Molten iron composition estimation device, composition estimation method, and desulfurization method

Abstract

Provided are a molten iron constituent estimation device, a constituent estimation method, and a desulfurization method that, in desulfurization processing of molten iron using mechanical agitation equipment, allow the constituents of the molten iron after desulfurization processing to be accurately estimated. A constituent estimation device (14) estimates the concentration of sulfur in molten iron (3) in desulfurization processing of the molten iron (3) using mechanical agitation desulfurization equipment (1), the constituent estimation device (14) comprising: a data input unit (140) that accepts input of current operation data in the desulfurization processing, said data including at least the molten iron temperature which is the temperature during the desulfurization processing and which is the temperature of the molten iron (3) measured using a non-contact temperature measurement device (12) after the start of agitation of the molten iron (3) and prior to the start of loading of a desulfurization agent (4); and a model calculation unit (142) that estimates the concentration of sulfur in the molten iron (3) after the desulfurization processing, from the current operation data and a machine learning model which represents the relationships, based on past operation data in the desulfurization processing, of the molten iron temperature during the desulfurization processing, the quantity of the desulfurization agent (4) loaded, and a reaction rate constant in the desulfurization processing.

Description

[Technical Field]

[0001] The present invention relates to an apparatus for estimating the composition of molten iron, a method for estimating the composition of molten iron, and a desulfurization method. [Background technology]

[0002] S content in steel leads to deterioration of hot brittleness and corrosion resistance, as well as reduction in toughness and workability, so there is a need to reduce the S concentration in steel. Furthermore, in recent years, there has been an increasing demand for higher purity and cleanliness in steel, and efforts are needed to further reduce the sulfur content of steel, i.e., to promote desulfurization and suppress resulfurization in the refining process of molten iron.

[0003] Desulfurization of molten iron is carried out in the pretreatment process of molten iron tapped from a blast furnace and in the secondary refining process of molten steel. For desulfurization in the pretreatment process of molten iron, the KR process using mechanical stirring equipment is widely used, and various methods have been proposed to achieve efficient desulfurization.

[0004] For example, Patent Document 1 proposes a component concentration calculation device and a component concentration calculation method for estimating the sulfur concentration in molten pig iron after refining based on past operational data in the refining process of molten iron. This method assumes that the desulfurization reaction of molten pig iron follows a first-order reaction equation, and estimates model parameters that are difficult to measure, such as reaction rate constants, included in the first-order reaction equation, using a component concentration estimation model from past operational data and the current molten pig iron components before desulfurization. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2020-15959 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the method of Patent Document 1 estimates the sulfur concentration in the molten pig iron based only on information obtained before the current desulfurization process, and does not disclose a method for controlling operating conditions using information obtained during the desulfurization process. Therefore, it may not be possible to accurately estimate the sulfur concentration in the molten pig iron after the desulfurization process. For example, if an unexpected change occurs during the desulfurization process, such as a sudden change in the molten pig iron temperature or a change in the state of entrainment of desulfurizing agents and slag in the molten pig iron, the desulfurization ability may decrease, resulting in poor desulfurization of the molten pig iron.

[0007] The present invention has been made in view of the above-mentioned problems, and aims to provide a molten pig iron composition estimation device, composition estimation method, and desulfurization method that can accurately estimate the S concentration, which is a component of molten pig iron after desulfurization treatment using mechanical stirring equipment. [Means for solving the problem]

[0008] (1) According to one aspect of the present invention, there is provided a molten pig iron composition estimation device for estimating the sulfur concentration in molten pig iron during desulfurization of the molten pig iron using mechanical stirring desulfurization equipment, the molten pig iron composition estimation device comprising: a data input unit for inputting current operational data for the desulfurization treatment, the data input unit including at least a molten pig iron temperature during the desulfurization treatment, the molten pig iron temperature being measured using a non-contact temperature measuring device after the start of stirring the molten pig iron and before the start of adding a desulfurizing agent; a machine learning model representing the relationship between the molten pig iron temperature during the desulfurization treatment, the amount of desulfurizing agent added, and a reaction rate constant for the desulfurization treatment, based on past operational data for the desulfurization treatment; and a model calculation unit for estimating the sulfur concentration in the molten pig iron after the desulfurization treatment from the current operational data.

[0009] (2) In the molten iron composition estimation device of (1) above, the data input unit inputs, as the past operation data, at least the molten iron temperature during the desulfurization treatment, the amount of desulfurization agent added, and the reaction rate constant, which is a constant in the desulfurization reaction formula expressed by formula (1), and the device further includes a model parameter determination unit that creates the machine learning model based on the past operation data input by the data input unit. [S]=[S]0·exp{K(t-t0)} ···(1) where [S] is the S concentration in the hot metal (mass%), [S]0 is the S concentration in the hot metal before the desulfurization treatment (mass%), and K is the reaction rate constant (s -1 ), t: desulfurization treatment time (s), t0: time from the start of stirring to the completion of slag entrainment in the molten iron (s)

[0010] (3) According to one aspect of the present invention, there is provided a method for estimating the sulfur concentration in molten pig iron during desulfurization treatment of molten pig iron using mechanical stirring desulfurization equipment, the method comprising the steps of: measuring the temperature of the molten pig iron during desulfurization treatment, which is the temperature of the molten pig iron after the start of stirring the molten pig iron and before the start of adding a desulfurizing agent, using a non-contact temperature measuring device; inputting current operational data for the desulfurization treatment, which includes at least the measured temperature of the molten pig iron during the desulfurization treatment; and estimating the sulfur concentration in the molten pig iron after the desulfurization treatment, based on past operational data for the desulfurization treatment, from a machine learning model that represents the relationship between the temperature of the molten pig iron during the desulfurization treatment, the amount of desulfurizing agent added, and a reaction rate constant for the desulfurization treatment, and the current operational data.

[0011] (4) In the method for estimating the components of molten iron described in (3) above, at least the molten iron temperature during the desulfurization treatment, the amount of desulfurization agent added, and the reaction rate constant, which is a constant in the desulfurization reaction formula shown in formula (1), in past operations are used as the past operational data, and the method further includes a step of creating the machine learning model based on the input past operational data. [S]=[S]0·exp{K(t-t0)} ···(1) where [S] is the S concentration in the hot metal (mass%), [S]0 is the S concentration in the hot metal before the desulfurization treatment (mass%), and K is the reaction rate constant (s -1 ), t: desulfurization treatment time (s), t0: time from the start of stirring to the completion of slag entrainment in the molten iron (s)

[0012] (5) According to one aspect of the present invention, there is provided a method for desulfurizing molten iron using mechanical stirring desulfurization equipment, in which, during the desulfurization treatment, the sulfur concentration in the molten iron after the desulfurization treatment is estimated using the method for estimating the composition of molten iron described in (3) or (4) above.

[0013] (6) The method for desulfurizing molten pig iron of (5) above further comprises, after the step of estimating the S concentration, a step of determining whether or not the S concentration in the molten pig iron after the desulfurization treatment is within a predetermined range, and if the S concentration in the molten pig iron after the desulfurization treatment is not within the predetermined range, the amount of desulfurization agent charged is changed, and the step of estimating the S concentration is performed again to re-estimate the S concentration in the molten pig iron.

[0014] (7) The method for desulfurizing molten pig iron according to (5) or (6) above further includes, after the step of estimating the S concentration, a step of measuring the temperature of the bath surface of the molten pig iron, a step of determining the state of slag entrapment on the bath surface of the molten pig iron from the measurement result of the step of measuring the temperature of the bath surface of the molten pig iron, and a step of adding a desulfurizing agent to the molten pig iron when it is determined that the slag entrapment is complete in the step of determining the state of slag entrapment.

[0015] (8) In any one of the above-mentioned (5) to (7) methods for desulfurizing molten pig iron, after adding a desulfurizing agent, a step of measuring the temperature of the bath surface of the molten pig iron, and a step of determining the state of slag entrainment on the bath surface of the molten pig iron from the measurement results of the step of measuring the temperature of the bath surface of the molten pig iron, and if it is determined that the slag is properly entrained in the step of determining the state of slag entrainment, continuing stirring by the impeller of the mechanical stirring type desulfurization equipment, and if it is determined that the slag is not properly entrained in the step of determining the state of slag entrainment, changing at least one of the rotation speed and immersion depth of the impeller. [Effects of the Invention]

[0016] According to one aspect of the present invention, there are provided a molten iron composition estimation device, a composition estimation method, and a desulfurization method that can accurately estimate the composition of molten iron after desulfurization treatment using mechanical stirring equipment. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a configuration diagram showing a mechanical stirring type desulfurization facility 1 according to one embodiment of the present invention. [Figure 2] 1 is a flowchart illustrating a method for desulfurizing molten iron according to one embodiment of the present invention. [Figure 3] 1 is a flowchart showing a method for estimating the components of molten iron according to one embodiment of the present invention. [Figure 4] 10 is a flowchart showing a method for determining the state of slag entrainment and changing the stirring conditions after the start of the introduction of the desulfurization agent. DETAILED DESCRIPTION OF THE INVENTION

[0018] In the following detailed description, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, identical or similar parts are designated by identical or similar reference numerals, and redundant explanations will be omitted. The drawings are schematic and may differ from the actual product. Furthermore, the embodiments shown below exemplify devices and methods for embodying the technical concept of the present invention, and the technical concept of the present invention does not specify the materials, structure, arrangement, etc. of component parts as described below. The technical concept of the present invention can be modified in various ways within the technical scope defined by the claims.

[0019] First, the inventors investigated the desulfurization behavior of hot metal desulfurization treatment using mechanically agitated desulfurization equipment by determining the amount of desulfurization agent added based on past and current operational data and adding the desulfurization agent to the hot metal. As a result, they found that the S concentration in the hot metal during desulfurization treatment can be accurately estimated by using the hot metal temperature before the start of desulfurization agent addition and estimating it based on a machine learning model that represents the relationship between the hot metal temperature, the amount of desulfurization agent added, and the reaction rate constant, and a first-order reaction equation. They also found that this estimation method can prevent insufficient desulfurization of the hot metal and excessive addition of desulfurization agent, thereby enabling efficient desulfurization treatment. The following describes a composition estimation device, a method for estimating the composition of hot metal, and a desulfurization method according to one embodiment of the present invention, based on these findings.

[0020] <Device configuration> A mechanical agitation desulfurization system according to one embodiment of the present invention will now be described. As shown in Fig. 1, the mechanical agitation desulfurization system 1 is a desulfurization treatment system (also referred to as a KR desulfurization treatment system) that desulfurizes molten pig iron 3 contained in a molten pig iron ladle 2 by mechanical agitation. The mechanical agitation desulfurization system 1 includes an impeller 10, a desulfurization agent charging device 11, a temperature measuring device 12, a control terminal 13, a component estimation device 14, and a determination device 15.

[0021] The impeller 10 is a mechanical stirrer having a rotating shaft and a refractory stirring blade at the tip of the rotating shaft. The impeller 10 is configured to be raised and lowered in a substantially vertical direction by a lifting device (not shown) and rotated around the shaft to which the stirring blade is connected at the tip by a rotating device (not shown) consisting of a drive motor and a reducer. The stirring blade at the tip of the impeller 10 is immersed in the molten pig iron 3, and the impeller mechanically stirs the molten pig iron 3 by rotating.

[0022] The desulfurization agent charging device 11 is a device that charges the desulfurization agent 4 into the molten pig iron 3. The desulfurization agent 4 is not limited to a specific substance, and a lime-based flux or a mixture of a lime-based flux and aluminum oxide can be used. The method of charging the desulfurization agent 4 is not limited to a specific method, and can include charging the desulfurization agent 4 all at once or continuously from above the molten pig iron ladle 2, or spraying the desulfurization agent 4 onto the surface of the molten pig iron 3 together with a carrier gas.

[0023] The temperature measuring device 12 is a non-contact thermometer disposed above the molten pig iron ladle 2 and measures the temperature of the bath surface of the molten pig iron 3 contained in the molten pig iron ladle 2. The temperature measuring device 12 is not particularly limited as long as it can measure the temperatures of the molten pig iron 3 and the slag 5 in a non-contact manner, and for example, a radiation thermometer or a thermograph can be used. In a method of measuring the temperature of the molten pig iron 3 by immersing a temperature measuring probe in the molten pig iron, there is a risk that the temperature measuring probe will come into contact with the impeller 10 or the solid slag 5 during desulfurization treatment, that is, when the impeller 10 is rotating. In this embodiment, by using a non-contact thermometer as the temperature measuring device 12, such a contact risk can be avoided and the temperatures of the molten pig iron 3 exposed at the bath surface of the molten pig iron 3 and the slag 5 covering the bath surface of the molten pig iron 3 can be measured.

[0024] The control terminal 13 controls the impeller 10 and the desulfurization agent charging device 11 to control the desulfurization treatment in the mechanical stirring desulfurization equipment 1. Specifically, the control terminal 13 instructs the impeller 10 on its operating conditions, such as its rotation speed and immersion depth, and acquires the results of these stirring conditions. The immersion depth of the impeller 10 refers to the depth to which the impeller 10 is immersed relative to the bath surface of the molten iron 3, indicated by the dotted line in the molten iron ladle 2 in FIG. 1 . The control terminal 13 also instructs the desulfurization agent charging device 11 on the amount and timing of the desulfurization agent 4 to be charged, and acquires the results of the amount and timing of the desulfurization agent 4. The control terminal 13 also instructs the desulfurization agent charging device 11 to charge the desulfurization agent 4 based on the amount of desulfurization agent 4 charged by the component estimation device 14, the slag entrapment determination result by the determination device 15, and the like. Furthermore, the control terminal 13 acquires the slag entrainment determination result from the determination device 15 and changes the stirring conditions during the desulfurization treatment as necessary. Furthermore, the control terminal 13 stores past operational data. The past operational data includes information about the molten pig iron 3 before and after the desulfurization treatment in past desulfurization treatments, as well as information about the operating conditions of the mechanical stirring desulfurization equipment 1. The past operational data includes, for example, the composition, temperature, and weight of the molten pig iron 3, the weight of the desulfurization slag, the amount of desulfurization agent 4 and other auxiliary materials charged, the rotation speed, immersion depth and number of uses of the impeller 10, the desulfurization treatment time, the time until the entrainment of the slag 5 is completed, and the number of uses of the molten pig iron ladle 2. The temperature of the molten pig iron 3 includes the temperature before the desulfurization treatment as well as the temperature of the molten pig iron during the desulfurization treatment, which will be described later. The time until the entrainment of the slag 5 is completed is the time from the start of stirring (mechanical stirring) of the molten pig iron 3 by the impeller 10 until the entrainment of the slag 5 into the molten pig iron 3 is completed. The other auxiliary materials are auxiliary materials other than the desulfurization agent 4 that are added to the molten pig iron 3, and examples thereof include iron-containing dust generated in the steelmaking process and used refractory waste.

[0025] The component estimation device 14 estimates at least the S concentration in the molten iron 3 as a component of the molten iron 3 after desulfurization based on past and current operational data and the temperature measurement results of the molten iron 3 by the temperature measurement device 12. The component estimation device 14 has a data input unit 140, a model parameter determination unit 141, and a model calculation unit 142. The component estimation method of the component estimation device 14 and details of each component will be described later.

[0026] The determination device 15 is a device that performs various determinations during desulfurization treatment and includes a temperature distribution image creation unit 150, a slag inclusion determination unit 151, and an S concentration determination unit 152. The temperature distribution image creation unit 150 creates a temperature distribution image from the measurement results of the temperature measurement device 12. The slag inclusion determination unit 151 determines whether or not slag 5 is entrained based on the temperature distribution image created by the temperature distribution image creation unit 150. The S concentration determination unit 152 determines whether or not the estimated value of the S concentration in the molten iron 3 after desulfurization treatment estimated by the component estimation device 14 is within a predetermined range, which will be described later. The determination method and each component of the determination device 15 will be described in detail later.

[0027] The control terminal 13, the component estimation device 14, and the determination device 15 may be provided in the form of programming executed by a computer, a PLC, or the like.

[0028] <Method for desulfurization of molten iron> A method for desulfurizing molten pig iron 3 according to this embodiment will be described. In this embodiment, desulfurization is performed according to the flowchart shown in FIG. 2. In this embodiment, the molten pig iron 3 is tapped from a blast furnace and, after tapping, is received in a molten pig iron holding and transporting vessel such as a hot metal ladle or a torpedo car. If necessary, the molten pig iron is subjected to preliminary molten pig iron treatments such as desiliconization and dephosphorization. The molten pig iron 3 is then transferred to a hot metal ladle 2 as necessary and transported to the mechanical stirring desulfurization equipment 1 while still contained in the hot metal ladle 2. Before the desulfurization, the composition, weight, and temperature of the molten pig iron 3 are measured, and the measurement results are recorded in the control terminal 13. If necessary, auxiliary materials such as desulfurization slag, which is the slag generated in the most recent desulfurization treatment, may be added to the hot metal ladle 2 in advance.

[0029] First, the data input unit 140 of the composition estimation device 14 acquires pre-desulfurization data, which is information about the molten iron 3 before desulfurization, from the control terminal 13 (S100). The pre-desulfurization data are pre-measured operating conditions related to the desulfurization process. The pre-desulfurization data include, for example, the composition, temperature, and weight of the molten iron 3, the weight of the desulfurization slag, and the number of uses of the molten iron ladle 2. The pre-desulfurization data also includes, as pre-set values ​​(initial values), the amounts of the desulfurization agent 4 and other auxiliary materials charged, the rotation speed of the impeller 10, the immersion depth and number of uses, the desulfurization process time, and the time until the entrainment of the slag 5 is completed. Furthermore, the pre-desulfurization data may also be stored in a host computer, server, or the like (not shown), and the data input unit 140 may acquire the pre-desulfurization data from the host computer, server, or the like. Note that step S100 may be performed before the desulfurization process, such as after tapping or hot metal pretreatment.

[0030] Next, the control terminal 13 starts the desulfurization process by immersing the stirring blades of the impeller 10 in the molten iron 3 and rotating the impeller 10 (S102). Pre-set stirring conditions such as the rotation speed and immersion depth of the impeller 10 are used.

[0031] Furthermore, the temperature measuring device 12 measures the temperature of the bath surface of the molten pig iron 3 (S104). Step S104 is performed after a predetermined time has elapsed since stirring by the impeller 10 began. This predetermined time is set as the time during which the molten pig iron 3 is sufficiently exposed at the bath surface (top surface) of the molten pig iron 3 to allow temperature measurement, and is appropriately set depending on the amount of slag 5, the shape and dimensions of the stirring blades of the impeller 10, the stirring conditions, etc. In a mechanical stirring desulfurization process, the bath surface of the molten pig iron 3 is usually started with the process covered with slag 5, such as desulfurization slag. Therefore, after stirring by the impeller 10 for a predetermined time, the molten pig iron 3 is exposed at the bath surface of the molten pig iron 3, making the temperature of the molten pig iron 3 measurable. The temperature measurement result of the molten pig iron 3 is transmitted to the control terminal 13 and stored. The temperature of the molten iron 3 measured in step S104, that is, the temperature of the molten iron 3 after the start of stirring during desulfurization and before the start of charging of the desulfurization agent 4, is also referred to as the molten iron temperature during desulfurization.

[0032] Thereafter, the component estimation device 14 estimates the S concentration in the desulfurized molten iron 3 (S106). The component estimation device 14 estimates the component (S concentration) of the molten iron 3 in the following manner.

[0033] (Method for estimating the composition of molten iron) As described above, the method for estimating the components of molten pig iron 3 according to this embodiment estimates the S concentration in the molten pig iron 3 after desulfurization. In this embodiment, the S concentration in the molten pig iron 3 after desulfurization is estimated based on the temperature of the molten pig iron 3 measured by the temperature measuring device 12, data on the molten pig iron 3 before desulfurization, and past operational data. Note that, hereinafter, the temperature of the molten pig iron 3 measured by the temperature measuring device 12 (the temperature of the molten pig iron during desulfurization) and the data on the molten pig iron 3 before desulfurization are collectively referred to as current operational data.

[0034] In the method for estimating the composition of the molten iron 3 according to this embodiment, the composition of the molten iron 3 is estimated according to the flowchart shown in Fig. 3. First, the data input unit 140 acquires current operation data and past operation data from the control terminal 13 (S200).

[0035] Next, the model parameter determination unit 141 creates a machine learning model that represents the relationship between the temperature of the molten iron 3, the amount of desulfurization agent 4 charged, and the reaction rate constant K from past operation data (S202). Here, the reaction rate constant K is a constant in the desulfurization reaction formula expressed by the following formula (1). [S]=[S]0·exp{K(t-t0)} ···(1) where [S] is the S concentration in the hot metal (mass%), [S]0 is the S concentration in the hot metal before the desulfurization treatment (mass%), and K is the reaction rate constant (s -1 ), t: desulfurization treatment time (s), t0: time from the start of stirring to the completion of slag entrainment in the molten iron (s).

[0036] If the desulfurization agent 4 is added when the slag 5 is not properly entrained in the molten pig iron 3 and the surface of the molten pig iron 3 is covered with slag, the desulfurization agent 4 may be trapped by the slag 5 before reacting with the sulfur in the molten pig iron 3, reducing its desulfurization ability and resulting in insufficient desulfurization of the molten pig iron 3. For this reason, it is important to create a model that takes into account the time t0 from the start of stirring to the completion of entrainment of the slag 5 in the molten pig iron 3. The time t0 from the start of stirring to the completion of entrainment of the slag 5 in the molten pig iron 3 can be determined by continuously measuring the temperature of the bath surface of the molten pig iron 3 using a temperature measuring device 12 and determining the state of entrainment of the slag 5, as described below.

[0037] Furthermore, since it is difficult to actually measure the reaction rate constant K in equation (1), it is important to determine it from past and current operational data.

[0038] The type of machine learning model is not particularly limited, and for example, a model utilizing a neural network can be applied. In this way, the reaction rate constant K can be determined with high accuracy based on a wide range of operational data.

[0039] Furthermore, the desulfurization reaction of the molten iron 3 proceeds more easily as the molten iron temperature increases and as the amount of desulfurization agent 4 charged increases. Therefore, when determining the reaction rate constant K, it is important to input the temperature of the molten iron 3 and the amount of desulfurization agent 4 charged as explanatory variables.

[0040] After step S202, the model parameter determination unit 141 determines the reaction rate constant K from the machine learning model created in step S202, the molten iron temperature during the desulfurization treatment measured in step S104, and pre-desulfurization data of the molten iron 3 (S204). In step S204, it is preferable to determine the reaction rate constant K using at least the initial value of the amount of desulfurization agent 4 charged, the weight of the desulfurization slag, and the amounts of other auxiliary materials charged, among the pre-desulfurization data of the molten iron 3.

[0041] Thereafter, the model calculation unit 142 estimates the S concentration in the molten iron 3 after desulfurization based on the desulfurization reaction formula shown in Equation (1) using the reaction rate constant K calculated in step S204 and the data before desulfurization of the molten iron 3 (S206). The estimated S concentration in the molten iron 3 after desulfurization is transmitted to the S concentration determination unit 152 of the determination device 15.

[0042] According to the method for estimating the composition of the molten pig iron 3 of this embodiment, the sulfur concentration in the molten pig iron 3 after desulfurization is estimated using the molten pig iron temperature measured during desulfurization in step S104. In estimating the sulfur concentration in the molten pig iron 3 after desulfurization, it is important to accurately estimate the reaction rate constant K during the desulfurization. The temperature of the molten pig iron 3 is one of the factors that significantly affect the reaction rate constant K. Therefore, the estimation accuracy can be improved by using the actual temperature during the desulfurization as the temperature of the molten pig iron 3, rather than the temperature measured before the desulfurization. Conventional knowledge has made it difficult to estimate the temperature of the molten pig iron during desulfurization based on the temperature before the desulfurization, due to various factors such as the usage status of the molten pig iron ladle 2 containing the molten pig iron 3 and the temperature and amount of desulfurization slag added. In contrast to this, in the present embodiment, the temperature of the molten iron 3 is measured during the desulfurization treatment in step S104, and by using the measured molten iron temperature during the desulfurization treatment, the reaction rate constant K can be accurately estimated, and the S concentration in the molten iron 3 after the desulfurization treatment can also be accurately estimated.

[0043] After step S106, the S concentration determination unit 152 determines whether the S concentration in the molten pig iron 3 after the desulfurization treatment estimated in step S106 is within a predetermined range (S108). The predetermined range of the S concentration is appropriately set as a preferable S concentration after the desulfurization treatment, depending on the target S concentration of the molten pig iron 3. Specifically, the upper limit of the predetermined range of the S concentration is set from the viewpoint of quality. On the other hand, the lower limit of the predetermined range of the S concentration is set as an acceptable value taking into account factors such as resulfurization in the subsequent refining treatment. The determination result of step S108 is transmitted to the control terminal 13.

[0044] If it is determined in step S108 that the S concentration in the molten pig iron 3 after desulfurization is not within the predetermined range, the control terminal 13 changes the amount (planned amount) of desulfurization agent 4 charged (S110). In step S110, if the estimated S concentration in the molten pig iron 3 after desulfurization is higher than the upper limit of the predetermined range, the amount of desulfurization agent 4 charged is changed to be greater than the amount of desulfurization agent 4 used in the estimation in the immediately preceding step S106. On the other hand, if the estimated S concentration in the molten pig iron 3 after desulfurization is lower than the lower limit of the predetermined range, the amount of desulfurization agent 4 charged is changed to be less than the amount of desulfurization agent 4 used in the estimation in the immediately preceding step S106. In other words, in step S108, the amount of desulfurization agent 4 charged is changed so that the S concentration in the molten pig iron 3 after desulfurization is within the predetermined range. The adjustment amount of the desulfurization agent 4 in step S108 is not particularly limited, but if the adjustment amount is too large, the S concentration after the desulfurization treatment may not fall within a predetermined range. On the other hand, if the adjustment amount is too small, the repetitive calculation time will be long, and it may take a long time to determine the amount of desulfurization agent 4 to be added. For this reason, it is preferable to set an appropriate adjustment amount depending on the specifications and operational performance of the mechanical stirring type desulfurization equipment 1.

[0045] After step S110, the processing from step S106 onwards is performed again. When the processing of step S106 is performed after step S110, the amount of desulfurization agent 4 charged, which is used to estimate the S concentration in the molten iron 3, is changed in step S110.

[0046] That is, in the repeated series of steps S106 to S110, the amount of desulfurization agent 4 charged is adjusted so that the estimated sulfur concentration in the molten pig iron 3 after desulfurization falls within a predetermined range. This allows the amount of desulfurization agent 4 charged to be set neither too much nor too little. If the amount of desulfurization agent 4 charged is too small, the sulfur concentration in the molten pig iron 3 after desulfurization will be higher than the target upper limit, making it necessary to perform the desulfurization process again or to perform a separate desulfurization process in a subsequent process. On the other hand, if the amount of desulfurization agent 4 charged is too large, there will be no problem with the quality of the molten pig iron 3, but the production cost will increase.

[0047] If it is determined in step S108 that the S concentration in the molten iron 3 after the desulfurization treatment is within the predetermined range, the control terminal 13 determines the amount of desulfurization agent 4 to be actually charged to be the amount used in estimating the S concentration in the molten iron 3 after the desulfurization treatment in the previous step S106 (S112).

[0048] After step S112, the temperature measuring device 12 measures the temperature of the bath surface of the molten iron 3 (S114). In step S114, the temperature measuring device 12 measures the temperature of a predetermined region on the bath surface of the molten iron 3 and transmits the measurement result to the determination device 15. The predetermined region on the bath surface refers to multiple points on the bath surface of the molten iron 3, and may be any region in which the entrainment of slag 5 on the bath surface of the molten iron 3, as described below, can be confirmed, but preferably covers 80% or more of the bath surface area of ​​the molten iron 3.

[0049] After step S114, the determination device 15 determines the state of slag entrapment from the measurement results of step S114 and determines whether the entrapment of slag 5 has been completed to the extent that the desulfurization agent 4 can be added (S116). In step S116, the determination device 15 determines the state of slag entrapment in the molten iron 3 based on the temperature difference between the molten iron 3 and the slag 5 on the bath surface of the molten iron 3 from the measurement results of the temperature of the bath surface of the molten iron 3. Because the temperature of the slag 5 is lower than that of the molten iron 3, the state of slag entrapment can be determined by verifying the temperature distribution on the bath surface of the molten iron 3.

[0050] Specifically, the temperature distribution image creation unit 150 of the determination device 15 creates a temperature distribution image at multiple points or a predetermined area on the bath surface of the molten iron 3 from the measurement results of step S114. Next, the slag inclusion determination unit 151 calculates the total area of ​​the exposed molten iron portion and the slag-covered portion in the created temperature distribution image. In this case, the points where the measured temperature is equal to or higher than the threshold value X (°C) are defined as exposed molten iron portions, and the points where the measured temperature is lower than the threshold value X (°C) are defined as slag-covered portions. The total area A of the exposed molten iron portions is calculated as follows: m and the total area of ​​the slag-covered part A sThe temperature of the slag-covered portion may be further limited to a lower limit value in consideration of the influence of the impeller 10, the molten iron ladle 2, etc. The slag entrapment determination unit 151 calculates the area ratio A m / A s The entrapment state is determined based on the area ratio A m / A s A threshold value Y1 may be set for X, and this threshold value Y1 may be used to determine whether or not the entrainment of the slag 5 has been completed. Although the threshold values ​​X and Y1 can be set arbitrarily, it is preferable that the threshold value Y1 be 4.0 or more.

[0051] If it is determined in step S116 that the entrainment of the slag 5 has not been completed, the processes from step S114 onwards are carried out again.

[0052] On the other hand, if it is determined in step S116 that the entrainment of slag 5 is complete, the control terminal 13 controls the desulfurization agent charging device 11 to charge the desulfurization agent 4 into the molten pig iron 3 in the amount determined in step S112 (S118). As described above, if the slag 5 is not sufficiently entrained, the charged desulfurization agent 4 may be trapped by the slag 5, reducing the desulfurization capacity. However, by determining the entrainment state of slag 5 in step S116 and charging the desulfurization agent 4 in step S118 after the slag 5 is sufficiently entrained, it is possible to prevent poor desulfurization. Another possible method for determining the entrainment of slag 5 is to visually check it with an operator. However, this method relies on the judgment criteria, and therefore the time required for the judgment varies even under the same operating conditions. Therefore, there are concerns that poor entrainment of slag 5 may reduce the desulfurization capacity, or that a delay in the start of desulfurization agent 4 charging may extend the desulfurization process time.

[0053] After step S118, that is, after the introduction of the desulfurization agent 4 has begun, stirring by the impeller 10 is continued for a predetermined time corresponding to the desulfurization treatment time, thereby completing the desulfurization treatment. After the desulfurization treatment is completed, the slag 5 in the hot metal ladle 2 may be removed as a post-treatment to suppress sulfur pickup from the slag 5 into the hot metal 3 after the desulfurization treatment. The hot metal 3 produced in this process undergoes a primary refining treatment in a converter or the like and a secondary refining treatment in an LF or RH vacuum degasser or the like, and is then turned into a steel material such as a slab by a continuous casting method or an ingot casting-blooming rolling method.

[0054] After step S118, that is, after the introduction of the desulfurization agent 4 is started, the determination of slag entrapment and the adjustment of the stirring conditions shown in Fig. 4 may be further performed. In the flowchart shown in Fig. 4, first, the temperature measuring device 12 measures the temperature of the bath surface of the molten iron 3 (S300). The measurement in step S300 may be performed in the same manner as in step S114.

[0055] Next, the determination device 15 determines the slag entrapment state from the measurement results in step S300, and determines whether the entrapment of the slag 5 is appropriate (S302). The determination in step S302 can be performed in the same manner as the determination in step S116. That is, a temperature distribution image is created by the temperature distribution image creation unit 150 from the measurement results in step S300, and the area ratio A of the exposed molten iron part to the slag covered part in the created temperature distribution image is calculated. m / A s The slag entrapment determination unit 151 determines the entrapment state of the slag 5 based on the area ratio A m / A s It is preferable to set the threshold value Y2 to a value greater than the threshold value Y1.

[0056] If it is determined in step S302 that the entrainment of slag 5 is inappropriate, the control terminal 13 acquires the determination result and changes the mixing conditions (S304). At this time, at least one of the rotation speed and immersion depth of the impeller 10 is changed as the mixing conditions so that the slag 5 is more likely to be entrained. Note that in step S304, the mixing conditions are changed so that the slag 5 is more likely to be entrained. In other words, when the rotation speed of the impeller 10 is changed, the mixing conditions are changed so that the rotation speed is increased, and when the immersion depth of the impeller 10 is changed, the immersion depth is changed so that the immersion depth is shallower.

[0057] The desulfurization agent 4 introduced into the molten pig iron 3 reacts with sulfur in the molten pig iron 3, then rises to the surface of the molten pig iron 3 and is captured by slag 5. Therefore, as the cumulative amount of desulfurization agent 4 introduced increases, the amount of slag in the molten pig iron ladle 2 also increases. Therefore, even if the stirring conditions are maintained constant, the entrainment of slag 5 into the molten pig iron 3 may become inappropriate as the cumulative amount of desulfurization agent 4 introduced increases. Regarding control of the rotation speed of the impeller 10, increasing the rotation speed can promote the entrainment of slag 5 into the molten pig iron 3. However, excessively increasing the rotation speed of the impeller 10 may result in equipment failure due to overloading of the impeller control device or accelerated wear of the impeller 10 refractory. Regarding the immersion depth of the impeller 10, it is preferable to control the height of the vortex formed on the surface of the molten pig iron 3 by mechanical stirring so that the tip of the vortex is below the top of the impeller 10.

[0058] On the other hand, if it is determined in step S302 that the entrainment of slag 5 is appropriate, the determination of slag entrainment and the adjustment of the stirring conditions are terminated. In the process shown in FIG. 4, if it is determined that the entrainment of slag 5 is insufficient, the stirring conditions are changed to increase the desulfurization efficiency. This allows the desulfurization efficiency to be stably increased.

[0059] <Modification> Although the present invention has been described above with reference to specific embodiments, it is not intended that the invention be limited by these descriptions. By referring to the description of the present invention, other embodiments of the present invention that include various modifications in addition to the disclosed embodiments will be apparent to those skilled in the art. Therefore, it should be understood that the embodiments of the invention set forth in the claims also encompass embodiments that include these modifications described herein, either alone or in combination.

[0060] For example, in the above embodiment, the S concentration after desulfurization is estimated as the composition estimation of the molten iron 3, but the present invention is not limited to this example. For example, the S concentration in the molten iron 3 during desulfurization after a predetermined time has elapsed may be estimated.

[0061] In the above embodiment, the process of creating the machine learning model in step S202 is performed after the desulfurization process is started, but the present invention is not limited to this example. The process of step S202 may be performed in advance before the desulfurization process is started.

[0062] Furthermore, in the above embodiment, the amount of desulfurization agent 4 charged is changed based on the estimated S concentration in the molten pig iron 3 after desulfurization so that the S concentration falls within a predetermined range. However, the present invention is not limited to this example. For example, the amount of desulfurization agent 4 charged may be kept constant and the desulfurization treatment time may be changed to adjust the estimated S concentration in the molten pig iron 3 after desulfurization so that it falls within a predetermined range. In an environment where there is ample time in operation, such as when there is a problem or when production capacity is reduced, there may be ample time for the desulfurization treatment. In such cases, it is possible to adjust the desulfurization treatment time. Therefore, by keeping the amount of desulfurization agent 4 charged constant and changing the desulfurization treatment time, the amount of desulfurization agent 4 charged can be reduced, potentially reducing production costs.

[0063] <Effects of the embodiment> (1) A molten iron component estimation device 14 according to one aspect of the present invention is a component estimation device 14 that estimates the S concentration in molten iron 3 during desulfurization of the molten iron 3 using mechanical stirring desulfurization equipment 1, a data input unit 140 for inputting current operational data for the desulfurization treatment, the data including at least the molten iron temperature during the desulfurization treatment, which is the temperature of the molten iron 3 measured using a non-contact temperature measuring device 12 after the start of stirring the molten iron 3 and before the start of charging the desulfurization agent 4; a model calculation unit 142 that estimates the S concentration in the molten iron 3 after desulfurization from a machine learning model that represents the relationship between the molten iron temperature during desulfurization, the amount of desulfurization agent 4 charged, and the reaction rate constant in the desulfurization, based on past operation data in the desulfurization, and from current operation data; Equipped with.

[0064] According to the above configuration (1), by using the molten pig iron temperature actually measured during the desulfurization treatment, a highly accurate machine learning model can be used, and the S concentration in the molten pig iron 3 after the desulfurization treatment can be accurately estimated. As a result, in the desulfurization treatment in the mechanical stirring type desulfurization equipment 1, the occurrence of desulfurization defects in the molten pig iron 3 can be suppressed, and the desulfurization treatment can be performed efficiently.

[0065] (2) In the configuration of (1) above, the data input unit 140 inputs, as past operational data, at least the temperature of the molten iron 3 measured using the non-contact temperature measuring device 12 before the start of the introduction of the desulfurization agent 4, the introduction amount of the desulfurization agent, and the reaction rate constant, which is a constant in the desulfurization reaction formula shown in formula (1), in past operations; The system further includes a model parameter determination unit 141 that creates a machine learning model based on the past operation data input by the data input unit 140.

[0066] According to the above configuration (2), the reaction rate constant K can be estimated with high accuracy. Furthermore, by taking into account the time t0 from the start of stirring to the completion of entrainment of slag 5 into the molten pig iron 3, it is possible to eliminate the influence of a decrease in desulfurization efficiency due to insufficient entrainment of slag 5, and it is possible to accurately estimate the S concentration in the molten pig iron 3 after desulfurization.

[0067] (3) A method for estimating the composition of molten pig iron (3) according to one aspect of the present invention is a method for estimating the S concentration in molten pig iron (3) during desulfurization of the molten pig iron (3) using mechanical stirring desulfurization equipment (1), a step (S104) of measuring the temperature of the molten iron 3 during desulfurization treatment, which is the temperature of the molten iron 3 after the start of stirring the molten iron 3 and before the start of charging the desulfurization agent 4, using a non-contact temperature measuring device 12; Steps (S200, S106) of inputting current operational data in the desulfurization treatment, including at least the measured hot metal temperature during the desulfurization treatment; a step (S206, S106) of estimating the S concentration in the hot metal 3 after the desulfurization treatment from a machine learning model that represents the relationship between the hot metal temperature during the desulfurization treatment, the amount of desulfurization agent charged, and the reaction rate constant in the desulfurization treatment, based on past operational data in the desulfurization treatment, and from current operational data; Equipped with.

[0068] According to the above configuration (3), the same effect as that of the above configuration (1) can be obtained.

[0069] (4) In the configuration of (3) above, at least the molten iron temperature during desulfurization treatment, the amount of desulfurization agent 4 charged, and the reaction rate constant K, which is a constant in the desulfurization reaction formula shown in formula (1), are used as past operation data, In the step of inputting the operational data, at least the molten iron temperature during the desulfurization treatment, the amount of the desulfurization agent 4 charged, and the reaction rate constant K, which is a constant in the desulfurization reaction formula shown in formula (1), in the past operation are input as the past operational data, The method further includes a step (S202) of creating a machine learning model based on the input past operational data.

[0070] According to the above configuration (4), the same effect as that of the above configuration (2) can be obtained.

[0071] (5) A method for desulfurizing molten iron (3) according to one aspect of the present invention is a method for desulfurizing molten iron (3) using mechanical stirring type desulfurization equipment (1), During the desulfurization treatment, the S concentration in the molten iron 3 after the desulfurization treatment is estimated using the method for estimating the composition of the molten iron 3 described in (3) or (4) above.

[0072] According to the above configuration (5), the same effect as that of the above configuration (1) can be obtained.

[0073] (6) In the configuration of (5), after the steps of estimating the S concentration (S206, S106), a step (S108) of determining whether the S concentration in the molten iron 3 after the desulfurization treatment is within a predetermined range is further provided; If the S concentration in the molten pig iron 3 after the desulfurization treatment is not within the predetermined range, the amount of desulfurization agent 4 charged is changed, and the steps of estimating the S concentration (S110, S106) are performed again to re-estimate the S concentration in the molten pig iron 3.

[0074] According to the above configuration (6), it is possible to suppress the occurrence of defective desulfurization. Moreover, it is possible to prevent excessive addition of the desulfurization agent 4, thereby reducing the cost of the desulfurization treatment and suppressing the extension of the desulfurization treatment time.

[0075] (7) In the configuration of (5) or (6), after the step of estimating the S concentration (S206, S106), a step of measuring the temperature of the bath surface of the molten iron 3 (S114); a step (S116) of determining the state of entrainment of slag 5 on the bath surface of molten iron 3 from the measurement result in the step (S114) of measuring the temperature of the bath surface of molten iron 3; In the step (S116) of determining the entrainment state of the slag 5, if it is determined that the entrainment of the slag 5 is completed, a step (S118) of adding a desulfurization agent 4 to the molten iron 3; Further provided are:

[0076] According to the above configuration (7), the desulfurization agent 4 can be reliably charged after the slag 5 is entrained, and therefore, a decrease in desulfurization efficiency can be prevented.

[0077] (8) In any one of the above (5) to (7), a step (S300) of measuring the temperature of the bath surface of the molten iron 3 after the desulfurization agent 4 is charged; a step (S302) of determining the state of entrainment of slag 5 on the bath surface of molten iron 3 from the measurement result of the step (S300) of measuring the temperature of the bath surface of molten iron 3; In the step (S302) of determining the entrainment state of the slag 5, if it is determined that the slag 5 is properly entrained, stirring by the impeller 10 of the mechanical stirring type desulfurization equipment 1 is continued, In the step (S302) of determining the state of entrainment of slag 5, if it is determined that slag 5 is not properly entrained, at least one of the rotation speed and immersion depth of impeller 10 is changed (S304).

[0078] According to the above configuration (8), even when the cumulative amount of the desulfurization agent 4 charged increases, the state of entrainment of the slag 5 can be appropriately controlled, and a decrease in the desulfurization efficiency can be prevented. [Example]

[0079] Examples conducted by the present inventors will be described. In the examples, in an actual furnace with a molten pig iron capacity of approximately 200 tons per charge, molten pig iron 3 tapped from a blast furnace was placed in a hot metal ladle 2 and subjected to desiliconization and dephosphorization treatments as necessary. The S concentration in the molten pig iron 3 after the desiliconization and dephosphorization treatments was 0.0300% by mass or less. Next, the hot metal ladle 2 containing the molten pig iron 3 was transported to a mechanically stirred desulfurization facility 1, where it was subjected to desulfurization treatment. The operation was carried out by varying the stirring conditions of the impeller 10 and the conditions for introducing the desulfurization agent 4. Burnt lime with a particle size of 0.5 mm or less was used as the desulfurization agent 4. The desulfurization agent 4 was introduced by spraying the desulfurization agent 4 onto the surface of the molten pig iron 3 together with a carrier gas.

[0080] In the operation of the example, when the desulfurization agent 4 was added to the molten pig iron 3 having the composition and temperature shown in Table 1, the sulfur concentration in the molten pig iron 3 after desulfurization was estimated using the composition estimation device 14 according to the above embodiment, and the amount of desulfurization agent 4 added was determined so that the estimated sulfur concentration would be equal to or less than the target value. When estimating the sulfur concentration in the molten pig iron 3 after desulfurization, the sulfur concentration in the molten pig iron during desulfurization was estimated using past operation data and current operation data based on a machine learning model that represents the relationship between the temperature of the molten pig iron 3, the amount of desulfurization agent 4 added, and the reaction rate constant K, and a first-order reaction equation. Then, the desulfurization treatment was performed by adding the desulfurization agent 4 to the molten pig iron 3 in the determined amount.

[0081] Furthermore, in Comparative Examples 1 to 3, instead of using a machine learning model and a first-order reaction equation, a multiple regression model was constructed based only on past operational data and representing the relationship between the temperature of the molten iron 3, the amount of desulfurization agent 4 charged, and the S concentration in the molten iron 3 after desulfurization, to determine the amount of desulfurization agent 4 charged. Furthermore, in Comparative Examples 4 to 9, when determining the amount of desulfurization agent 4 charged, similar to the above embodiment, the temperature of the molten iron 3 before desulfurization was used instead of the temperature of the molten iron during desulfurization.

[0082] In Examples 4 to 6 and 10 to 12, the processes of steps S114 and S116 were performed to determine the state of entrainment of slag 5 in the molten pig iron 3, and the introduction of the desulfurization agent 4 was started after the entrainment of slag 5 in the molten pig iron 3 was completed. In the other Examples and Comparative Examples, the introduction of the desulfurization agent 4 was started before the entrainment of slag 5 in the molten pig iron 3 was completed.

[0083] Furthermore, in Examples 7 to 12, the processes of steps S300, S302, and S304 were performed, and the state of entrainment of slag 5 into the molten pig iron 3 was judged after the start of the introduction of the desulfurization agent 4. If the entrainment of slag 5 into the molten pig iron 3 was not appropriate, the stirring conditions were changed. The changed stirring conditions are shown in Table 1 under Control of Stirring Conditions.

[0084] Furthermore, the results of investigating the composition of the obtained molten pig iron 3 in the molten pig iron ladle 2 after desulfurization are also shown in Table 1. Note that the contact risk in Table 1 refers to the risk of contact between the temperature measurement probe and solid slag, and is rated as "none" when a non-contact thermometer is used, and "high" when a contact thermometer is used and the temperature measurement probe comes into contact with solid slag, making it impossible to use it three or more times in succession. Furthermore, the desulfurization rate in Table 1 is the difference between the S concentration in the molten pig iron 3 before desulfurization and the S concentration in the molten pig iron 3 after desulfurization, expressed as a percentage of the S concentration in the molten pig iron 3 before desulfurization.

[0085] [Table 1]

[0086] From the results shown in Table 1, it was confirmed that under the conditions (Examples 1 to 3) in which the component estimation device 14 according to the above embodiment was used to estimate the S concentration in the molten iron 3 after desulfurization treatment and the amount of desulfurization agent 4 added was determined so that the estimated S concentration was below the target value, the desulfurization rate was 80% or more.

[0087] In addition, in Examples 4 to 6, the temperature during the desulfurization treatment was measured using the temperature measuring device 12, the state of entrainment of the slag 5 was determined before the desulfurization agent 4 was charged, and the desulfurization agent 4 was charged after the entrainment of the slag 5 into the molten iron 3 was completed. Under these conditions, it was confirmed that the desulfurization effect was further improved compared to Examples 1 to 3, and the desulfurization rate was 90% or more.

[0088] Furthermore, in Examples 7 to 9, the temperature during the desulfurization treatment is measured using the temperature measuring device 12, the state of entrainment of the slag 5 is judged after the start of the introduction of the desulfurization agent 4, and the stirring conditions are changed if the entrainment of the slag 5 into the molten iron 3 is not appropriate. Even under these conditions, it was confirmed that the desulfurization effect was further improved compared to Examples 1 to 3, and the desulfurization rate reached 90% or more.

[0089] Furthermore, in Examples 10 to 12, the temperature during the desulfurization treatment was measured using the temperature measuring device 12, and the entrainment state of the slag 5 was determined before the introduction of the desulfurization agent 4 and after the introduction of the desulfurization agent 4 was started. Furthermore, under these conditions, the desulfurization agent 4 was introduced after the entrainment of the slag 5 into the molten pig iron 3 was completed, and the stirring conditions were changed if the entrainment of the slag 5 into the molten pig iron 3 was not appropriate. Even under these conditions, the desulfurization effect was further improved compared to Examples 1 to 3, with the desulfurization rate reaching 90% or more, and it was confirmed that the desulfurization rate was even higher than in Examples 4 to 9.

[0090] On the other hand, under the conditions (Comparative Examples 1 to 3) where the amount of desulfurization agent 4 added was determined using a multiple regression model constructed based only on past operating data, it was confirmed that the desulfurization rate was less than 60% because the amount of desulfurization agent 4 added was insufficient.

[0091] Furthermore, when the temperature of the molten pig iron 3 was measured using a non-contact temperature measuring device 12 before the start of stirring (Comparative Examples 4 to 6), it was confirmed that the amount of desulfurization agent 4 charged was excessive, although the desulfurization rate was equivalent to the results shown in Examples 1 to 3 in Table 1. This is because the temperature measuring device 12 actually measures the temperature of the slag 5 present on the bath surface of the molten pig iron 3, and the measured temperature of the molten pig iron 3 is lower than the actual temperature.

[0092] Furthermore, when the temperature of the molten iron 3 was measured using a contact thermometer before the start of stirring (Comparative Examples 7 to 9), the desulfurization rate and the amount of desulfurization agent 4 added were comparable to those shown in Examples 1 to 3, but it was confirmed that there was a high risk of the temperature measuring probe coming into contact with the solid slag. This makes it difficult to use a contact thermometer continuously. [Explanation of symbols]

[0093] 1 Mechanical agitation desulfurization equipment 10 impeller 11 Desulfurization agent injection device 12 Temperature measuring device 13 Control terminal 14 Component Estimation Device 140 Data Entry Section 141 Model parameter determination unit 142 Model Calculation Section 15 Judgment device 150 Temperature distribution image creation unit 151 Slag entrapment detection unit 152 S concentration determination section 2 molten iron ladle 3. Molten iron 4. Desulfurization agent 5. Slug

Claims

1. A molten iron component estimation device for estimating the S concentration in molten iron during desulfurization of molten iron using mechanical stirring desulfurization equipment, comprising: a data input unit for inputting current operational data for the desulfurization treatment, the data including a molten pig iron temperature during desulfurization treatment, which is the temperature of the molten pig iron measured using a non-contact temperature measuring device after the start of stirring the molten pig iron and before the start of adding the desulfurization agent, and pre-desulfurization treatment data including at least the components of the molten pig iron, the amount of the desulfurization agent added, the desulfurization treatment time, and the time until slag entrainment is completed; a model parameter determination unit that creates a machine learning model based on past operation data of the desulfurization treatment, the machine learning model representing at least the molten iron temperature and the amount of desulfurization agent charged during the desulfurization treatment as explanatory variables and a reaction rate constant in the desulfurization treatment as a response variable; a model calculation unit that estimates the S concentration in the molten iron after desulfurization treatment based on the machine learning model and the current operational data; Equipped with the past operational data includes, in past operations, at least the molten iron temperature during the desulfurization treatment, the amount of the desulfurization agent charged, and the reaction rate constant, which is a constant in the desulfurization reaction formula represented by formula (1), the model calculation unit determines the reaction rate constant from the machine learning model and the current operational data, and estimates the S concentration in the molten iron after desulfurization using the determined reaction rate constant, the data before desulfurization, and equation (1). [S] = [S] 0 ・exp{K(t-t 0 )} ...(1) where [S] is the S concentration in the molten iron (mass%), [S] 0 is the S concentration in the molten iron before the start of desulfurization (mass%), K is the reaction rate constant (s −1 ), t is the desulfurization time (s), and t 0 is the time from the start of stirring to the completion of slag entrainment in the molten iron (s).

2. A method for estimating the sulfur concentration in molten pig iron during desulfurization of the molten pig iron using a mechanical stirring desulfurization facility, comprising: measuring the temperature of the molten iron during desulfurization treatment, which is the temperature of the molten iron after the start of stirring the molten iron and before the start of adding the desulfurization agent, using a non-contact temperature measuring device; inputting current operational data for the desulfurization treatment, the current operational data including the measured molten iron temperature during the desulfurization treatment and pre-desulfurization treatment data including at least the components of the molten iron, the amount of the desulfurization agent charged, the desulfurization treatment time, and the time until completion of slag entrainment; creating a machine learning model based on past operational data of the desulfurization treatment, the machine learning model representing at least the molten iron temperature and the amount of desulfurization agent charged during the desulfurization treatment as explanatory variables and a reaction rate constant in the desulfurization treatment as a response variable; estimating a sulfur concentration in the molten iron after desulfurization treatment based on the machine learning model and the current operational data; Equipped with As the past operational data, at least the molten iron temperature during the desulfurization treatment, the amount of the desulfurization agent charged, and the reaction rate constant, which is a constant in the desulfurization reaction formula represented by formula (1), are used in past operations, the step of estimating the S concentration comprises determining the reaction rate constant from the machine learning model and the current operational data, and estimating the S concentration in the molten iron after desulfurization using the determined reaction rate constant, the data before desulfurization, and equation (1). [S] = [S] 0 ・exp{K(t-t 0 )} ...(1) where [S] is the S concentration in the molten iron (mass%), [S] 0 is the S concentration in the molten iron before the start of desulfurization (mass%), K is the reaction rate constant (s −1 ), t is the desulfurization time (s), and t 0 is the time from the start of stirring to the completion of slag entrainment in the molten iron (s).

3. A method for desulfurizing molten iron using a mechanical stirring type desulfurization facility, comprising: A method for desulfurizing molten pig iron, comprising: estimating a sulfur concentration in the molten pig iron after the desulfurization treatment using the method for estimating a composition of molten pig iron according to claim 2 during the desulfurization treatment after the start of stirring the molten pig iron and before the start of adding a desulfurization agent.

4. the method further comprises, after the step of estimating the S concentration, a step of determining whether or not the S concentration in the molten iron after the desulfurization treatment is within a predetermined range; 4. The method for desulfurizing molten iron according to claim 3, wherein, when the S concentration in the molten iron after desulfurization is not within a predetermined range, the amount of desulfurizing agent charged is changed, the step of estimating the S concentration is performed again, and the S concentration in the molten iron is re-estimated.

5. a step of measuring a temperature of the bath surface of the molten iron after the step of estimating the S concentration; a step of determining a state of slag entrainment on the bath surface of the molten iron from a measurement result in the step of measuring the temperature of the bath surface of the molten iron; a step of adding a desulfurization agent to the molten iron when it is determined that the slag entrainment has been completed in the step of determining the state of slag entrainment; The method of desulfurizing hot metal according to claim 3, further comprising:

6. a step of measuring the temperature of the bath surface of the molten iron after adding the desulfurization agent; a step of determining a state of slag entrainment on the bath surface of the molten iron from a measurement result in the step of measuring the temperature of the bath surface of the molten iron; In the step of determining the slag entrainment state, if it is determined that the slag is properly entrained, continuing agitation by the impeller of the mechanical agitation type desulfurization equipment; 4. The method for desulfurizing molten iron according to claim 3, wherein, when it is determined in the step of determining the slag entrainment state that the slag is not properly entrained, at least one of the rotation speed and the immersion depth of the impeller is changed.

Images