Silicon concentration prediction method, operation guidance method, silicon concentration prediction device, operation guidance device, operation guidance system, and terminal device

Abstract

The silicon concentration prediction method includes: a prediction step (S1) for predicting a future prediction value and a current value of silicon concentration using a statistical model and physical model in which an operating variable of a blast furnace is used as input and silicon concentration is used as output; and an adjustment amount calculation step (S3) for, if the predicted value or the current value largely deviate from a target value, calculating the adjustment amount of the charging amount of a desiliconization material for the operation action that reduces the silicon concentration by charging the desiliconization material, or for calculating the adjustment amount of the operating variable for the operation action that controls the heat level in the blast furnace in order to increase the silicon concentration at the time of tapping before desiliconization.

Description

Si concentration prediction method, operation guidance method, Si concentration prediction device, operation guidance device, operation guidance system, and terminal device

[0001] The present disclosure relates to a Si concentration prediction method, an operation guidance method, a Si concentration prediction device, an operation guidance device, an operation guidance system, and a terminal device.

[0002] In the blast furnace and converter processes in the steel industry, the silicon concentration in molten pig iron (molten pig iron silicon concentration) is an important variable because it is an indicator of the product for the blast furnace and a component of the raw material for the converter. ２ In response to social demands for reduction, reductions in the molten iron blending ratio (pig iron ratio) in converters are being promoted, and Si in the molten iron is being actively utilized as a heat source in converters.

[0003] If the Si concentration in the molten pig iron is too low, it is necessary to add an excess heat source (such as FeSi) to the converter, which leads to an increase in raw material costs. On the other hand, if the Si concentration in the molten pig iron is too high, slopping may occur in the pretreatment process, reducing productivity, or it may become necessary to add excess quicklime to adjust the basicity. As such, since there is an optimum point for the Si concentration, it is necessary to adjust the Si concentration to the optimum point on the blast furnace side.

[0004] Various techniques for predicting the Si concentration in a blast furnace have been proposed. For example, Patent Document 1 proposes a method for predicting the Si concentration in the blast furnace by calculating a predicted value of the future molten iron temperature when the operation amount is maintained, constructing a regression equation based on the calculated predicted value, and inputting the value into the regression equation.

[0005] Japanese Patent Application Laid-Open No. 2021-17607

[0006] To adjust the Si concentration, possible operational actions include lowering the Si concentration by adding desiliconizing material to the casthouse or controlling the heat level in the blast furnace to change the Si concentration at the time of tapping before desiliconization. Here, the heat level refers to the temperature range within the furnace. The temperature range may be constant or variable. In current blast furnace operations, analyzing the Si concentration takes time, so actual values ​​are obtained one to two hours after tapping. Therefore, when adding desiliconizing material to the casthouse, it is necessary to accurately estimate (predict) the current Si concentration. Furthermore, when changing the Si concentration by controlling the heat level in the blast furnace, the thermal inertia of the blast furnace process is significantly affected, and operational actions have limited immediate effect, so predictions of more than two hours in advance are essential. Therefore, a highly accurate prediction method that can accommodate both of these operational actions is needed.

[0007] In addition, there is a need for coordination between the ironmaking (blast furnace) and steelmaking processes. For example, if it were possible to appropriately inform the ironmaking operator whether or not to add desiliconization material after tapping, based on the amount of heat source required for the blowing charge in the converter on the steelmaking side, it is thought that this would lead to further reductions in steelmaking costs. However, conventional methods were limited to predicting the Si concentration in the blast furnace process alone.

[0008] The present disclosure has been made to solve the above problems and aims to provide a Si concentration prediction method, an operation guidance method, a Si concentration prediction device, an operation guidance device, an operation guidance system, and a terminal device that are capable of predicting the Si concentration with high accuracy.

[0009] (1) A method for predicting a Si concentration according to an embodiment of the present disclosure includes: a prediction step of predicting a future predicted value and a current value of the Si concentration using a statistical model and a physical model that have operational variables of a blast furnace as inputs and an Si concentration as output; and an adjustment amount calculation step of calculating, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of an amount of desiliconizing material to be added in an operational action of adding a desiliconizing material to reduce the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling the heat level in the blast furnace to increase the Si concentration at the time of tapping iron before desiliconization.

[0010] (2) As one embodiment of the present disclosure, in (1), in the prediction step, the statistical model is used to predict the current value and the predicted value up to a predetermined time, and the physical model is used to predict the predicted value beyond the predetermined time, and the predetermined time is determined based on the time at which the prediction accuracy of the statistical model becomes lower than the prediction accuracy of the physical model.

[0011] (3) As one embodiment of the present disclosure, in (1) or (2), the operational variables that are inputs to the statistical model include at least one of tuyere embedding temperature, furnace heat index, solution loss carbon amount, furnace top gas temperature, tuyere tip gas temperature, and blast volume consumption rate.

[0012] (4) As an embodiment of the present disclosure, in any one of (1) to (3), the operational variables that are inputs to the physical model include at least one of a blast flow rate, a blast oxygen flow rate, a pulverized coal flow rate, a coke rate, a blast moisture content, and a blast temperature.

[0013] (5) An operation guidance method according to an embodiment of the present disclosure includes a step of having an operator present the predicted value predicted by any one of the Si concentration prediction methods (1) to (4) and the current value.

[0014] (6) An operation guidance method according to an embodiment of the present disclosure includes an input step in which a corrected target value of a Si concentration is input, and the adjustment amount calculation step calculates an adjustment amount of the operation variable using the corrected target value input in the input step as the target value.

[0015] (7) As an embodiment of the present disclosure, in (6), the corrected target value is set based on input information from an operator other than an ironmaking operator.

[0016] (8) An Si concentration prediction device according to an embodiment of the present disclosure includes: a memory unit that stores a statistical model and a physical model that receive operational variables of a blast furnace as input and output a Si concentration; a prediction unit that predicts a future predicted value and a current value of the Si concentration using the statistical model and the physical model; and an adjustment amount calculation unit that calculates, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of an amount of desiliconization material to be added in an operational action of adding a desiliconization material to reduce the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling the heat level in the blast furnace to increase the Si concentration at the time of tapping iron before desiliconization.

[0017] (9) An operation guidance device according to an embodiment of the present disclosure includes: a storage unit that stores a statistical model and a physical model that receive operational variables of a blast furnace as input and output a Si concentration; a prediction unit that predicts a future predicted value and a current value of the Si concentration using the statistical model and the physical model and presents the predicted value and the current value to an operator; and an adjustment amount calculation unit that calculates, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of an amount of desiliconization material to be added in an operational action of adding a desiliconization material to reduce the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling a heat level in the blast furnace to increase the Si concentration at the time of tapping iron before desiliconization.

[0018] (10) An operation guidance system according to an embodiment of the present disclosure includes an operation guidance device and a terminal device, wherein the operation guidance device or the terminal device includes: a storage unit that stores a statistical model and a physical model that receive operational variables of a blast furnace as input and output a Si concentration; a prediction unit that predicts a future predicted value and a current value of the Si concentration using the statistical model and the physical model and outputs the predicted value and the current value; an adjustment amount calculation unit that calculates, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of an amount of desiliconization material to be charged in an operational action of charging a desiliconization material to reduce the Si concentration or an adjustment amount of the operational variable in an operational action of controlling a heat level in a blast furnace to increase the Si concentration at the time of tapping iron before desiliconization, and outputs the adjustment amount; an acquisition unit that acquires the predicted value, the current value, and the adjustment amount; an input unit that receives input of a corrected target value of the Si concentration and a future time or time zone to be corrected; and a transmission unit that transmits the input corrected target value and the future time or time zone to be corrected. and a display unit that displays the acquired predicted value, current value, adjustment amount, and correction target value, as well as the future time or time period to be corrected.

[0019] (11) A terminal device according to an embodiment of the present disclosure includes: an acquisition unit that acquires, when a future predicted value and a current value of a Si concentration predicted by a statistical model and a physical model that have blast furnace operation variables as input and Si concentration as output, calculates an adjustment amount for an amount of desiliconization material to be added in an operation action of adding desiliconization material to decrease the Si concentration or an adjustment amount for an operation variable in an operation action of controlling a heat level in a blast furnace to increase the Si concentration at the time of tapping iron before desiliconization, if the predicted value or the current value significantly deviates from a target value; an acquisition unit that acquires the predicted value, the current value, and the adjustment amount; an input unit that receives an input of a correction target value for the Si concentration and a future time or time zone for which the correction should be made; a transmission unit that transmits the input correction target value and the future time or time zone for which the correction should be made; and a display unit that displays the acquired predicted value, the current value, the adjustment amount, the correction target value, and the future time or time zone for which the correction should be made.

[0020] (12) As an embodiment of the present disclosure, in (11), the device further includes an inter-terminal communication unit that transmits and receives information about the correction target value to and from another terminal device.

[0021] According to the present disclosure, it is possible to provide a Si concentration prediction method, an operation guidance method, a Si concentration prediction device, an operation guidance device, an operation guidance system, and a terminal device that are capable of predicting the Si concentration with high accuracy.

[0022] FIG. 1 is a diagram showing input / output information of a statistical model used in the present disclosure. FIG. 2 is a diagram illustrating a prediction result by the statistical model. FIG. 3 is a diagram showing input / output information of a physical model used in the present disclosure. FIG. 4 is a diagram illustrating an example of a guidance screen for an operator. FIG. 5 is a diagram showing an example of the configuration of a Si concentration prediction device according to an embodiment. FIG. 6 is a flowchart showing a Si concentration prediction method according to an embodiment.

[0023] Hereinafter, with reference to the drawings, a Si concentration prediction method, an operation guidance method, a Si concentration prediction device, an operation guidance device, an operation guidance system, and a terminal device according to an embodiment of the present disclosure will be described. In this disclosure, a statistical model and a physical model are used. The statistical model and the physical model are used selectively depending on the prediction time, and a highly accurate prediction is combined and presented to, for example, an operator. Below, the mechanism for determining the Si concentration, the statistical model, and the physical model will be described in this order. In the description of this embodiment, the Si concentration means the "Si concentration in molten iron," i.e., the molten iron Si concentration.

[0024] The following two mechanisms are known to determine the Si concentration in a blast furnace. Here, [x] in the reaction formula indicates the component x in the molten iron, and (x) indicates the component x in the slag. First, in the first mechanism, SiO gas is generated in the combustion section of the tuyere of the blast furnace (SiO ２ The second mechanism is the SiO+[C]→[Si]+CO absorption at the slag-metal interface in the hearth of the blast furnace. ２ Reduction reaction ((SiO ２ ) + 2C → [Si] + 2CO).

[0025] In molten iron, the thermodynamic equilibrium of [Si] exceeds 10%. However, the Si concentration measured is at most about 2%. Therefore, it is thought that [Si] has not reached equilibrium. In addition, both mechanisms are significantly affected by the thermal state in the furnace. Therefore, in this embodiment, factors related to furnace heat are taken into account when calculating the predicted value of the Si concentration.

[0026] The statistical model is not limited to a specific model, but for example, the LW-PLS (Locally-Weighted Partial Least Squares) model can be adopted as in this embodiment. The LW-PLS model places emphasis on past data similar to the current operating conditions and makes it possible to predict the Si concentration while suppressing overfitting due to multicollinearity.

[0027] As shown in FIG. 1 , the main time-varying input variables given to the statistical model are the tuyere embedding temperature, furnace heat index, solution loss carbon content, furnace top gas temperature, tuyere tip gas temperature, and blast rate consumption. These input variables are blast furnace operation variables, and are measured values ​​obtained by sensors installed in the blast furnace or values ​​obtained from known conversion formulas based on the measured values. Here, the blast furnace operation variables are parameters set or measured in relation to the operation of the blast furnace. The input of the statistical model may include at least one of these operation variables. The tuyere embedding temperature, furnace top gas temperature, and tuyere tip gas temperature are the temperatures of the embedded part of the tuyere, the furnace top gas, and the gas at the tuyere tip, respectively. The furnace heat index is the amount of heat supplied to the blast furnace. The blast rate consumption is the amount of blast used per ton of molten iron produced.

[0028] The output variable of the statistical model is the Si concentration. The Si concentration, which changes from moment to moment, can be calculated using the statistical model. The current value and predicted value of the Si concentration can be calculated (predicted) using the statistical model. Figure 2 shows the results of predicting the Si content in the molten iron after two hours using the statistical model (the LW-PLS model in this embodiment), and good prediction accuracy was obtained.

[0029] Here, the number of hours into the future for which a predicted value is obtained needs to be flexibly changed depending on the operational action that controls the Si concentration. For example, if the operational action is to lower the Si concentration by adding desiliconizing material to the casthouse, the current value only needs to be predicted, since the change has a high immediate effect. On the other hand, if the operational action is to control the heat level in the blast furnace to increase the Si concentration at the time of tapping before desiliconization, the effect of thermal inertia is large and the immediate effect is weak, so a prediction of more than two hours into the future is essential.

[0030] Statistical models make predictions based on measurements from blast furnace sensors, resulting in reduced accuracy in long-term predictions. As described above, statistical models use in-furnace sensor information, such as tuyere embedding temperature and furnace top gas temperature, as input. When controlling the heat level in a blast furnace, accurate predictions become possible only after the sensor information begins to reflect changes in the heat level. Therefore, prediction accuracy may be reduced when the impact of changes in blast furnace operation variables (such as pulverized coal flow rate and coke ratio) has not yet been reflected in the sensor information. In other words, statistical models have difficulty achieving sufficient accuracy in long-term predictions (for example, predictions beyond two hours). Therefore, it is preferable to use physical models for long-term predictions.

[0031] The physical model is a physical model (unsteady-state model) capable of calculating the state inside (inside) a blast furnace in an unsteady state, which is configured from a group of partial differential equations that take into account physical phenomena such as ore reduction, heat exchange between ore and coke, and ore melting, similar to the method described in the reference (K. Takatani et al., ISIJ International, Vol. 39 (1999), pp. 15). The unsteady state includes the occurrence of events such as blow-through and hanging.

[0032] As shown in Figure 3, the main time-varying input variables given to the physical model are the blast flow rate, blast oxygen flow rate, pulverized coal flow rate, coke rate, blast moisture, and blast temperature. These input variables are blast furnace operation variables. The input of the physical model needs to include at least one of these operation variables. The blast flow rate, blast oxygen flow rate, and pulverized coal flow rate are the flow rates of air, oxygen, and pulverized coal sent to the blast furnace, respectively. The coke rate is the coke rate at the furnace top, and is the weight of coke used per ton of molten iron produced. The blast moisture is the humidity of the air sent to the blast furnace. The blast temperature is the temperature of the air sent to the blast furnace.

[0033] The main output variables of the physical model are the gas utilization rate, solution loss carbon amount, reducing agent ratio, ironmaking rate, ironmaking temperature, and Si concentration. The Si concentration, which changes over time, can be calculated using the physical model. The time interval for this calculation is not particularly limited, but is one hour in this embodiment. The time difference between "t+1" and "t" in the equation for the physical model described below is one hour in this embodiment. In this embodiment, the physical model is a three-dimensional unsteady model that can estimate the three-dimensional temperature distribution in the furnace, etc. However, the form of the physical model is not limited to a three-dimensional unsteady model.

[0034] The physical model can be expressed by the following equations (1) and (2).

[0035]

[0036] Here, x(t) is a state variable calculated in the physical model. Examples of the state variables include the coke temperature, iron temperature, ore oxidation degree, and raw material descending speed. y(t) is the Si concentration, which is a control variable. u(t) is the input variable described above, which can be manipulated by an operator operating the blast furnace. That is, the input variables are the blast flow rate BV(t), blast oxygen flow rate BVO(t), pulverized coal flow rate PCI(t), coke ratio CR(t), blast moisture BM(t), and blast temperature BT(t). u(t) can be expressed as (BV(t), BVO(t), PCI(t), CR(t), BM(t), BT(t)). By repeatedly calculating equations (1) and (2), the future Si concentration can be predicted.

[0037] In this embodiment, the Si concentration is predicted using either a statistical model or a physical model depending on "how many hours into the future the predicted value is desired." The combined prediction is presented to, for example, an operator. FIG. 4 shows an example screen displaying the Si concentration predicted in this manner to an ironmaking operator and a steelmaking operator. The screen in FIG. 4 is a guidance screen that allows the operator to take appropriate operational actions depending on the predicted Si concentration. In the example of FIG. 4 , the tuyere embedding temperature to the tuyere tip gas temperature indicate the operation results of the blast furnace, and the blast flow rate to the blast oxygen flow rate indicate operational variables that the operator can control during blast furnace operation. The horizontal axis indicates time, with zero corresponding to the current time. In the example of FIG. 4 , the target value of the Si concentration is 0.5 wt%. In this embodiment, the statistical model is used for predictions up to two hours into the future, and the physical model is used for predictions three hours or more into the future. That is, a statistical model is used to predict the current value of the Si concentration and its predicted value up to a predetermined time, and a physical model is used to predict the predicted value of the Si concentration beyond the predetermined time. An example of the predetermined time is two hours. Here, the predetermined time may be determined based on the time at which the prediction accuracy of the statistical model becomes lower than the prediction accuracy of the physical model. For example, the predetermined time may be determined by comparing the prediction accuracy of the statistical model and the physical model through an experiment using actual operation data (past measurement data, etc.). For example, if the prediction accuracy of the statistical model becomes lower than the prediction accuracy of the physical model when the prediction target time is extended to 2.5 hours in an experiment, the predetermined time may be determined to be two hours.

[0038] Conventionally, steelmaking operators often only received estimated information on the current Si concentration based on measured values. By presenting the predicted Si concentration trend as shown in Figure 4 to at least the steelmaking operator, the steelmaking operator can promptly notify the ironmaking operator of appropriate operational actions for adjusting the amount of desiliconizing material added and the Si concentration. While the ironmaking operator actually performs the operational actions, the steelmaking operator, who understands the tapping schedule, can check the screen shown in Figure 4 and notify the ironmaking operator, enabling collaboration that was previously impossible with conventional predictions and decisions limited to the ironmaking side. Here, the ironmaking operator and the steelmaking operator, both in different locations, can simultaneously view the same predicted Si concentration trend based on a statistical model and a physical model. In other words, the predicted Si concentration trend as shown in Figure 4 may be simultaneously displayed on a display device visible to both the ironmaking operator and the steelmaking operator. Sharing the same information enables strong collaboration. As a result, steelmaking costs can be reduced.

[0039] A specific example of such an operation is changing the target value of the future Si concentration. This is because the action to control the Si concentration, described later, is determined based on the discrepancy between the target value of the Si concentration and the predicted value of the Si concentration. The target value of the Si concentration is determined in relation to blast furnace operation, with reference to a tapping schedule for steelmaking. The tapping schedule is determined in multiple stages, changing the time unit, for example, by setting a tapping schedule for approximately 24 hours in advance each day based on a monthly or weekly production plan, and then finalizing the tapping schedule approximately every six hours. Because blast furnaces have a long time constant (e.g., 8 hours or more), the target value of the Si concentration is determined temporarily based on the Si concentration required by the steelmaking plant, obtained from the 24-hour tapping schedule, taking into account operating conditions. The required Si concentration is then determined based on the finally determined tapping schedule. The ironmaking plant can determine the target value of the Si concentration by acquiring information on the changed Si concentration from the steelmaking plant (specifically, the corrected target value of the Si concentration, which will be described later, and the future time or time period for which the correction should be made). Furthermore, the tapping order in steelmaking may be changed several hours in advance due to the tapping of an emergency material or a problem. Even in such cases, the change can be addressed by changing the target value of the Si concentration, etc.

[0040] Furthermore, Si in molten iron serves as a heat source during steelmaking. Therefore, for molten iron with a Si concentration below the target value, additional processing, such as the charging of Si alloys or other auxiliary materials that serve as heat sources, is required to secure a heat source, leading to increased costs. In some cases, it may become impossible to allocate the target material, which may lead to a reconsideration of allocation or an increase in inventory. If it were possible to change the target value of Si concentration, such cost increases could be prevented, enabling lower steelmaking costs.

[0041] The details of the adjustment amount will be described below for the case where the Si concentration is reduced by adding a desiliconizing material as an operational action to control the Si concentration. When it is predicted that the Si concentration will be in excess of the target value based on the sensitivity of the desiliconizing material consumption rate to the amount of reduction in the Si concentration, the amount of desiliconizing material added can be adjusted so that the target value of the Si concentration matches the predicted value. The adjustment amount is Δu in the following formula (3).

[0042]

[0043] where α is the relaxation coefficient. ｒｅｆ is the target value of the Si concentration. ｐｒｅ (t) is the predicted value of the Si concentration after time t calculated by the statistical model or physical model. ｕ (t) is the change in the Si concentration after t hours when a unit amount of desiliconization material is operated, and is obtained by a step response test in an actual furnace. Here, although the target value of the Si concentration is assumed to be constant in equation (3), if the target value is changed, y ｒｅｆ The target value of the Si concentration after t hours may be given as (t). Here, since the operational action of adding desiliconizing material has a high immediate effect, t=0 may be set.

[0044] For example, if the Si concentration does not reach the target even after stopping the introduction of desiliconizing material, an operational action other than the desiliconizing material introduction action is required. The details of the adjustment amount will be explained below for the case where the heat level in the blast furnace is controlled to increase the Si concentration at the time of tapping before desiliconization, as an operational action to control the Si concentration. For example, when blast moisture is used as the operational variable to be adjusted, the adjustment amount of blast moisture is ΔBM in the following equation (4).

[0045]

[0046] where β is the relaxation coefficient. ＢＭ (t) is the amount of change in Si concentration after t hours when the blast humidity is controlled by a unit amount, and can be obtained by a step response test in an actual furnace or a step response calculation using a physical model. Similar control is possible using not only the blast humidity but also, for example, the blast temperature or the pulverized coal flow rate. Here, although the target value of the Si concentration is assumed to be constant in equation (4), when the target value is changed, y ｒｅｆ The target value of the Si concentration after t hours may be given as (t). When these operational variables are used, it is desirable to set t = 2 to 8. Furthermore, since the response time differs depending on the operational variable, the value of t is determined depending on the selected operational variable.

[0047] The calculation of the adjustment amount according to Equation (3) or Equation (4) may be performed according to an instruction from an operator, but in this embodiment, it is automatically performed when the predicted or current value of the Si concentration significantly deviates from the target value. Here, a significant deviation from the target value may be determined when the magnitude of the value obtained by subtracting the target value from the predicted or current value exceeds a threshold value. The threshold value may be determined based on, for example, the magnitude of the deviation from the target value that is acceptable in the production of molten iron.

[0048] FIG. 5 is a diagram showing an example of the configuration of a Si concentration prediction device 10 according to an embodiment. As shown in FIG. 5, the Si concentration prediction device 10 includes a storage unit 11, a prediction unit 12, and an adjustment amount calculation unit 13. The Si concentration prediction device 10 acquires operational variables including actual measurement values ​​(sensor information) and predicts the Si concentration using the statistical model and physical model described above. The Si concentration prediction device 10 may also acquire various instructions, including an instruction to start the prediction process. The Si concentration prediction device 10 may present the predicted value and the current value to an operator, in which case it also functions as an operation guidance device. When functioning as an operation guidance device, the Si concentration prediction device 10 displays the predicted future value and the current value of the Si concentration on a display unit 30. The display unit 30 may be a display device such as a liquid crystal display (LCD) or an organic electroluminescence panel (EL panel). Here, the display unit 30 may be a display device included in a terminal device 40 used by an operator. The operator includes an ironmaking and steelmaking operator. The display unit 30 may display, for example, a screen such as that shown in FIG. 4 . The terminal device 40 may be a mobile terminal such as a smartphone or tablet. An operation guidance system may be configured including the operation guidance device (Si concentration prediction device 10) and the terminal device 40. In the operation guidance system, the terminal device 40 may include an acquisition unit 41, an input unit 42, a transmission unit 43, and a display unit 30. The inter-terminal communication unit 44 will be described later. The acquisition unit 41 may acquire the predicted value, current value, and adjustment amount of the operation variable in the operation action output from the operation guidance device. The input unit 42 is realized by an input device such as a keyboard or a pointing device, and inputs the correction value of the target value of the Si concentration and the future time or time zone to be corrected. For example, this information is input when an operator at a steelmaking plant, having confirmed changes in the predicted value of the future Si concentration and changes to the steelmaking plan, requests an operator at an ironmaking plant to change the target value of the future Si concentration. The request to change the target value of the Si concentration may be made by a different communication means, without going through the system. Hereinafter, the target value changed by the request for change may be referred to as a corrected target value.The transmitter 43 transmits the input corrected target value of the Si concentration and the future time or time zone for which the correction should be made to the operation guidance device (Si concentration prediction device 10). The display unit 30 may display the predicted value, current value, and adjustment amount acquired by the acquirer 41 as described above. The display unit 30 may further display the corrected target value and the future time or time zone for which the correction should be made. Messages may be transmitted and received between multiple terminal devices 40. In this case, the display unit 30 has a function for displaying transmitted and received messages. As shown in FIG. 5 , the multiple terminal devices 40 may each include an inter-terminal communication unit 44, and requests for changing the target value of the Si concentration, the time zone for the change, the corrected target value, and the like may be transmitted and received between the multiple terminal devices 40. For example, information regarding the correction of the target value of the Si concentration may be transmitted and received between the terminal device 40 used by the ironmaking operator and the terminal device 40 used by the steelmaking operator via their respective inter-terminal communication units 44, thereby sharing information in real time. Furthermore, by utilizing such a function, a corrected target value of the Si concentration may be set based on input information (e.g., a request to change the target value of the Si concentration) from a steelmaking operator (an operator other than an operator in the ironmaking business). Here, the acquisition unit 41 may be realized, for example, by a processor (arithmetic processing unit) of the terminal device 40. The number of terminal devices 40 is not limited to one, but may be multiple, as in the above example. For example, the terminal devices 40 may be installed at the respective locations where the steelmaking operator and the ironmaking operator are stationed, and may be communicatively connected to the operation guidance device via a network such as a local area network (LAN) or other communication means. The inter-terminal communication unit 44 may be a communication means using a network, but is not limited to a specific one as long as it is capable of transmitting and receiving information regarding the corrected target value of the Si concentration to and from another terminal device.

[0049] The components of the Si concentration prediction device 10 will be described below. The storage unit 11 stores a statistical model and a physical model that use blast furnace operation variables as input and Si concentration as output. The storage unit 11 also stores programs and data related to the prediction of Si concentration. The storage unit 11 may include any storage device, such as a semiconductor storage device, an optical storage device, or a magnetic storage device. The semiconductor storage device may include, for example, a semiconductor memory. The storage unit 11 may include multiple types of storage devices.

[0050] The prediction unit 12 predicts future and current values ​​of the Si concentration using a statistical model and a physical model. When the Si concentration prediction device 10 also functions as an operation guidance device, the prediction unit 12 presents the predicted and current values ​​to the operator by displaying them on the display unit 30.

[0051] The adjustment amount calculation unit 13 calculates adjustment amounts for operational variables in operational actions when the predicted values ​​or current values ​​significantly deviate from the target values. The operational action may be to decrease the Si concentration by adding a desiliconizing material, or to control the heat level in the blast furnace to increase the Si concentration at the time of tapping iron before desiliconizing. That is, the adjustment amounts calculated by the adjustment amount calculation unit 13 include adjustment amounts for both decreasing and increasing the Si concentration, and also include, for example, an adjustment amount for the amount of desiliconizing material added. In the case of an operational action of adding a desiliconizing material, the adjustment amount calculation unit 13 may calculate an adjustment amount for the amount of desiliconizing material added according to the above formula (3). Here, if a corrected target value has been input, the adjustment amount calculation unit 13 calculates the adjustment amount using the corrected target value as the target value. In the case of an operational action of controlling the heat level in the blast furnace, the adjustment amount calculation unit 13 may calculate an adjustment amount for the blast moisture, blast temperature, or pulverized coal flow rate according to the above formula (4). For example, a computer that manages the production of molten pig iron may automatically change the conditions for producing molten pig iron based on the calculated adjustment amount. Here, when the Si concentration prediction device 10 also functions as an operation guidance device, the adjustment amount calculation unit 13 may present the calculated adjustment amount to an operator by displaying it on the display unit 30. Such presentation to the operator (operation guidance) can be executed as part of the production method for producing molten pig iron or steel.

[0052] The Si concentration prediction device 10 may be realized by a computer such as a process computer that controls the operation of a blast furnace or the production of molten iron. The computer includes, for example, a memory, a hard disk drive (storage device), a CPU (processing device), and the like. Various functions are realized by organic cooperation between hardware such as the CPU and memory, an OS, and necessary application programs. The memory unit 11 may be realized by, for example, a storage device. The prediction unit 12 and the adjustment amount calculation unit 13 may be realized by, for example, a processing device.

[0053] Fig. 6 is a flowchart showing a Si concentration prediction method according to one embodiment. The Si concentration prediction device 10 predicts the Si concentration according to the flowchart shown in Fig. 6. The Si concentration prediction method shown in Fig. 6 may be executed as part of a method for producing molten iron.

[0054] The prediction unit 12 predicts the future predicted value and the current value of the Si concentration using a statistical model and a physical model (step S1, prediction step). The prediction unit 12 may display the predicted value and the current value to an operator.

[0055] When the predicted value or the current value of the Si concentration significantly deviates from the target value (Yes in step S2), the adjustment amount calculation unit 13 calculates the adjustment amount of the operational variable in the operational action as described above (step S3, adjustment amount calculation step). If a corrected target value has been input in the adjustment amount calculation step, the adjustment amount calculation unit 13 calculates the adjustment amount of the operational variable using the corrected target value as the target value. The processing of the Si concentration prediction method may further include a step (input step) of inputting the corrected target value via the input unit 42 and the transmission unit 43. The series of processing of the Si concentration prediction method may be repeatedly executed at predetermined intervals, or may be executed again, for example, when the target value is changed. The adjustment amount calculation unit 13 may present the calculated adjustment amount to the operator. Here, when neither the predicted value nor the current value of the Si concentration deviates from the target value (No in step S2), the calculation of the adjustment amount is not required.

[0056] As described above, the Si concentration prediction method, operation guidance method, Si concentration prediction device 10, operation guidance device, operation guidance system, and terminal device 40 according to the present embodiment can predict the Si concentration with high accuracy by selectively using a statistical model and a physical model depending on the time period of the prediction target. Furthermore, if a steelmaking plant requests a change in the Si concentration, the target value of the Si concentration can be changed, allowing the ironmaking plant to appropriately calculate operational actions (adjustments to operational variables) according to the predicted values ​​of the statistical model and the physical model. Therefore, deviation of the Si concentration from the target value can be prevented even in operations involving both the ironmaking plant and the steelmaking plant.

[0057] Although embodiments of the present disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art would easily be able to make various modifications or alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included within the scope of the present disclosure. For example, functions included in each component or step can be rearranged so as not to cause logical inconsistencies, and multiple components or steps can be combined or divided into one. The embodiments of the present disclosure can also be realized as a program executed by a processor included in an apparatus or a storage medium on which a program is recorded. It should be understood that these are also included within the scope of the present disclosure.

[0058] The configuration of the Si concentration prediction device 10 shown in FIG. 5 is one example. The Si concentration prediction device 10 does not need to include all of the components shown in FIG. 5 . The Si concentration prediction device 10 may also include components other than those shown in FIG. 5 . The operation guidance system includes an operation guidance device (Si concentration prediction device 10) and a terminal device 40, but the components included therein are not limited to the example shown in FIG. 5 . For example, the terminal device 40 may be configured to include at least one of the prediction unit 12 and the adjustment amount calculation unit 13. Therefore, the operation guidance system may be configured such that the operation guidance device or the terminal device 40 includes the memory unit 11, the prediction unit 12, the adjustment amount calculation unit 13, the acquisition unit 41, the input unit 42, the transmission unit 43, and the display unit 30.

[0059] REFERENCE SIGNS LIST 10 Si concentration prediction device 11 Storage unit 12 Prediction unit 13 Adjustment amount calculation unit 30 Display unit 40 Terminal device 41 Acquisition unit 42 Input unit 43 Transmission unit 44 Inter-terminal communication unit

Claims

1. A prediction step of predicting a future predicted value and a current value of the Si concentration using a statistical model and a physical model having an input of an operational variable of a blast furnace and an output of the Si concentration; and an adjustment amount calculation step of calculating, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of the amount of desiliconization material fed in an operational action of feeding the desiliconization material to reduce the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling the heat level in the blast furnace to increase the Si concentration at the time of tapping before desiliconization.

2. In the prediction step, the statistical model is used to predict the current value and the predicted value up to a predetermined time, and the physical model is used to predict the predicted value beyond the predetermined time, 2. The Si concentration prediction method according to claim 1, wherein the predetermined time is determined based on a time at which the prediction accuracy of the statistical model becomes lower than the prediction accuracy of the physical model.

3. The Si concentration prediction method according to claim 1 or 2, wherein the operational variables that are inputs to the statistical model include at least one of tuyere embedding temperature, furnace heat index, solution loss carbon amount, furnace top gas temperature, tuyere tip gas temperature, and blast volume consumption rate.

4. 3. The method for predicting Si concentration according to claim 1, wherein the operational variables that are inputs to the physical model include at least one of a blast flow rate, a blast oxygen flow rate, a pulverized coal flow rate, a coke ratio, a blast moisture content, and a blast temperature.

5. 3. An operation guidance method comprising the step of having an operator present the predicted value and the current value predicted by the Si concentration prediction method according to claim 1 or 2.

6. An input step of inputting a corrected target value of the Si concentration, 6. The operation guidance method according to claim 5, wherein the adjustment amount calculation step calculates an adjustment amount for the operation variable using the corrected target value input in the input step as the target value.

7. The operation guidance method according to claim 6, wherein the corrected target value is set based on input information from an operator other than an ironmaking operator.

8. A storage unit that stores a statistical model and a physical model in which the operation variables of the blast furnace are input and the Si concentration is output; a prediction unit that predicts a future predicted value and a present value of the Si concentration using the statistical model and the physical model; and an adjustment amount calculation unit that calculates, when the predicted value or the current value significantly deviates from a target value, an adjustment amount of the amount of desiliconization material fed in an operational action of feeding the desiliconization material to reduce the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling the heat level in the blast furnace to increase the Si concentration at the time of tapping before desiliconization.

9. A storage unit that stores a statistical model and a physical model in which the operation variables of the blast furnace are input and the Si concentration is output; a prediction unit that predicts a future predicted value and a current value of the Si concentration by using the statistical model and the physical model, and displays the predicted value and the current value to an operator; and an adjustment amount calculation unit that calculates, when the predicted value or the current value significantly deviates from the target value, an adjustment amount of the amount of desiliconization material fed in an operational action of lowering the Si concentration by feeding the desiliconization material, or an adjustment amount of the operational variable in an operational action of controlling the heat level in the blast furnace to increase the Si concentration at the time of tapping before desiliconization.

10. An operation guidance device and a terminal device, The operation guidance device or the terminal device is A storage unit that stores a statistical model and a physical model in which the operation variables of the blast furnace are input and the Si concentration is output; a prediction unit that predicts a future predicted value and a present value of the Si concentration using the statistical model and the physical model, and outputs the predicted value and the present value; an adjustment amount calculation unit that calculates an adjustment amount of an amount of desiliconization material fed in an operational action of feeding a desiliconization material to reduce a Si concentration, or an adjustment amount of the operational variable in an operational action of controlling a heat level in a blast furnace to increase a Si concentration at the time of tapping before desiliconization, when the predicted value or the current value significantly deviates from a target value, and outputs the adjustment amount; an acquisition unit that acquires the predicted value, the current value, and the adjustment amount; an input section for inputting a correction target value of the Si concentration and a future time or time period to be corrected; a transmission unit that transmits the input correction target value and the future time or time period to be corrected; a display unit that displays the acquired predicted value, the current value, the adjustment amount, and the correction target value, as well as a future time or time zone to be corrected.

11. an acquisition unit that acquires, when a future predicted value and a current value of the Si concentration predicted by a statistical model and a physical model having an input of operational variables of a blast furnace and an output of a Si concentration significantly deviates from a target value, an adjustment amount of an amount of desiliconization material to be fed in an operational action of feeding a desiliconization material to lower the Si concentration, or an adjustment amount of the operational variable in an operational action of controlling a heat level in the blast furnace to increase the Si concentration at the time of tapping before desiliconization is calculated, and an input section for inputting a correction target value of the Si concentration and a future time or time period to be corrected; a transmission unit that transmits the input correction target value and the future time or time period to be corrected; a display unit that displays the acquired predicted value, the current value, the adjustment amount, and the correction target value, as well as a future time or time zone to be corrected.

12. The terminal device according to claim 11 , further comprising an inter-terminal communication unit for transmitting and receiving information regarding the correction target value between the terminal device and another terminal device.