in some cases, so that the correlation coefficient of each continuous casting process parameter under different time intervals is calculated, and then the highest correlation coefficient and the corresponding interval are output.
When the normal distribution is satisfied, the first calculation unit 22 is called to calculate the Pearson correlation coefficient of the continuous casting process parameter, and the correlation coefficient is calculated by using a card method test method for the Pearson correlation coefficient. Specifically:
under the condition that the data has normal distribution, calculating Pearson correlation coefficients of continuous casting process parameters, when the continuous casting process parameters comprise a plurality of process quality parameters, calculating the Pearson correlation coefficients in different time intervals, then automatically matching, calculating and optimizing the continuous casting process parameters, checking normal and scatter diagrams through a normal map, and refining a plurality of continuous casting process parameters with highest correlation coefficients in the parameter automatic optimizing process.
After the Pearson correlation coefficient is calculated, the correlation coefficient can be calculated by a card method, and the correlation coefficient of the continuous casting process parameters is further tested, so that a plurality of continuous casting process parameters with the highest correlation coefficient are extracted as target process parameters.
When the normal distribution is not satisfied, the second calculation unit 23 is called for calculating the Spearman correlation coefficient of the continuous casting process parameter, and the correlation coefficient is calculated by using a card method test method for the Spearman correlation coefficient. Specifically:
in the case where the data does not satisfy the normal distribution, spearman correlation coefficient analysis is automatically added, and when the continuous casting process parameter contains a plurality of process quality parameters, pearson correlation coefficients in different time intervals can be calculated. And then carrying out automatic matching calculation optimizing on the continuous casting process parameters, checking a normalization and a scatter diagram through a normalization diagram, and extracting a plurality of continuous casting process parameters with highest correlation coefficients in the parameter automatic optimizing process.
After the Spearman correlation coefficient is calculated, the correlation coefficient can be calculated by a card method, and the correlation coefficient of the continuous casting process parameters is further tested, so that a plurality of continuous casting process parameters with the highest correlation coefficient are extracted as target process parameters.
The adjustment module 3 is configured to circularly input the target process parameter into a pre-trained evaluation model until a process evaluation score is obtained that is greater than a preset threshold.
The second obtaining module 4 is configured to obtain historical process parameters and corresponding historical process evaluation scores.
The historical process parameter is a historical value of the target process parameter, and the historical process evaluation score is a process evaluation score corresponding to the historical value of the target process parameter.
The input module 5 is used for taking the historical process parameters as input, taking the historical process evaluation scores as output, training a preset model, and generating an evaluation model.
The preset model includes at least one of a linear model, an LSTM network model, and a random forest model.
The self-adaptive model after training is used for off-line prediction of data, predicts what level the working state of the current continuous casting unit is, carries out process scoring aiming at each target process parameter in a targeted manner, and comprehensively carries out evaluation and scoring of the continuous casting unit in the process to obtain comprehensive digital scoring under the working state of the current continuous casting unit so as to achieve the digital evaluation effect of the unit.
Taking the drawing speed process parameters as examples: 1.1-1.8 process parameters, wherein the score of 1.5 is 10,1.6, the score of 1.4 is 9,1.7, the score of 1.3 is 8 …, and the like, the pull rate process with the optimal process parameter of 1.5m/s and the pull rate process with the worst process parameter of 0.7m/s are determined, so that a pull rate process parameter evaluation system is formed. Meanwhile, the system can be adjusted timely according to the actual process production condition.
Based on the process evaluation score, the optimization adjustment work of parameters is carried out on several target process parameters (such as pulling speed, crystallizer liquid level adjustment, secondary cooling water distribution and the like) of the system in a targeted manner, the process is optimized through the self-adaptive optimization adjustment of each round, so that the optimal production effect in the process is achieved, the efficiency of the quality slab is effectively improved, the parameter optimization effect of a gold slab is achieved, the parameters of the gold slab can be dynamically adjusted to an optimal level in real time, and the optimal stable operation of production is achieved.
After the parameters are adjusted, the parameters are sent to the L1 through communication to carry out process dynamic adjustment of the unit, so that the operation effect of the optimal mode of the industrial brain process is realized.
According to the embodiment, the continuous casting process parameters which are most relevant to the production quality of the continuous casting machine can be screened out by calculating the correlation coefficient of the continuous casting process parameters, so that the more relevant continuous casting process parameters are only scored and adjusted, the calculation time can be saved, and the requirement of quickly adjusting the continuous casting machine process parameters is met; the continuous casting process parameters are circularly input into the model for scoring, so that the scoring of the adjusted continuous casting process parameters can be continuously obtained until the scoring is higher than a preset threshold value, thereby realizing accurate adjustment of the continuous casting process parameters and fully playing the production quality of the continuous casting machine.
Example 4
On the basis of embodiment 3, this embodiment provides a continuous casting process parameter determination system, and referring to fig. 5, the determination system further includes a determination module 6, a generation module 7, and an adjustment module 8.
The adjustment module 8 is configured to adjust the target process parameter based on the rule, and then circularly input the continuously adjusted target process parameter into a pre-trained evaluation model until a process evaluation score is obtained that is greater than a preset threshold. Specifically:
the continuous casting process data comprises a first process rule, and the judging module 6 is used for judging target process parameters and corresponding process evaluation scores which do not accord with the first process rule as invalid data; the generating module 7 is configured to generate a second process rule according to the invalid data.
And training a preset model by taking invalid data conforming to the second process rule and historical data of the target process parameter as the historical process parameter.
The method for verifying whether the process rule is met is as follows: and carrying out time sequence analysis and actual off-line analysis statistical graph display by calculating data meeting Pearson and Spearman statistics and Kendall correlation coefficient data meeting process rule consistency comparison analysis, and carrying out verification of process rule conditions under the existing process rule conditions based on the statistical data.
The method of generating the new process rules is as follows: and the data of Kendall correlation coefficients are adopted, but the data of Pearson and Spearman statistics and the data of process rule consistency comparison analysis are met, the data of the data are subjected to corresponding graphic display through time sequence data analysis and offline data analysis, and the corresponding process rules are extracted through time sequence data analysis.
Because the cleaned data of each round has corresponding process rules, strategic adjustment of target process parameters is performed through recognition of data patterns, and dynamic adjustment of a quality prediction algorithm is performed through a pattern recognition mode of the strategic algorithm. In order to ensure the accuracy of the quality prediction algorithm and the quality of the algorithm, a dynamic algorithm model monitoring module is introduced to provide dynamic monitoring of an algorithm model, and when the accuracy of the quality prediction algorithm is reduced and the calculated quality of the quality prediction algorithm is reduced, corresponding algorithm adjustment is carried out to ensure the accurate operation of the quality of the algorithm.
And training an evaluation model by using the historical process parameters conforming to the process rules and the corresponding historical process evaluation scores.
The target process parameter is adjusted based on the first process rule and the second process rule.
As new process rules can be continuously extracted from the target process parameters, the target process parameters can be adjusted through the process rules, so that the effect of accurately and quickly adjusting the target process parameters is achieved, the parameters are quickly adjusted, and the production quality of the continuous casting machine is improved.
In the final quality slab processing stage, the surface inspection process is detected through the surface inspection equipment and the like, then the process rule is adjusted in real time in a process reverse tracing mode, and the process reverse parameter optimization and optimization are carried out in a process decision tree mode in the reverse tracing process, so that the aim of decision parameter optimization is fulfilled. And optimizing continuous casting process parameters to finally realize a quality closed loop effect.
According to the method, the data of the training evaluation model are verified through the process rules, the training accuracy of the evaluation model is guaranteed, and the target process parameters are adjusted through the process rules, so that the effect of accurately and quickly adjusting the target process parameters is achieved, the parameters are quickly adjusted, and the production quality of the continuous casting machine is improved.
Example 5
Fig. 6 is a schematic structural diagram of an electronic device according to the present embodiment. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed implements the method of determining the continuous casting process parameters of embodiment 1 or embodiment 2. The electronic device 30 shown in fig. 6 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 6, the electronic device 30 may be embodied in the form of a general purpose computing device, which may be a server device, for example. Components of electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, a bus 33 connecting the different system components, including the memory 32 and the processor 31.
The bus 33 includes a data bus, an address bus, and a control bus.
The processor 31 executes various functional applications and data processing, such as the determination method of continuous casting process parameters of embodiment 1 or embodiment 2 of the present invention, by running a computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through an input/output (I/O) interface 35. Also, model-generating device 30 may also communicate with one or more networks, such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet, via network adapter 36. As shown, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in connection with the model-generating device 30, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, data backup storage systems, and the like.
It should be noted that although several units/modules or sub-units/modules of an electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present invention. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
Example 6
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the continuous casting process parameter determination method of embodiment 1 or embodiment 2.
More specifically, among others, readable storage media may be employed including, but not limited to: portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible embodiment, the invention can also be realized in the form of a program product comprising program code for causing a terminal device to carry out the steps of the method for determining the parameters of a continuous casting process of embodiment 1 or embodiment 2, when said program product is run on the terminal device.
Wherein the program code for carrying out the invention may be written in any combination of one or more programming languages, which program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on the remote device or entirely on the remote device.
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 method for determining parameters of a continuous casting process, the method comprising:
acquiring continuous casting process data; the continuous casting process data comprises a plurality of continuous casting process parameters;
calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine, and screening out a target process parameter from the continuous casting process data according to the correlation coefficient;
and circularly inputting the target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value.
2. The method for determining continuous casting process parameters according to claim 1, wherein the determination method is trained to obtain the evaluation model by the steps of:
acquiring historical process parameters and corresponding historical process evaluation scores;
taking the historical process parameters as input, taking the historical process evaluation scores as output to train a preset model, and generating the evaluation model; the preset model comprises at least one of a linear model, an LSTM network model and a random forest model.
3. The method of determining a continuous casting process parameter as claimed in claim 1, wherein the step of calculating a correlation coefficient between the continuous casting process parameter and a quality of a continuous casting machine comprises;
checking whether the continuous casting process parameters meet normal distribution;
when normal distribution is met, calculating a Pearson correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a card method test method aiming at the Pearson correlation coefficient;
and when the normal distribution is not met, calculating a Spearman correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting the card method test method aiming at the Spearman correlation coefficient.
4. The method of determining continuous casting process parameters according to claim 1, wherein the continuous casting process data includes a first process rule, and prior to the step of cycling the target process parameters into a pre-trained evaluation model, further comprising:
determining target process parameters and corresponding process evaluation scores which do not accord with the first process rule as invalid data;
generating a second process rule according to the invalid data;
the target process parameter is adjusted based on the first process rule and the second process rule.
5. A system for determining parameters of a continuous casting process, said system comprising:
the first acquisition module is used for acquiring continuous casting process data; the continuous casting process data comprises a plurality of continuous casting process parameters;
the screening module is used for calculating a correlation coefficient between the continuous casting process parameter and the quality of the continuous casting machine and screening target process parameters from the continuous casting process data according to the correlation coefficient;
and the adjusting module is used for circularly inputting the target process parameters into a pre-trained evaluation model until the process evaluation score is larger than a preset threshold value.
6. The continuous casting process parameter determination system of claim 5, wherein the determination system is trained to obtain the evaluation model by the following modules, comprising:
the second acquisition module is used for acquiring the historical process parameters and the corresponding historical process evaluation scores;
the input module is used for taking the historical process parameters as input, taking the historical process evaluation scores as output and training a preset model, and generating the evaluation model; the preset model comprises at least one of a linear model, an LSTM network model and a random forest model.
7. The continuous casting process parameter determination system of claim 5, wherein the screening module comprises:
the testing unit is used for testing whether the continuous casting process parameters meet normal distribution; when the normal distribution is satisfied, the first computing unit is called, and when the normal distribution is not satisfied, the second computing unit is called;
the first calculation unit is used for calculating a Pearson correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting a card method test method aiming at the Pearson correlation coefficient;
the second calculating unit is used for calculating a Spearman correlation coefficient of the continuous casting process parameter, and calculating the correlation coefficient by adopting the card method test method aiming at the Spearman correlation coefficient.
8. The continuous casting process parameter determination system of claim 5, wherein the continuous casting process data comprises a first process rule, the determination system further comprising:
a judging module, configured to judge that the target process parameter and the corresponding process evaluation score do not conform to the first process rule are invalid data;
the generation module is used for generating a second process rule according to the invalid data;
and the adjusting module is used for adjusting the target process parameters based on the first process rule and the second process rule.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory for execution on the processor, characterized in that the processor implements the method of determining the continuous casting process parameters according to any one of claims 1-4 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of determining a continuous casting process parameter according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310187762.6A CN116186936B (en) | 2023-03-01 | 2023-03-01 | Method, system, equipment and medium for determining continuous casting process parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310187762.6A CN116186936B (en) | 2023-03-01 | 2023-03-01 | Method, system, equipment and medium for determining continuous casting process parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116186936A true CN116186936A (en) | 2023-05-30 |
| CN116186936B CN116186936B (en) | 2024-03-22 |
Family
ID=86442132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310187762.6A Active CN116186936B (en) | 2023-03-01 | 2023-03-01 | Method, system, equipment and medium for determining continuous casting process parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116186936B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117055509A (en) * | 2023-09-25 | 2023-11-14 | 四川德润钢铁集团航达钢铁有限责任公司 | Method for predicting short-process steel process parameters based on artificial intelligence |
| CN117631627A (en) * | 2023-12-01 | 2024-03-01 | 邵东智能制造技术研究院有限公司 | Digital transformation method based on industrial Internet |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256260A (en) * | 2018-02-05 | 2018-07-06 | 北京科技大学 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
| CN109783898A (en) * | 2018-12-27 | 2019-05-21 | 广东工业大学 | A kind of intelligent optimization method of injection molding manufacturing technique parameter |
| CN110188331A (en) * | 2019-06-03 | 2019-08-30 | 腾讯科技（深圳）有限公司 | Model training method, conversational system evaluation method, device, equipment and storage medium |
| CN111651729A (en) * | 2020-06-02 | 2020-09-11 | 山东莱钢永锋钢铁有限公司 | Method for predicting blockage of secondary cooling water nozzle in continuous casting |
| CN112949970A (en) * | 2020-12-14 | 2021-06-11 | 邯郸钢铁集团有限责任公司 | Method for controlling quality of steel strip product in whole process and automatically judging grade |
| CN113640516A (en) * | 2021-08-16 | 2021-11-12 | 天津医科大学总医院 | Application of peripheral blood EPCs (Epiches sinensis) as life time prediction marker for old people |
| WO2022042401A1 (en) * | 2020-08-28 | 2022-03-03 | 北京字节跳动网络技术有限公司 | Multimedia content publishing method and apparatus, electronic device, and storage medium |
-
2023
- 2023-03-01 CN CN202310187762.6A patent/CN116186936B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256260A (en) * | 2018-02-05 | 2018-07-06 | 北京科技大学 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
| CN109783898A (en) * | 2018-12-27 | 2019-05-21 | 广东工业大学 | A kind of intelligent optimization method of injection molding manufacturing technique parameter |
| CN110188331A (en) * | 2019-06-03 | 2019-08-30 | 腾讯科技（深圳）有限公司 | Model training method, conversational system evaluation method, device, equipment and storage medium |
| CN111651729A (en) * | 2020-06-02 | 2020-09-11 | 山东莱钢永锋钢铁有限公司 | Method for predicting blockage of secondary cooling water nozzle in continuous casting |
| WO2022042401A1 (en) * | 2020-08-28 | 2022-03-03 | 北京字节跳动网络技术有限公司 | Multimedia content publishing method and apparatus, electronic device, and storage medium |
| CN112949970A (en) * | 2020-12-14 | 2021-06-11 | 邯郸钢铁集团有限责任公司 | Method for controlling quality of steel strip product in whole process and automatically judging grade |
| CN113640516A (en) * | 2021-08-16 | 2021-11-12 | 天津医科大学总医院 | Application of peripheral blood EPCs (Epiches sinensis) as life time prediction marker for old people |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117055509A (en) * | 2023-09-25 | 2023-11-14 | 四川德润钢铁集团航达钢铁有限责任公司 | Method for predicting short-process steel process parameters based on artificial intelligence |
| CN117055509B (en) * | 2023-09-25 | 2024-03-08 | 四川德润钢铁集团航达钢铁有限责任公司 | Method for predicting short-process steel process parameters based on artificial intelligence |
| CN117631627A (en) * | 2023-12-01 | 2024-03-01 | 邵东智能制造技术研究院有限公司 | Digital transformation method based on industrial Internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116186936B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116186936B (en) | Method, system, equipment and medium for determining continuous casting process parameters | |
| CN109086804B (en) | Hydraulic equipment early failure prediction method based on fusion of multi-source state monitoring information and reliability characteristics | |
| CN109544399B (en) | Power transmission equipment state evaluation method and device based on multi-source heterogeneous data | |
| Wang et al. | A hybrid prognostics approach for estimating remaining useful life of wind turbine bearings | |
| CN114757048B (en) | Health state assessment method, device, equipment and medium for fan foundation | |
| CN114721336B (en) | Information security event early warning method for technological parameters of instrument control system | |
| CN112418682B (en) | Safety evaluation method for fusion of multi-source information | |
| CN112270129A (en) | Plant growth prediction method based on big data analysis | |
| CN112598144A (en) | CNN-LSTM burst fault early warning method based on correlation analysis | |
| CN117389236A (en) | Propylene oxide production process optimization method and system | |
| CN115689114A (en) | Submarine cable running state prediction method based on combined neural network | |
| CN116227745A (en) | Big data-based research and analysis method and system for fishing vessels | |
| CN111445065A (en) | Energy consumption optimization method and system for refrigeration group control of data center | |
| CN111222968A (en) | Enterprise tax risk management and control method and system | |
| CN114139604A (en) | Online learning-based electric power industrial control attack monitoring method and device | |
| CN113313304A (en) | Power grid accident abnormity analysis method and system based on big data decision tree | |
| CN112734201A (en) | Multi-equipment overall quality evaluation method based on expected failure probability | |
| CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
| CN113673811B (en) | On-line learning performance evaluation method and device based on session | |
| CN113221108B (en) | Comprehensive evaluation method for industrial control system vulnerability scanning tool | |
| CN112966345B (en) | Rotary machine residual life prediction hybrid shrinkage method based on countertraining and transfer learning | |
| CN114971164A (en) | Sludge treatment equipment abnormity detection method and system based on artificial intelligence | |
| CN113392576A (en) | Staying balloon main cable tension state assessment early warning method | |
| CN117688480B (en) | Bridge damage identification method based on damage frequency panorama and random forest | |
| CN117592870B (en) | Comprehensive analysis system based on water environment monitoring information |
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 |