A method for setting a target temperature of a converter tapping in a BOF-RH-CC process

CN122979550APending Publication Date: 2026-10-27BAOSHAN IRON & STEEL CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202510528827.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-25
Publication Date
2026-10-27

Smart Images

  • Figure CN122979550A_ABST
    Figure CN122979550A_ABST
Patent Text Reader

Abstract

The application discloses a BOF-RH-CC process flow converter tapping target temperature setting method, comprising the following steps: S1: collecting the actual performance production data of the converter, RH refining and continuous casting process, and counting the temperature drop from the converter to the refining process, the refining process temperature drop and the temperature drop from the refining process to the continuous casting process; S2: taking the liquidus temperature of the steel grade as the starting point, gradually accumulating the temperature drop of the previous process to obtain the basic target temperature of the converter tapping temperature; S3: extracting the historical process data of the steel grade, taking the historical process parameters as the input, and taking the converter tapping temperature compensation value as the output, and establishing a converter tapping temperature compensation prediction model; S4: according to the process parameters of the new furnace, the converter tapping temperature compensation value of the furnace is obtained, and the basic target temperature obtained in step S2 is combined, so that the final target temperature of the furnace is obtained. The application realizes the dynamic adjustment of the target temperature by predicting the compensation value of the converter tapping temperature in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of steelmaking technology, and in particular to a method for setting the target tapping temperature of a converter in a BOF-RH-CC process. Background Technology

[0002] Steel temperature is one of the important process parameters in the steelmaking process. The level of steel temperature control is a "barometer" of the stable operation of the steelmaking system. Steel temperature has a great impact on ensuring the smooth operation of the continuous casting process, reducing raw material consumption and energy consumption, and improving the quality of cast billets. Therefore, it is necessary to control the steel temperature within a reasonable range.

[0003] The core of molten steel temperature control in the steelmaking-continuous casting process is the stability of the molten steel temperature and its superheat in the ladle and tundish. This requires not only relatively stable molten steel temperature control in each process, but also stable temperature changes between processes.

[0004] In the BOF-RH-CC production process, the heating capacity of the RH refining furnace is generally limited (heating in the RH refining process is achieved by blowing oxygen and then adding deoxidizers, the deoxidation products of which reduce the cleanliness of the molten steel and increase the calming time, so the temperature cannot be increased significantly). Therefore, the temperature control capability of the converter is more stringent under this production process.

[0005] The publicly available document CN113255102A discloses a method for predicting the carbon content and temperature of molten steel at the converter endpoint. This method treats each converter smelting process as a case and describes each process as a case. The case description includes a description of case features and a description of the solution. Case features include single-value type influencing factors and time-series type influencing factors. The solution includes the carbon content and temperature of the molten steel at the converter endpoint. Using the current converter smelting process as the problem case and historical converter smelting processes as historical cases, a case reasoning algorithm is used to retrieve similar cases from the historical cases. Based on the retrieved similar cases and their corresponding molten steel carbon content and temperature at the converter endpoint, the predicted values ​​of the carbon content and temperature of the molten steel at the converter endpoint for the problem case are obtained through case reuse.

[0006] Patent document CN117093868A discloses a converter endpoint prediction method based on multi-task learning, comprising: acquiring converter parameter information; preprocessing the converter parameter information to obtain an input vector; inputting the input vector into a pre-trained prediction model to simultaneously obtain the predicted converter molten steel temperature and converter carbon content; obtaining the predicted converter endpoint range based on the predicted converter molten steel temperature and converter carbon content; starting smelting of molten iron; and generating a termination reminder when it is determined that the converter molten steel temperature and the converter carbon content have reached the predicted converter endpoint range. This disclosure can consider the diversity of process conditions and the complexity of steel smelting processes, and can also avoid the problem of traditional data-driven models easily getting trapped in local minima, achieving accurate simultaneous prediction of converter endpoint temperature and carbon content.

[0007] Patent document CN115456264A discloses a method for predicting the endpoint carbon content and endpoint temperature of small and medium-sized converters. The method acquires historical production data of small and medium-sized converters and performs dimensional filtering. Then, it constructs a clustering model based on the Shared Nearest Neighbor Propagation (SNN-AP) algorithm. The filtered dataset is input into the clustering model to obtain a set of cluster centroids and corresponding cluster datasets based on the model training dataset. An endpoint carbon content prediction model and an endpoint temperature prediction model are established for each dataset. The dataset of each category is input into the corresponding prediction model for training to obtain a mature prediction model. Data items corresponding to small and medium-sized converters and comparison sequences are collected and input into the mature prediction model of the corresponding category to obtain the predicted current carbon content and temperature.

[0008] The aforementioned patents mainly focus on predicting the converter's final tapping temperature, but lack research on whether the target tapping temperature is reasonable, especially for RH-type steels. If the target tapping temperature is too low, even if the final tapping temperature matches the target, a large amount of oxygen blowing is needed to raise the temperature during subsequent RH refining, resulting in a decrease in the cleanliness of the molten steel. Therefore, setting a reasonable converter tapping temperature is particularly important. Summary of the Invention

[0009] The purpose of this invention is to provide a method for setting the target tapping temperature of converter steel in the BOF-RH-CC process, which solves the problem that the target tapping temperature of converter steel is difficult to control accurately in existing patents.

[0010] The above-mentioned technical objective of this invention has been achieved by the following technical solutions:

[0011] A method for setting the target tapping temperature of a converter in a BOF-RH-CC process includes the following steps:

[0012] S1: Collect actual production data of converter, RH refining and continuous casting processes, and statistically analyze the temperature drop during the transfer process from converter to refining, the temperature drop during the refining process and the temperature drop during the transfer process from refining to continuous casting.

[0013] S2: Starting from the liquidus temperature of the steel grade, gradually add the temperature drop of the previous process to obtain the basic target temperature for the converter tapping temperature;

[0014] S3: Extract historical process data of steel grades, use historical process parameters as input and converter tapping temperature compensation value as output, and establish a converter tapping temperature compensation prediction model.

[0015] S4: Based on the process parameters of the new heat, obtain the converter tapping temperature compensation value for this heat, and combine it with the basic target temperature obtained in step S2 to obtain the final target temperature for this heat.

[0016] Step S1 specifically includes the following steps:

[0017] S11: Temperature data acquisition, collecting molten steel temperature data when tapping from the converter, collecting molten steel temperature data at the start of RH refining, and collecting molten steel temperature data at the start of continuous casting.

[0018] S12: Temperature drop statistics. Based on the temperature at the time of steel tapping from the converter and the temperature at the start of RH refining, the temperature drop during the transfer process is calculated. The temperature drop during the transfer process from the converter to the refining is the difference between the steel tapping temperature of the converter and the RH inlet temperature.

[0019] The specific production data items collected in step S11 for the converter, RH refining, and continuous casting processes include:

[0020] Converter tapping temperature, RH refining station inlet temperature, RH refining station outlet temperature, continuous casting start temperature, continuous casting tundish superheat, steel grade liquidus temperature, converter tapping start time, RH inlet time, RH outlet time, continuous casting start time, and continuous casting start sequence number.

[0021] The temperature drop statistics in step S12 specifically include the following steps:

[0022] The temperature drop during the transfer process from converter to refining is the difference between the converter tapping temperature and the RH inlet temperature.

[0023] The temperature drop during the refining process is calculated based on the temperature at the start and end of the RH refining process. The temperature drop during the refining process is the difference between the RH inlet temperature and the RH outlet temperature.

[0024] Based on the temperature at the end of refining and the temperature at the beginning of continuous casting, the temperature drop during the transfer process is calculated. The temperature drop during the transfer process from refining to continuous casting is the difference between the RH outlet temperature and the continuous casting start temperature.

[0025] The formula for calculating the basic target temperature in step S2 is as follows:

[0026] T 目标 =T 转炉 +ΔT 补偿 (X);

[0027] Among them, T 转炉 The tapping temperature of the converter is expressed by the following formula:

[0028] T 精炼结束 =T 液相线 +ΔT 过热度 +ΔT1;

[0029] T 精炼开始 =T 精炼结束 +ΔT2;

[0030] T 转炉 =T 精炼开始 +ΔT3;

[0031] Wherein, ΔT1 represents the average temperature drop during the refining to continuous casting transfer process; ΔT2 represents the average temperature drop during the refining process; and ΔT3 represents the average temperature drop during the converter to refining transfer process.

[0032] Step S3 specifically includes the following steps:

[0033] S31: Obtain historical process data for steel grades, specifically including information such as process transfer time and ladle thermal state;

[0034] S32: Preprocess the acquired process data, clean the collected data, and remove outliers, missing values, or duplicate data.

[0035] S33: Select a machine learning algorithm to train the prediction model, using historical process parameters as input features and converter tapping temperature compensation value as output target, and train the model.

[0036] S34: Use validation set data to validate the trained model, evaluate the model's predictive performance, and calculate the model's prediction error to ensure that the model has no significant bias.

[0037] S35: The trained and validated model is applied to production to predict the compensation value of the converter tapping temperature in real time. Based on the real-time process parameter input, the model outputs the compensation value of the converter tapping temperature, thereby obtaining the final target tapping temperature.

[0038] The model inputs in step S33 include time factors and ladle factors, wherein the time factors include...

[0039] Converter tapping time, transfer time from converter to refining, RH refining treatment time, and transfer time from RH refining to continuous casting; steel factors include ladle age, empty ladle time, and ladle baking time.

[0040] Step S4 specifically includes the following steps:

[0041] S41: The basic target temperature for converter tapping. The predicted converter tapping temperature compensation value is added to the basic target temperature to obtain the final target temperature for this heat.

[0042] S42: Record the calculated final target temperature in the production record or process file for subsequent tracking and analysis, and collect actual data during the production process for continuous verification and optimization of the compensation prediction model.

[0043] In summary, the present invention has the following beneficial effects:

[0044] 1. Improved Production Accuracy: A high hit rate across multiple prediction error ranges indicates that the model's predictions are relatively accurate and can provide reliable guidance for production. By tapping steel according to the target values ​​given by the model, more precise temperature control during the production process can be ensured, reducing product quality issues caused by temperature fluctuations.

[0045] 2. Improved Production Efficiency: Precise temperature control helps reduce interruptions and adjustments during production, thereby improving efficiency. When the converter tapping temperature is optimized, product quality and consistency can be improved. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the structure of the present invention.

[0047] Figure 2 This is a comparison chart of the actual tapping temperature and the predicted tapping temperature of the present invention. Detailed Implementation

[0048] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below with reference to the figures and specific embodiments.

[0049] like Figure 1 As shown, the present invention proposes a method for setting the target tapping temperature of a converter in a BOF-RH-CC process, comprising the following steps:

[0050] S1: Collect actual production data of converter, RH refining and continuous casting processes, and statistically analyze the temperature drop during the transfer process from converter to refining, the temperature drop during the refining process and the temperature drop during the transfer process from refining to continuous casting.

[0051] Step S1 specifically includes the following steps:

[0052] S11: Temperature data acquisition, collecting molten steel temperature data when tapping from the converter, collecting molten steel temperature data at the start of RH refining, and collecting molten steel temperature data at the start of continuous casting.

[0053] S12: Temperature drop statistics, based on the temperature at the time of tapping from the converter and the temperature at the start of RH refining, calculate the temperature drop during the transfer process;

[0054] The temperature drop during the transfer process from converter to refining is the difference between the converter tapping temperature and the RH inlet temperature.

[0055] The temperature drop during the refining process is calculated based on the temperature at the start and end of the RH refining process. The temperature drop during the refining process is the difference between the RH inlet temperature and the RH outlet temperature.

[0056] Based on the temperature at the end of refining and the temperature at the beginning of continuous casting, the temperature drop during the transfer process is calculated. The temperature drop during the transfer process from refining to continuous casting is the difference between the RH outlet temperature and the continuous casting start temperature.

[0057] The collected production data items for the converter, RH refining, and continuous casting processes include: converter tapping temperature, RH refining inlet temperature, RH refining outlet temperature, continuous casting start temperature, continuous casting tundish superheat, steel grade liquidus temperature, converter tapping start time, RH inlet time, RH outlet time, continuous casting start time, and continuous casting start sequence number.

[0058] S2: Starting from the liquidus temperature of the steel grade, the temperature drop from the previous process is gradually added to obtain the basic target temperature for the converter tapping temperature; the formula for calculating the basic target temperature is as follows:

[0059] T 目标 =T 转炉 +ΔT 补偿 (X);

[0060] Among them, T 转炉 The tapping temperature of the converter is expressed by the following formula:

[0061] T 精炼结束 =T 液相线 +ΔT 过热度 +ΔT1;

[0062] T 精炼开始 =T 精炼结束 +ΔT2;

[0063] T 转炉 =T 精炼开始 +ΔT3;

[0064] Wherein, ΔT1 represents the average temperature drop during the refining to continuous casting transfer process; ΔT2 represents the average temperature drop during the refining process; and ΔT3 represents the average temperature drop during the converter to refining transfer process.

[0065] S3: Extract historical process data of steel grades, use historical process parameters as input and converter tapping temperature compensation value as output, and establish a converter tapping temperature compensation prediction model.

[0066] Step S3 specifically includes the following steps:

[0067] S31: Obtain historical process data for steel grades, specifically including information such as process transfer time and ladle thermal state;

[0068] S32: Preprocess the acquired process data, clean the collected data, and remove outliers, missing values, or duplicate data.

[0069] S33: Select a machine learning algorithm to train the prediction model, using historical process parameters as input features and converter tapping temperature compensation value as output target, and train the model.

[0070] The model input includes two parts: time factors and ladle factors. The time factors include: converter tapping time, transfer time from converter to refining, RH refining treatment time and transfer time from RH refining to continuous casting.

[0071] The transfer time from converter to refining: During this period, the temperature of the molten steel will change, mainly affected by factors such as ambient heat dissipation and internal heat conduction within the molten steel. Temperature control during RH refining is crucial to the quality of the final product. The length of the RH refining treatment time affects the heating, degassing, and impurity removal effects of the molten steel, thus influencing its temperature. The transfer time from RH refining to continuous casting: The length of this transfer time directly affects the temperature state of the molten steel before reaching the continuous casting process, thereby impacting temperature control and product quality during continuous casting.

[0072] Ladle factors include: ladle age, ladle empty time (the time interval between the stop time of the previous heat and the start time of the next heat in the converter), and ladle baking time.

[0073] Ladle age: As the ladle age increases, the heat preservation performance of the ladle may gradually decrease, leading to increased temperature loss of molten steel during transportation.

[0074] Ladle emptying time: The longer the ladle is empty, the lower the temperature inside the ladle may be. When the next batch of molten steel is poured into the ladle, the cooling rate of the molten steel may increase due to the low temperature inside the ladle.

[0075] Ladle baking time: Ladle baking is an important means to improve the insulation performance of the ladle and reduce temperature loss. The baking time directly affects the insulation effect of the ladle. The longer the baking time, the better the insulation performance of the ladle is likely to be, and the temperature loss of the molten steel during the transmission process will be reduced accordingly. Therefore, using the ladle baking time as an input factor helps the model to more accurately predict the insulation performance of the ladle and the temperature changes of the molten steel.

[0076] Machine learning algorithms can employ algorithms such as case-based reasoning, neural networks, support vector machines, and random forests.

[0077] S34: Use validation set data to validate the trained model, evaluate the model's predictive performance, and calculate the model's prediction error to ensure that the model has no significant bias and can be put into application.

[0078] S35: The trained and validated model is applied to production to predict the compensation value of the converter tapping temperature in real time. Based on the real-time process parameter input, the model outputs the compensation value of the converter tapping temperature, thus obtaining the final target tapping temperature. The model's prediction results are as follows: Figure 2 As shown.

[0079] S4: Based on the process parameters of the new heat, obtain the converter tapping temperature compensation value for this heat, and combine it with the basic target temperature obtained in step S2 to obtain the final target temperature for this heat.

[0080] Step S4 specifically includes the following steps:

[0081] S41: The basic target temperature for converter tapping. The predicted converter tapping temperature compensation value is added to the basic target temperature to obtain the final target temperature for this heat.

[0082] S42: Record the calculated final target temperature in the production record or process file for subsequent tracking and analysis, and collect actual data during the production process for continuous verification and optimization of the compensation prediction model.

[0083] Traditional methods often rely on experience to set the converter tapping temperature, resulting in inaccurate temperature control and affecting product quality and production efficiency. The BOF-RH-CC process's converter tapping target temperature setting method achieves precise control of the converter tapping temperature through steps such as data acquisition and statistical analysis, basic target temperature setting, establishment of compensation prediction models, and real-time prediction and adjustment.

[0084] Example

[0085] In this embodiment, a method for setting the target tapping temperature of the converter in the BOF-RH-CC process is proposed, which specifically includes the following steps:

[0086] Step 1: Collect actual production data for the converter, RH refining and continuous casting processes, and statistically analyze the temperature drop during the transfer process from converter to refining, the temperature drop during the refining process and the temperature drop during the transfer process from refining to continuous casting.

[0087] In this embodiment, the liquidus temperature of the corresponding steel grade is 1531℃, and its superheat temperature is 28℃. The temperature control of molten steel in the steelmaking-continuous casting section is shown in Tables 1 and 2 below:

[0088]

[0089] Table 1. Temperature control of molten steel in the steelmaking-continuous casting process section.

[0090]

[0091]

[0092] Table 2 Temperature Drop in Steelmaking-Continuous Casting Process

[0093] Step 2: Starting from the liquidus temperature of the steel grade, gradually accumulate the temperature drop of the previous process / stage to obtain the basic target temperature for the converter tapping temperature; using the temperature drop of the steelmaking-continuous casting process / stage in the table above, and substituting it into the calculation formula of step S2, establish the basic temperature regime for this steel grade as shown in Table 3 below:

[0094]

[0095] Table 3 Basic Temperature Regime

[0096] Step 3: Extract information such as the process delay time and ladle thermal state from the historical process data of this steel grade. Use these process parameters as input to the model and the converter tapping temperature compensation value as output to establish a converter tapping temperature compensation prediction model. The model input process parameters are shown in the table below:

[0097]

[0098] Step 4: Obtain the converter tapping temperature compensation value for the new heat based on the process parameters, and combine it with the obtained basic target temperature to obtain the final target temperature for the heat.

[0099] If the target average tapping temperature given by the model is 1680.3℃, the actual average tapping temperature is 1682.4℃. Following the model settings, the average tapping temperature of the converter was reduced by 2.1℃, thus optimizing the tapping temperature.

[0100] The statistics of the predictive indicators are shown in Table 5:

[0101]

[0102] Table 5. Statistics of Model Prediction Indicators

[0103] The table shows that the hit rates for model predictions within the error ranges of [-5℃, 5℃], [-10℃, 10℃], and [-15℃, 15℃] are 61.33%, 78.33%, and 89%, respectively. The high hit rates across multiple error ranges indicate that the model predictions are relatively accurate and can provide reliable guidance for production. By tapping steel according to the target values ​​given by the model, more precise temperature control during production can be ensured, reducing product quality issues caused by temperature fluctuations. According to the model prediction results, the average converter tapping temperature can be reduced by 2.1℃. Optimizing the converter tapping temperature can improve product quality and consistency.

[0104] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," "left," and "right," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. These terms are used only for the convenience of describing this invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention. Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, terms such as "set" and "connect" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances. In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0105] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for setting the target tapping temperature of a converter in a BOF-RH-CC process, characterized in that, Includes the following steps: S1: Collect actual production data of converter, RH refining and continuous casting processes, and statistically analyze the temperature drop during the transfer process from converter to refining, the temperature drop during the refining process and the temperature drop during the transfer process from refining to continuous casting. S2: Starting from the liquidus temperature of the steel grade, gradually add the temperature drop of the previous process to obtain the basic target temperature for the converter tapping temperature; S3: Extract historical process data of steel grades, use historical process parameters as input and converter tapping temperature compensation value as output, and establish a converter tapping temperature compensation prediction model. S4: Based on the process parameters of the new heat, obtain the converter tapping temperature compensation value for this heat, and combine it with the basic target temperature obtained in step S2 to obtain the final target temperature for this heat.

2. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 1, characterized in that, Step S1 specifically includes the following steps: S11: Temperature data acquisition, collecting molten steel temperature data when tapping from the converter, collecting molten steel temperature data at the start of RH refining, and collecting molten steel temperature data at the start of continuous casting. S12: Temperature drop statistics. Based on the temperature at the time of steel tapping from the converter and the temperature at the start of RH refining, the temperature drop during the transfer process is calculated. The temperature drop during the transfer process from the converter to the refining is the difference between the steel tapping temperature of the converter and the RH inlet temperature.

3. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 2, characterized in that, The specific production data items collected in step S11 for the converter, RH refining, and continuous casting processes include: Converter tapping temperature, RH refining station inlet temperature, RH refining station outlet temperature, continuous casting start temperature, continuous casting tundish superheat, steel grade liquidus temperature, converter tapping start time, RH inlet time, RH outlet time, continuous casting start time, and continuous casting start sequence number.

4. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 2, characterized in that, The temperature drop statistics in step S12 specifically include the following steps: The temperature drop during the transfer process from converter to refining is the difference between the converter tapping temperature and the RH inlet temperature. The temperature drop during the refining process is calculated based on the temperature at the start and end of the RH refining process. The temperature drop during the refining process is the difference between the RH inlet temperature and the RH outlet temperature. Based on the temperature at the end of refining and the temperature at the beginning of continuous casting, the temperature drop during the transfer process is calculated. The temperature drop during the transfer process from refining to continuous casting is the difference between the RH outlet temperature and the continuous casting start temperature.

5. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 1, characterized in that, The formula for calculating the basic target temperature in step S2 is as follows: T 目标 =T 转炉 +ΔT 补偿 (X); Among them, T 转炉 The tapping temperature of the converter is expressed by the following formula: T 精炼结束 =T 液相线 +ΔT 过热度 +ΔT1; T 精炼开始 =T 精炼结束 +ΔT2; T 转炉 =T 精炼开始 +ΔT3; Wherein, ΔT1 represents the average temperature drop during the refining to continuous casting transfer process; ΔT2 represents the average temperature drop during the refining process; and ΔT3 represents the average temperature drop during the converter to refining transfer process.

6. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 1, characterized in that, Step S3 specifically includes the following steps: S31: Obtain historical process data for steel grades, specifically including information such as process transfer time and ladle thermal state; S32: Preprocess the acquired process data, clean the collected data, and remove outliers, missing values, or duplicate data. S33: Select a machine learning algorithm to train the prediction model, using historical process parameters as input features and converter tapping temperature compensation value as output target, and train the model. S34: Use validation set data to validate the trained model, evaluate the model's predictive performance, and calculate the model's prediction error to ensure that the model has no significant bias. S35: The trained and validated model is applied to production to predict the compensation value of the converter tapping temperature in real time. Based on the real-time process parameter input, the model outputs the compensation value of the converter tapping temperature, thereby obtaining the final target tapping temperature.

7. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 6, characterized in that, The model inputs in step S33 include time factors and ladle factors, wherein the time factors include... Converter tapping time, transfer time from converter to refining, RH refining treatment time, and transfer time from RH refining to continuous casting; steel factors include ladle age, empty ladle time, and ladle baking time.

8. The method for setting the target tapping temperature of a converter in a BOF-RH-CC process according to claim 1, characterized in that, Step S4 specifically includes the following steps: S41: The basic target temperature for converter tapping. The predicted converter tapping temperature compensation value is added to the basic target temperature to obtain the final target temperature for this heat. S42: Record the calculated final target temperature in the production record or process file for subsequent tracking and analysis, and collect actual data during the production process for continuous verification and optimization of the compensation prediction model.

Citation Information

Patent Citations

  • Method and device for predicting carbon content and temperature of molten steel at end point of converter

    CN113255102A

  • Method for predicting end-point carbon content and end-point temperature of small and medium-sized converter

    CN115456264A

  • Converter end point prediction method and device based on multi-task learning

    CN117093868A