A method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis

Abstract

The present invention discloses a method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis. The iron-containing raw materials are divided into an iron portion, a slag portion, a rust portion, and a coating portion. The following are calculated in sequence: the weight of the iron portion entering the dust removal ash along with the smoke, the weight of the oxidized iron portion, the weight of the Fe contained in the converter slag formed after the Si element in the iron portion is oxidized, the weight of the Fe carried into the converter by the slag portion, the weight of the Fe contained in the converter slag formed by the SiO2 in the slag portion, and the weight of the Fe carried into the converter by the rust portion, thereby characterizing the yield of the iron-containing raw materials. The present invention is conducive to guiding the preferential selection of materials and the formulation of standard technical and economic indicators in production. It can also be used for preferential purchasing plans based on cost-effectiveness, ultimately reducing production costs and improving economic benefits for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of converter smelting, and in particular to a method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis. Background Art

[0002] During the converter smelting process, the yield of incoming ferrous raw materials must be calculated. This is used to optimize material selection from a cost-effectiveness perspective and objectively evaluate technical and economic indicators. This impacts steelmaking cost control and also influences scrap allocation and procurement. The ferrous raw material yield is the ratio of the molten steel produced in a batch of converter steel to the total ferrous raw materials used to produce that batch of steel.

[0003] In the existing technology, a certain material is usually added in a fixed amount, and the yield of other materials is fixed, and the measurement is performed with a limited number of samples. However, the measurement of the yield is limited by the influence of operations such as splashing and slag retention, or the data is difficult to obtain, and whether the yield of other materials is reasonable is still questionable. The yield fluctuates greatly, resulting in data distortion and affecting judgment, which is not conducive to large-scale production guided by cost control and the formation of standard yield indicators.

[0004] In addition, in the existing technology, the water output rate is usually used as an important indicator of the purchase price, and the impact of the converter slag and dust ash in the converter smelting process on the yield of the material is not taken into account. At the same time, the trial results are used to evaluate and decide whether to purchase. The long cycle is not conducive to quickly, timely and accurately seizing market opportunities. Summary of the Invention

[0005] In response to the shortcomings in the existing technology, the present invention provides a method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis, which can reflect the metal recovery of iron-containing raw materials in converter smelting, and is helpful for procurement pricing and optimal matching.

[0006] The present invention achieves the above technical objectives through the following technical means.

[0007] A method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis:

[0008] (1) The iron-containing raw material is assumed to consist of four parts: iron part, slag part, rust part and coating part, and the weight proportions are recorded as Y1, Y2, Y3 and Y4 respectively, where Y1 = 100% - Y2 - Y3 - Y4;

[0009] The C, Si, Mn, P, and S element contents of the iron part were detected and recorded as X1, X2, X3, X4, and X5 respectively;

[0010] The SiO2 and TFe contents in the slag were detected and recorded as X6 and X7 respectively;

[0011] The rust part is composed of Fe2O3 and crystal water, with Fe2O3 accounting for 90%, denoted as X8;

[0012] The coating is completely burned;

[0013] (2) The output of converter smelting consists of three parts: molten steel, converter slag and dust ash, of which the dust ash is generally 0.66% of the weight of the iron part, recorded as Z1;

[0014] Detect the content of C, Si, Mn, P, and S elements in molten steel, which are recorded as X9, X10, X11, X12, and X13 respectively;

[0015] Detect the SiO2 and TFe contents in converter slag and record them as X14 and X15 respectively;

[0016] Detect the SiO2 and TFe contents in the dust removal ash and record them as X16 and X17 respectively;

[0017] (3) The weight of the iron-containing raw materials entering the converter and participating in the production smelting is recorded as N3;

[0018] The weight of the iron part that enters the dust removal ash along with the smoke is N3*Z1*X17, recorded as M1;

[0019] The oxidized iron element is (N3*Y1-M1)*(X1+X2+X3+X4+X5-X9-X10-X11-X12-X13), and the weight of this part is recorded as M2;

[0020] The Si element in the iron part is oxidized to form converter slag, which contains Fe. The weight of this part is Denoted as M3;

[0021] The Fe carried into the converter by the slag is N3*Y2*X7, and the weight of this part is recorded as M4;

[0022] The SiO2 in the slag forms converter slag in the converter, which contains Fe. The weight of this part is Recorded as M5;

[0023] The Fe brought into the converter by the rust is The weight of this part is recorded as M6;

[0024] Finally, the iron-containing raw material yield is expressed as: (N3*Y1-M1-M2-M3+M4-M5+M6) / N1.

[0025] A further technical solution is that the weight of the iron-containing raw material entering the converter and participating in the production smelting is the weight of the initial iron-containing raw material N1 minus the weight N2 of the part sucked away when the material is added to the high-level silo.

[0026] A further technical solution: If the iron-containing raw materials are added to the converter through the molten iron ladle or scrap steel bucket, N2 is 0; if the iron-containing raw materials are added through the high-level silo, N2 is 300kg.

[0027] A further technical solution is that for molten iron and pig iron, the enterprise has the test data of C, Si, Mn, P, and S, and X1, X2, X3, X4, and X5 take the average value within a certain time period; for other iron-containing materials except molten iron and pig iron, if there are test conditions, the value is taken from the test data; if there are no test conditions, the value is taken from the composition of scrap steel on the market.

[0028] Further technical solutions are as follows: for molten iron and pig iron, the company has the detection data of SiO2 and TFe of blast furnace molten iron slag, and X6 and X7 are taken as the average value within a certain period of time; for scrap steel, the slag part is mainly soil, and the SiO2 content of the soil is generally 50%-80%, and X6 and X7 are determined within this range; for blast furnace return ore, sintered ore, magnetic separation powder, and iron oxide scale, X6 and X7 are determined by the company's detection data; for slag and steel materials, they are inferred based on the tailings products of steel slag treatment and the characteristics of their common origin.

[0029] According to a further technical solution, X9, X10, X11, X12 and X13 are average values ​​within a certain period of time.

[0030] For further technical solutions, X14 and X15 are determined by the company's test data, and the influence of iron balls must be taken into account in the value of X15. The proportion of iron balls in converter slag is 10%.

[0031] A further technical solution is that for molten iron, Y2 is the proportion of slag in the molten iron, and the enterprise calculates it based on the measurement of the slag thickness of the molten iron; for pig iron, there is a slag skimming process in the casting process, and the slag skimming rate is 60-80%, thereby determining Y2; for scrap steel, Y2 is visually judged by its proportion of mud, with 0 for no mud, 0.1% for little mud, 0.5% for general use, and 2% for heavy mud; slag steel materials are regarded as a mixture of iron and tailings, and the slag part is the proportion of tailings, with Y2 = 20% for large-block screening, Y2 = 35% for initial magnetic separation, and Y2 = 50% for multiple magnetic separations; Y2 = 100% for other iron-containing materials.

[0032] A further technical solution is to determine the value of Y3 by pickling and cleaning materials of different thicknesses and different degrees of corrosion, and then weighing them for measurement to form a value matrix with thickness and degree of corrosion as independent variables:

[0033] Thickness 1mm: slight rust, Y3 = 1.00%; general rust, Y3 = 3.00%; severe rust, Y3 = 5.00%;

[0034] Thickness 2mm: slight rust, Y3 = 0.50%; general rust, Y3 = 1.50%; severe rust, Y3 = 2.50%;

[0035] Thickness 3mm: slight rust, Y3 = 0.33%; general rust, Y3 = 1.00%; severe rust, Y3 = 1.67%;

[0036] Thickness 4mm: slight rust, Y3 = 0.25%; general rust, Y3 = 0.75%; severe rust, Y3 = 1.25%;

[0037] Thickness 5mm: slight rust, Y3 = 0.20%; general rust, Y3 = 0.60%; severe rust, Y3 = 1.00%;

[0038] Thickness 6mm: slight rust, Y3 = 0.17%; general rust, Y3 = 0.50%; severe rust, Y3 = 0.83%;

[0039] Thickness 7mm: slight rust, Y3 = 0.14%; general rust, Y3 = 0.43%; severe rust, Y3 = 0.71%;

[0040] Thickness 8mm: slight rust, Y3 = 0.13%; general rust, Y3 = 0.38%; severe rust, Y3 = 0.63%;

[0041] Thickness 9mm: slight rust, Y3 = 0.11%; general rust, Y3 = 0.33%; severe rust, Y3 = 0.56%;

[0042] Thickness 10mm: slight rust, Y3 = 0.10%; general rust, Y3 = 0.30%; severe rust, Y3 = 0.50%;

[0043] Thickness > 10mm: slight rust, Y3 = 0.08%; general rust, Y3 = 0.24%; severe rust, Y3 = 0.40%.

[0044] A further technical solution is to determine the value of Y4 by measuring the weight of materials with different thicknesses and coating coverages after firing, pickling, and cleaning, and forming a value matrix with thickness and coating coverage as independent variables:

[0045] Thickness is 1mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 1.00%; coating coverage is 50%, Y3 = 2.00%; coating coverage is 75%, Y3 = 3.00%; coating coverage is 100%, Y3 = 4.00%;

[0046] Thickness is 2mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.50%; coating coverage is 50%, Y3 = 1.00%; coating coverage is 75%, Y3 = 1.50%; coating coverage is 100%, Y3 = 2.00%;

[0047] Thickness is 3mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.33%; coating coverage is 50%, Y3 = 0.67%; coating coverage is 75%, Y3 = 1.00%; coating coverage is 100%, Y3 = 1.33%;

[0048] Thickness is 4mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.25%; coating coverage is 50%, Y3 = 0.50%; coating coverage is 75%, Y3 = 0.75%; coating coverage is 100%, Y3 = 1.00%;

[0049] Thickness is 5mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.20%; coating coverage is 50%, Y3 = 0.40%; coating coverage is 75%, Y3 = 0.60%; coating coverage is 100%, Y3 = 0.80%;

[0050] Thickness is 6mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.17%; coating coverage is 50%, Y3 = 0.33%; coating coverage is 75%, Y3 = 0.50%; coating coverage is 100%, Y3 = 0.67%;

[0051] Thickness is 7mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.14%; coating coverage is 50%, Y3 = 0.29%; coating coverage is 75%, Y3 = 0.43%; coating coverage is 100%, Y3 = 0.57%;

[0052] Thickness is 8mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.13%; coating coverage is 50%, Y3 = 0.25%; coating coverage is 75%, Y3 = 0.38%; coating coverage is 100%, Y3 = 0.50%;

[0053] Thickness is 9mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.11%; coating coverage is 50%, Y3 = 0.22%; coating coverage is 75%, Y3 = 0.33%; coating coverage is 100%, Y3 = 0.44%;

[0054] Thickness is 10mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.10%; coating coverage is 50%, Y3 = 0.20%; coating coverage is 75%, Y3 = 0.30%; coating coverage is 100%, Y3 = 0.40%;

[0055] Thickness > 10mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.08%; coating coverage is 50%, Y3 = 0.16%; coating coverage is 75%, Y3 = 0.24%; coating coverage is 100%, Y3 = 0.32%.

[0056] The beneficial effects of the present invention are as follows: the present invention determines the yield of iron-containing raw materials for steelmaking by establishing the iron balance and input-output logic of converter smelting, obtaining detection data in accordance with the actual situation of the enterprise, and formulating a standardized value matrix through testing methods; it effectively improves the rationality and simplicity of establishing the standard for the yield of iron-containing raw materials, while reducing the degree of influence of actual working conditions on the yield test results, reducing the difficulty of operation and improving the accuracy and recognition of the final value, which is conducive to guiding the preferential selection of materials and the formulation of standard technical and economic indicators in production, and can also be used for optimal procurement planning based on cost-effectiveness to improve the competitiveness of enterprises. DETAILED DESCRIPTION

[0057] The present invention will be further described below with reference to specific embodiments, but the protection scope of the present invention is not limited thereto.

[0058] 1. A method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis, the specific operation is as follows:

[0059] (1) The iron-containing raw material is assumed to consist of four parts: iron part, slag part, rust part and coating part, and the weight proportions are recorded as Y1, Y2, Y3 and Y4 respectively, where Y1 = 100% - Y2 - Y3 - Y4;

[0060] The C, Si, Mn, P, and S element contents of the iron portion are detected and denoted as X1, X2, X3, X4, and X5, respectively. The specific detection method is the existing technology.

[0061] The SiO2 and TFe contents in the slag are detected and denoted as X6 and X7 respectively; the specific detection means are the existing technology;

[0062] The rust part is generally considered to be composed of Fe2O3 and crystal water in this field, with Fe2O3 accounting for 90%, which is recorded as X8;

[0063] Since the coating part is affected relatively little, it is considered to be completely burned.

[0064] (2) Based on the principle of steelmaking, the output of converter smelting consists of three parts: molten steel, converter slag and dust ash. The dust ash is generally taken as 0.66% of the weight of the iron part (it can also be taken according to the actual situation of the enterprise), which is recorded as Z1;

[0065] Detect the C, Si, Mn, P, and S element contents in the molten steel (converter end point), which are denoted as X9, X10, X11, X12, and X13, respectively; the specific detection means are the existing technology;

[0066] The SiO2 and TFe contents in the converter slag are detected and recorded as X14 and X15 respectively; the specific detection means are the existing technology;

[0067] The SiO2 and TFe contents in the dust removal ash are detected and recorded as X16 and X17 respectively; the specific detection means are the existing technology.

[0068] (3) Take a certain amount of iron-containing raw material and record its weight as N1 (kg); considering that there may be materials added from the high-level silo in the converter, which are inevitably sucked away by the dust removal system and do not enter the converter, the weight of this part is recorded as N2 (kg); therefore, the weight of the iron-containing raw material entering the converter and participating in the production and smelting is N1-N2, and the weight of this part is recorded as N3 (kg);

[0069] Due to the influence of evaporation and oxidation, part of the iron enters the dust removal ash along with the smoke. The weight of this part is N3*Z1*X17, recorded as M1 (kg);

[0070] During the production and smelting process, the elements of the iron part (i.e. C, Si, Mn, P, S) are oxidized to (N3*Y1-M1)*(X1+X2+X3+X4+X5-X9-X10-X11-X12-X13), and the weight of this part is recorded as M2 (kg);

[0071] The Si element in the iron part is oxidized to form converter slag, which contains Fe. The weight of this part is Denoted as M3 (kg); where: 28 is the atomic weight of Si, 60 is the atomic weight of SiO2;

[0072] The Fe carried into the converter by the slag is N3*Y2*X7, and the weight of this part is recorded as M4;

[0073] The SiO2 in the slag forms converter slag in the converter, which contains Fe. The weight of this part is Recorded as M5 (kg);

[0074] The Fe brought into the converter by the rust is The weight of this part is recorded as M6 (kg); where: 160 is the atomic weight of Fe2O3, 112 is the atomic weight of Fe2;

[0075] Therefore, the yield of iron-containing raw materials is (N3*Y1-M1-M2-M3+M4-M5+M6) / N1.

[0076] 2. To implement the above technical solution, it is necessary to determine the values ​​of N1, N2, X1-X7, X9-X15, and Y2-Y4. The specific operations are as follows:

[0077] (1) N1 can take any value, and in the present invention, it is 1000 kg;

[0078] (2) If the iron-containing raw materials are added to the converter through the ladle or scrap bucket, N2 is 0; if the iron-containing raw materials are added through the high-level silo, the dust removal air volume varies with the size of the grate, and the proportion of the material sucked away by the dust removal varies with the air volume. Generally, 10-20% of the material is sucked away by a 50-ton converter, 15-30% by a 100-ton converter, and 20-40% by a 150-ton converter and above. Therefore, the present invention takes a 150-ton converter as an example and takes N2 as 300 kg (each enterprise can use the value according to actual conditions);

[0079] (3) For molten iron and pig iron, each enterprise basically has the test data of C, Si, Mn, P, and S, and the average value within a certain period of time can be taken. The present invention takes X1=4.82%, X2=0.36%, X3=0.28%, X4=0.135%, and X5=0.025%; for other iron-containing materials except molten iron and pig iron, the values ​​are taken based on the test data if there are test conditions, and the values ​​are generally taken based on the composition of scrap steel in the market if there are no test conditions. Under no test conditions, the present invention takes the average composition of all steel products of a certain enterprise within one year as X1=0.23%, X2=0.45%, X3=1.16%, X4=0.025%, and X5=0.025%;

[0080] (4) For molten iron and pig iron, all enterprises have the detection data of SiO2 and TFe in blast furnace molten iron slag. The average value within a certain period of time can be taken. In this invention, X6=32% and X7=0.4% are taken. For scrap steel, the slag part is mainly soil, and the SiO2 content of soil is generally 50%-80%. In this invention, X6=65% and X7=0 are taken. For blast furnace return ore, sintered ore, magnetic separation powder, iron oxide scale, etc., since the materials are basically in small particle state, the detection is relatively easy. All enterprises have the detection data. In this invention, the SiO2 content of magnetic separation powder of a certain enterprise is taken. 2. The average values ​​of TFeO detected over a certain period of time are X6 = 7.6% and X7 = 53.2%. For slag steel materials such as ladle slag steel, casting slag steel, screening slag steel, and magnetic separation slag steel, detection is difficult due to their large size. Generally, no relevant detection data is available from any company. However, this can be estimated based on the characteristics of the tailings products from steel slag treatment and their common origin. In the present invention, the average values ​​of SiO2 and TFeO detected over a certain period of time in the tailings product of a certain company, X6 = 15.4% and X7 = 19%, are used as the SiO2 and TFe contents of the slag portion of the slag steel.

[0081] (5) X9-X13 are the components of the molten steel at the converter end point. Each company basically has the test data of C, Si, Mn, P, and S. The average value within a certain period of time can be taken. In the present invention, X9=0.065%, X10=0.00%, X11=0.10%, X12=0.018%, and X13=0.025% are taken;

[0082] (6) X14-X15 is the composition of converter slag. All companies basically have test data for SiO2 and TFe. At the same time, because the test data generally do not include iron beads in converter slag, the influence of iron beads needs to be taken into account in the value of X15. Generally, iron beads account for about 10% of converter slag. In this invention, X14=15% and X15=24.5%;

[0083] (7) X16-X17 are the dust ash components. Each company basically has the test data of SiO2 and TFe. The average value within a certain period of time can be taken. In this invention, X16=1.0% and X17=58% are taken;

[0084] (8) For molten iron, Y2 is the proportion of slag in molten iron. Each enterprise measures the slag thickness of the molten iron. The present invention takes Y2 = 1.0%; for pig iron, since there is a slag skimming process in pig iron casting, the slag skimming rate is generally 60-80%. The present invention takes Y2 = 0.3%; for scrap steel, the proportion of mud is visually judged, and 0% is taken for no mud, 0.1% for little mud, 0.5% for general use, and 2% for heavy mud; slag steel materials can be regarded as a mixture of iron and tailings, and the slag part is the tailings ratio. Generally, Y2 = 20% is taken for large block screening, Y2 = 35% is taken for primary magnetic separation, and Y2 = 50% is taken for multiple magnetic separations; Y2 = 100% is taken for other iron-containing materials such as high-grade, blast furnace return ore, sintered ore, and iron oxide scale;

[0085] (9) Rust (i.e., Y3) is mainly found in pig iron and scrap steel, and is caused by moisture and oxidation. The degree of its influence is mainly related to the thickness of the material and the degree of rust. Materials of different thicknesses and degrees of rust are pickled and cleaned, then weighed and measured. A value matrix with thickness and degree of rust as independent variables is formed to facilitate value selection, see Table 1. The degree of rust is determined by those skilled in the art based on experience:

[0086] Table 1 Thickness\Corrosion degree value matrix

[0087]

[0088]

[0089] (10) The coating part (i.e., Y4) mainly exists in scrap steel. Its influence is mainly related to the material thickness and coating coverage. The weight of materials with different thicknesses and coating coverages after firing, pickling, and cleaning is measured and calculated, and a value matrix with thickness and coating coverage as independent variables is formed to facilitate value selection; see Table 2:

[0090] Table 2 Thickness\Coating Coverage Value Matrix

[0091] Material thickness (mm)\coating coverage 0％ 25％ 50％ 75％ 100％ 1 0.00％ 1.00％ 2.00％ 3.00％ 4.00％ 2 0.00％ 0.50％ 1.00％ 1.50％ 2.00％ 3 0.00％ 0.33％ 0.67％ 1.00％ 1.33％ 4 0.00％ 0.25％ 0.50％ 0.75％ 1.00％ 5 0.00％ 0.20％ 0.40％ 0.60％ 0.80％ 6 0.00％ 0.17％ 0.33％ 0.50％ 0.67％ 7 0.00％ 0.14％ 0.29％ 0.43％ 0.57％ 8 0.00％ 0.13％ 0.25％ 0.38％ 0.50％ 9 0.00％ 0.11％ 0.22％ 0.33％ 0.44％ 10 0.00％ 0.10％ 0.20％ 0.30％ 0.40％ ＞ 0.00％ 0.08％ 0.16％ 0.24％ 0.32％

[0092] It should be noted that the value matrix formed by material thickness, rust degree and coating coverage as independent variables in Tables 1 and 2 is a standard with enterprise characteristics formed after actual testing of a certain enterprise, and is not necessarily applicable to all converter conditions. Therefore, each enterprise should make corrections based on its own actual situation.

[0093] (11) Example 1: In this example, the iron-containing raw material is molten iron. Based on the corresponding values ​​above, the raw material yield is calculated as shown in Table 3.

[0094] Table 3 Calculation results of Example 1

[0095]

[0096] Example 2: In this example, the iron-containing raw material is molten iron. According to the corresponding values ​​above, the raw material yield is calculated as shown in Table 4.

[0097] Table 4 Calculation results of Example 2

[0098]

[0099]

[0100] Example 3: In this example, the iron-containing raw material is pure scrap steel. According to the corresponding values ​​above, the raw material yield is calculated as shown in Table 5.

[0101] Table 5 Calculation results of Example 3

[0102]

[0103]

[0104] Example 4: In this example, the iron-containing raw material is pure scrap steel. According to the corresponding values ​​above, the raw material yield is calculated as shown in Table 6.

[0105] Table 6 Calculation results of Example 4

[0106]

[0107]

[0108] Example 5: In this example, the iron-containing raw material is screened slag steel. According to the corresponding values ​​above, the calculated raw material yield is shown in Table 7.

[0109] Table 7 Calculation results of Example 5

[0110]

[0111]

[0112] In summary, the method for analyzing and calculating the yield of iron-containing raw materials for steelmaking of the present invention effectively improves the rationality and simplicity of establishing the standard for the yield of iron-containing raw materials by establishing the iron balance and input-output logic of converter smelting, obtaining detection data in accordance with the actual situation of the enterprise, and formulating a standardized value matrix through testing methods. At the same time, it reduces the degree of influence of actual working conditions on the yield test results, reduces the difficulty of operation, and improves the accuracy and recognition of the final value. It is beneficial to guide the preferential selection of materials and the formulation of standard technical and economic indicators in production, and can also be used for optimal procurement planning based on cost-effectiveness to serve large-scale production.

[0113] The embodiments described are preferred implementations of the present invention, but the present invention is not limited to the above implementations. Any obvious improvements, substitutions or modifications that can be made by those skilled in the art without departing from the essence of the present invention are within the scope of protection of the present invention.

Claims

1. A method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis, characterized in that: (1) The iron-containing raw material is assumed to consist of four parts: iron part, slag part, rust part and coating part, and the weight proportions are recorded as Y1, Y2, Y3 and Y4 respectively, where Y1 = 100% - Y2 - Y3 - Y4; The C, Si, Mn, P, and S element contents of the iron part were detected and recorded as X1, X2, X3, X4, and X5 respectively; The SiO2 and TFe contents in the slag were detected and recorded as X6 and X7 respectively; The rust part is composed of Fe2O3 and crystal water, with Fe2O3 accounting for 90%, denoted as X8; The coating is completely burned; (2) The output of converter smelting consists of three parts: molten steel, converter slag and dust ash, of which the dust ash is 0.66% of the weight of the iron part, recorded as Z1kg; Detect the content of C, Si, Mn, P, and S elements in molten steel, which are recorded as X9, X10, X11, X12, and X13 respectively; Detect the SiO2 and TFe contents in converter slag and record them as X14 and X15 respectively; Detect the SiO2 and TFe contents in the dust removal ash and record them as X16 and X17 respectively; (3) The weight of the iron-containing raw materials entering the converter and participating in the production smelting is recorded as N3kg; The weight of the iron part that enters the dust removal along with the smoke is N3*Z1*X17, recorded as M1kg; The oxidized iron element is (N3*Y1-M1)*(X1+X2+X3+X4+X5-X9-X10-X11-X12-X13), and the weight of this part is recorded as M2kg; The Si element in the iron part is oxidized to form converter slag, which contains Fe. The weight of this part is Recorded as M3kg; The Fe carried into the converter by the slag is N3*Y2*X7, and the weight of this part is recorded as M4kg; The SiO2 in the slag forms converter slag in the converter, which contains Fe. The weight of this part is Recorded as M5kg; The Fe brought into the converter by the rust is The weight of this part is recorded as M6kg; Finally, the iron-containing raw material yield is expressed as: (N3*Y1-M1-M2-M3+M4-M5+M6) / N1.

2. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: The weight of the iron-containing raw materials entering the converter and participating in the production smelting is the weight of the initial iron-containing raw materials N1kg minus the weight N2kg of the part sucked away when the material is added to the high-level silo.

3. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 2, characterized in that: If the iron-containing raw materials are added to the converter through the ladle or scrap bucket, N2 is 0; If the iron-containing raw materials are added through the high-level silo, take 300kg of N2.

4. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: For molten iron and pig iron, the company has the test data of C, Si, Mn, P, and S. X1, X2, X3, X4, and X5 are averaged over a certain period of time; For other iron-containing materials except molten iron and pig iron, the value is determined by the test data if there are testing conditions; if there are no testing conditions, the value is determined by the composition of scrap steel on the market.

5. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: For molten iron and pig iron, the company has the test data of SiO2 and TFe in blast furnace slag, and X6 and X7 are the average values ​​within a certain period of time; For scrap steel, the slag is mainly soil, and the SiO2 content of the soil is 50%-80%. X6 and X7 are determined within this range; For blast furnace return ore, sintered ore, magnetic separation powder, and iron scale, X6 and X7 are determined by the company's test data; For slag steel materials, speculation is made based on the tailings products of steel slag treatment and their common origin.

6. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: The X9, X10, X11, X12, and X13 are average values ​​within a certain period of time.

7. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: X14 and X15 are determined by the company's test data. At the same time, the influence of iron balls must be taken into account in the value of X15. Iron balls account for 10% of the converter slag.

8. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: For molten iron, Y2 is the proportion of molten iron with slag, which is calculated by the company based on the measured slag thickness of the molten iron; For pig iron, there is a slag skimming process in the casting process, and the slag skimming rate is 60-80%, which determines Y2; For scrap steel, the proportion of mud is visually inspected to determine Y2, with 0% for no mud, 0.1% for light mud, 0.5% for normal mud, and 2% for heavy mud. Slag steel materials are considered as a mixture of iron and tailings. The slag portion is the tailings ratio. For bulk screening, Y2 = 20%, for primary magnetic separation, Y2 = 35%, and for multiple magnetic separation, Y2 = 50%. For other iron-containing materials, Y2=100%.

9. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: When determining the value of Y3, materials of different thicknesses and different degrees of corrosion are pickled and cleaned, and then weighed and measured to form a value matrix with thickness and degree of corrosion as independent variables: Thickness 1mm: slight rust, Y3 = 1.00%; general rust, Y3 = 3.00%; severe rust, Y3 = 5.00%; Thickness 2mm: slight rust, Y3 = 0.50%; For general rust, Y3 = 1.50%; for severe rust, Y3 = 2.50%; Thickness 3mm: slight rust, Y3 = 0.33%; general rust, Y3 = 1.00%; severe rust, Y3 = 1.67%; Thickness 4mm: slight rust, Y3 = 0.25%; general rust, Y3 = 0.75%; severe rust, Y3 = 1.25%; Thickness 5mm: slight rust, Y3 = 0.20%; For general rust, Y3 = 0.60%; for severe rust, Y3 = 1.00%; Thickness 6mm: slight rust, Y3 = 0.17%; General rust, Y3 = 0.50%; severe rust, Y3 = 0.83%; Thickness 7mm: slight rust, Y3 = 0.14%; General rust, Y3 = 0.43%; severe rust, Y3 = 0.71%; Thickness 8mm: slight rust, Y3 = 0.13%; general rust, Y3 = 0.38%; severe rust, Y3 = 0.63%; Thickness 9mm: slight rust, Y3 = 0.11%; General rust, Y3 = 0.33%; severe rust, Y3 = 0.56%; Thickness 10mm: slight rust, Y3 = 0.10%; For general rust, Y3 = 0.30%; for severe rust, Y3 = 0.50%; Thickness > 10mm: slight rust, Y3 = 0.08%; general rust, Y3 = 0.24%; Severe rust, Y3=0.40%.

10. The method for calculating the yield of iron-containing raw materials for steelmaking based on big data analysis according to claim 1, characterized in that: When determining the value of Y4, materials with different thicknesses and coating coverages are taken for measurement after firing, pickling, and cleaning to form a value matrix with thickness and coating coverage as independent variables: Thickness is 1mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 1.00%; coating coverage is 50%, Y3 = 2.00%; coating coverage is 75%, Y3 = 3.00%; coating coverage is 100%, Y3 = 4.00%; Thickness is 2mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.50%; coating coverage is 50%, Y3 = 1.00%; coating coverage is 75%, Y3 = 1.50%; coating coverage is 100%, Y3 = 2.00%; Thickness is 3mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.33%; coating coverage is 50%, Y3 = 0.67%; coating coverage is 75%, Y3 = 1.00%; coating coverage is 100%, Y3 = 1.33%; Thickness is 4mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.25%; coating coverage is 50%, Y3 = 0.50%; coating coverage is 75%, Y3 = 0.75%; coating coverage is 100%, Y3 = 1.00%; Thickness is 5mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.20%; coating coverage is 50%, Y3 = 0.40%; coating coverage is 75%, Y3 = 0.60%; coating coverage is 100%, Y3 = 0.80%; Thickness is 6mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.17%; coating coverage is 50%, Y3 = 0.33%; coating coverage is 75%, Y3 = 0.50%; coating coverage is 100%, Y3 = 0.67%; Thickness is 7mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.14%; coating coverage is 50%, Y3 = 0.29%; coating coverage is 75%, Y3 = 0.43%; coating coverage is 100%, Y3 = 0.57%; Thickness is 8mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.13%; coating coverage is 50%, Y3 = 0.25%; coating coverage is 75%, Y3 = 0.38%; coating coverage is 100%, Y3 = 0.50%; Thickness is 9mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.11%; coating coverage is 50%, Y3 = 0.22%; coating coverage is 75%, Y3 = 0.33%; coating coverage is 100%, Y3 = 0.44%; Thickness is 10mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.10%; coating coverage is 50%, Y3 = 0.20%; coating coverage is 75%, Y3 = 0.30%; coating coverage is 100%, Y3 = 0.40%; Thickness > 10mm: coating coverage is 0%, Y3 = 0.00%; coating coverage is 25%, Y3 = 0.08%; coating coverage is 50%, Y3 = 0.16%; coating coverage is 75%, Y3 = 0.24%; The coating coverage is 100%, and Y3=0.32%.

Images