A method for predicting molten iron composition in automated steelmaking process

Abstract

The present invention belongs to the technical field of automated steelmaking, and discloses a method for predicting the composition of molten iron applied to the automated steelmaking process, the method comprising: sampling, inspecting and calculating the composition loss of molten iron in the process of tapping from a torpedo tank to a ladle, and calibrating the composition of molten iron before tapping to the ladle; sampling, inspecting and calculating the composition loss of molten iron in the process of adding iron from the ladle to a converter, and calibrating the composition of molten iron before adding iron to the converter. The present invention is simple to operate, easy to implement, and can obtain more accurate and reliable real-time parameters for calculation models at all levels. When applied specifically, it is not necessary to innovate the existing automated steelmaking equipment, and can be applied to a wide range of automated steelmaking scenarios.

Description

Technical Field

[0001] The invention relates to the technical field of automated steelmaking, and in particular to a method for predicting molten iron composition. Background Art

[0002] The automated steelmaking process relies on multiple models such as the automated steelmaking static calculation model, process control model, and dynamic calculation model to accurately and continuously monitor and control the smelting process to ensure the safety and stability of the automated steelmaking process and obtain the expected steel. When the model is used to control and monitor the automated steelmaking process, the numerical value of the specific parameters in the input model will directly determine the model output.

[0003] Specifically for the automated converter steelmaking process, the existing technology often establishes models and calculates theories for each corresponding equipment and corresponding parameters, calculates the specific composition, temperature, required oxygen supply, etc. of the molten iron in the designated torpedo tank, ladle or converter and other steelmaking equipment as raw data, and controls the consumption of raw and auxiliary materials, heat balance control, oxygen balance control, etc. in the smelting process according to the calculation model and raw data to ultimately achieve automated steelmaking. It is worth noting that in the process of automated converter steelmaking, after the ore is melted into molten iron, it must undergo multiple transfers from the upper steelmaking equipment to the lower steelmaking equipment. The molten iron remains in a molten state during the transfer process. Affected by external factors such as temperature, solubility, and degree of reaction, there is often a deviation between the actual content of a specific element in the actual composition of the molten iron and the original data. If the deviation is not corrected and the original theoretical calculated value of the molten iron composition is directly input into the next-level calculation model for direct calculation, then the output result of the next-level calculation model will inevitably have a deviation, which will directly affect the automated steelmaking process; and if a sampling / inspection device is added to the corresponding next-level steelmaking equipment to obtain the real-time parameters of the corresponding steelmaking equipment, not only will the sampling / inspection equipment itself have high requirements for pressure and high temperature resistance and great difficulty in sampling / inspection, but the innovation of the equipment will also have the adverse effect of soaring costs of the steelmaking production line, affecting the overall efficiency of the steel plant. Summary of the invention

[0004] Based on this, it is necessary to provide a method for predicting molten iron composition, which is applied to the automated steelmaking process. The changes in molten iron composition caused by various influencing factors during the molten iron transfer process are included in the consideration of molten iron composition analysis to correct the error, and the composition of the molten iron is predicted before it enters the next level of steelmaking equipment. This provides more accurate, reliable and timely model calculation parameters for the automated steelmaking process, ensuring the stable progress of the automated steelmaking process.

[0005] The technical solution of the present invention is as follows:

[0006] The present invention provides a method for predicting the composition of molten iron used in an automated steelmaking process, the method comprising: sampling, inspecting and calculating the composition loss of the molten iron in the process of tapping from a torpedo tank to a ladle, and calibrating the composition of the molten iron before the molten iron is tapped to the ladle; sampling, inspecting and calculating the composition loss of the molten iron in the process of adding iron from the ladle to a converter, and calibrating the composition of the molten iron before adding iron to the converter. Before the molten iron is tapped into the ladle, the molten iron is sampled and its composition is tested. The test results of the molten iron are calibrated by comprehensively considering the influence of external factors such as temperature, solubility, and reaction degree on the content of a specific element in the molten iron, and the composition of the molten iron after tapping from the torpedo tank to the molten iron is predicted to be put into the relevant calculation model of the next level of steelmaking equipment. Such sampling, testing, calibration, and prediction methods are not only easy to operate, but also do not require operators to innovate existing automated steelmaking equipment. They only need to rely on the gap between the torpedo tank and the ladle to sample and send for inspection, which enhances operability. Since calibration is required after the test results are obtained, the use of calibrated data to predict the specific composition of the molten iron tapped into the ladle can further eliminate the interference of other interference factors on the model data, more accurately fit the actual situation, and ensure accurate and reliable control of the automated steelmaking process. The same is true for the process of adding iron from the ladle to the converter.

[0007] Optionally, part of the molten iron that is about to be tapped from the torpedo tank into the ladle is collected as the first process sample, and the remaining molten iron is tapped into the ladle; the first process sample is sent for inspection, and the first process sample component inspection result is obtained to calculate the first process sample calibration result.

[0008] Optionally, a first sampling time threshold and an iron-out time threshold are set; the sampling time of the first process sample does not exceed the first sampling time threshold, and the iron-out time of the remaining molten iron after sampling the first process sample to the ladle does not exceed the iron-out time threshold. Setting a reasonable first sampling time threshold and an iron-out time threshold can avoid excessive influence of the transfer process on the composition of the molten iron as much as possible. The detection process of the process sample after sampling and the iron-out process are carried out simultaneously, which can also promote the orderly and smooth execution of the automated steelmaking process.

[0009] Optionally, after the first process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon, the mass percentage of silicon, the mass percentage of manganese, the mass percentage of phosphorus, the mass percentage of sulfur, and the mass percentage of titanium in the first process sample is detected. The molten iron remains molten during the transfer from the upper-level steelmaking equipment to the lower-level steelmaking equipment. The content of carbon, sulfur, phosphorus and other elements in the molten iron is greatly affected by factors such as temperature, oxygen supply, and reaction degree. It is necessary to detect the specific composition of each element to provide more sufficient, more reliable, and more multi-dimensional calculation raw materials for the relevant calculation model of the lower-level steelmaking equipment.

[0010] Optionally, for the element E determined in the first process sample, the percentage of its component loss is calculated using the following formula:

[0011]

[0012] In formula 1, is the mass percentage of the element E in the molten iron of the torpedo tank; is the recovery rate coefficient of element E in the iron-making process, which is an empirical value; It is the loss coefficient of element E in the iron-making process, which is an empirical value. The above empirical value is obtained through a large number of field tests and cumulative data analysis. Different recovery coefficients and loss coefficients are selected for different elements E to correct the loss of each specific element in the specific process in a targeted manner.

[0013] Optionally, for the determined element E in the first process sample, the mass percentage of the element E detected after the first process sample is sent for inspection and the component loss percentage of the determined element E are calculated. The product of is taken as the first process sample calibration result, and the first process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

[0014] Optionally, part of the molten iron that is about to be added from the ladle to the converter is collected as the second process sample, and the remaining molten iron is added to the converter; the second process sample is sent for inspection, and the second process sample component inspection result is obtained to calculate the second process sample calibration result.

[0015] Optionally, a second sampling time threshold and an iron adding time threshold are set; the sampling time of the second process sample does not exceed the second sampling time threshold, and the iron adding time for adding iron to the converter with the remaining molten iron after sampling the second process sample does not exceed the iron adding time threshold; after the second process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon, the mass percentage of silicon, the mass percentage of manganese, the mass percentage of phosphorus, the mass percentage of sulfur, and the mass percentage of titanium in the second process sample is detected.

[0016] Optionally, for the element E determined in the second process sample, the percentage of its component loss is calculated using the following formula:

[0017]

[0018] In formula 2, is the mass percentage of element E in the molten iron in the ladle; It is the recovery rate coefficient of element E in the process of adding iron to the converter, which is an empirical value; The loss coefficient of element E in the process of adding iron to the converter is an empirical value.

[0019] Optionally, for the determined element E in the second process sample, the mass percentage of the element E detected after the second process sample is sent for inspection and the component loss percentage of the determined element E are calculated. The product of is taken as the second process sample calibration result, and the second process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

[0020] The beneficial effects of the technical solution of the present invention are as follows: the present invention is simple to operate and easy to implement, and can obtain more accurate and reliable real-time parameters for calculation models at all levels. When applied specifically, there is no need to innovate the existing automated steelmaking equipment, and the present invention can be applied to a wide range of automated steelmaking scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of the method for predicting molten iron composition applied to the automated steelmaking process implemented in a specific implementation manner.

[0023] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0026] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0027] refer to Figure 1 .

[0028] In this specific embodiment, a method for predicting the composition of molten iron applied to an automated steelmaking process is provided, the method comprising: sampling, inspecting and calculating the composition loss of the molten iron in the process of being tapped from a torpedo tank to a ladle, and calibrating the composition of the molten iron before the molten iron is tapped to the ladle; sampling, inspecting and calculating the composition loss of the molten iron in the process of being added to iron from the ladle to a converter, and calibrating the composition of the molten iron before the molten iron is added to the converter.

[0029] In this specific embodiment, part of the molten iron that is about to be tapped from the torpedo tank into the ladle is collected as the first process sample, and the remaining molten iron is tapped into the ladle; the first process sample is sent for inspection, and the first process sample component inspection result is obtained to calculate the first process sample calibration result.

[0030] In this specific implementation, the first sampling time threshold is set to 30 seconds, and the iron-tapping time threshold is set to 5 minutes; the sampling time of the first process sample does not exceed the first sampling time threshold, and the iron-tapping time of the remaining molten iron after sampling the first process sample does not exceed the iron-tapping time threshold.

[0031] In this specific embodiment, after the first process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon, the mass percentage of silicon, the mass percentage of manganese, the mass percentage of phosphorus, the mass percentage of sulfur, and the mass percentage of titanium in the first process sample is detected.

[0032] In this specific embodiment, the element E is determined in the first process sample, and its component loss percentage is calculated by the following formula:

[0033]

[0034] In formula 1, is the mass percentage of the element E in the molten iron of the torpedo tank; is the recovery rate coefficient of element E in the iron-making process, which is an empirical value; It is the loss coefficient of element E in the iron-making process, which is an empirical value.

[0035] In this specific embodiment, for the element E determined in the first process sample, the mass percentage of the element E detected after the first process sample is sent for inspection and the component loss percentage of the determined element E are calculated. The product of is taken as the first process sample calibration result, and the first process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

[0036] In this specific embodiment, part of the molten iron that is about to be added to the converter from the ladle is collected as the second process sample, and the remaining molten iron is added to the converter; the second process sample is sent for inspection, and the second process sample component inspection result is obtained to calculate the second process sample calibration result.

[0037] In this specific embodiment, the second sampling time threshold is set to 30 seconds, and the iron adding time threshold is set to 5 minutes; the sampling time of the second process sample does not exceed the second sampling time threshold, and the iron adding time of the remaining molten iron after sampling the second process sample to add iron to the converter does not exceed the iron adding time threshold; after the second process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon element, mass percentage of silicon element, mass percentage of manganese element, mass percentage of phosphorus element, mass percentage of sulfur element, and mass percentage of titanium element in the second process sample is detected.

[0038] In this specific embodiment, the element E is determined in the second process sample, and its component loss percentage is calculated by the following formula:

[0039]

[0040] In formula 2, is the mass percentage of element E in the molten iron in the ladle; It is the recovery rate coefficient of element E in the process of adding iron to converter, which is an empirical value; The loss coefficient of element E in the process of adding iron to the converter is an empirical value.

[0041] In this specific embodiment, for the determined element E in the second process sample, the mass percentage of the element E detected after the second process sample is sent for inspection and the component loss percentage of the determined element E are calculated. The product of is taken as the second process sample calibration result, and the second process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

[0042] In the automated converter steelmaking process provided in this application, eight groups of verification examples were obtained:

[0043] Verification Example 1:

[0044] The composition of the molten iron in the torpedo tank was sampled for 10 seconds. The results of the laboratory test showed that the composition of C: 4.37%, Si: 0.42%, Mn: 0.36%, P: 0.130%, S: 0.045%, Ti: 0.025%. After calculation according to the prediction formula 1, the relevant composition was corrected to: C: 4.27%, Si: 0.41%, Mn: 0.36%, P: 0.130%, S: 0.045%, Ti: 0.0238%. The molten iron of the furnace was added to the converter from the ladle, and the iron addition time was 4.5 minutes. After calculation according to the prediction formula 2, the relevant composition was corrected to: C: 4.17%, Si: 0.403%, Mn: 0.36%, P: 0.130%, S: 0.045%, Ti: 0.0235%.

[0045] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the ladle and converter furnace at the same time. The laboratory test results are compared as follows:

[0046] The composition of molten iron in the ladle: C: 4.268%, Si: 0.409%, Mn: 0.36%, P: 0.130%, S: 0.045%, Ti: 0.0228%.

[0047] The composition of molten iron in the converter furnace is: C: 4.16%, Si: 0.398%, Mn: 0.36%, P: 0.130%, S: 0.045%, Ti: 0.0236%.

[0048] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0049] Verification Example 2:

[0050] During a furnace smelting in a steel plant, the composition of the molten iron in a torpedo tank was sampled for 18 seconds. After testing in the laboratory, the results were C: 4.23%, Si: 0.45%, Mn: 0.39%, P: 0.135%, S: 0.055%, Ti: 0.028%. After calculation according to prediction formula 1, the relevant components were corrected to: C: 4.13%, Si: 0.437%, Mn: 0.39%, P: 0.135%, S: 0.055%, Ti: 0.0266%. The molten iron of this furnace was added to the converter from the ladle, and the iron addition time was 4.2 minutes. After calculation according to prediction formula 2, the relevant components were corrected to: C: 4.03%, Si: 0.432%, Mn: 0.36%, P: 0.130%, S: 0.055%, Ti: 0.0263%.

[0051] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the ladle and converter furnace at the same time. The laboratory test results are compared as follows:

[0052] The composition of molten iron in the ladle: C: 4.128%, Si: 0.435%, Mn: 0.36%, P: 0.130%, S: 0.055%, Ti: 0.0265%.

[0053] The composition of molten iron in the converter furnace is: C: 4.02%, Si: 0.43%, Mn: 0.36%, P: 0.130%, S: 0.055%, Ti: 0.0261%.

[0054] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0055] Verification Example 3:

[0056] During a furnace smelting in a steel plant, the composition of the molten iron in a torpedo tank was sampled for 15 seconds. The results of the laboratory test showed that the composition of C: 4.59%, Si: 0.22%, Mn: 0.55%, P: 0.110%, S: 0.038%, and Ti: 0.033%. After calculation according to the prediction formula 1, the relevant composition was corrected to: C: 4.49%, Si: 0.213%, Mn: 0.55%, P: 0.110%, S: 0.038%, and Ti: 0.0314%. The molten iron of the furnace was added to the converter from the ladle, and the iron addition time was 4.8 minutes. After calculation according to the prediction formula 2, the relevant composition was corrected to: C: 4.39%, Si: 0.211%, Mn: 0.55%, P: 0.110%, S: 0.038%, and Ti: 0.031%.

[0057] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the ladle and converter furnace at the same time. The laboratory test results are compared as follows:

[0058] The composition of molten iron in the ladle: C: 4.48%, Si: 0.211%, Mn: 0.55%, P: 0.110%, S: 0.038%, Ti: 0.0312%.

[0059] The composition of molten iron in the converter furnace is: C: 4.37%, Si: 0.21%, Mn: 0.55%, P: 0.110%, S: 0.038%, Ti: 0.0309%.

[0060] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0061] Verification Example 4:

[0062] During a furnace smelting in a steel plant, the composition of the molten iron in the torpedo tank was sampled for 20 seconds. After testing in the laboratory, the results were C: 3.98%, Si: 0.62%, Mn: 0.46%, P: 0.098%, S: 0.033%, Ti: 0.021%. After calculation according to prediction formula 1, the relevant components were corrected to: C: 3.88%, Si: 0.601%, Mn: 0.46%, P: 0.098%, S: 0.033%, Ti: 0.020%. The molten iron of this furnace was added to the converter from the ladle, and the iron addition time was 4.1 minutes. After calculation according to prediction formula 2, the relevant components were corrected to: C: 3.78%, Si: 0.595%, Mn: 0.46%, P: 0.098%, S: 0.033%, Ti: 0.0198%.

[0063] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the ladle and converter furnace at the same time. The laboratory test results are compared as follows:

[0064] The composition of molten iron in the ladle: C: 387%, Si: 0.609%, Mn: 0.46%, P: 0.098%, S: 0.033%, Ti: 0.0218%.

[0065] The composition of molten iron in the converter furnace is: C: 3.76%, Si: 0.598%, Mn: 0.46%, P: 0.098%, S: 0.033%, Ti: 0.0216%.

[0066] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0067] Verification Example 5:

[0068] In a furnace smelting at a steel plant, the molten iron in the torpedo tank was not sampled, but was sampled after the iron was tapped into the ladle. The sampling time was 25 seconds. The results of laboratory testing were C: 4.98%, Si: 0.60%, Mn: 0.36%, P: 0.090%, S: 0.038%, Ti: 0.025%. The molten iron in this furnace was added to the converter from the ladle, and the iron adding time was 4.9 minutes. After calculation according to prediction formula 2, the relevant components were corrected to: C: 4.88%, Si: 0.594%, Mn: 0.36%, P: 0.090%, S: 0.038%, Ti: 0.0248%.

[0069] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the converter furnace. The laboratory test results are compared as follows:

[0070] The composition of molten iron in the converter furnace is: C: 4.85%, Si: 0.598%, Mn: 0.36%, P: 0.090%, S: 0.038%, Ti: 0.0246%.

[0071] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0072] Verification Example 6:

[0073] In a furnace smelting at a steel plant, the molten iron in the torpedo tank was not sampled, but was sampled after the iron was tapped into the ladle. The sampling time was 30 seconds. The results of laboratory testing were C: 3.58%, Si: 0.69%, Mn: 0.45%, P: 0.088%, S: 0.023%, Ti: 0.019%. The molten iron in this furnace was added to the converter from the ladle, and the iron adding time was 5.0 minutes. After calculation according to prediction formula 2, the relevant components were corrected to: C: 3.48%, Si: 0.683%, Mn: 0.45%, P: 0.088%, S: 0.023%, Ti: 0.0188%.

[0074] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the converter furnace. The laboratory test results are compared as follows:

[0075] The composition of molten iron in the converter furnace is: C: 3.45%, Si: 0.680%, Mn: 0.45%, P: 0.088%, S: 0.023%, Ti: 0.0186%.

[0076] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0077] Verification Example 7:

[0078] In a steel mill, no sample was taken from the torpedo molten iron in a furnace. The sample was taken after the iron was discharged to the ladle. The sampling time was 26 seconds. The results of laboratory testing were C: 4.33%, Si: 0.55%, Mn: 0.66%, P: 0.078%, S: 0.038%, Ti: 0.025%. The molten iron of this furnace was added from the ladle to the converter. The iron adding time was 4.7 minutes. According to the prediction formula 2, the relevant components were corrected to: C: 4.23%, Si: 0.544%, Mn: 0.66%, P: 0.078%, S: 0.038%, Ti: 0.0248%.

[0079] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the converter furnace. The laboratory test results are compared as follows:

[0080] The composition of molten iron in the converter furnace is: C: 4.22%, Si: 0.548%, Mn: 0.66%, P: 0.078%, S: 0.038%, Ti: 0.0246%.

[0081] Judging from the above comparison results, the predicted composition is closer to the actual composition, which provides a data basis for the dynamic and static calculation model of steelmaking.

[0082] Verification Example 8:

[0083] In a steel mill, no sample was taken from the molten iron in the torpedo tank. The sample was taken after the iron was discharged to the ladle. The sampling time was 28 seconds. The results of laboratory testing were C: 4.28%, Si: 0.42%, Mn: 0.35%, P: 0.095%, S: 0.032%, Ti: 0.027%. The molten iron of this furnace was added to the converter from the ladle. The iron adding time was 3.8 minutes. According to the prediction formula 2, the relevant components were corrected to: C: 4.18%, Si: 0.416%, Mn: 0.35%, P: 0.095%, S: 0.032%, Ti: 0.0267%.

[0084] In order to verify the accuracy of the prediction, sampling and analysis were carried out in the converter furnace. The laboratory test results are compared as follows:

[0085] The composition of molten iron in the converter furnace is: C: 4.14%, Si: 0.412%, Mn: 0.35%, P: 0.095%, S: 0.032%, Ti: 0.0262%.

[0086] It can be clearly seen from the above eight groups of verification embodiments that the molten iron composition prediction method applied to the automated steelmaking process provided in this specific real-time mode has a high degree of fit with the actual data, and the predicted composition is closer to the actual composition, which can provide a stable, reliable and accurate data basis for the dynamic and static calculation model of steelmaking.

[0087] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A method for predicting molten iron composition in an automated steelmaking process, characterized in that: The method comprises: sampling, inspecting and calculating the component loss of the molten iron in the process of tapping from the torpedo tank to the ladle, and calibrating the molten iron composition before the molten iron is tapped to the ladle; sampling, inspecting and calculating the component loss of the molten iron in the process of adding iron from the ladle to the converter, and calibrating the molten iron composition before the molten iron is added to the converter; Collect part of the molten iron that is about to be tapped from the torpedo tank into the ladle as the first process sample, and tap the remaining molten iron into the ladle; Sending the first process sample for inspection, obtaining the first process sample component inspection result to calculate the first process sample calibration result; Setting a first sampling time threshold and an iron tapping time threshold; The sampling time of the first process sample does not exceed the first sampling time threshold, and the time for tapping the remaining molten iron to the ladle after sampling the first process sample does not exceed the tapping time threshold; After the first process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon element, the mass percentage of silicon element, the mass percentage of manganese element, the mass percentage of phosphorus element, the mass percentage of sulfur element, and the mass percentage of titanium element in the first process sample is detected; For the element E determined in the first process sample, the percentage of its component loss is calculated using the following formula: In formula 1, is the mass percentage of the element E in the molten iron of the torpedo tank; is the recovery rate coefficient of element E in the iron-making process, which is an empirical value; It is the loss coefficient of element E in the iron-making process, which is an empirical value.

2. The method for predicting molten iron composition in an automated steelmaking process according to claim 1, characterized in that: For the determined element E in the first process sample, calculate the mass percentage of the element E detected after the first process sample is sent for inspection and the component loss percentage of the determined element E The product of is taken as the first process sample calibration result, and the first process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

3. The method for predicting molten iron composition in an automated steelmaking process according to claim 1, characterized in that: Collect part of the molten iron that is about to be added to the converter from the ladle as the second process sample, and add the remaining molten iron to the converter; The second process sample is sent for inspection, and a component inspection result of the second process sample is obtained to calculate a calibration result of the second process sample.

4. The method for predicting molten iron composition in an automated steelmaking process according to claim 3, characterized in that: A second sampling time threshold and an iron adding time threshold are set; the sampling time of the second process sample does not exceed the second sampling time threshold, and the iron adding time of adding iron to the converter from the remaining molten iron after sampling the second process sample does not exceed the iron adding time threshold; After the second process sample is sent for inspection, the mass percentage of at least one specific element among the mass percentage of carbon element, the mass percentage of silicon element, the mass percentage of manganese element, the mass percentage of phosphorus element, the mass percentage of sulfur element, and the mass percentage of titanium element in the second process sample is detected.

5. The method for predicting molten iron composition in an automated steelmaking process according to claim 4, characterized in that: For the element E determined in the second process sample, the percentage of its component loss is calculated using the following formula: In formula 2, is the mass percentage of element E in the molten iron in the ladle; It is the recovery rate coefficient of element E in the process of adding iron to converter, which is an empirical value; The loss coefficient of element E in the process of adding iron to the converter is an empirical value.

6. The method for predicting molten iron composition in an automated steelmaking process according to claim 5, characterized in that: For the determined element E in the second process sample, calculate the mass percentage of the element E detected after the second process sample is sent for inspection and the component loss percentage of the determined element E The product of is taken as the second process sample calibration result, and the second process sample calibration result is input into the calculation model as the actual mass percentage of element E in the molten iron ladle to control the automated steelmaking process.

Images