Molten iron temperature control method, molten iron temperature control device, operation guidance method, blast furnace operation method, and molten iron manufacturing method

Abstract

The molten iron temperature control method executed by the molten iron temperature control device (10) includes a model calculation step of calculating the molten iron temperature or an action determination value of an operational action for controlling the molten iron temperature using a plurality of models that input operational data of a blast furnace, and an operational action determination step of selecting one of the plurality of models using the calculated molten iron temperature or action determination value based on a determination criterion that is based on trends in the prediction accuracy of the plurality of models, and determining an operation variable and an operation amount as an operational action.

Description

[Technical Field]

[0001] The present disclosure relates to a molten iron temperature control method, a molten iron temperature control device, an operation guidance method, a blast furnace operation method, and a molten iron manufacturing method. [Background technology]

[0002] In a blast furnace, iron ore and coke are charged from the top of the furnace. As the charged iron ore and coke descend towards the bottom of the furnace, their temperature is raised by hot air and pulverized coal blown in from the bottom of the furnace. During this process, the iron oxide in the iron ore is reduced by the carbon contained in the coke and pulverized coal, and the resulting hot metal (molten iron) is discharged at a temperature of approximately 1500°C.

[0003] Blast furnaces are operated without interruption, and once they are shut down due to operational trouble, it takes a long time to restart them. Therefore, stable operation of blast furnaces is required. Meanwhile, in recent years, blast furnace operations have been required to reduce the amount of reducing material (coke and pulverized coal) used in order to reduce CO2 emissions and production costs. The demand for reduced reducing material usage can make stable operation of blast furnaces difficult. Furthermore, with the declining birthrate and aging population, it is expected that securing operators will become more difficult in the future. Therefore, there is a need for highly efficient and stable blast furnace operation through process automation.

[0004] Controlling the molten iron temperature is particularly important for achieving highly efficient and stable blast furnace operation. If the molten iron temperature drops too low, the molten iron or by-product slag may solidify in the furnace, potentially resulting in a long-term shutdown. Conversely, setting the target temperature too high to avoid a drop in the molten iron temperature can lead to excessive consumption of reducing material. By suppressing the molten iron temperature variation, it becomes possible to lower the target temperature while maintaining the molten iron temperature above the lower limit. Therefore, suppressing the molten iron temperature variation reduces the amount of reducing material used, resulting in reduced CO2 emissions and cost savings.

[0005] Against this background, a molten iron temperature control method using a physical model (see Patent Document 1) and a molten iron temperature control method using a statistical model (see Patent Document 2) have been proposed. For example, Patent Document 1 discloses a method for controlling the molten iron temperature based on a predicted value in order to compensate for the error between the calculated value and the actual measured value of at least one of the reducing agent ratio, solution loss carbon amount, ironmaking rate, and gas utilization rate. The technology in Patent Document 1 calculates a predicted value of the molten iron temperature using the physical model while adjusting the gas reduction equilibrium parameter or the coke rate parameter at the furnace top in the physical model, assuming that the current operating variables are maintained.

[0006] Patent Document 2 discloses a method for predicting a furnace heat evaluation index by creating a prediction formula for a furnace heat evaluation index that expresses the relationship between the operating conditions of a blast furnace and the furnace heat evaluation index using information about the operating conditions in a performance data set, and inputting the operating conditions to be predicted. The technology in Patent Document 2 determines the parameters of the prediction formula by solving an optimization problem using a function that weights the similarity to the operating conditions to be predicted as an evaluation function for evaluating the prediction error of the prediction formula.

[0007] Patent Document 3 discloses a molten iron temperature control method that uses a one-dimensional convolutional neural network to construct a behavioral model in which an operator determines operational actions, and then uses the constructed behavioral model to determine operational actions to bring the molten iron temperature in a blast furnace to a target temperature. The behavioral model uses at least one of the molten iron temperature, tuyere embedding temperature, and coke rate as observed variables (input data), and at least one of the pulverized coal rate, blast moisture, and coke rate as manipulated variables (output data). [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Japanese Patent Application Publication No. 2018-024935 [Patent Document 2] Japanese Patent Application Laid-Open No. 2015-117431 [Patent Document 3] Patent Publication No. 2021-018569 Summary of the Invention [Problem to be solved by the invention]

[0009] The method described in Patent Document 1 can predict changes in molten iron temperature over a long period of time (e.g., 4 to 12 hours). However, it is difficult to predict sudden changes in molten iron temperature due to hanging or slippage caused by a sudden deterioration in permeability, or due to these furnace abnormalities. The method described in Patent Document 2 can input various observational information, such as the results of furnace reactions. Therefore, the method described in Patent Document 2 can predict sudden changes in molten iron temperature that are difficult to predict using physical models, but the prediction range is limited to a short period of time (e.g., 1 to 4 hours). The method described in Patent Document 3 can learn and imitate past exemplary operational actions performed by operators based on their experience, even under conditions where the prediction accuracy of physical or statistical models decreases. However, the method relies on the learning data used in machine learning, and the prediction accuracy of the generated machine learning model decreases when there is little data similar to the situation to be addressed. As such, each model has its own advantages and disadvantages, and when a single model is used, the prediction accuracy decreases and appropriate operational actions may not be suggested.

[0010] In addition, to control the hot metal temperature, the pulverized coal ratio, blast moisture, and blast temperature are manipulated as operational actions. The pulverized coal ratio is the amount of pulverized coal per ton of hot metal. The blast moisture is the amount of moisture added to the hot blast. The blast temperature is the temperature of the hot blast. In recent years, to reduce the reducing agent ratio, the blast temperature has been manipulated to maintain a constant value near its upper limit. Manipulating the blast moisture is also known to be a highly effective way of controlling the hot metal temperature. Here, the decomposition of water vapor is an endothermic reaction. Therefore, increasing the blast moisture content above the atmospheric humidity increases the amount of reducing agent required to maintain a constant hot metal temperature. Conversely, by lowering the blast moisture content to the same amount as the atmospheric humidity and manipulating the pulverized coal ratio, the amount of reducing agent required to maintain a constant hot metal temperature can be reduced. However, when the high-temperature coke burning at the tuyere tip is replaced with room-temperature pulverized coal, the gas temperature at the tuyere tip drops, and it takes about five hours for the hot metal temperature to rise. In other words, adjusting the pulverized coal ratio has a less immediate effect than adjusting the blast moisture content. Therefore, in order to achieve both a reduction in the reducing agent rate and highly accurate hot metal temperature control, it is necessary to appropriately use the control variables of the operational actions.

[0011] In view of the above circumstances, an object of the present disclosure is to provide a molten iron temperature control method, a molten iron temperature control device, an operation guidance method, a blast furnace operation method, and a molten iron production method that are capable of achieving both a reduction in the reducing agent rate and highly accurate molten iron temperature control. [Means for solving the problem]

[0012] (1) A method for controlling the temperature of molten iron according to an embodiment of the present disclosure includes: a model calculation step of calculating the molten iron temperature or an action determination value for an operational action for controlling the molten iron temperature using a plurality of models that input operational data of the blast furnace; and an operational action determination step of selecting one of the plurality of models using the calculated molten iron temperature or the action determination value based on a determination criterion that is based on trends in the prediction accuracy of the plurality of models, and determining an operation variable and an operation amount as the operational action.

[0013] (2) As one embodiment of the present disclosure, in (1), The plurality of models are a physical model capable of expressing a transient state by calculating heat transfer, chemical reactions, and fluid flow inside the blast furnace; and a statistical model for extracting similar operating conditions based on past operating data of the blast furnace and predicting the molten iron temperature.

[0014] (3) As an embodiment of the present disclosure, in (1) or (2), The plurality of models are The system further includes a machine learning model that is generated by machine learning using learning data that links past operation data of the blast furnace with exemplary operation actions performed by operators, and that takes the operation data of the blast furnace as input and outputs operation actions that are determined to be appropriate.

[0015] (4) As an embodiment of the present disclosure, in any one of (1) to (3), The operational action determination step determines an operation variable and an operation amount as the operational action based on the predicted long-term molten iron temperature calculated using the physical model, the predicted short-term molten iron temperature calculated using the statistical model, the action determination value calculated using the machine learning model, a blast moisture control range determined in consideration of a reduction in the reducing agent rate, and a limit on the use of pulverized coal based on operational constraints.

[0016] (5) As an embodiment of the present disclosure, in any one of (1) to (4), The operational action determination step determines an operation variable and an operation amount as the operational action based on the action determination value when the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature are both within a target range.

[0017] (6) As an embodiment of the present disclosure, in any one of (1) to (5), The operational action determination step determines an operation variable and an operation amount as the operational action based on the predicted molten iron temperature in the short time future when both the predicted molten iron temperature in the long time future and the predicted molten iron temperature in the short time future deviate from their target ranges and the corresponding operational actions match, or when the predicted molten iron temperature in the long time future is within the target range and the predicted molten iron temperature in the short time future deviates from the target range.

[0018] (7) As an embodiment of the present disclosure, in any one of (1) to (6), In the operational action determination step, when the long-term future predicted molten iron temperature deviates from a target range and the respective operational actions corresponding to the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature do not match, and the operational action corresponding to the long-term future predicted molten iron temperature is at least not in conflict with the operational action corresponding to the action determination value, an operation variable and an operation variable are determined as an operational action based on the long-term future predicted molten iron temperature, and when the operational action corresponding to the long-term future predicted molten iron temperature does not match with the operational action corresponding to the action determination value, no proactive operational action is executed.

[0019] (8) As an embodiment of the present disclosure, in any one of (1) to (7), The operational constraints include at least one of an upper limit of tuyere gas temperature, a lower limit of tuyere gas temperature, an upper limit of reducing agent rate, a lower limit of reducing agent rate, and a lower limit of furnace top gas temperature.

[0020] (9) As an embodiment of the present disclosure, in any one of (1) to (8), The control range of the blast humidity is determined by adding a value to the atmospheric humidity that allows reduction of the blast humidity by an amount determined as a one-time operation amount at least once.

[0021] (10) A molten iron temperature control device according to an embodiment of the present disclosure includes: a model calculation unit that calculates the molten iron temperature or an action determination value for an operational action for controlling the molten iron temperature using a plurality of models that input operational data of the blast furnace; and an operational action determination unit that uses the calculated molten iron temperature or the action determination value to select one of the plurality of models based on a determination criterion that is based on trends in the prediction accuracy of the plurality of models, and determines an operation variable and an operation amount as the operational action.

[0022] (11) As an embodiment of the present disclosure, in (10), The plurality of models are a physical model capable of expressing a transient state by calculating heat transfer, chemical reactions, and fluid flow inside the blast furnace; and a statistical model for extracting similar operating conditions based on past operating data of the blast furnace and predicting the molten iron temperature.

[0023] (12) As an embodiment of the present disclosure, in (10) or (11), The plurality of models are The system further includes a machine learning model that is generated by machine learning using learning data that links past operation data of the blast furnace with exemplary operation actions performed by operators, and that takes the operation data of the blast furnace as input and outputs operation actions that are determined to be appropriate.

[0024] (13) As an embodiment of the present disclosure, in any one of (10) to (12), The operational action determination unit determines operation variables and operation amounts as the operational action based on the predicted long-term molten iron temperature calculated using the physical model, the predicted short-term molten iron temperature calculated using the statistical model, the action determination value calculated using the machine learning model, a blast moisture control range determined in consideration of a reduction in reducing agent rate, and a pulverized coal use restriction based on operational constraints.

[0025] (14) An operation guidance method according to an embodiment of the present disclosure includes: The operational action determined by any of the molten iron temperature control methods (1) to (9) is presented so that the operator of the blast furnace can confirm it.

[0026] (15) A method for operating a blast furnace according to an embodiment of the present disclosure includes: The method includes a step of controlling the blast furnace in accordance with the operational action determined by the molten iron temperature control method according to any one of (1) to (9).

[0027] (16) A method for producing molten iron according to an embodiment of the present disclosure includes: (15) A step of controlling the blast furnace according to the blast furnace operation method to produce molten iron. [Effects of the Invention]

[0028] According to the present disclosure, it is possible to provide a molten iron temperature control method, a molten iron temperature control device, an operation guidance method, a blast furnace operation method, and a molten iron production method that are capable of achieving both a reduction in the reducing agent rate and highly accurate molten iron temperature control. [Brief explanation of the drawings]

[0029] [Figure 1] FIG. 1 is a block diagram showing the configuration of a molten iron temperature control device according to an embodiment of the present disclosure. [Figure 2A] FIG. 2A is a flowchart showing the flow of processing by the operational action decision unit. [Figure 2B] FIG. 2B is a flowchart showing the flow of processing by the operational action decision unit. [Figure 3] FIG. 3 is a diagram showing changes in the molten iron temperature, coke rate, pulverized coal rate, blast humidity, and atmospheric humidity after four days of operation using a blast furnace operating method using a molten iron temperature control device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram showing a comparison of molten iron temperature variation and reducing agent ratio when a blast furnace operation method using a molten iron temperature control device according to an embodiment of the present disclosure is carried out and when a conventional operation method by an operator is carried out. [Figure 5]FIG. 5 is a diagram showing an example of a system configuration including a molten iron temperature control device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0030] Hereinafter, a molten iron temperature control method, a molten iron temperature control device 10 (see FIG. 1), an operation guidance method, a blast furnace operation method, and a molten iron production method according to an embodiment of the present disclosure will be described with reference to the drawings.

[0031] (Device configuration) FIG. 1 is a block diagram showing the configuration of a molten iron temperature control device 10 according to an embodiment of the present disclosure. The molten iron temperature control device 10 according to an embodiment of the present disclosure is configured by an information processing device such as a computer. When the molten iron temperature control device 10 is a computer, an arithmetic processing device such as a CPU (Central Processing Unit) executes a program to function as a model calculation unit 11 and an operational action determination unit 12. The processing performed by the model calculation unit 11 may be referred to as a model calculation step. Furthermore, the processing performed by the operational action determination unit 12 may be referred to as an operational action determination step. The functions of each unit will be described later.

[0032] An operational database 20 is connected to the molten iron temperature control device 10 in a data-readable form. In this embodiment, the operational database 20 stores operational factors such as the furnace top coke ratio, blast flow rate, oxygen enrichment amount, blast temperature, blast moisture, and pulverized coal flow rate. The operational database 20 also stores actual values ​​of process variables calculated based on the volume fractions of CO and CO2 in the discharged furnace top gas. The operational database 20 also stores historical data on temperatures and pressures measured at at least one of the furnace body, furnace top, and furnace bottom. Examples of process variables include the molten iron temperature, iron-making rate, solution loss carbon amount, and gas utilization rate.

[0033] The molten iron temperature control device 10 executes each process of the molten iron temperature control method using the model calculation unit 11 and the operational action determination unit 12, identifies operation variables for molten iron temperature control, and outputs the optimal action as guidance.

[0034] (Operation of model calculation unit 11) The model calculation unit 11 calculates the molten iron temperature or an action determination value for an operational action for controlling the molten iron temperature using multiple models that use blast furnace operation data as input. The action determination value will be described later. In this embodiment, the model calculation unit 11 executes processing using a physical model, a statistical model, and a machine learning model when a command to execute model calculation is input to the molten iron temperature control device 10. Although three models are used in this embodiment, the number is not limited to three and may be, for example, two or four or more. The multiple models used by the model calculation unit 11 are generated in advance and stored in a storage device accessible to the molten iron temperature control device 10. The model calculation unit 11 reads the models from the storage device before executing the calculation process.

[0035] The physical model is capable of representing transient states by calculating heat transfer, chemical reactions, and fluid flow within a blast furnace. Fluids include not only gases but also solids. The physical model in this embodiment is similar to the method described in Reference 1 (Hadano Michiharu et al., "Study of Blast Furnace Burn-in Operation Using a Non-Steady-State Model," Iron and Steel, Vol. 68, p. 2369). That is, the physical model is composed of a group of partial differential equations that consider multiple physical phenomena, such as iron ore reduction, heat exchange between iron ore and coke, and iron ore melting, and is capable of calculating variables (output variables) that represent the state inside the blast furnace in a non-steady state. Because the physical model can predict the reactions that occur inside the furnace, it is capable of long-term predictions (4 to 12 hours) into the future, including when the operating variables are changed recently. Here, the long period (4 to 12 hours) in the physical model predictions takes into account the time it takes for the raw materials charged from the top of the blast furnace to descend.

[0036] The statistical model predicts the molten iron temperature by extracting similar operating conditions based on past operation data of the blast furnace. The statistical model in this embodiment is a model using the just-in-time method described in Reference 2 (Shigeru Yamamoto, "Just-In-Time Predictive Control: Predictive Control Based on Accumulated Data," Measurement and Control, Vol. 52, No. 10, p. 878). The statistical model predicts the molten iron temperature a short time (1 to 4 hours) into the future using measured values ​​of temperature and pressure measured at the furnace body, top, and bottom of the blast furnace and actual values ​​of process variables as explanatory variables. The statistical model sequentially constructs a local linear function using data near the explanatory variables at the current time. The reason for linking the explanatory variables at the current time with the molten iron temperature 1 to 4 hours into the future is to take into account the residence time of the molten iron at the hearth.

[0037] The machine learning model is generated by machine learning using learning data that links past operation data of the blast furnace with exemplary operation actions performed by operators. The generated machine learning model receives operation data of the blast furnace as input and outputs operation actions that are determined to be appropriate. The machine learning model may use a one-dimensional convolutional neural network technique, similar to the method described in Patent Document 3, for example. The machine learning model in this embodiment outputs a value (hereinafter referred to as an action determination value) obtained by subtracting the calculated determination probability of an action to lower the temperature of the molten iron from the determination probability of an action to raise the temperature of the molten iron. Here, the action to raise the temperature of the molten iron is an operation action to raise the temperature of the molten iron. Similarly, the action to lower the temperature of the molten iron is an operation action to lower the temperature of the molten iron. In other words, the machine learning model in this embodiment includes the action determination value as an operation action that is determined to be appropriate to output. In addition, machine learning using a one-dimensional convolutional neural network of a machine learning model may involve learning not only the direction of action (increase or decrease in pulverized coal ratio, blast moisture, etc.) but also the amount of operation (amount to be increased or decreased).

[0038] Here, the following three points must be considered when determining the manipulated variables for operational actions to control the hot metal temperature. The first point is the relationship between model selection and the time delay before changes in the manipulated variables are reflected in the hot metal temperature. As mentioned above, compared to pulverized coal ratio and blast moisture, blast moisture has a faster effect (i.e., better response). Therefore, when a statistical model predicts a short-term sudden rise or fall in the hot metal temperature, blast moisture manipulation takes priority. When a physical model predicts a long-term deviation in the hot metal temperature from the target, either the pulverized coal ratio or the blast moisture manipulation is selected. The machine learning model is used to proactively execute appropriate operational actions when both the physical model and the statistical model determine that no action is necessary or when the prediction accuracy of the physical model and the statistical model deteriorates due to disturbances.

[0039] The prediction accuracy of physical models and statistical models can be significantly reduced when disturbances that are difficult to measure are large. Therefore, the operational actions corresponding to the long-term future hot metal temperature based on the physical model and the short-term future hot metal temperature based on the statistical model may conflict with each other. In this case, it is difficult to determine which operational action to execute or when to switch operational actions. Furthermore, if the long-term future hot metal temperature based on the physical model is predicted to deviate from the target range, but the short-term future hot metal temperature based on the statistical model is predicted to be within the target range, it is difficult to determine the timing to execute the operational action corresponding to the long-term future hot metal temperature. However, even in such cases, experienced operators can observe the trends in the operational data and execute appropriate operational actions at the appropriate times.

[0040] Furthermore, even when it is determined that the long-term future molten iron temperature based on the physical model and the short-term future molten iron temperature based on the statistical model are both within the target range and no operational action is required, an experienced operator may look at the trend of the operational data and determine that it would be better to take operational action at the appropriate time.

[0041] Machine learning models can be used to mimic the operational actions of exemplary operators to proactively take appropriate operational actions at the appropriate time, even in such cases. Machine learning models can also be used to determine the appropriateness of operational actions based on physical and statistical models.

[0042] The second point is a guideline for determining the blast moisture control amount based on the desired blast moisture range, taking into account the realization of low RAR operation and the response to sudden changes in molten iron temperature. When blast moisture is high, the blast moisture is reduced as an action to raise the molten iron temperature. Reducing the blast moisture reduces the RAR. However, if the blast moisture is reduced when it is close to atmospheric humidity, the blast moisture becomes almost the same as atmospheric humidity. As a result, the only control variable for increasing the molten iron temperature is the pulverized coal ratio, and the action is limited to increasing the pulverized coal ratio. Therefore, the responsiveness of operational actions deteriorates when the molten iron temperature suddenly changes. It is considered preferable to continue operations while maintaining the blast moisture at a predetermined value so that the blast moisture can be reduced responsively when the molten iron temperature suddenly drops, in order to achieve both molten iron temperature control and RAR reduction. Here, the predetermined value may be determined by adding a value (see β in FIGS. 2A and 2B) that allows a reduction in blast humidity by an amount determined as a single operation amount to be performed at least once to the atmospheric humidity. Alternatively, the predetermined value may have a range so that the blast humidity is maintained within a desired range. That is, if a long-term decrease in the molten iron temperature is predicted based on a physical model, and the blast humidity exceeds the desired range, an action to decrease the blast humidity is prioritized. If a long-term increase in the molten iron temperature is predicted based on a physical model, and the blast humidity falls below the desired range, an action to increase the blast humidity is prioritized. Hereinafter, the desired range of blast humidity may be referred to as the "control range."

[0043] The third issue is the restriction of pulverized coal use based on operational constraints. For example, increasing the pulverized coal ratio when the reducing agent ratio is high may increase the amount of fines in the lower furnace, resulting in poor permeability. Furthermore, when the tuyere gas temperature is low, pulverized coal has poor combustibility, so increasing the pulverized coal ratio may result in unburned pulverized coal and poor permeability. Therefore, when the reducing agent ratio is at a predetermined upper limit or the tuyere gas temperature is at a predetermined lower limit, reducing the blast moisture content is preferable to increase the hot metal temperature. Furthermore, reducing the pulverized coal ratio when the reducing agent ratio is low increases the risk of problems such as poor permeability or a sudden drop in hot metal temperature due to unexpected disturbances. Reducing the pulverized coal ratio when the tuyere gas temperature is high may further increase the tuyere gas temperature, potentially damaging equipment around the tuyere. Furthermore, if the pulverized coal ratio is reduced when the furnace top gas temperature is low, the furnace top gas temperature will further decrease, which may cause zinc in the raw materials to adhere to the furnace wall, worsening gas permeability, or may cause soot to be generated at the furnace top, deteriorating furnace top equipment. Therefore, when the reducing agent ratio is at a predetermined lower limit, when the tuyere gas temperature is at a predetermined upper limit, or when the furnace top gas temperature is at a predetermined lower limit, it is preferable to take action to increase the blast moisture in order to reduce the molten pig iron temperature.

[0044] The manipulated variables based on the physical model and the statistical model may be calculated using, for example, a known model predictive control technique or a known method for defining influence coefficients, or may be constants. The manipulated variables based on the machine learning model may be calculated by defining influence coefficients for action determination values, or may be constants. The operational action determination unit 12 is constructed based on such concepts for determining manipulated variables and manipulated variables.

[0045] (Operation of the operational action decision unit 12) 2A and 2B are flowcharts showing the processing flow of the operational action decision unit 12. 2A and 2B constitute one flowchart. The processing of the flowchart selects one of a plurality of models based on a judgment criterion based on the trend of the prediction accuracy of the plurality of models. The operation of the operational action decision unit 12 will be described with reference to FIGS. 2A and 2B. The flowcharts of FIGS. 2A and 2B start when an execution command for operational action decision is input to the molten iron temperature control device 10, and the processing proceeds to step S1.

[0046] In the process of step S1, the operational action determination unit 12 determines the difference between the predicted value of the hot metal temperature based on the physical model calculated by the model calculation unit 11 (physical model-predicted hot metal temperature, long-term predicted hot metal temperature) and the target value of the hot metal temperature (target hot metal temperature). The target range of the difference between the physical model-predicted hot metal temperature and the target hot metal temperature (target range of long-term predicted hot metal temperature) is set to be greater than -α1 and less than α1. If the physical model-predicted hot metal temperature τ1 hours into the future is less than -α1 compared to the target hot metal temperature, the operational action determination process proceeds to step S11 so that an operational action to increase the hot metal temperature is taken. If the physical model-predicted hot metal temperature τ1 hours into the future is greater than α1 compared to the target hot metal temperature, the operational action determination process proceeds to step S21 so that an operational action to decrease the hot metal temperature is taken. If the physical model-predicted hot metal temperature τ1 hours into the future is greater than or equal to -α1 and less than or equal to α1 compared to the target hot metal temperature, it is determined that no action is required based on the physical model prediction, and the operational action determination process proceeds to step S31. Here, τ1 is the future time predicted using the physical model. τ1 is preferably set to 4 to 12 hours, taking into account the approximately 8 hours it takes for raw materials charged from the top of the blast furnace to descend to the lower part of the furnace (tuyere) and the time delay until the pulverized coal combustion in the tuyere is reflected in the hot metal temperature. Furthermore, α1 is preferably set to 1 to 30°C depending on the hot metal temperature control target.

[0047] In the process of step S11, the operational action determination unit 12 determines the relationship between the difference between the blast humidity and the atmospheric humidity at the current time and the control range of the blast humidity determined in consideration of the reduction in the reducing agent ratio. 3 ), an action to reduce the blast moisture content is presented to raise the molten iron temperature, and the series of operational action decision processes ends. 3 ), the operational action determination process proceeds to step S12. Here, β is a value that allows reduction of the blown air humidity by an amount determined as a one-time operation amount to be performed at least once.

[0048] In the processing of step S12, the operational action determination unit 12 makes a determination regarding the reducing agent ratio and the tuyere gas temperature in accordance with the pulverized coal use restriction based on the operational constraints. If the reducing agent ratio is at the upper limit or the tuyere gas temperature is at the lower limit, the action of lowering the blast moisture is preferable to increasing the pulverized coal ratio in order to increase the molten pig iron temperature, and therefore the operational action determination processing proceeds to step S15. If the reducing agent ratio is less than the upper limit and the tuyere gas temperature is higher than the lower limit, the operational action determination processing proceeds to step S13. Here, in FIG. 2A, the case where the reducing agent ratio is at the upper limit or the tuyere gas temperature is at the lower limit corresponds to Yes in step S12. Also, the case where the reducing agent ratio is less than the upper limit and the tuyere gas temperature is higher than the lower limit corresponds to No in step S12. The upper limit of the reducing agent ratio and the lower limit of the tuyere gas temperature may be determined in advance based on, for example, past performance data or experimental data.

[0049] In the processing of step S13, the operational action decision unit 12 determines the difference between the predicted value of the hot metal temperature based on the statistical model calculated by the model calculation unit 11 (statistical model predicted hot metal temperature, short-time ahead predicted hot metal temperature) and the target value of the hot metal temperature (target hot metal temperature). The target range of the difference between the statistical model predicted hot metal temperature and the target hot metal temperature (target range of short-time ahead predicted hot metal temperature) is set to be greater than or equal to -α2 and less than or equal to α2. If the statistical model predicted hot metal temperature τ2 hours ahead is less than -α2 compared to the target hot metal temperature, there is a high possibility that the hot metal temperature will suddenly drop. Therefore, it is determined that an action to reduce the blast moisture, which has good responsiveness, is desirable, and the operational action determination processing proceeds to step S15. That is, if the long-term future predicted hot metal temperature (Step S1) and the short-term future predicted hot metal temperature (Step S13) both deviate from the target range and the corresponding operational actions are consistent, the process proceeds to Step S15, where the manipulated variables and manipulated variables for a responsive operational action to reduce blast moisture are determined based on the short-term future predicted hot metal temperature. If the hot metal temperature predicted by the statistical model τ2 hours into the future is greater than or equal to -α2 compared to the target hot metal temperature, that is, if the long-term future predicted hot metal temperature and the corresponding operational actions corresponding to the short-term future predicted hot metal temperature do not agree, the operational action determination process proceeds to Step S14. Here, τ2 is the future time predicted using the statistical model. τ2 is preferably set to 1 to 4 hours, taking into account the prediction accuracy of the statistical model. α2 is preferably set to 1 to 30°C depending on the hot metal temperature control target. Here, α2 is preferably set to a value greater than α1 so that an action is taken in response to a sudden change in the hot metal temperature.

[0050] In the process of step S14, the operational action decision unit 12 determines the action determination value (machine learning model action determination value) based on the machine learning model calculated by the model calculation unit 11. If the machine learning model action determination value is less than −α3, the action to increase the hot metal temperature based on the prediction of a hot metal temperature decrease based on the physical model conflicts with the action to decrease the hot metal temperature based on the machine learning model, so the operational action decision unit 12 does not take any proactive action. In other words, if the operational action to decrease the hot metal temperature corresponding to the machine learning model action determination value conflicts with the operational action to increase the hot metal temperature corresponding to the predicted hot metal temperature long into the future based on the physical model, no proactive action is taken. Therefore, the series of operational action decision processes ends without any action. On the other hand, if the machine learning model action determination value is −α3 or greater, the operational action based on the machine learning model action determination value is an action to increase the hot metal temperature or a wait-and-see approach (no proactive action is taken), so it is at least not contradictory to the operational action to increase the hot metal temperature corresponding to the prediction of a hot metal temperature decrease long into the future based on the physical model. That is, when the operational action corresponding to the long-term predicted hot metal temperature based on the physical model and the operational action corresponding to the machine learning model action judgment value are at least not contradictory, the operational action decision unit 12 proposes an action to increase the pulverized coal ratio based on the prediction of the long-term future hot metal temperature decrease based on the physical model, and the series of operational action judgment processes ends. Here, the machine learning model action judgment value is a value obtained by subtracting the calculated probability of determining the hot metal temperature increase action from the probability of determining the hot metal temperature decrease action, as described above. Here, the machine learning model action judgment value is not limited to a specific type of value such as probability, as long as it numerically indicates whether the hot metal temperature increase action or the hot metal temperature decrease action is appropriate. For example, machine learning may be performed using the operation amount of the action performed by an exemplary operator obtained as past performance data, and the operation amount itself may be output as the machine learning model action judgment value. Furthermore, α3 may be determined according to the machine learning model action judgment value, for example, based on past performance data or experimental data.

[0051] In the process of step S15, the operational action determination unit 12 determines the relationship between the difference between the blast humidity and the atmospheric humidity at the current time and the control range of the blast humidity determined in consideration of the reduction in the reducing agent ratio. 3 ), there is no room to reduce the blast humidity, so it is determined that no action is required, and the series of operational action determination processes ends. Here, γ is set to a value smaller than the above β. If the blast humidity at the current time is atmospheric humidity + γ (g / Nm 3 ) indicates that the amount of vent humidity is approximately the same as the amount of atmospheric humidity. 3 ) or more, an action to reduce the blast moisture content is presented in order to increase the molten iron temperature, and the series of operational action determination processes is terminated.

[0052] In the process of step S21, the operational action determination unit 12 determines the relationship between the difference between the blast humidity and the atmospheric humidity at the current time and the control range of the blast humidity determined in consideration of the reduction in the reducing agent ratio. 3 ), an action to increase the blast moisture content is presented to lower the molten iron temperature, and the series of operational action decision processes ends. 3 ) or more, the operational action determination process proceeds to step S22 to avoid excessive ventilation humidity.

[0053] In the processing of step S22, the operational action determination unit 12 makes a determination regarding the reducing agent ratio, tuyere gas temperature, and top gas temperature in accordance with the pulverized coal use restriction based on the operational constraints. If the reducing agent ratio is at the lower limit, the tuyere gas temperature is at the upper limit, or the top gas temperature is at the lower limit, an action of increasing the blast moisture is preferable to an action of decreasing the pulverized coal ratio in order to decrease the molten iron temperature, and therefore the operational action determination processing proceeds to step S25. If the reducing agent ratio is greater than the lower limit, the tuyere gas temperature is below the upper limit, and the top gas temperature is above the lower limit, the operational action determination processing proceeds to step S23. Here, in FIG. 2B, the cases where the reducing agent ratio is at the lower limit, the tuyere gas temperature is at the upper limit, or the top gas temperature is at the lower limit correspond to "Yes" in step S22. The cases where the reducing agent ratio is greater than the lower limit, the tuyere gas temperature is below the upper limit, and the top gas temperature is above the lower limit correspond to "No" in step S22. Furthermore, the lower limit of the reducing agent ratio, the upper limit of the tuyere gas temperature, and the lower limit of the furnace top gas temperature may be determined in advance based on, for example, past performance data or experimental data.

[0054] In step S23, the operational action determination unit 12 determines the difference between the statistical model-predicted hot metal temperature calculated by the model calculation unit 11 and the target hot metal temperature. If the statistical model-predicted hot metal temperature τ2 hours in the future is greater than the target hot metal temperature by α2, it is determined that a rapid rise in the hot metal temperature is likely, and therefore an action to increase the blast moisture content, which has good responsiveness, is desirable. The operational action determination process then proceeds to step S25. That is, if the long-term future predicted hot metal temperature (step S1) and the short-term future predicted hot metal temperature (step S23) both deviate from the target range and the corresponding operational actions are consistent, that is, to reduce the hot metal temperature, the process proceeds to step S25, where the manipulated variables and manipulated variables for an action to increase the blast moisture content, which has good responsiveness, are determined as the operational action, based on the short-term future predicted hot metal temperature. If the statistical model predicted hot metal temperature τ2 hours from now is equal to or less than α2 compared to the target hot metal temperature, that is, if the operational actions corresponding to the predicted hot metal temperature for a long time and a short time do not match, the operational action determination process proceeds to step S24.

[0055] In the process of step S24, the operational action decision unit 12 makes a decision on the machine learning model action judgment value calculated by the model calculation unit 11. If the machine learning model action judgment value is greater than α3, the molten iron temperature lowering action based on the prediction of the molten iron temperature rise based on the physical model conflicts with the molten iron temperature raising action based on the machine learning model, and therefore the operational action decision unit 12 does not take any proactive action. In other words, if the operational action corresponding to the machine learning model action judgment value conflicts with the operational action corresponding to the long-term future predicted molten iron temperature based on the physical model, no proactive action is taken. Therefore, the series of operational action decision processes ends without any action. On the other hand, if the machine learning model action judgment value is equal to or less than α3, the operational action based on the machine learning model action judgment value is a molten iron temperature lowering action or a wait-and-see action (no proactive action is taken), and therefore at least does not conflict with the operational action of molten iron temperature lowering corresponding to the long-term future prediction of the molten iron temperature rise based on the physical model. In other words, if the operational action for the long-term future predicted molten iron temperature based on the physical model and the operational action corresponding to the machine learning model action judgment value are at least not contradictory, the operational action decision unit 12 will present an action to reduce the pulverized coal ratio based on the prediction of the long-term future molten iron temperature rise based on the physical model, and the series of operational action judgment processes will end.

[0056] In the process of step S25, the operational action determination unit 12 determines the relationship between the difference between the blast humidity and the atmospheric humidity at the current time and the control range of the blast humidity determined in consideration of the reduction in the reducing agent ratio. 3 ), it indicates that the blast moisture is being added in greater amounts than the atmospheric moisture. Therefore, if the blast moisture is increased, the amount of moisture added to the furnace will be excessive, increasing the risk of a sudden drop in the hot metal temperature. Therefore, if the blast moisture at the current time is greater than atmospheric moisture + δ(g / Nm 3), it is determined that no action is required, and the series of operational action determination processes ends. Here, δ is set to a value smaller than the above β. δ may be the same value as γ, for example. If the supply air humidity at the current time is the atmospheric humidity + δ (g / Nm 3 ) or less, an action to increase the blast moisture content is proposed to lower the molten iron temperature, and the series of operational action determination processes is terminated.

[0057] In step S31, the operational action decision unit 12 determines the difference between the statistical model-predicted hot metal temperature calculated by the model calculation unit 11 and the target hot metal temperature. In step S31, if the physical model determines that the hot metal temperature will not change significantly in the long term (the predicted hot metal temperature in the long term is within the target range), but the statistical model predicts that the hot metal temperature will change suddenly in the short term (the predicted hot metal temperature in the short term deviates from the target range), the statistical model's prediction of the hot metal temperature in the short term is prioritized. If the statistical model-predicted hot metal temperature τ2 hours into the future is less than -α2 compared to the target hot metal temperature, it is determined that a sudden drop in the hot metal temperature is likely, and therefore a responsive action to reduce the blast moisture is desirable, and the operational action decision process proceeds to step S15. If the statistical model predicted hot metal temperature τ2 hours from now is greater than α2 compared to the target hot metal temperature, it is determined that there is a high possibility that the hot metal temperature will rise sharply, and therefore it is desirable to take action to increase the blast moisture content, which has good responsiveness, and the operational action determination process proceeds to step S25.If the statistical model predicted hot metal temperature τ2 hours from now is greater than or equal to -α2 and less than or equal to α2 compared to the target hot metal temperature, the operational action determination process proceeds to step S32.

[0058] In step S32, the operational action decision unit 12 determines the machine learning model action judgment value calculated by the model calculation unit 11. In step S32, if it is determined that the future hot metal temperature will not change significantly in either the physical model or the statistical model, i.e., if the long-term future predicted hot metal temperature based on the physical model and the short-term future predicted hot metal temperature based on the statistical model are both within the target range, the machine learning model action judgment value is prioritized. If the machine learning model action judgment value is greater than α3, the operational action decision unit 12 proposes an action to increase the pulverized coal ratio, and the series of operational action decision processes ends. If the machine learning model action judgment value is less than −α3, the operational action decision unit 12 proposes an action to decrease the pulverized coal ratio, and the series of operational action decision processes ends. If the machine learning model action judgment value is greater than −α3 and less than α3, the operational action decision unit 12 determines that no action is necessary, and the series of operational action decision processes ends.

[0059] In this way, the operational action determination unit 12 determines the manipulated variables and manipulated variables as operational actions based on the values ​​calculated by the model calculation unit 11, the blast moisture control range determined in consideration of the reduction in reducing agent rate, and the pulverized coal use limit based on the operational constraints. The values ​​calculated by the model calculation unit 11 include a long-term future predicted molten iron temperature calculated using a physical model, a short-term future predicted molten iron temperature calculated using a statistical model, and an action determination value calculated using a machine learning model.

[0060] FIG. 5 is a diagram showing an example of a system configuration including the molten iron temperature control device 10. The system may include the molten iron temperature control device 10, an operation data server 94, a control computer 74, and a display unit 95. The operation data server 94 stores data related to the molten iron production process. The molten iron temperature control device 10 acquires, from the operation data server 94, actual values ​​of the production process executed in the molten iron production facility. A storage device (e.g., a memory) in which the operation data server 94 stores data related to the production process corresponds to the operation database 20. The control computer 74 controls the molten iron production facility. The display unit 95 displays the guidance operation variables (operational actions determined according to the above flowchart) output from the molten iron temperature control device 10 functioning as an operation guidance device. Here, the display unit 95 may be a display device such as a liquid crystal display (LCD) or an organic electroluminescence panel (OLED). The display unit 95 may be realized by a display of a terminal device such as a smartphone or a tablet. The operation data server 94, the control computer 74, and the display unit 95 can communicate with the molten iron temperature control device 10 via a network. The network is, for example, the Internet.

[0061] The molten iron temperature control device 10 may execute an operation guidance method that presents the operation actions determined by the above process so that the blast furnace operator can confirm them. Presentation may include displaying the information on the display unit 95, but audio may also be used, and is not limited to a specific presentation method. The operator may change the operating conditions of the molten iron production facility based on the guidance manipulated variables (operation variables and manipulated variables) displayed on the display unit 95. Such operation guidance for the molten iron production facility may be executed as part of a production method for producing molten iron. Furthermore, the molten iron temperature control device 10 may output the determined manipulated variables and manipulated variables to the control computer 74, which may control the molten iron production facility in accordance with the manipulated variables and manipulated variables. The content of the operation actions determined by the molten iron temperature control device 10 may be automatically reflected in production or operation, for example, by using a communication function between the control computer 74 and the molten iron production facility. In other words, the output and automatic change of such manipulated variables and manipulated quantities may be performed as part of the molten iron production method and operation method. Here, the operation data server 94, the control computer 74, and the display unit 95 may be located in the same place as the molten iron temperature control device 10 (for example, in the same plant), or may be located physically separately.

[0062] As described above, the molten iron temperature control method executed by the molten iron temperature control device 10 may be part of a blast furnace operation method. For example, the blast furnace operation method may include a step of controlling the blast furnace in accordance with an operational action determined by the molten iron temperature control method. Furthermore, the molten iron temperature control method or the blast furnace operation method may be part of a molten iron production method. For example, the molten iron production method may include a step of controlling the blast furnace in accordance with the blast furnace operation method to produce molten iron.

[0063] (Example) The operation was carried out by controlling the pulverized coal ratio and blast moisture using the hot metal temperature control device 10. Here, α1 and α2 were set to 30°C, α3 was set to 0.3, and β was set to 7g / Nm 3 γ was set to 0g / Nm 3 Also, δ was set to 12g / Nm 3Here, α3 in this embodiment is a probability and is a dimensionless number.

[0064] FIG. 3 shows changes in the molten pig iron temperature, coke rate, pulverized coal rate, blast moisture, and atmospheric humidity during four days of operation using the blast furnace operating method using the molten pig iron temperature control device 10 according to this embodiment. The numbers on the horizontal axis indicate the number of days. The molten pig iron temperature graph in FIG. 3 shows the difference from the target molten pig iron temperature at time zero. The other graphs assume the average value for the period (average value over four days) to be zero. In the molten pig iron temperature graph in FIG. 3, the dotted line represents the target value, and the solid line represents the actual value. In the blast moisture and atmospheric humidity graphs in FIG. 3, the dotted line represents the blast moisture and the solid line represents the atmospheric humidity. The coke rate graph in FIG. 3 shows significant fluctuations due to manual operation by the operator, but the blast moisture and pulverized coal rate were subsequently manipulated as operational actions by the molten pig iron temperature control device 10. The operational action of the hot metal temperature control device 10 reduced the effect of fluctuations in the coke rate on the hot metal temperature over time, and the hot metal temperature was controlled close to the target value. As a result of automatically controlling the blast moisture and pulverized coal rate by the hot metal temperature control device 10 throughout the entire period, the hot metal temperature was able to be kept within the range of -30 to 30°C.

[0065] Fig. 4 is a diagram showing a comparison of the molten iron temperature variation and the reducing agent rate when a blast furnace operation method using the molten iron temperature control device 10 according to this embodiment is carried out with a conventional operation method by an operator. In the comparison in Fig. 4, the molten iron temperature variation and the reducing agent rate resulting from the conventional operation method are normalized to 1. As Fig. 4 shows, by using the molten iron temperature control device 10, it is possible to achieve both improved accuracy in molten iron temperature control and a reduced reducing agent rate compared to the conventional method.

[0066] As described above, the molten iron temperature control method, molten iron temperature control device 10, operation guidance method, blast furnace operation method, and molten iron manufacturing method according to the present embodiment can achieve both a reduction in the reducing agent rate and highly accurate molten iron temperature control. In other words, by selectively using the execution results of multiple models related to blast furnace operation, it is possible to compensate for the shortcomings of each model and to implement optimal operational actions, including the determination of manipulated variables for molten iron temperature control.

[0067] Although the embodiments have been described, the present disclosure is not limited by the descriptions and drawings that form a part of the present disclosure according to the present embodiments. In other words, other embodiments, examples, operational techniques, etc. that can be made by those skilled in the art based on the present embodiments are all included in the scope of the technology of the present disclosure.

[0068] For example, in the above embodiment, a process is performed in which a hot metal temperature prediction based on a physical model is used as a base, and the prediction is complemented by a hot metal temperature prediction based on a statistical model and a hot metal temperature control action prediction based on a machine learning model. For example, the order of the flowchart may be rearranged to change the priority of the models that serve as the basis for presenting actions. Examples in which the priority of the models is changed are included in the scope of the technology disclosed herein. Furthermore, while the above embodiment uses a physical model, a statistical model, and a machine learning model, for example, the machine learning model may be omitted. For example, if it is unlikely that the prediction accuracy of the physical model and the statistical model will deteriorate due to the influence of disturbances, it is possible to achieve both a reduction in the reducing agent rate and highly accurate hot metal temperature control even if the machine learning model is omitted. [Explanation of symbols]

[0069] 10. Hot metal temperature control device 11 Model calculation section 12 Operational Action Decision Unit 20 Operation Database 74 Control computer 94 Operational Data Server 95 Display section

Claims

1. a model calculation step of calculating the molten iron temperature or an action determination value for an operational action for controlling the molten iron temperature using a plurality of models that input operational data of the blast furnace; an operational action determination step of selecting one of the plurality of models based on a determination criterion based on trends in prediction accuracy of the plurality of models using the calculated molten iron temperature or the action determination value, and determining an operation variable and an operation amount as the operational action; The plurality of models are a physical model capable of expressing a transient state by calculating heat transfer, chemical reactions, and fluid flow inside the blast furnace; a statistical model for extracting similar operating conditions based on past operation data of the blast furnace and predicting the molten iron temperature; a machine learning model that is generated by machine learning using learning data that links past operation data of the blast furnace with exemplary operation actions performed by an operator, and that inputs the operation data of the blast furnace and outputs the action determination value of an operation action that is determined to be appropriate; The operational action determination step includes: determining an operation variable and an operation amount as the operational action based on the long-term future predicted molten iron temperature calculated using the physical model, the short-term future predicted molten iron temperature calculated using the statistical model, and the action determination value calculated using the machine learning model; a control method for controlling a molten iron temperature, the control method comprising: determining an operation variable and an operation amount as the operation action based on the action determination value when the operation actions corresponding to the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature are different, or when it is determined that neither of the operation actions corresponding to the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature is necessary.

2. 2. The molten iron temperature control method according to claim 1, wherein the operational action determination step further determines an operation variable and an operation amount as the operational action based on a control range of blast moisture determined in consideration of a reduction in a reducing agent rate and a limit on the use of pulverized coal based on an operational constraint.

3. 2. The molten iron temperature control method according to claim 1, wherein the operational action determination step determines an operation variable and an operation amount as the operational action based on the action determination value when the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature are both within target ranges.

4. 2. The molten iron temperature control method according to claim 1, wherein the operational action determination step determines an operation variable and an operation amount as the operational action based on the predicted molten iron temperature in the short time future when both the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature deviate from their target ranges and the corresponding operational actions match, or when the long-term future predicted molten iron temperature is within the target range and the short-term future predicted molten iron temperature deviates from the target range.

5. 2. The molten iron temperature control method according to claim 1, wherein the operational action determination step determines manipulated variables and manipulated variables as operational actions based on the long-time-future predicted molten iron temperature when the long-time-future predicted molten iron temperature deviates from a target range and the operational actions corresponding to the long-time-future predicted molten iron temperature and the short-time-future predicted molten iron temperature do not match, and the operational action corresponding to the long-time-future predicted molten iron temperature is not at least contradictory to the operational action corresponding to the action determination value, and does not execute any proactive operational action when the operational action corresponding to the long-time-future predicted molten iron temperature does not match the operational action corresponding to the action determination value.

6. 3. The method for controlling molten iron temperature according to claim 2, wherein the operational constraints include at least one of an upper limit of tuyere gas temperature, a lower limit of tuyere gas temperature, an upper limit of reducing agent rate, a lower limit of reducing agent rate, and a lower limit of furnace top gas temperature.

7. 3. The molten iron temperature control method according to claim 2, wherein the control range of the blast moisture is determined by adding a value that allows a reduction in the blast moisture by an amount determined as a one-time operation amount to be performed at least once to the atmospheric humidity.

8. a model calculation unit that calculates the molten iron temperature or an action determination value for an operational action for controlling the molten iron temperature using a plurality of models that input operational data of the blast furnace; an operational action determination unit that uses the calculated molten iron temperature or the action determination value to select one of the plurality of models based on a determination criterion that is based on trends in prediction accuracy of the plurality of models, and determines an operation variable and an operation amount as the operational action, The plurality of models are a physical model capable of expressing a transient state by calculating heat transfer, chemical reactions, and fluid flow inside the blast furnace; a statistical model for extracting similar operating conditions based on past operation data of the blast furnace and predicting the molten iron temperature; a machine learning model that is generated by machine learning using learning data that links past operation data of the blast furnace with exemplary operation actions performed by an operator, and that inputs the operation data of the blast furnace and outputs the action determination value of an operation action that is determined to be appropriate; The operational action determination unit determining an operation variable and an operation amount as the operational action based on the long-term future predicted molten iron temperature calculated using the physical model, the short-term future predicted molten iron temperature calculated using the statistical model, and the action determination value calculated using the machine learning model; a molten iron temperature control device that determines an operation variable and an operation amount as the operation action based on the action determination value when the operation actions corresponding to the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature are different, or when it is determined that neither of the operation actions corresponding to the long-term future predicted molten iron temperature and the short-term future predicted molten iron temperature is necessary.

9. 9. The molten iron temperature control device according to claim 8, wherein the operational action determination unit further determines an operation variable and an operation amount as the operational action based on a control range of blast moisture determined in consideration of a reduction in a reducing agent rate and a limit on the use of pulverized coal based on an operational constraint.

10. An operation guidance method comprising presenting the operation action determined by the molten iron temperature control method according to any one of claims 1 to 7 so as to be visible to an operator of the blast furnace.

11. A method for operating a blast furnace, comprising the step of controlling the blast furnace in accordance with the operational action determined by the method for controlling molten iron temperature according to any one of claims 1 to 7.

12. A method for producing molten iron, comprising the step of controlling the blast furnace in accordance with the method for operating a blast furnace according to claim 11 to produce molten iron.

Images