Blast furnace heat trend prediction method and storage medium

Abstract

The invention discloses a blast furnace heat trend prediction method which comprises the following steps: acquiring blast furnace data including molten iron silicon content data Sn; based on heat balance of a high-temperature area at the lower part of the blast furnace, calculating by using blast furnace data to obtain an initial furnace heat index TQ of the blast furnace, and smoothing to obtain a furnace heat index TQn; calculating the heat DQn of the influence of the furnace top gas temperature change on the furnace heat trend; calculating a furnace heat trend pre-judgment index SQn according to the furnace heat index TQn and the heat DQn; carrying out linear fitting on the SQn-4t and the Sn to obtain a fitting coefficient; and judging the furnace heat trend of the blast furnace based on the change of SQn. The invention further discloses a computer readable storage medium. The method has the advantages that the prediction model is quantified, a two-dimensional prediction mechanism based on the heat index and the gas flow temperature is formed, the prediction sensitivity of the furnace heat change trend is greatly improved, the prediction result is more scientific, and the prediction accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of blast furnace ironmaking technology, specifically to a method for predicting blast furnace heat trends and a storage medium. Background Technology

[0002] Blast furnace smelting is the core process for producing molten iron in the global steel industry. Its equipment is a large, closed reactor with high temperature (up to 2000℃) and high pressure. Due to the complex internal physicochemical processes and harsh environment, it is difficult to directly and accurately monitor the real-time status, making control very difficult.

[0003] Blast furnace thermal state is a key indicator for blast furnace control. It refers to the temperature level maintained during blast furnace smelting and reflects the balance of energy supply and demand. When the energy input to the blast furnace exceeds the required energy, the thermal state tends to rise, even leading to overheating; conversely, the thermal state tends to fall, even leading to undercooling. Maintaining a suitable and stable thermal state is a prerequisite for ensuring efficient blast furnace operation and avoiding malfunctions, and it also directly affects enterprise costs and product quality.

[0004] Based on the principle of energy conservation, the thermal state of a blast furnace can theoretically be characterized by calculating the difference between heat input and heat output; the thermal index calculation is one typical method. This calculation considers the physical heat of raw materials and the heat of chemical reaction, and can reflect the thermal state of the furnace to a certain extent. However, in actual blast furnace production, complex factors such as fluctuations in gas temperature and changes in heat transfer efficiency within the furnace are not fully incorporated into the calculation model, leading to deviations between the theoretical calculation results and the actual thermal state, especially with larger errors when blast furnace temperature fluctuations occur.

[0005] In blast furnace production, the silicon content and temperature of molten iron are commonly used to characterize the furnace's thermal state for two reasons: 1. Both are strongly correlated with the furnace's internal temperature level; 2. Both serve as important quality indicators for molten iron. The latent heat change caused by variations in molten iron silicon content is far greater than the sensible heat change caused by variations in molten iron temperature, hence it is often referred to as "furnace temperature." However, the biggest drawback of using molten iron silicon content and temperature to characterize the furnace's thermal state is the time lag. From the generation of molten iron to its detection, it undergoes processes such as flow within the furnace and tapping, meaning the results cannot reflect instantaneous furnace heat in real time, interfering with timely control. Therefore, the research and optimization of prediction technologies for molten iron silicon content and temperature have always been a hot topic in the blast furnace field.

[0006] Currently, the industry primarily employs data-driven methods such as neural networks and nonlinear regression to analyze the relationship between key parameters like blast volume, blast temperature, blast humidity, pulverized coal injection rate, and coke ratio and blast furnace silicon content or molten iron temperature. However, these methods neglect the time lag characteristic of parameter influence during the smelting process. Although the prediction accuracy is high when using historical data, the accuracy drops and the prediction effect is poor when blast furnace smelting conditions change, making it difficult to meet the actual production control needs and lacking real practical application value.

[0007] Therefore, it is necessary to improve existing technologies. Summary of the Invention

[0008] The purpose of this invention is to address the shortcomings of existing technologies by providing a method and storage medium for predicting blast furnace heat trends, thereby improving prediction accuracy.

[0009] The technical solution adopted in this invention is: a method for predicting the thermal trend of a blast furnace, comprising: Obtain blast furnace data, including silicon content data in molten iron. S n ; Based on the heat balance in the high-temperature zone at the bottom of the blast furnace, the initial furnace heat index of the blast furnace is calculated using blast furnace data. TQ The furnace thermal index was obtained after smoothing. TQ n ; Calculate the heat effect of changes in furnace top gas temperature on furnace thermal trend. DQ n ; According to the furnace heat index TQ n and calories DQ n Calculate the furnace heat trend prediction index SQ n ;Will t Furnace heat trend prediction indicators 1 hour ago SQ n-4t With iron and silicon content S n Perform linear fitting to obtain the fitting coefficients; Based on the obtained fitting coefficients, SQ n The changes are used to judge the thermal trend of the blast furnace.

[0010] According to the above scheme, based on SQ n The specific method for judging the blast furnace heat trend based on changes is as follows: compare the current furnace heat trend prediction index. SQ n and the value of the previous calculation time SQ n-1 Calculate the difference between the two and make a judgment according to the following conditions: (1) When At that time, the furnace heating trend is judged. t It will drop significantly in the next few hours; (2) When At that time, the furnace heating trend is judged. t It will drop slightly in the next few hours; (3) When At that time, the furnace heating trend is judged.t The situation will be relatively stable in the next few hours; (4) When At that time, the furnace heating trend is judged. t It will rise slightly in the next few hours; (5) When At that time, the furnace heating trend is judged. t It will rise sharply in the next few hours.

[0011] According to the above scheme, regarding the silicon content data of molten iron, if T n If there is no directly detectable data on the silicon content of molten iron, then... T n The most recent moment before T n-1 Corresponding silicon content S n-1 With the most recent moment T n+1 Corresponding silicon content S n+1 Based on this, calculations were performed. S n .

[0012] According to the above plan, S n The calculation formula is: (1).

[0013] According to the above scheme, the initial furnace heat index of the blast furnace is calculated using formula (2). TQ : (2); In formula (2), Q 1 represents the heat introduced by the blower, in MJ / thm; Q 2 represents the heat released by carbon combustion in front of the air vent, in MJ / thm; Q 3 represents the heat consumed in water decomposition, in MJ / thm; Q 4 represents the heat consumed by the solution loss reaction, in MJ / thm; Q 5 represents the heat loss in the furnace belly, in MJ / thm; Q 6 represents the heat consumption of pulverized coal decomposition, in MJ / thm.

[0014] According to the above scheme, the furnace heat index is obtained. TQ n The specific method is as follows: The nth smoothed item in chronological order TQ for TQ n , TQ 1. Calculate using formula (2), exceptTQ TQ other than 1 n Calculate according to formula (3), which is as follows: (3); In formula (3), TQ n-1 The (n-1)th smoothed version in chronological order TQ The unit is MJ / thm.

[0015] According to the above plan, the heat... DQ n The calculation method is as follows: the calculation frequency is set to once every 15 minutes, and the calculation is performed using formula (4): (4); In formula (4), DQ n The heat caused by the change in the temperature of the gas at the furnace top, in MJ / thm; T 1 represents the average furnace top temperature over the past year, in °C; T 2 represents the average furnace top temperature over the past 15 minutes, in °C; C Specific heat capacity of the top gas, kJ / (kg·K); ρ Density of gas at the furnace top, kg / m³ 3 ; TV The amount of gas produced, in m 3 / min; W The value represents the rate of molten iron formation, in thm / min.

[0016] According to the above scheme, blast furnace data includes blast furnace monitoring data. The blast furnace monitoring data is calculated in 15-minute statistical cycles, and the average value within the cycle is used as valid data.

[0017] According to the above plan, t The value range is 1 to 2.

[0018] The present invention also employs a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the blast furnace heat trend prediction method described above.

[0019] The beneficial effects of this invention are as follows: 1. Based on current research methods and actual blast furnace production operations, this invention uses the heat balance (i.e., heat input and output) of the high-temperature zone of the blast furnace to calculate the furnace heat index, and performs correlation analysis between the calculation results and the silicon content of the molten iron in the blast furnace to predict the trend of blast furnace heat change. This method quantifies the prediction model and forms a two-dimensional prediction mechanism based on the heat index and gas flow temperature, which greatly improves the prediction sensitivity of the furnace heat change trend, makes the prediction results more scientific, and improves the prediction accuracy. 2. This invention fully considers the time lag characteristics of parameter influence during the smelting process, smooths the data to compensate for the lag effect, effectively avoids the deviation caused by lag in traditional prediction, and ensures the accuracy and reliability of the prediction results. 3. The present invention is less affected by human factors, requires no additional auxiliary testing equipment, and does not increase production costs. Attached Figure Description

[0020] Figure 1 This is a flowchart of the blast furnace heat trend prediction method in this invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the description of the embodiments of this application, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and 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 the embodiments of this application. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0023] In the description of the embodiments of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application based on the specific circumstances.

[0024] In the embodiments of this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0025] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples, without contradiction. Additionally, the term "a plurality of" indicates two or more.

[0026] like Figure 1 The method shown includes the following steps for predicting the heat trend of a blast furnace: Step 1: Obtain blast furnace data: Collect blast furnace data for the most recent year, including blast furnace monitoring data and iron silicon content data. n .

[0027] In this invention, the blast furnace monitoring data must meet the requirement of accurate acquisition every 15 minutes. Specifically, the monitoring data is collected in 15-minute statistical cycles, and the average value within each cycle is read and calculated as valid data. The blast furnace monitoring data includes data that can be directly monitored by the equipment, such as furnace top temperature and gas generation, as well as process monitoring data calculated using existing methods, such as the heat generated by the blast furnace, the heat released by carbon combustion in front of the tuyeres, the heat consumed by water decomposition, the heat consumed by the melting reaction, the heat loss in the furnace belly, the heat consumed by pulverized coal decomposition, and the rate of molten iron formation.

[0028] In this invention, because the detection of silicon content in molten iron needs to be carried out for each molten iron ladle and torpedo ladle, the time interval of the detection data is not fixed and irregular. In order to achieve a one-to-one correspondence between the silicon content data of molten iron and the blast furnace monitoring data in the time dimension, it is necessary to process the collected historical data of silicon content in molten iron. The specific processing method is as follows: For a certain target time Tn The silicon content of the molten iron at that moment needs to be calculated. S n (Dimensionless data), if T n If there is no directly detectable data on the silicon content of molten iron, then... T n The most recent moment before T n-1 Corresponding silicon content S n-1 With the most recent moment T n+1 Corresponding silicon content S n+1 Based on this, calculations were performed. S n The calculation formula is as follows: (1).

[0029] Step 2: Based on the heat balance in the high-temperature zone at the bottom of the blast furnace, calculate the initial furnace heat index using blast furnace data. TQ The blast furnace heat index was obtained by smoothing the process. TQ n .

[0030] In this invention, the high-temperature zone refers to the belly, waist, and lower part of the blast furnace, where the temperature is above 1200℃. The initial furnace heat index of the blast furnace... TQ The heat balance calculation is performed using the high-temperature zone, specifically the heat gain in the high-temperature zone. Q 1+ Q 2) Subtract the heat expenditure from the high-temperature zone ( Q 3+ Q 4+ Q 5+ Q 6) The formula is as follows: (2); In formula (2), Q 1 represents the heat introduced by the blast, in MJ / thm (the heat per ton of molten iron, hm is the abbreviation for molten iron, commonly used in the industry). Q 2 represents the heat released by carbon combustion in front of the air vent, in MJ / thm; Q 3 represents the heat consumed in water decomposition, in MJ / thm; Q 4 represents the heat consumed by the solution loss reaction, in MJ / thm; Q 5 represents the heat loss in the furnace belly, in MJ / thm; Q 6 represents the heat consumption of pulverized coal decomposition, in MJ / thm.

[0031] In this invention, TQ The calculation frequency is once every 15 minutes, of whichQ 1 to Q 6 are commonly used parameters in industry production, and can be calculated from the blast furnace monitoring data in step one. They are conventional technologies and will not be elaborated on in this article.

[0032] In furnace heat index TQ In practical applications, it has been found that because its calculation is based on the thermal balance of the lower high-temperature zone under steady-state conditions within a 15-minute short cycle of the blast furnace, when the blast furnace operating parameters are adjusted slightly... TQ Significant fluctuations will occur, causing the initial furnace heat index to deviate from the actual thermal state of the blast furnace. To resolve this issue, the initial furnace heat index needs to be adjusted. TQ Smoothing process is performed to obtain the furnace heat index. TQ n The specific processing method is as follows; The nth smoothed item in chronological order TQ for TQ n , TQ 1. Calculate using formula (2), except TQ 1 and others TQ n (n≥2) Calculate according to formula (3), which is as follows: (3); In formula (3), TQ n-1 The (n-1)th smoothed version in chronological order TQ , MJ / thm; TQ The nth unsmoothed time sequence calculated according to formula (2) TQ , MJ / thm.

[0033] Step 3: Calculate the heat effect of the change in furnace top gas temperature on the furnace thermal trend. DQ n .

[0034] When blast furnace operation fluctuates or malfunctions, such as pipe leaks, charge slippage, or charge collapse, insufficient preheating of the burden by the gas in the medium-low temperature zone of the upper part of the blast furnace can occur, leading to an increase in the furnace top temperature and affecting the thermal balance of the high-temperature zone in the lower part of the blast furnace. Since the temperature of the burden inside the blast furnace cannot be directly monitored, while the temperature of the furnace top gas is available for real-time monitoring, it is necessary to calculate the heat effect caused by changes in the furnace top gas temperature. DQ n The calculation method is as follows: the calculation frequency is set to once every 15 minutes, and the calculation is performed using formula (4): (4) In formula (4), DQ nThe heat caused by the change in the temperature of the gas at the furnace top, in MJ / thm; T 1 represents the average furnace top temperature over the past year, in °C; T 2 represents the average furnace top temperature over the past 15 minutes, in °C; C Specific heat capacity of the top gas, kJ / (kg·K); ρ Density of gas at the furnace top, kg / m³ 3 ; TV The amount of gas produced, in m 3 / min; W The value represents the rate of molten iron formation, in thm / min.

[0035] The parameters in formula (4) are as follows T 1. T 2. TV , ρ , W All of these can be obtained using existing technologies.

[0036] Step 4: Calculate the furnace heat trend prediction index SQ n , SQ n = TQ n - DQ n The calculation frequency is also once every 15 minutes; S n Furnace heat trend prediction index t hours ago SQ n-4t Perform a corresponding fit to obtain the fit coefficients and the fit formula, where , A and B All are fitting coefficients.

[0037] In this invention, the following is adopted: SQ n Compared with step one S n Linear fitting was performed, using historical data from the most recent month as the sample for the fitting analysis. Because... SQ n Used to predict furnace heat. S n As a result, based on practice, SQ n Earlier than S n Approximately t hours t The value ranges from 1 to 2. The larger the blast furnace volume, the... t The larger the value, the greater the value (t is an empirical value). When performing linear fitting, the silicon content in the molten iron... S n and t Furnace heat trend prediction index 1 hour agoSQ n-4t (The frequency is 15 minutes each time, so data from t hours ago is sufficient.) SQ n-4t Perform a linear fit to obtain the fitting coefficients. A , B and fitting formula .

[0038] Step 5: Based on the obtained fitting coefficients, SQ n The changes are used to judge the thermal trend of the blast furnace.

[0039] based on SQ n The specific method for judging the blast furnace heat trend based on changes is as follows: compare the current furnace heat trend prediction index. SQ n The value of the previous calculation time (i.e., the previous 15 minutes). SQ n-1 Calculate the difference between the two and make a judgment according to the following conditions: (1) When At that time, the furnace heating trend is judged. t The concentration will decrease significantly after several hours, with the corresponding Si content decreasing by more than 0.2%. (2) When At that time, the furnace heating trend is judged. t The concentration will decrease slightly after a few hours, corresponding to a decrease in Si content of 0.1% to 0.2%. (3) When At that time, the furnace heating trend is judged. t The situation will stabilize after a few hours, with the corresponding increase or decrease in Si content not exceeding 0.1%. (4) When At that time, the furnace heating trend is judged. t It will rise slightly after a few hours, corresponding to an increase of 0.1%-0.2% in Si content; (5) When At that time, the furnace heating trend is judged. t The concentration will increase significantly after a few hours, corresponding to an increase in Si content of more than 0.2%.

[0040] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the blast furnace heat trend prediction method.

[0041] Example 1 This embodiment determines a certain 3000m 3 The steps for determining the heat trend of a primary blast furnace are as follows: Step 1: Collect data.

[0042] In this embodiment, data is collected from the blast furnace secondary database, including blast furnace monitoring data and iron silicon content detection data. The collected data must include at least the data from the most recent year. The accuracy requirement for the collected blast furnace monitoring data is 15 minutes, that is, the average value is read every 15 minutes. The monitoring data includes direct equipment monitoring data (such as furnace top temperature and gas generation) and existing calculated process monitoring data (such as heat from blast furnace, heat released by carbon combustion in front of the tuyeres, heat consumption from moisture decomposition, heat consumption from dissolution reaction, heat loss in the furnace belly, heat consumption from pulverized coal decomposition, and iron generation rate).

[0043] In this embodiment, all iron-silicon content detection data are collected and preprocessed. For the iron-silicon content at a certain time point, if there is no iron-silicon content detection data for that time point, linear fitting calculation is performed using the most recent preceding data and the most recent following data. Let a target time T be... n To calculate the silicon content of the molten iron at that moment... S n The moment before the most recent detection data was T n-1 Corresponding to the silicon content of molten iron S n-1 The latest moment for which detection data is available is T n+1 Corresponding to the silicon content of molten iron S n+1 The calculation method is shown in formula (1).

[0044] For example, at 8:00 AM on June 25, 2025, there was no data on the silicon content of molten iron; the most recent available data was at the moment T. n-1 The calculation for 7:50 AM (the goal here is data alignment; the irregularly distributed iron-silicon content data is adjusted to a value every 15 minutes) corresponds to the iron-silicon content S. n-1 It is 0.30%, the most recent last moment. T n+1 The time is 8:15, corresponding to the silicon content of molten iron. S n+1 If the silicon content is 0.36%, then according to formula (1), the silicon content of molten iron at point 8 is (0.36%-0.30%)×10 / 25+0.30%≈0.32%.

[0045] Step 2: Calculate the blast furnace heat index using formula (2). TQ The blast furnace heat index is then obtained by smoothing the surface. TQ n .

[0046] For example, at 8:00 AM on June 25, 2025, Q1 to Q The values ​​for 6 are 488 MJ / thm, 3588 MJ / thm, 349 MJ / thm, 1625 MJ / thm, 52 MJ / thm, and 12 MJ / thm, respectively. These values ​​were calculated using formula (2). TQ It is 2038 MJ / thm. TQ n-1 It is 2102 MJ / thm, which can be obtained according to formula (3). TQ n It is 2089 MJ / thm.

[0047] Step 3: Calculate the heat effect of the change in furnace top gas temperature on the furnace thermal trend. DQ n The calculation frequency is once every 15 minutes, and the effect of the change in the temperature of the gas at the top of the furnace is calculated according to formula (4).

[0048] For example, 8:00 AM on June 25, 2025 T 1 is 143℃. T 2 is 128℃. C It is 1.23 kJ / (kg·K). ρ It is 1.3 kg / m 3 , TV It is 9102 kg / m 3 , W It is 6.3 thm / min, which can be calculated. DQ n It is 35 MJ / thm.

[0049] Step 4: Calculate the furnace heat trend prediction index SQ n , SQ n = TQ n - DQ n The calculation frequency is also once every 15 minutes.

[0050] In this embodiment, the calculated time is 8:00 AM on June 25, 2025. SQ n The value is 2089-35=2054 (MJ / thm); using SQ n Compared with step one S n Linear fitting was performed using data from the most recent month (from 7:45 AM on May 26th to 7:45 AM on June 25th). Based on practical experience, this blast furnace... SQ n Earlier than S n Approximately 1.5 hours, that ist The value is taken over 1.5 hours; when performing linear fitting, S n The furnace heat trend prediction index data from t hours ago is... SQ n-6 Perform linear fitting to obtain A=152055.

[0051] because S n and SQ n-6 The correlation is strong, so a linear fitting method is used here, which is a conventional technique.

[0052] Step 5: Compare with the current furnace heat trend prediction index SQ n The value SQ in the first 15 minutes n-1 Based on SQ n The changes in these factors can be used to determine the thermal trend of the blast furnace. The specific method is as follows: (1) When If the temperature is high, it is judged that the furnace heat trend will drop significantly after 1.5 hours; (2) When If the temperature is high, it is judged that the furnace heat trend will decrease slightly after 1.5 hours; (3) When If the temperature is high, it is judged that the furnace heat trend will be relatively stable after 1.5 hours. (4) When If the temperature is high, it is judged that the furnace heat trend will rise slightly after 1.5 hours; (5) When If the temperature is high, it is judged that the furnace heat trend will rise significantly after 1.5 hours.

[0053] Based on the above steps, at 8:00 AM on June 25, 2025, SQ n The value is 2054 MJ / thm. The SQ value at 7:45 AM on June 25, 2025 was calculated using the same method. n-1 2084 MJ / thm, SQ n -SQ n-1 =-30MJ / thm. Therefore, it is judged that the heat trend of the blast furnace will be relatively stable after 1.5 hours.

[0054] To verify the judgment result of step five, the original detection data of ferrosilicon content at around 9:30 on June 25, 2025 were found. At 9:16, it was 0.31% and at 9:32, it was 0.28%. According to formula (1), the ferrosilicon content at 9:30 was (0.28%-0.31%)×14 / 16+0.31%≈0.28%. Compared with the ferrosilicon content of 0.32% at 8 o'clock, the change in silicon content was within 0.1%, indicating that the furnace heat trend was stable and the judgment of the furnace heat trend was correct.

[0055] Example 2 In most cases, the furnace temperature is relatively stable during blast furnace production, as shown in Example 1. However, there are times when the furnace temperature fluctuates significantly. For example, in the case of the blast furnace in Example 1, at 15:30 on July 18, 2025, data statistics and calculations were performed according to the steps in Example 1.

[0056] Step 1: Calculate and process the silicon content data of molten iron. The results show that the silicon content of molten iron at 15:19 was 0.47% and at 15:39 was 0.49%. Therefore, the silicon content of molten iron at 15:30 is calculated to be (0.49% - 0.47%) × 9 / 20 + 0.47% ≈ 0.48%. Step 2, Calculation TQ n At 3:30 PM on July 18, 2025, Q 1 to Q The values ​​for 6 are 493 MJ / thm, 3213 MJ / thm, 305 MJ / thm, 1652 MJ / thm, 37 MJ / thm, and 10 MJ / thm, respectively. These values ​​were calculated using formula (2). TQ It is 1702 MJ / thm. TQ n-1 It is 1917 MJ / thm, which can be obtained according to formula (3). TQ n It is 1874 MJ / thm.

[0057] Step 3: Calculate the heat effect of the change in furnace top gas temperature on the furnace thermal trend. DQ n The calculation frequency is once every 15 minutes, and the effect of the change in the temperature of the gas at the top of the furnace is calculated according to formula (4). At 15:30 on July 18, 2025, T 1 represents 155℃. T 2 is 123℃. C It is 1.23 kJ / (kg·K). ρ It is 1.3 kg / m 3 , TV 9325 kg / m 3 , WIt is 6.1 thm / min, which can be calculated. DQ n It is 78 MJ / thm.

[0058] Step 4: Calculate the furnace heat trend prediction index SQ n 3:30 PM on July 18, 2025 SQ n The result is 1874-78=1796MJ / thm. Using data from the most recent month (15:15 on June 18th to 15:15 on July 18th)... S n and SQ n-6 Perform linear fitting to obtain .

[0059] Step 5: Compare with the current furnace heat trend prediction index SQ n And the value of the previous 15 minutes SQ n-1 ,based on SQ n The changes in these factors can be used to determine the thermal trend of the blast furnace. The specific method is as follows: (1) When If the temperature is high, it is judged that the furnace heat trend will drop significantly after 1.5 hours; (2) When If the temperature is high, it is judged that the furnace heat trend will decrease slightly after 1.5 hours; (3) When If the temperature is high, it is judged that the furnace heat trend will be relatively stable after 1.5 hours. (4) When If the temperature is high, it is judged that the furnace heat trend will rise slightly after 1.5 hours; (5) When If the temperature is high, it is judged that the furnace heat trend will rise significantly after 1.5 hours.

[0060] Based on the above steps, at 3:30 PM on July 18, 2025... SQ n The value is 1796 MJ / thm. The same method was used to calculate the value at 15:15 on July 18, 2025. SQ n-1 It is 1968 MJ / thm. SQ n - SQ n-1 =-172MJ / thm. Therefore, it is judged that the blast furnace heat trend will decrease slightly after 1.5 hours.

[0061] Considering that the silicon content of the blast furnace iron is suitable to be controlled within the range of 0.3%-0.5%, there is no need to adopt furnace heat regulation measures. We can wait for the furnace heat to decrease slightly by 0.1%-0.2% to a better level. At this time, the blast furnace judged by this method that no furnace heat regulation measures were adopted. The judgment result was then verified. The original detection data of silicon iron content at around 17:00 on July 18, 2025 were found. At 16:45, it was 0.40%, and at 17:07, it was 0.34%. According to formula (1), the silicon content of the blast furnace iron at 17:00 was (0.34%-0.40%)×15 / 22+0.40%≈0.36%. Compared with the silicon content of 0.48% at 15:30, the silicon content decreased by 0.12%, which is within the range of 0.1%-0.2%, which is a slight decrease. The furnace heat decreased slightly, and the judgment was correct.

[0062] If judged based on traditional manual experience, seeing the silicon content of molten iron at 15:19 and 0.49% at 15:39, one might assume that the furnace temperature remains unchanged or has increased slightly. However, considering that the silicon content of molten iron in this blast furnace is ideally controlled within the range of 0.3%-0.5%, seeing that the silicon content is close to the upper limit might lead to unnecessary control measures that could cause fluctuations in furnace conditions.

[0063] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

[0064] Finally, it should be noted that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. However, any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A blast furnace heat trend prediction method characterized by, Includes: Obtaining blast furnace data, including hot metal silicon content data S n ; Based on the heat balance of the high temperature zone of the lower part of the blast furnace, the initial furnace heat index of the blast furnace is obtained by using the data of the blast furnace TQ , and the furnace heat index is obtained after smoothing TQ n ; Heat to calculate the effect of change in top gas temperature on furnace heat trend DQ n ; According to the furnace heat index TQ n and heat DQ n Calculate the furnace heat trend prediction index SQ n ; the t furnace heat trend prediction index of the previous hour SQ n-4t with the silicon content of the hot metal S n linear fitting is performed to obtain the fitting coefficient; Based on the obtained fitting coefficients, the blast furnace thermal trend is judged based on SQ n the change of the blast furnace thermal trend.

2. The blast furnace heat trend prediction method according to claim 1, wherein, Based on SQ n The specific method for determining the blast furnace heat trend based on the change is: comparing the current blast furnace heat trend prediction index SQ n with the value at the previous calculation time SQ n-1 , calculating the difference between the two, and making a judgment according to the following cases: (1) When the furnace heat trend t will decrease significantly after 1 hour; (2) When the furnace heat trend is t to decrease slightly after 1 hour. (3) When the furnace heat trend t will be more stable after 1 hour. (4) When the furnace heat trend t will rise slightly after 4 hours; (5) When the furnace heat trend t will rise sharply after 6 hours.

3. The blast furnace heat trend prediction method of claim 1, wherein, For the hot metal silicon content data, if T n There is no direct detection of hot metal silicon content data at the moment, then with T n The previous moment T n-1 The corresponding silicon content S n-1 The corresponding silicon content T n+1 The corresponding silicon content S n+1 As the basis, the calculation is S n .

4. The blast furnace heat trend prediction method as claimed in claim 3, characterized by, S n The calculation formula is: （1）。 5. The blast furnace heat trend prediction method of claim 1, wherein, The initial furnace heat index of the blast furnace is calculated using equation (2) TQ : （2）； In equation (2), Q 1 is the heat brought in by the blast, MJ / thm; Q 2 is the heat released by carbon combustion before the tuyere, MJ / thm; Q 3 is the heat consumed by water decomposition, MJ / thm; Q 4 is the heat consumed by solution loss reaction, MJ / thm; Q 5 is the heat loss in the bosh, MJ / thm; Q 6 is the heat consumed by pulverized coal decomposition, MJ / thm.

6. The blast furnace thermal trend prediction method of claim 5, wherein, Obtaining a furnace heat index TQ n The specific method is: Smoothed in time order n-th TQ For TQ n , TQ 1 calculated using equation (2), except TQ 1 TQ n calculated using equation (3), which is as follows: （3）； In formula (3), TQ n-1 the time-sequentially (n-1)th smoothed value TQ , in MJ / thm.

7. The blast furnace thermal trend prediction method of claim 1, wherein, Heat DQ n The calculation method is: the calculation frequency is set to once every 15 minutes, and formula (4) is used for calculation: （4）； In formula (4), DQ n Heat for the influence of the change of the top gas temperature, MJ / thm; T 1 is the average value of the top temperature in the past year, ℃; T 2 is the average value of the top temperature in the past 15 minutes, ℃; C Specific heat capacity of the top gas, kJ / (kg·K); p Density of the top gas, kg / m 3 ; TV Gas generation amount, m 3 / min; W Molten iron production rate, thm / min.

8. The blast furnace heat trend prediction method of claim 1, wherein, The blast furnace data includes blast furnace monitoring data, and the blast furnace monitoring data is read and calculated in every 15 minutes as a statistical period, and the average value in the period is taken as effective data.

9. The blast furnace thermal trend prediction method of claim 1, wherein, t the value range of a is 1~2.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is executed by the processor to realize the steps of the blast furnace heat trend prediction method in any one of claims 1-9.

Images