CN115081678A - Converter tapping weight pre-calculation method - Google Patents
Converter tapping weight pre-calculation method Download PDFInfo
- Publication number
- CN115081678A CN115081678A CN202210536047.4A CN202210536047A CN115081678A CN 115081678 A CN115081678 A CN 115081678A CN 202210536047 A CN202210536047 A CN 202210536047A CN 115081678 A CN115081678 A CN 115081678A
- Authority
- CN
- China
- Prior art keywords
- weight
- tapping
- alpha
- beta
- converter
- 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
- 238000010079 rubber tapping Methods 0.000 title claims abstract description 72
- 238000004364 calculation method Methods 0.000 title abstract description 7
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 51
- 229910052742 iron Inorganic materials 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000007774 longterm Effects 0.000 claims abstract description 17
- 238000009628 steelmaking Methods 0.000 claims abstract description 7
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 229910000831 Steel Inorganic materials 0.000 claims description 17
- 239000010959 steel Substances 0.000 claims description 17
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 235000008733 Citrus aurantifolia Nutrition 0.000 claims description 9
- 235000011941 Tilia x europaea Nutrition 0.000 claims description 9
- 239000004571 lime Substances 0.000 claims description 9
- 239000002699 waste material Substances 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 238000005303 weighing Methods 0.000 claims description 5
- 238000007664 blowing Methods 0.000 claims description 4
- 230000036284 oxygen consumption Effects 0.000 claims description 2
- 238000003723 Smelting Methods 0.000 description 6
- 229910045601 alloy Inorganic materials 0.000 description 4
- 239000000956 alloy Substances 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229910000604 Ferrochrome Inorganic materials 0.000 description 1
- 229910000519 Ferrosilicon Inorganic materials 0.000 description 1
- 229910000720 Silicomanganese Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- -1 silicomanganese Chemical compound 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- 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
-
- 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
- Y02P10/20—Recycling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Databases & Information Systems (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The invention relates to the technical field of converter steelmaking, and discloses a converter tapping weight pre-calculation method, which is used for determining influence factors of the converter tapping weight according to correlation analysis; establishing a prediction and regression model for the tapping weight of the converter; estimating the extreme influence quantity of each influence factor on the tapping quantity by combining the influence factor and the correlation of the molten iron tapping weight, and further setting alpha i And beta i The iterative search interval of (2); separately searching for alpha by using minimum variance method i And beta i Short-period iterative solution, medium-period iterative solution and long-period iterative solution; and pre-calculating the short-term predicted tapping weight value, the medium-term predicted tapping weight value and the long-term predicted tapping weight value according to the solving result, and determining a final converter tapping weight predicted value according to the predicted values and the confidence weights. Compared with the prior art, the utility modelThe method has better real-time working condition adaptability and higher converter tapping weight prediction precision.
Description
Technical Field
The invention relates to the technical field of converter steelmaking, in particular to a method for pre-calculating tapping weight of a converter.
Background
Converter steelmaking is currently the most common steelmaking method. After the smelting of the converter is finished, before tapping, a certain amount of steel ladle alloy and carbon powder, such as silicomanganese, high-carbon ferrochrome, carbon powder, ferrosilicon and the like, are sometimes required to be added to adjust the content of elements such as C, Si, Mn, Cr and the like in molten steel. Therefore, in order to improve the accuracy of the addition amounts of elements such as C, Si, Mn, and Cr, it is necessary to predict the converter tap weight as accurately as possible.
The traditional converter tapping weight calculation method is characterized by manual unchanged weight estimation, poor real-time working condition adaptability and low weight estimation precision. Because different steel grades have fixed standard ranges of the alloy element content percentage, if the total weight of the molten steel is not accurately estimated, the alloy element content percentage can not reach a target value or even exceed a limit range directly under the condition of adding a certain amount of alloy elements, and then a product is unqualified.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention provides a converter tapping weight pre-calculation method, which is used for establishing a dynamic converter tapping weight prediction model and better predicting the converter tapping weight under the premise of considering molten iron components and smelting process factors.
The technical scheme is as follows: the invention provides a method for pre-calculating tapping weight of a converter, which comprises the following steps:
step 1: determining influence factors of the tapping weight of the converter according to correlation analysis, wherein the influence factors comprise the weight of molten iron, the weight of scrap steel, the Mn content of the molten iron, the addition amount of lime and the oxygen consumption for converting;
step 2: establishing a prediction and regression model for tapping weight of a special furnace, wherein the model comprises the following steps:
in the formula, X Fe 、X Waste material 、X Mn 、X cao 、X o Respectively represents the weight of molten iron, the weight of scrap steel, the Mn content of molten iron, the addition amount of refined lime and the oxygen blowing amount in steelmaking, W pre For predicted tapping weight of converter, alpha i And beta i I is 1 to 5, each representing a coefficient of a related term;
and step 3: and (3) estimating the extreme influence quantity of each factor on the tapping quantity by combining the influence factors in the step (1) and the correlation of the tapping weight of the molten iron, and further setting alpha i And beta i The iterative search interval of (2);
and 4, step 4: separately searching for alpha by using minimum variance method i And beta i Short-period iterative solution of, alpha i And beta i Of the intermediate-period iterative solution alpha i And beta i Long-period iterative solution of (2);
and 5: and (4) according to the solving result in the step (4), precalculating the short-term predicted tapping weight value, the medium-term predicted tapping weight value and the long-term predicted tapping weight value, and determining a final converter tapping weight predicted value according to the short-term predicted value credit weight, the medium-term predicted value credit weight and the long-term predicted value credit weight.
Further, α in said step 3 i And beta i The iterative search interval of (a) is set to: alpha is alpha 1 ∈[0.88,0.99],β 1 ∈[0.7,1.0];α 2 ∈[0.70,0.99],β 2 ∈[0.7,1.0];α 3 ∈[1,20],β 3 ∈[0.5,1.5];α 4 ∈[1,20],β 4 ∈[0.5,1.5];α 5 ∈[1,30],β 5 ∈[0.5,1.5]。
Further, α in the step 4 i And beta i The short-period iterative solution adopts the production data of the last 40 heats for self-learning and searchingFinding out optimal parameters; alpha is alpha i And beta i The middle-period iterative solution carries out self-learning by adopting the production data of the latest 400 heats, and an optimal parameter is searched; alpha is alpha i And beta i The long-period iterative solution carries out self-learning by adopting the production data of the latest 4000 heats, and the optimal parameters are searched.
Further, self-learning, the specific operation of finding the optimal parameter is as follows:
let alpha i And beta i (i-1-5), each selecting a suitable step size, and iterating in a respective iteration search interval, so as to obtain α for each group of searched α i And beta i The value (i ═ 1 to 5) is known, and the coefficients equivalent to those of formula (2) are known, and in this case, the sum of the variances of the predicted weight and the actual weight can be obtained by formula (2), as shown in the following equation:
in the formula, W act-j Weighing the converter tapping weight of the jth sample; w pre-j The predicted weight for the jth sample, n-40 or 400 or 4000;
suppose alpha i And beta i Iterate in each range, there are n possible combinations, then according to equation (3), their corresponding Var values can be solved, and Var is set 1 、Var 2 ...Var n Solving for their minimum values according to equation (4):
Var min =Min(Var 1 、Var 2 …Var n ) (4)
easy to understand, Var min Corresponding alpha i And beta i The (i ═ 1-5) value is the optimum value for the short or medium or long term range.
Further, the short-term predicted value credit acquisition weight, the medium-term predicted value credit acquisition weight and the long-term predicted value credit acquisition weight are respectively 0.5, 0.3 and 0.2.
Has the advantages that:
1. the invention introduces a prediction model of tapping weight of a converter based on historical data collected on site. In actual production, after smelting of each furnace is finished, the actual production data of the furnace are put into a historical database, and relevant self-learning coefficients are updated in real time. Compared with the manual almost unchanged weight estimation experience, the dynamic converter tapping weight prediction model can better predict the converter tapping weight under the premise of considering molten iron components and smelting process factors, so that the dynamic converter tapping weight prediction model has better real-time working condition adaptability and higher converter tapping weight prediction accuracy.
2. Various working conditions self-learned in a short period of time better accord with the current actual working conditions, so the confidence collection weight is set to be larger. However, if short-term data is excessively collected, a large deviation may be caused in the prediction result with respect to short-term fluctuations in the quality of scrap, short-term fluctuations in the quality of lime, short-term fluctuations in the quality of molten iron, short-term fluctuations in instrumentation and weighing equipment, and the like, which may occur in a short term. Therefore, to maintain stability of the prediction accuracy, it is necessary to "neutralize" to some extent the adverse effects that may be brought about by the short-term self-learning data with the medium-term self-learning data and the long-term self-learning data. The method fully utilizes the high precision of short-term self-learning, and has better real-time working condition adaptability and higher converter tapping weight prediction precision in order to fully utilize medium-long term data to 'neutralize' abnormal fluctuation possibly existing in the short-term self-learning data.
Drawings
FIG. 1 is a flow chart of a converter tapping weight on-line real-time pre-calculation method of the invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention discloses an on-line real-time pre-calculation method for tapping weight of a converter, which mainly comprises the following steps:
determining influence factors of tapping weight of converter according to correlation analysis
Firstly, analyzing factors which may influence the tapping weight of the converter, including the weight of molten iron, the weight of scrap steel, the Si content of the molten iron, the Mn content of the molten iron, the P content of the molten iron, the S content of the molten iron, the oxygen blowing amount in the smelting process, the lime addition amount, the fixed oxygen value at the smelting end point and the like.
Respectively carrying out correlation test on the parameters and the actual tapping weight of the converter, wherein a correlation formula is shown as a formula (1),
wherein X is any one of the above-mentioned various influencing factors; y is the real tapping weight of the converter; n is the total number of samples; r is a correlation coefficient; i is a sample number;is the average of all samples X;the test results are shown in table 1 as the average of all samples Y.
TABLE 1 correlation statistics of various factors with tapping weight
Therefore, in the examples of the present invention, the factors that influence the tapping weight of the converter were determined to be the molten iron weight, the scrap weight, the Mn content of the molten iron, the lime addition amount, and the oxygen amount for blowing.
The invention establishes a model shown as formula (2) for predicting and regressing the tapping weight of a special furnace:
of the formula (X) Fe 、X Waste material 、X Mn 、X cao 、X o Respectively representing the weight of molten iron, the weight of scrap steel, the Mn content of the molten iron, the addition amount of refined lime and steelmaking blowingOxygen amount, W pre Is the predicted tapping weight of the converter. Alpha is alpha i And beta i (i-1-5) respectively represent coefficients of the correlation terms.
The size of the extreme influence quantity of each factor on the tapping quantity is estimated by combining the correlation of each influence factor and the tapping weight of molten iron, and the alpha is further calculated i And beta i The iterative search interval of (i-1-5) is set to: alpha 1 epsilon 0.88, 0.99],β1∈[0.7,1.0];α2∈[0.70,0.99],β2∈[0.7,1.0];α3∈[1,20],β3∈[0.5,1.5];α4∈[1,20],β4∈[0.5,1.5];α5∈[1,30],β5∈[0.5,1.5]。
Second, each coefficient α is performed below i And beta i And (i-1-5) carrying out short-term, medium-term and long-term regression iterative search and corresponding precalculation of tapping weight.
1)α i And beta i Short-period iterative solution and tapping prediction
Short term self-learning self-learns using production data of the last 40 heats (about 1 day production furnace times). Namely, the data of the last 40 heats of production is subjected to iterative loop, and the optimal parameters are searched. The specific search mode is as follows: let alpha i And beta i (i-1-5), each selecting a suitable step size, and iterating within the respective ranges mentioned above, respectively, then for each set of searched α i And beta i The value (i-1-5) is known as each coefficient equivalent to the formula (2), and in this case, the sum of the variances of the predicted weight and the actual weight of the 40 heats can be obtained by the formula (2), as shown in the following formula,
in the formula, W act-j Weighing the converter tapping weight of the jth sample; w pre-j The predicted weight for the jth sample.
Suppose alpha i And beta i (i-1-5) are iterated in the respective ranges, and if there are n possible combinations, then their corresponding Var values can be solved according to equation (3), and set as Var respectively 1 、Var 2 …Var n Solving for their minimum according to equation (4):
Var min =Min(Var 1 、Var 2 …Var n ) (4)
easy to understand, Var min Corresponding alpha i And beta i The (i ═ 1 to 5) value is the optimum value for the short term range. Respectively setting them as alpha i is short And beta i is short (i ═ 1-5), when the next steel is smelted, it can be determined by its X Fe 、X Waste of 、X Mn 、X cao 、X o Predicting the tapping weight of the steel, as shown in the formula (5):
in summary, α i is short And beta i is short (i-1-5) is the short-term iterative optimum of the corresponding term, W pre short And predicting the steel weight value for the short term solved correspondingly.
2)α i And beta i Intermediate period iterative solution and tapping prediction
Medium-term self-learning is performed by using the production data of the last 400 heats (the number of production furnaces of about 10 days), and the parameter optimization iteration method is the same as that of 2, except that the number of samples is changed from 40 of short-term iteration to 400 of medium-term iteration, and the optimal value of the corresponding coefficient is set as alpha in i And beta in i (i ═ 1-5), when the next steel is smelted, it can be determined by its X Fe 、X Waste material 、X Mn 、X cao 、X o The actual value of the steel is predicted, the tapping weight is expressed as the formula (6),
3)α i and beta i Long period iterative solution and tapping prediction
Long-term self-learning is performed by using production data of the latest 4000 heats (about 100 days of production furnace times), and parameters of the self-learning are optimizedThe iteration method is the same as 2, except that the number of samples is changed from 40 in the short-term iteration to 4000 in the long-term iteration, and the optimal value of the corresponding coefficient is set as alpha i length And beta i length (i ═ 1-5), when the next steel is smelted, it can be determined by its X Fe 、X Waste material 、X Mn 、X cao 、X o Predicting the tapping weight of the actual value of the steel, and displaying the actual value as shown in a formula (7),
third, comprehensive prediction of tapping weight of converter
From practical operation experience, various working conditions learned in a short-term self-learning mode are more consistent with the current practical working conditions, and therefore the confidence weight of the working conditions is larger. However, if short-term data is excessively collected, a large deviation may be caused in the prediction result with respect to short-term fluctuations in the quality of scrap, short-term fluctuations in the quality of lime, short-term fluctuations in the quality of molten iron, short-term fluctuations in instrumentation and weighing equipment, and the like, which may occur in a short term. Therefore, to maintain stability of the prediction accuracy, it is necessary to "neutralize" to some extent the adverse effects that may be brought about by the short-term self-learning data with the medium-term self-learning data and the long-term self-learning data.
In conclusion, in order to fully utilize the high precision of the short-term self-learning and fully utilize the medium-term and long-term data to 'neutralize' abnormal fluctuation possibly existing in the short-term self-learning data, the method determines to comprehensively adopt the short-term, medium-term and long-term self-learning data to predict the tapping weight of the converter. The invention finally sets the short-term predicted value credit collecting weight to be 0.5, the medium-term predicted value credit collecting weight to be 0.3 and the long-term predicted value credit collecting weight to be 0.2, and finally determines the predicted value of the tapping weight of the converter by adopting the following formula:
W pre =0.5W pre short +0.3*W pre Medium + 0.2W pre short (8)
The above embodiments are merely illustrative of the technical concepts and features of the present invention, and the purpose of the embodiments is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (5)
1. A method for pre-calculating the tapping weight of a converter is characterized by comprising the following steps:
step 1: determining influence factors of the tapping weight of the converter according to correlation analysis, wherein the influence factors comprise the weight of molten iron, the weight of scrap steel, the Mn content of the molten iron, the addition amount of lime and the oxygen consumption for converting;
step 2: establishing a prediction and regression model for the tapping weight of the converter, wherein the model comprises the following steps:
in the formula, X Fe 、X Waste material 、X Mn 、X cao 、X o Respectively represents the weight of molten iron, the weight of scrap steel, the Mn content of molten iron, the addition amount of refined lime and the oxygen blowing amount in steelmaking, W pre For predicted tapping weight of converter, alpha i And beta i I is 1 to 5, each representing a coefficient of a related term;
and step 3: and (3) estimating the extreme influence quantity of each influence factor on the tapping quantity by combining the influence factor in the step (1) and the correlation of the molten iron tapping weight, and further setting alpha i And beta i The iterative search interval of (2);
and 4, step 4: separately searching for alpha by using minimum variance method i And beta i Short-period iterative solution of, alpha i And beta i Of the intermediate-period iterative solution, alpha i And beta i Long-period iterative solution of (2);
and 5: and (4) according to the solving result in the step (4), precalculating the short-term predicted tapping weight value, the medium-term predicted tapping weight value and the long-term predicted tapping weight value, and determining a final converter tapping weight predicted value according to the short-term predicted value credit weight, the medium-term predicted value credit weight and the long-term predicted value credit weight.
2. The method for precalculating tapping weight of converter according to claim 1, wherein α is in step 3 i And beta i The iterative search interval of (a) is set to: alpha is alpha 1 ∈[0.88,0.99],β 1 ∈[0.7,1.0];α 2 ∈[0.70,0.99],β 2 ∈[0.7,1.0];α 3 ∈[1,20],β 3 ∈[0.5,1.5];α 4 ∈[1,20],β 4 ∈[0.5,1.5];α 5 ∈[1,30],β 5 ∈[0.5,1.5]。
3. The method for precalculating tapping weight of converter according to claim 1, wherein α in step 4 is i And beta i The short-period iterative solution adopts the production data of the latest 40 heats for self-learning, and the optimal parameters are searched; alpha is alpha i And beta i The middle-period iterative solution carries out self-learning by adopting the production data of the latest 400 heats, and an optimal parameter is searched; alpha is alpha i And beta i The long-period iterative solution adopts the production data of the latest 4000 heats for self-learning, and the optimal parameters are searched.
4. The method for precalculating tapping weight of a converter according to claim 3, wherein the concrete operations of self-learning and finding the optimal parameters are as follows:
let alpha i And beta i (i-1-5), each selecting a suitable step size, and iterating in a respective iteration search interval, so as to obtain α for each group of searched α i And beta i The value (i ═ 1 to 5) is known, and the coefficients equivalent to those of formula (2) are known, and in this case, the sum of the variances of the predicted weight and the actual weight can be obtained by formula (2), as shown in the following equation:
in the formula, W act-j Weighing the converter tapping weight of the jth sample; w pre-j For predicted weight of j sampleAmount, n ═ 40 or 400 or 4000;
suppose alpha i And beta i Iterate in each range, there are n possible combinations, then according to equation (3), their corresponding Var values can be solved, and Var is set 1 、Var 2 ...Var n Solving for their minimum values according to equation (4):
Var min =Min(Var 1 、Var 2 ...Var n ) (4)
easy to understand, Var min Corresponding alpha i And beta i The (i ═ 1-5) value is the optimum value for the short or medium or long term range.
5. The method of claim 1, wherein the short-term predicted value credit acquisition weight, the medium-term predicted value credit acquisition weight, and the long-term predicted value credit acquisition weight are respectively 0.5, 0.3, and 0.2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210536047.4A CN115081678A (en) | 2022-05-17 | 2022-05-17 | Converter tapping weight pre-calculation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210536047.4A CN115081678A (en) | 2022-05-17 | 2022-05-17 | Converter tapping weight pre-calculation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115081678A true CN115081678A (en) | 2022-09-20 |
Family
ID=83247111
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210536047.4A Pending CN115081678A (en) | 2022-05-17 | 2022-05-17 | Converter tapping weight pre-calculation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115081678A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103320559A (en) * | 2013-07-10 | 2013-09-25 | 鞍钢股份有限公司 | Blast furnace molten iron sulfur content forecasting method |
CN110551867A (en) * | 2018-06-01 | 2019-12-10 | 上海梅山钢铁股份有限公司 | Converter smelting control method based on slag component prediction |
CN113919206A (en) * | 2021-08-23 | 2022-01-11 | 南京钢铁股份有限公司 | Narrow composition control method for steelmaking alloying |
-
2022
- 2022-05-17 CN CN202210536047.4A patent/CN115081678A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103320559A (en) * | 2013-07-10 | 2013-09-25 | 鞍钢股份有限公司 | Blast furnace molten iron sulfur content forecasting method |
CN110551867A (en) * | 2018-06-01 | 2019-12-10 | 上海梅山钢铁股份有限公司 | Converter smelting control method based on slag component prediction |
CN113919206A (en) * | 2021-08-23 | 2022-01-11 | 南京钢铁股份有限公司 | Narrow composition control method for steelmaking alloying |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101845531B (en) | Converter smelting endpoint molten steel carbon and temperature control system and method thereof | |
CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
CN110991089B (en) | Method for forecasting carbon content in later stage of converter steelmaking | |
CN108342540B (en) | A kind of steel mill RH refining equipment automatic control system | |
CN113919206A (en) | Narrow composition control method for steelmaking alloying | |
CN106834593B (en) | A method of RH refining furnace decarbonization process data are determined with reference heats method | |
CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
CN101881981A (en) | Closed loop control system for temperature and components of RH (Rockwell Hardness) molten steel | |
CN110378064A (en) | A method of the prediction dead stock column temperature of blast furnace furnace core | |
CN116469481B (en) | LF refined molten steel composition forecasting method based on XGBoost algorithm | |
CN104726635A (en) | Optimum burden calculation method for electric furnace smelting | |
CN113192568A (en) | Refining furnace desulfurization terminal point forecasting method and system | |
Xin et al. | Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network | |
CN110930065A (en) | Casting blank quality determination method and system | |
CN115081678A (en) | Converter tapping weight pre-calculation method | |
CN110502781A (en) | A kind of ferroalloy production blending optimization method based on priori knowledge | |
CN111518980A (en) | Correction method and system for converter end point carbon content prediction model | |
CN115270397A (en) | Neural network vermicular graphite cast iron vermicular rate prediction method based on Tensorflow | |
You et al. | Compound control method of carbon content in argon–oxygen refining ferrochromium alloy | |
CN108830452B (en) | Method for representing holographic information of quality of steel product | |
CN117708708B (en) | Quality rating and recommending method for ferroalloy for steel making | |
CN112417639B (en) | Digital analysis method for structural evolution of hot-rolled low-carbon steel oxide scale | |
CN111383723B (en) | Blast furnace ironmaking component precontrolling method | |
CN117851816A (en) | Method for predicting steelmaking end point component of converter | |
CN114561509B (en) | Method for predicting carbon content of electric arc furnace end point |
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 |