CN116306272A - Converter heat loss rate prediction method based on big data - Google Patents
Converter heat loss rate prediction method based on big data Download PDFInfo
- Publication number
- CN116306272A CN116306272A CN202310200248.1A CN202310200248A CN116306272A CN 116306272 A CN116306272 A CN 116306272A CN 202310200248 A CN202310200248 A CN 202310200248A CN 116306272 A CN116306272 A CN 116306272A
- Authority
- CN
- China
- Prior art keywords
- loss rate
- heat loss
- data
- converter
- molten iron
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004519 manufacturing process Methods 0.000 claims abstract description 145
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 94
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 88
- 239000010959 steel Substances 0.000 claims abstract description 88
- 229910052742 iron Inorganic materials 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000009628 steelmaking Methods 0.000 claims abstract description 16
- DALUDRGQOYMVLD-UHFFFAOYSA-N iron manganese Chemical compound [Mn].[Fe] DALUDRGQOYMVLD-UHFFFAOYSA-N 0.000 claims abstract description 13
- QMQXDJATSGGYDR-UHFFFAOYSA-N methylidyneiron Chemical compound [C].[Fe] QMQXDJATSGGYDR-UHFFFAOYSA-N 0.000 claims abstract description 13
- DPTATFGPDCLUTF-UHFFFAOYSA-N phosphanylidyneiron Chemical compound [Fe]#P DPTATFGPDCLUTF-UHFFFAOYSA-N 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 28
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 25
- 229910052799 carbon Inorganic materials 0.000 claims description 25
- 239000002893 slag Substances 0.000 claims description 25
- 238000003723 Smelting Methods 0.000 claims description 13
- 239000007789 gas Substances 0.000 claims description 12
- 238000010079 rubber tapping Methods 0.000 claims description 12
- 230000036284 oxygen consumption Effects 0.000 claims description 11
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 claims description 10
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 229910052748 manganese Inorganic materials 0.000 claims description 10
- 239000011572 manganese Substances 0.000 claims description 10
- 229910052698 phosphorus Inorganic materials 0.000 claims description 10
- 239000011574 phosphorus Substances 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 10
- 239000000203 mixture Substances 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims description 6
- 229910052717 sulfur Inorganic materials 0.000 claims description 6
- 239000011593 sulfur Substances 0.000 claims description 6
- MBMLMWLHJBBADN-UHFFFAOYSA-N Ferrous sulfide Chemical compound [Fe]=S MBMLMWLHJBBADN-UHFFFAOYSA-N 0.000 claims description 5
- 102000005298 Iron-Sulfur Proteins Human genes 0.000 claims description 5
- 108010081409 Iron-Sulfur Proteins Proteins 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- XWHPIFXRKKHEKR-UHFFFAOYSA-N iron silicon Chemical compound [Si].[Fe] XWHPIFXRKKHEKR-UHFFFAOYSA-N 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000000463 material Substances 0.000 description 16
- 230000008569 process Effects 0.000 description 9
- 238000012795 verification Methods 0.000 description 6
- 230000003647 oxidation Effects 0.000 description 5
- 238000007254 oxidation reaction Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000007664 blowing Methods 0.000 description 3
- 239000002826 coolant Substances 0.000 description 3
- 239000000779 smoke Substances 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000011324 bead Substances 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 1
- 229910000805 Pig iron Inorganic materials 0.000 description 1
- 235000011941 Tilia x europaea Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 229910000514 dolomite Inorganic materials 0.000 description 1
- 239000010459 dolomite Substances 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004571 lime Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000012546 transfer 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]
- G06F30/20—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
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C5/00—Manufacture of carbon-steel, e.g. plain mild steel, medium carbon steel or cast steel or stainless steel
- C21C5/28—Manufacture of steel in the converter
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/2457—Query processing with adaptation to user needs
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C2300/00—Process aspects
- C21C2300/06—Modeling of the process, e.g. for control purposes; CII
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- 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
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Artificial Intelligence (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The invention relates to a converter heat loss rate prediction method based on big data, which is used for predicting the heat loss rate during converter steelmaking and comprises the following steps: s1, collecting current production data of a converter to be tested, wherein the current production data comprises the following steps: the molten iron temperature, the molten iron weight, the scrap steel weight, the molten iron carbon mass fraction, the molten iron manganese mass fraction and the molten iron phosphorus mass fraction; s2, inputting the current production data into a trained heat loss rate prediction model, and predicting the final heat loss rate of the converter event to be detected; the heat loss rate prediction model is a heat loss rate prediction model obtained by training a pre-constructed initial heat loss rate prediction model based on historical production data of the converter. The method has the beneficial effects of solving the technical problems of low calculation accuracy of the heat loss rate and large deviation from reality.
Description
Technical Field
The invention relates to the field of converter steelmaking, in particular to a converter heat loss rate prediction method based on big data.
Background
The converter steelmaking is a complex high-temperature physical and chemical process, which is a smelting process finished by taking molten iron, scrap steel, slag formers and the like as main raw materials and generating heat by physical heat of molten iron and chemical reaction among molten iron components without using external energy sources, and aims to obtain qualified molten steel temperature and components. In actual production, the temperature and the composition of molten iron are complex, and materials such as scrap steel, slag formers, coolants and the like need to be correspondingly changed to realize the control targets of the composition and the temperature of the molten steel, so that the accurate control of the addition amount of each material is important. The heat loss rate is an important parameter affecting the accuracy of material consumption prediction.
In the prior art, the heat loss rate of the converter is mainly determined by means of artificial experience and a mechanism model. The artificial experience is greatly dependent on the operation experience due to the influence of thinking inertia, has a limitation on the reaction capability and has high randomness. The mechanism model is relatively idealized, and because the parameter in the model cannot be obtained or accurately obtained under the field condition limitation, the model has lower precision, and the capability of coping with complex nonlinear and strong coupling relations of multivariable input and output in the converter production process is limited, so that the heat loss rate cannot be accurately given.
Disclosure of Invention
First, the technical problem to be solved
In view of the defects and shortcomings of the prior art, the invention provides a converter heat loss rate prediction method based on big data, which solves the technical problems of low calculation accuracy of the heat loss rate and large deviation from reality.
(II) technical scheme
In order to achieve the above purpose, the invention mainly provides a converter heat loss rate prediction method based on big data, which mainly comprises the following technical scheme:
s1, collecting current production data of a converter to be tested, wherein the current production data comprises the following steps: the molten iron temperature, the molten iron weight, the scrap steel weight, the molten iron carbon mass fraction, the molten iron manganese mass fraction and the molten iron phosphorus mass fraction;
s2, inputting the current production data into a trained heat loss rate prediction model, and predicting the final heat loss rate of the converter event to be detected;
the heat loss rate prediction model is a heat loss rate prediction model obtained by training a pre-constructed initial heat loss rate prediction model based on historical production data of the converter.
Optionally, after S2, the method further includes:
and adjusting the current production data based on the predicted heat loss rate until the predicted heat loss rate can meet the steel grade end point control target.
Optionally, the step S1 further includes: s0, training a pre-constructed initial heat loss rate prediction model based on historical production data of the converter to be tested to obtain a heat loss rate prediction model, wherein the method comprises the following steps of:
a1, collecting historical production data of the converter to be tested, wherein the historical production data is a set of complete production data of each single production of the converter to be tested;
a2, carrying out data preprocessing on the historical production data;
a3, calculating the heat loss rate corresponding to each single production of the converter based on the historical production data subjected to data preprocessing;
a4, judging characteristic data affecting the heat loss rate in the historical production data by means of a predefined correlation calculation formula;
and A5, screening the characteristic data of the historical production data, and inputting the characteristic data of each single production and the heat loss rate of the current production into a pre-constructed initial heat loss rate prediction model for training to obtain a heat loss rate prediction model.
Optionally, in step A1, the category of the complete production data of each single production includes:
smelting number, gun age, date of manufacture, steel code, heat interval time, molten iron weight, molten iron temperature, scrap weight, molten iron carbon mass fraction, molten iron silicon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, molten iron sulfur mass fraction, slag type and weight, furnace lining composition, target tapping temperature, target steel grade carbon mass fraction, target steel grade manganese mass fraction, target steel grade phosphorus mass fraction and/or target steel grade sulfur mass fraction.
Optionally, the A2 includes:
a21, cleaning the historical production data, and deleting invalid characteristic values:
the invalid characteristic value includes; smelting number, gun age, production date and steel code;
a22, carrying out outlier replacement on the cleaned historical production data;
the outlier includes: zero value, null value, discrete value.
Optionally, the a22 specifically is:
and replacing the abnormal value by taking an average value of the historical production data which is in the same category as the abnormal value in the historical production data as a replacement value.
Optionally, step A3 includes:
a31, calculating the slag quantity and components, total volume of furnace gas, oxygen consumption and/or molten steel quality of each single production of the converter based on the historical production data;
a32, calculating the heat income amount and the heat expenditure amount of the current production based on the slag amount and the components, the total volume of furnace gas, oxygen consumption and/or molten steel quality;
a33, the heat loss rate= (the heat incomes-the heat outgoing amount)/the heat incomes.
Optionally, in step A4, the predefined correlation calculation formula is:
n is the total heat in the historical production data, x i Is the actual value of the characteristic data, x is the mean value of the characteristic data, y i Is the actual value of the rate of heat loss,
is the average value of heat loss rate.
Optionally, in step A4, the characteristic data affecting the heat loss rate includes:
the method comprises the steps of heat interval time, molten iron temperature, molten iron weight, scrap steel weight, molten iron carbon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, target tapping temperature, end point molten steel volume, target steel grade carbon mass fraction, target steel grade manganese mass fraction and target steel grade phosphorus mass fraction.
Optionally, step A5 includes:
a51, screening and marking the historical production data to obtain the characteristic data of each single production and the label corresponding to the characteristic data;
a52, taking the characteristic data of each single production and the heat loss rate of the current production as sample data, and inputting the sample data into the initial heat loss rate prediction model; the sample data comprises a training set and a testing set; the test set is used for testing the heat loss rate prediction model;
a53, adjusting parameters of the initial heat loss rate prediction model;
a54, training the initial heat loss rate prediction model through the training set to obtain a heat loss rate prediction model.
Optionally, after S5, the method further includes:
s6, inputting the characteristic data of each single production in the test set into the heat loss rate prediction model to generate a predicted heat loss rate when the test set is produced;
calculating a determination coefficient and a root mean square error of the predicted heat loss rate of the current production based on the predicted heat loss rate of the current production and the heat loss rate of the same single production in the test set; testing the heat loss rate prediction model based on the decision coefficient and root mean square error;
determining coefficient R 2 The calculation formula is as follows:
the root mean square error RMSE calculation formula is as follows:
n is the total sample amount of the test set, f i For the predicted value of the model output, y i For the actual value of the characteristic data sample, y i Is the characteristic data sample mean value.
(III) beneficial effects
According to the converter heat loss rate prediction method based on big data, the heat loss rate is predicted by inputting the current production data of the converter to be detected into the trained heat loss rate prediction model, and further, the converter material consumption is judged according to the heat loss rate, the proper converter material proportion is determined, and the converter endpoint carbon temperature hit rate is improved. According to the method, the heat loss rate from the beginning to the end of the converter is predicted with higher precision before the converter steelmaking process begins, so that reasonable proportioning of materials is realized, the target steel endpoint carbon temperature hit rate is high, the quality qualification rate of steel tapping of the converter steelmaking is improved, the probability of returning to the converter is reduced, and the resource waste is reduced.
Drawings
FIG. 1 is a schematic flow chart of a converter heat loss rate prediction method based on big data according to an embodiment of the present invention;
FIG. 2 is a flow chart of calculating a heat loss rate according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of feature selection according to an embodiment of the present invention;
FIG. 4 is a line graph of predicted heat loss rate using a heat loss rate prediction model according to an embodiment of the present invention;
FIG. 5 is a line graph of predicted heat loss rate using a heat loss rate prediction model according to another embodiment of the present invention.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Converter steelmaking is a low-cost steelmaking mode, and the steelmaking process is completed in the converter by utilizing the physical heat of molten iron and chemical reaction between molten iron components to generate heat under the condition of no external energy source through molten iron, scrap steel and the like. Has the advantages of high production speed, high yield, high single furnace yield, low cost and less investment.
However, the converter steelmaking method can produce a large amount of steel, but has stricter requirements on pig iron components, and the proportion of materials such as scrap steel, slag formers, coolants and the like can often determine the components and the temperature of the produced molten steel, namely the target steel carbon temperature, and the molten steel can be tapped as the target steel when the target steel carbon temperature reaches the requirements. Therefore, during converter steelmaking, the accurate control of the addition amount of the added materials is important. In the converter blowing process, high-temperature slag and molten steel can transfer heat to the external space of the converter to cause heat loss, and the heat loss rate is the proportion of the heat loss to the heat income of the converter and is an important parameter affecting the material consumption prediction accuracy, therefore, the invention provides a converter heat loss rate prediction method based on big data, which is implemented in the embodiment shown in fig. 1:
s1, collecting current production data of a converter to be tested;
s2, inputting the current production data into a trained heat loss rate prediction model, and predicting the final heat loss rate of the converter event to be detected.
The heat loss rate prediction model is a heat loss rate prediction model obtained by training a pre-constructed initial heat loss rate prediction model based on historical production data of the converter.
In an embodiment, the current production data may include: the molten iron temperature, the molten iron weight, the scrap steel weight, the molten iron carbon mass fraction, the molten iron manganese mass fraction, the molten iron phosphorus mass fraction and the like;
in other embodiments, the method may further comprise:
and adjusting the current production data based on the predicted heat loss rate until the predicted heat loss rate can meet the steel grade end point control target.
Or, calculating the end point carbon temperature of converter steelmaking at the current production data based on the predicted heat loss rate; and adjusting the current production data based on the end point carbon temperature until the calculated end point carbon temperature meets the steel grade end point control target.
In an embodiment, before S1, training a pre-constructed initial heat loss rate prediction model based on the historical production data of the converter to be tested to obtain a heat loss rate prediction model, including:
a1, collecting historical production data of the converter to be tested, wherein the historical production data is a set of complete production data of each single production of the converter to be tested.
The collection of the complete production data can avoid the repeated collection of the data produced at the same time in the historical production data, and can ensure the authenticity of the data, the false data which is not kneaded or the finger derivatives given by the manual experience, and avoid the inaccuracy of the data samples.
In this embodiment, the types of the complete production data of each single production include:
smelting number, gun age, date of manufacture, steel code, heat interval time, molten iron weight, molten iron temperature, scrap weight, molten iron carbon mass fraction, molten iron silicon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, molten iron sulfur mass fraction, slag type and weight, furnace lining composition, target tapping temperature, target steel carbon mass fraction, target steel manganese mass fraction, target steel phosphorus mass fraction and/or target steel sulfur mass fraction, etc.
Of course, in actual production, the types of the complete production data can be added and deleted in a small range according to the actual production.
Further, after the historical production data of the converter to be detected is collected, the problems of data deviation caused by misoperation, equipment failure or other reasons of field data collection personnel may exist, and abnormal data with null values, zero values and larger discrete degrees exists in the data of part of the heat. The missing value can reduce the sample information, the excessive abnormal value can cause deviation of the model prediction result, and the repeated value can cause the variance of the data to be reduced and the distribution to be changed, so that the step A2 can be implemented:
and carrying out data preprocessing on the historical production data, and adopting a deletion method, a substitution method, an interpolation method and the like to process the missing values, the repeated values and the abnormal values.
For example, in one embodiment the A2 implementation steps include:
a21, cleaning the historical production data, and deleting invalid characteristic values:
the invalid characteristic value may include; characteristics of no relation to heat loss rate such as smelting number, gun age, production date, steel code and the like;
a22, carrying out outlier replacement on the cleaned historical production data;
the outlier includes: zero value, null value, discrete value.
Specifically, the a22 may replace the abnormal value by using, as a replacement value, an average value of the historical production data of the same category as the abnormal value in the historical production data.
For example, in one embodiment, the characteristics of the greater relationship between the heat loss rate and the contents of the molten iron weight, the scrap steel weight, the molten iron temperature, the molten iron carbon mass fraction, the molten iron manganese mass fraction, the molten iron phosphorus mass fraction, the molten iron sulfur mass fraction, and the like are replaced by the average value.
Further, step A3 is implemented, and the heat loss rate corresponding to each single production of the converter is calculated based on the historical production data subjected to data preprocessing.
In some embodiments, this step may also be referred to as modeling the mechanism by which the converter to be tested makes the converter steelmaking.
The method can be implemented as follows;
a31, calculating the slag quantity and the composition, the total volume of furnace gas, the oxygen consumption and/or the molten steel quality of each single production of the converter based on the historical production data.
A32, calculating the heat income amount and the heat expenditure amount of the current production based on the slag amount and the components, the total volume of furnace gas, the oxygen consumption amount and/or the molten steel quality.
A33, the heat loss rate= (the heat incomes-the heat outgoing amount)/the heat incomes.
In the embodiment shown in fig. 2, calculating the heat loss rate includes:
b1, calculating the slag amount and the components:
the slag amount and the composition are determined by calculating the oxidation product amount of elements in the molten iron and the scrap steel, the added slag former and the product amount of furnace lining erosion.
B2, calculating total volume of furnace gas:
the total volume of the furnace gas is the sum of the current furnace gas volume, the free oxygen volume in the furnace gas and the nitrogen volume in the furnace gas.
B3, calculating oxygen consumption:
and determining oxygen consumption of each element, and calculating the total oxygen consumption by using the oxygen consumption of each element and the oxygen content of the final steel.
And B4, calculating the mass of molten steel:
and each loss of molten iron in blowing is calculated, and the quality of molten steel can be calculated preliminarily.
Wherein each loss may include; element oxidation loss, smoke loss, amount of iron beads in slag and/or amount of splash iron loss.
B5, calculating heat income based on the oxygen consumption:
the heat income comprises the physical heat of molten iron, the heat release of element oxidation in molten iron and scrap steel, the heat release of slag formation, the heat release of smoke oxidation and the heat release of carbon oxidation in furnace lining.
B6, calculating heat expenditure:
the heat expenditure comprises molten steel physical heat, slag physical heat, decomposition heat of a slag former, smoke physical heat, furnace gas physical heat, iron bead physical heat in slag, splash metal physical heat, heat loss in the blowing process and the like. The invention calculates other heat of heat removal loss first.
Further, B7 is performed to calculate the heat loss rate:
the heat loss rate= (the heat incomes-the heat expenditure amount)/the heat incomes.
Based on the step of calculating the heat loss rate, the heat loss rate corresponding to the complete production data for each single production is calculated. The complete production data for each single production and its corresponding heat loss rate are taken as a sample of data. In practical applications, as many complete production data as possible should be collected for a sufficient number of productions and the corresponding heat loss rate calculated to avoid overfitting during model training.
For example, in one embodiment, complete data for more than thousand runs is collected.
Further, step A4 is implemented, and feature data affecting the heat loss rate in the historical production data is judged by means of a predefined correlation calculation formula.
In this embodiment, a pearson correlation coefficient method is selected for judgment and selection, and the predefined correlation calculation formula is as follows:
n is the total heat of the historical production data, x i Is the actual value of the characteristic data and,
is the mean value of the characteristic data, y i Is the actual value of the heat loss rate, +.>
Is the average value of heat loss rate.
By carrying out correlation screening on various feature data of the historical production data, a feature group with strong interpretation power on the target variable can be selected from all features, namely, features with larger correlation with the heat loss rate are selected from all features, so that the model training effect is better, and the accuracy of predicting the heat loss rate is high.
In other embodiments, other correlation calculations may be selected for calculation, and are not intended to be limiting.
As in the embodiment of fig. 3, all features include at least: the heat interval time, the weight of molten iron, the temperature of molten iron, the quantity of scrap steel, the type and weight of slag, the mass fraction of carbon in molten iron, the mass fraction of silicon in molten iron, the mass fraction of manganese in molten iron, the mass fraction of phosphorus in molten iron, the mass fraction of sulfur in molten iron, the target tapping temperature, the target tapping quantity, the mass fraction of carbon in target steel grade, the mass fraction of manganese in target steel grade, the mass fraction of phosphorus in target steel grade and/or the mass fraction of sulfur in target steel grade, and the like. Through the correlation screening, the selected relevant characteristic types comprise: the steel-making process comprises the steps of heat interval time, molten iron temperature, molten iron weight, scrap steel weight, molten iron carbon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, target tapping temperature, end-point molten steel volume, target steel grade carbon mass fraction, target steel grade manganese mass fraction, target steel grade phosphorus mass fraction and the like.
Further, step A5 is implemented, the historical production data are screened according to the related characteristic types, the related characteristic data in each single production data are reserved, the characteristic data of each single production and the heat loss rate of the current production are input into a pre-built initial heat loss rate prediction model for training, and the obtained heat loss rate prediction model is obtained.
In practice, a heat loss rate prediction model is established based on big data, and at least two models should be established for comparison, including but not limited to: XGBoost, lightGBM, random forests, etc., prevent the deviation of the generated heat loss rate prediction model.
Specifically, in an embodiment, the initial heat loss rate prediction model is a LightGBM heat loss rate prediction model (Light Gradient Boosting Machine, a lightweight framework implementing GBDT algorithm), and in step A5, the method may include:
a51, screening and marking the historical production data to obtain the characteristic data of each single production and the label corresponding to the characteristic data; the method comprises the following steps:
looking at the new DataFrame using data.head (), ensuring that features and tags are within specified ranges; using data.dropna () to ensure that there is no NaN value in the data; looking at data types and data amounts using df.info (), it may be necessary to convert the data types as needed; the minimum, maximum, mean, median, standard deviation, and quartile range for each column can be known using df.
A52, taking the characteristic data of each single production and the heat loss rate of the current production as sample data, and inputting the sample data into the LightGBM heat loss rate prediction model; dividing the sample data into a training set and a testing set; the test set is used for testing the heat loss rate prediction model.
In one embodiment, the sample data is split using the train_test_split function of Scikit-learn.
A53, adjusting parameters of the initial heat loss rate prediction model;
a54, training the initial heat loss rate prediction model through the training set to obtain a heat loss rate prediction model.
Further, in some embodiments, step S6 is also implemented, inputting the feature data of each single production in the test set to the heat loss rate prediction model, generating a predicted heat loss rate when produced;
and calculating a determination coefficient and a root mean square error of the predicted heat loss rate of the current production based on the predicted heat loss rate of the current production and the heat loss rate of the same single production in the test set.
And testing the heat loss rate prediction model based on the decision coefficient and the root mean square error, and judging the effectiveness of the heat loss rate prediction model.
Determining coefficient (R) 2 ) Representing the fitting degree of the model; root Mean Square Error (RMSE), also known as standard error, is used as a measure of machine learning model predictionsThe root mean square error is the arithmetic square root of the mean square error, and the reason for introducing the root mean square error and the standard deviation is completely consistent, namely, the dimension of the mean square error is different from the dimension of the data, and the degree of dispersion cannot be intuitively reflected, so that the root mean square error is obtained by dividing the square root on the mean square error.
Determining coefficient R 2 The calculation formula is as follows:
the root mean square error RMSE calculation formula is as follows:
n is the total quantity of characteristic data samples of the test set, f i For the predicted value of the model output, y i For the actual values of the feature data samples,
is the characteristic data sample mean value.
According to the converter heat loss rate prediction method based on big data provided by the embodiments, the heat loss rate is predicted by inputting the current production data of the converter to be detected into the trained heat loss rate prediction model, and further, the converter material consumption is judged according to the heat loss rate, the proper converter material proportion is determined, and the converter endpoint carbon temperature hit rate is improved. According to the method, the heat loss rate from the beginning to the end of the converter is predicted with higher precision before the converter steelmaking process begins, so that reasonable proportioning of materials is realized, the target steel endpoint carbon temperature hit rate is high, the quality qualification rate of steel tapping of the converter steelmaking is improved, the probability of returning to the converter is reduced, and the resource waste is reduced.
The model prediction deviation caused by data repetition or errors in training samples is avoided by collecting complete production data, all the features are subjected to relevant screening, the generalization capability is stronger, excessive features and excessive fitting can be avoided, the calculation complexity and the training difficulty are reduced, and the model precision is increased.
And testing the model through the determination coefficient and the root mean square error to determine the accuracy of the model.
In order to better explain the technical solution proposed by the present invention, a more specific embodiment will be used for explanation.
Example 1
The converter to be measured is a 150t converter of a steelworks.
First, a heat loss rate prediction model of the converter is established.
Step A1 is carried out, historical production data of the 150t converter is collected, the data are field actual data recorded by a steel mill, incomplete data are removed through preliminary screening, the production data of 1938 heats are collected as historical production data, and the data are of the type (also called as data characteristics): smelting number, gun age, production date, steel code, heat interval time, molten iron weight, molten iron temperature, scrap weight, molten iron carbon mass fraction, molten iron silicon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, molten iron sulfur mass fraction, slag type and weight, furnace lining composition, target tapping temperature, target steel carbon mass fraction, target steel manganese mass fraction, target steel phosphorus mass fraction, target steel sulfur mass fraction.
Wherein the slag material comprises lime, dolomite, etc.
And (3) further performing step A2, and preprocessing the collected historical data. Features that are not related to heat loss rate are deleted, for example: smelting number, gun age, production date, steel code and the like; according to the rule of data cleaning, deleting the invalid characteristic values, wherein the deleting method adopts whole-column characteristic deletion; and processing abnormal data with null value, zero value and larger discrete degree by adopting a substitution method.
Further, step A3 is carried out, and the corresponding heat loss rate of each single production is calculated.
And (3) performing feature selection in the step A4 based on the heat loss rate and the historical production data, and judging feature data with great influence on the heat loss rate of the converter, namely related feature data.
In this embodiment, the model input variables are finally determined: the method comprises the steps of heat interval time, molten iron temperature, molten iron weight, scrap steel weight, molten iron carbon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, target tapping temperature, end point molten steel volume, target steel grade carbon mass fraction, target steel grade manganese mass fraction and target steel grade phosphorus mass fraction. Screening the related characteristic data of the 1938 heat, and dividing the related characteristic data into a training set and a testing set, wherein the ratio is 7:3; in this embodiment, a total of 1938 heats are selected as sample data, 1357 sets of data are randomly selected as training sets, and 581 sets of data are selected as test sets.
In this embodiment, 10% of the data in the training set may also be selected as the validation set.
Inputting the characteristic data into a pre-constructed initial heat loss rate prediction model for training, wherein the super-parameter tuning specifically comprises the following steps: the objective: the type of the model application, defining the parameter value as 'regression'; num_leave: the number of leaf nodes of the tree, defined num_leave=16; max_depth: the maximum depth of the tree, which may control the overfit, defines max_depth=7; learning_rate: learning rate, defining learning_rate=0.01; feature_fraction: the proportion of the feature is selected for each iteration during training of the LightGBM model, and the proportion represents that all the features are selected for each iteration; min_data_in_leaf: the minimum number of samples in a leaf node is typically used to process the fit, defining min_data_in_leaf=5.
Further, in order to realize accurate learning prediction capability of the model on training data in the learning process and good prediction capability on new data, the embodiment performs step A6 to select a decision coefficient (R 2 ) And Root Mean Square Error (RMSE) assessment model. Table 1 shows the evaluation index of the 150t converter LightGBM heat loss rate prediction model.
Table 1:
as can be seen from Table 1, the predicted hit rate of the heat loss rate was 91% within the error range of.+ -. 0.02.
As shown in fig. 4, fig. 4 is a graph of a comparison of predicted heat loss rate and actual heat loss rate of the 150t converter.
Further, in this embodiment, a verification set is further provided, 136 sets of data in the sample data are randomly selected as the verification set, and the verification set is used for calculating the hit rate of carbon temperature based on a metallurgical principle, and the hit rate reaches 93% when the target carbon content is calculated to be within +/-0.02%; the final temperature is within the range of +/-15 ℃ of the target temperature, and the hit rate can reach 92%.
Example 2
In this example a converter of a steelworks 220 t.
In this embodiment, the collected historical production data is 1780 heats, where the ratio of the divided training set to the test set is: 7:3, 10% from the training set was selected as the validation set. In this embodiment, a total 1780 heat is selected as the sample data, 1246 sets of data are randomly selected as the training set, 534 sets of data are the test set, and 178 sets of data are the verification set. Table 2 shows the evaluation index of the 220t converter LightGBM heat loss rate prediction model.
Table 2:
specifically, as shown in table 2, the heat loss rate is within ±0.02, and the hit rate can reach 93%.
As shown in fig. 5, fig. 5 is a graph of a comparison of predicted heat loss rate and actual heat loss rate of the 220t converter.
Further, 178 groups of data in the sample data are randomly selected as verification sets, and the target carbon content of the end point carbon of the fusion model converter is within +/-0.02% through trial calculation, so that the hit rate reaches 95%; the final temperature is within the range of +/-15 ℃ of the target temperature, and the hit rate can reach 93%.
R of LightGBM heat loss rate prediction model in the embodiment of the invention 2 Reaches more than 0.85 and has lower RMSE; the fitting effect of the predicted value to the actual value accords with the expectation, and the heat lossThe hit rate is more than 90% within the range of +/-0.02, so that the predicted value of the LightGBM heat loss rate prediction model is very close to the actual value.
According to the converter heat loss rate prediction method based on big data, a mechanism model for calculating the heat loss rate is established according to material balance and heat balance, and a converter heat loss rate prediction model is established based on the big data of converter smelting. The obtained prediction model can directly calculate the heat loss rate in the smelting process in the complex physicochemical reaction process of the converter smelting, thereby ensuring the addition amount of the slag former, the coolant and the carburant in the converter smelting process. Through verification, the converter heat loss rate prediction model can accurately predict the heat loss rate in the converter process, so that the carbon temperature hit rate of the converter endpoint is improved.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium; may be a communication between two elements or an interaction between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the description of the present specification, the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., refer to particular features, structures, materials, or characteristics described in connection with the embodiment or example as being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that alterations, modifications, substitutions and variations may be made in the above embodiments by those skilled in the art within the scope of the invention.
Claims (10)
1. A converter heat loss rate prediction method based on big data for predicting a heat loss rate at the time of converter steelmaking, comprising:
s1, collecting current production data of a converter to be tested, wherein the current production data comprises the following steps: the molten iron temperature, the molten iron weight, the scrap steel weight, the molten iron carbon mass fraction, the molten iron manganese mass fraction and the molten iron phosphorus mass fraction;
s2, inputting the current production data into a trained heat loss rate prediction model, and predicting the final heat loss rate of the converter event to be detected;
the heat loss rate prediction model is a heat loss rate prediction model obtained by training an initial heat loss rate prediction model based on historical production data of the converter.
2. The converter heat loss rate prediction method according to claim 1, further comprising, after S2:
and adjusting the current production data based on the predicted heat loss rate until the predicted heat loss rate can meet the steel grade end point control target.
3. The converter heat loss rate prediction method according to claim 1, further comprising, prior to S1:
s0, training a pre-constructed initial heat loss rate prediction model based on historical production data of the converter to be tested to obtain a heat loss rate prediction model, wherein the method comprises the following steps of:
a1, collecting historical production data of the converter to be tested, wherein the historical production data is a set of complete production data of each single production of the converter to be tested;
a2, carrying out data preprocessing on the historical production data;
a3, calculating the heat loss rate corresponding to each single production of the converter based on the historical production data subjected to data preprocessing;
a4, judging characteristic data affecting the heat loss rate in the historical production data by means of a predefined correlation calculation formula;
and A5, screening the characteristic data of the historical production data, and inputting the characteristic data of each single production and the heat loss rate of the current production into a pre-constructed initial heat loss rate prediction model for training to obtain a heat loss rate prediction model.
4. A converter heat loss rate prediction method according to claim 3, wherein in step A1, the category of the complete production data for each single production includes:
smelting number, gun age, date of manufacture, steel code, heat interval time, molten iron weight, molten iron temperature, scrap weight, molten iron carbon mass fraction, molten iron silicon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, molten iron sulfur mass fraction, slag type and weight, furnace lining composition, target tapping temperature, target steel grade carbon mass fraction, target steel grade manganese mass fraction, target steel grade phosphorus mass fraction and/or target steel grade sulfur mass fraction.
5. The converter heat loss rate prediction method according to claim 4, wherein the A2 includes:
a21, cleaning the historical production data, and deleting invalid characteristic values:
the invalid characteristic value includes; smelting number, gun age, production date and steel code;
a22, carrying out outlier replacement on the cleaned historical production data;
the outlier includes: zero value, null value, discrete value.
6. The converter heat loss rate prediction method according to claim 5, wherein the a22 specifically comprises:
and replacing the abnormal value by taking an average value of the historical production data which is in the same category as the abnormal value in the historical production data as a replacement value.
7. A converter heat loss rate prediction method according to claim 3, wherein step A3 comprises:
a31, calculating the slag quantity and components, total volume of furnace gas, oxygen consumption and/or molten steel quality of each single production of the converter based on the historical production data;
a32, calculating the heat income amount and the heat expenditure amount of the current production based on the slag amount and the components, the total volume of furnace gas, oxygen consumption and/or molten steel quality;
a33, the heat loss rate= (the heat incomes-the heat outgoing amount)/the heat incomes.
8. A converter heat loss rate prediction method according to claim 3, wherein in step A4, the predefined correlation calculation formula is:
n is the total heat of the historical production data, x i Is the actual value of the characteristic data and,
is the mean value of the characteristic data, y i Is the actual value of the heat loss rate, +.>
Is the average value of heat loss rate.
The characteristic data affecting the heat loss rate includes:
the method comprises the steps of heat interval time, molten iron temperature, molten iron weight, scrap steel weight, molten iron carbon mass fraction, molten iron manganese mass fraction, molten iron phosphorus mass fraction, target tapping temperature, end point molten steel volume, target steel grade carbon mass fraction, target steel grade manganese mass fraction and target steel grade phosphorus mass fraction.
9. The converter heat loss rate prediction method according to claim 8, wherein step A5 includes:
a51, screening and marking the historical production data to obtain the characteristic data of each single production and the label corresponding to the characteristic data;
a52, taking the characteristic data of each single production and the heat loss rate of the current production as sample data, and inputting the sample data into the initial heat loss rate prediction model; the sample data comprises a training set and a testing set; the test set is used for testing the heat loss rate prediction model;
a53, adjusting parameters of the initial heat loss rate prediction model;
a54, training the initial heat loss rate prediction model through the training set to obtain a heat loss rate prediction model.
10. The converter heat loss rate prediction method according to claim 9, further comprising, after S5:
s6, inputting the characteristic data of each single production in the test set into the heat loss rate prediction model to generate a predicted heat loss rate when the test set is produced;
calculating a determination coefficient and a root mean square error of the predicted heat loss rate of the current production based on the predicted heat loss rate of the current production and the heat loss rate of the same single production in the test set; testing the heat loss rate prediction model based on the decision coefficient and root mean square error;
determining coefficient R 2 The calculation formula is as follows:
the root mean square error RMSE calculation formula is as follows:
n is the total sample amount of the test set, f i For the predicted value of the model output, y i For the actual values of the feature data samples,
is the characteristic data sample mean value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200248.1A CN116306272A (en) | 2023-03-03 | 2023-03-03 | Converter heat loss rate prediction method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200248.1A CN116306272A (en) | 2023-03-03 | 2023-03-03 | Converter heat loss rate prediction method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116306272A true CN116306272A (en) | 2023-06-23 |
Family
ID=86786361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310200248.1A Pending CN116306272A (en) | 2023-03-03 | 2023-03-03 | Converter heat loss rate prediction method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116306272A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117553921A (en) * | 2024-01-12 | 2024-02-13 | 山东钢铁股份有限公司 | Converter molten steel temperature prediction method, system, terminal and storage medium |
-
2023
- 2023-03-03 CN CN202310200248.1A patent/CN116306272A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117553921A (en) * | 2024-01-12 | 2024-02-13 | 山东钢铁股份有限公司 | Converter molten steel temperature prediction method, system, terminal and storage medium |
| CN117553921B (en) * | 2024-01-12 | 2024-04-19 | 山东钢铁股份有限公司 | Converter molten steel temperature prediction method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108676955B (en) | A kind of BOF Steelmaking Endpoint carbon content and temprature control method | |
| CN105925750A (en) | Steelmaking end point prediction method based on neural networks | |
| Chen et al. | Energy consumption modelling using deep learning technique—a case study of EAF | |
| Cox et al. | Application of neural computing in basic oxygen steelmaking | |
| Liu et al. | A dynamic analytics method based on multistage modeling for a BOF steelmaking process | |
| CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
| CN111651931A (en) | Blast furnace fault diagnosis rule derivation method based on deep neural network | |
| CN116306272A (en) | Converter heat loss rate prediction method based on big data | |
| CN113239482A (en) | Dynamic prediction method and device for converter post-blowing carbon content | |
| CN113962050A (en) | Oxygen scheduling calculation method combining production consumption prediction and pipe network calculation | |
| Sala et al. | Multivariate time series for data-driven endpoint prediction in the basic oxygen furnace | |
| KR20170094560A (en) | Method and device for predicting, controlling and/or regulating steelworks processes | |
| CN112036081A (en) | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction | |
| CN117612651A (en) | Method for predicting manganese content of converter endpoint | |
| Shi et al. | Key issues and progress of industrial big data-based intelligent blast furnace ironmaking technology | |
| CN1403594A (en) | Intelligent blast furnace smelt controlling system | |
| JP2005036289A (en) | Model parameter decision method and program therefor, and model prediction method and program therefor | |
| Takalo-Mattila et al. | Explainable Steel Quality Prediction System Based on Gradient Boosting Decision Trees | |
| Alshawarghi et al. | Predictive models and detection methods applicable in water detection framework for industrial electric arc furnaces | |
| Wang et al. | An integrated CBR model for predicting endpoint temperature of molten steel in AOD | |
| Zhang | Optimal control problem of converter steelmaking production process based on operation optimization method | |
| CN115456264B (en) | Endpoint carbon content and endpoint temperature prediction method for small and medium-sized converter | |
| CN116384254A (en) | Error correction method and system for predicting molten steel temperature of LF refining furnace | |
| KR100328937B1 (en) | Method for predicting blowing of converter using neural network | |
| CN114217592A (en) | Control system and method for copper top-blowing production process |
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 |