JP2024005899A - Device, method, and program for statistical model construction, and device, method and program for estimating phosphorus concentration in molten steel - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a statistical model construction device or the like capable of constructing a statistical model capable of accurately estimating a dephosphorization rate constant even when the blowing treatment is stopped midway.

SOLUTION: A statistical model construction device includes a data collection part 331 for collecting operation data on the blowing treatment of a converter 11, and a statistical model construction part 333 for constructing a statistical model using operation data as an explanatory variable and a dephosphorization rate constant in the blowing treatment as an objective variable. The dephosphorization rate constant is defined as a proportionality constant assuming that an amount of change in the phosphorus concentration in molten steel of the converter relative to the cumulative per-unit oxygen supply to the converter is proportional to the phosphorus concentration in the molten steel of the converter. The statistical model construction part constructs the statistical model using operation data on the past blowing treatment collected by the data collection part.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present invention relates to a statistical model construction device, method, and program in converter blowing processing, and a device, method, and program for estimating phosphorus concentration in molten steel in converter blowing processing. In particular, the present invention provides a statistical model construction device, method, and program that can construct a statistical model that can accurately estimate a dephosphorization rate constant even when the blowing process is stopped in the middle of the blowing process. The present invention also relates to an apparatus, method, and program for estimating phosphorus concentration in molten steel that can accurately estimate phosphorus concentration in molten steel in a converter during blowing using this statistical model.

In the blowing process of a converter, controlling the components in the molten steel at the end of the blowing process (when the blowing stops), especially controlling the phosphorus concentration in the molten steel, is important for quality control of steel. In order to control the phosphorus concentration in molten steel, for example, the height of the top blowing lance, the top blowing oxygen flow rate, the bottom blowing gas flow rate, and the timing and amount of input of auxiliary raw materials such as quicklime and sintered ore are controlled as manipulated variables. It is used. These manipulated variables are based on information obtained before the start of the blowing process, such as the target phosphorus concentration in the molten steel, standards created based on hot metal data, and operational data related to past blowing processes. It is often determined based on

However, when the operation amount is determined based only on information obtained before the start of the blowing process, there is a problem in that the phosphorus concentration in the molten steel at the end of the blowing process varies greatly. Therefore, if it is possible to successively estimate the phosphorus concentration in molten steel with high accuracy during the blowing process using operational data that includes information obtained during the blowing process, the target phosphorus concentration in the molten steel during the blowing process can be estimated. It is thought that by performing additional operations to reach , it is possible to suppress variations in the phosphorus concentration in the molten steel at the end of the blowing process.

As a technique for successively estimating the phosphorus concentration in molten steel during blowing treatment, for example, a technique described in Patent Document 1 has been proposed. Patent Document 1 assumes a first-order reaction equation for the transition of the phosphorus concentration in molten steel during the blowing process, and also includes information on the dephosphorization rate constant, which is a proportional constant of the first-order reaction equation, obtained during the blowing process. The phosphorus concentration in the molten steel during the blowing process is estimated using a statistical model expressed by a multiple regression equation using the operational data related to the blowing process, and using this estimated dephosphorization rate constant. The technology is described. Furthermore, Patent Document 1 also discloses a technology for controlling the phosphorus concentration in molten steel by comparing the estimated phosphorus concentration in molten steel and the target phosphorus concentration in molten steel and changing the manipulated variable based on the comparison result. Are listed.

Here, a primary chemical reaction refers to a reaction in which the amount of change in the concentration of a reactant per unit time is determined in proportion to the concentration of the reactant, and the proportionality constant is called a rate constant. Although the dephosphorization reaction in the blowing process of a converter is not a first-order reaction, the shape of its transition is similar to a first-order reaction. By applying the amount to the first-order reaction equation, we estimate the change in phosphorus concentration in molten steel during blowing. Specifically, in the technique described in Patent Document 1, the elapsed time from the start of the blowing process is used as the time (reaction time) in the primary reaction equation, and the dephosphorization rate constant is constructed using this elapsed time. The phosphorus concentration in molten steel during the blowing process is estimated using a statistical model (multiple regression equation) based on the statistical model (dephosphorization rate estimated using this statistical model). estimated using a constant).

However, during the blowing process, the blowing process may be temporarily stopped to remove slag, etc. (i.e., the supply of oxygen to the converter is temporarily stopped), or the blowing process may be temporarily stopped due to some operational trouble. There are cases in which operations include non-blowing time, which is the time when blowing is not performed, such as stopping the refining process. In such a case, since the length of the non-blowing time varies depending on the blowing process, the technique described in Patent Document 1, which uses the elapsed time from the start of the blowing process as the reaction time, cannot estimate the dephosphorization rate constant. There was a risk that the error, and even the estimation error of the phosphorus concentration in molten steel, would become large.

JP2013-23696A

The present invention was made in order to solve the problems of the prior art as described above, and it is possible to accurately estimate the dephosphorization rate constant even when the blowing process is stopped in the middle of the blowing process. A statistical model construction device, method and program capable of constructing a possible statistical model, and a statistical model construction device, method and program capable of constructing a statistical model that can be used to accurately estimate the phosphorus concentration in molten steel in a converter during blowing process. An object of the present invention is to provide a phosphorus concentration estimation device, method, and program.

To solve the above problem, for example, instead of the elapsed time from the start of the blowing process, the oxygen supply time (oxygen feeding time) to the converter excluding the non-blowing time is used as the reaction time of the primary reaction equation. It is also possible. However, dephosphorization is a reaction in which phosphorus in molten steel is oxidized using an oxygen source in a converter and incorporated into slag. If the amount of oxygen blown per hour or the amount of auxiliary raw material (oxygen-containing auxiliary raw material) input per unit time is different, the amount of dephosphorization will be different, so the dephosphorization rate constant and ultimately the phosphorus concentration in molten steel can be determined with precision. It is considered difficult to estimate.

Therefore, as a result of intensive study, the inventors of the present invention found that the cumulative oxygen supply unit (accumulated value of oxygen supply per unit weight of molten steel) supplied to the converter was used instead of the elapsed time from the start of the blowing process. It has been found that by using the reaction time of the first-order reaction equation, the dephosphorization rate constant and, by extension, the phosphorus concentration in molten steel can be estimated with high accuracy even when the blowing process is stopped in the middle of the blowing process.

The present invention was completed based on the above findings of the present inventors.
That is, in order to solve the above-mentioned problems, the present invention includes a data collection unit that collects operational data regarding the blowing process of a converter, the operational data as an explanatory variable, and the dephosphorization rate constant in the blowing process as an objective variable. a statistical model construction unit that constructs a statistical model in which the dephosphorization rate constant is such that the amount of change in phosphorus concentration in molten steel in the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is It is defined as a proportionality constant when it is assumed that it is proportional to the phosphorus concentration in molten steel in the converter, and the statistical model construction unit constructs the statistical model using operational data regarding past blowing processes collected by the data collection unit. Provides a statistical model construction device for constructing statistical models.

According to the statistical model construction device of the present invention, the dephosphorization rate constant is such that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is the phosphorus concentration in the molten steel of the converter. It is defined as the proportionality constant assuming that it is proportional. In other words, it is assumed that the dephosphorization reaction in the converter blowing process is a first-order reaction, and that the amount of change in the phosphorus concentration in molten steel per unit time is proportional to the phosphorus concentration in molten steel, as in a normal first-order reaction. It is assumed that the amount of change in the phosphorus concentration in molten steel with respect to the cumulative oxygen supply rate is proportional to the phosphorus concentration in molten steel, and this proportionality constant is defined as the dephosphorization rate constant. Therefore, if a statistical model built according to this definition is used, the dephosphorization rate constant can be determined accurately even when the blowing process is stopped in the middle of the blowing process, as found by the present inventors. It is possible to estimate.
Note that "using operational data as an explanatory variable" is a concept that is not limited to the case where all data items of the collected operational data are used as explanatory variables, but also includes the case where some data items are used as explanatory variables. .
Moreover, "accumulative oxygen supply amount basic unit" means the cumulative value of the oxygen supply amount per unit weight of molten steel from the start of the blowing process.

In the statistical model construction device according to the present invention, the cumulative oxygen supply amount basic unit supplied to the converter is, for example, the cumulative blown oxygen amount basic unit blown into the converter.
In addition, "cumulative blown oxygen amount per unit" means the cumulative value of the amount of oxygen per unit weight of molten steel blown from the start of the blowing process, for example, the cumulative value of the amount of oxygen blown from the top blowing lance. It corresponds to the cumulative value of the amount of oxygen blown from the tuyere, or the cumulative value of the amount of oxygen blown from both the top blowing lance and the tuyere divided by the weight of the molten steel in the converter.

Preferably, in the statistical model construction device according to the present invention, the cumulative oxygen supply amount basic unit supplied to the converter is equal to the cumulative blown oxygen amount basic unit blown into the converter, and the cumulative oxygen amount basic unit blown into the converter. This is the sum of the basic unit of oxygen generated from auxiliary raw materials.
According to the above-mentioned preferred configuration, in addition to the cumulative amount of oxygen blown into the converter, the dephosphorization rate is Constants can be estimated with even higher accuracy.
Note that "oxygen amount generated from auxiliary raw materials per unit of production" means the amount of oxygen per unit weight of molten steel generated from auxiliary raw materials (oxygen-containing auxiliary raw materials). ) and the amount of oxygen contained per unit weight of the auxiliary material (volume of oxygen contained), which can be calculated by dividing the product by the weight of the molten steel in the converter.

Moreover, in order to solve the above-mentioned problem, the present invention includes a data collection unit that collects operational data regarding the blowing process of a converter, the operational data as an explanatory variable, and a dephosphorization rate constant in the blowing process as an objective variable. a phosphorus concentration estimator that estimates a phosphorus concentration in molten steel in the converter during the blowing process using a statistical model, wherein the dephosphorization rate constant is determined based on the cumulative oxygen supplied to the converter. It is defined as a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the supply amount unit is proportional to the phosphorus concentration in the molten steel of the converter, and the phosphorus concentration estimation section Using the collected operational data regarding the new blowing process and the statistical model, an estimated value of the dephosphorization rate constant in the new blowing process is calculated, and the conversion rate before the new blowing process is calculated. The new blowing process is performed based on the phosphorus concentration in the hot metal of the furnace, the calculated estimated value of the dephosphorization rate constant, and the cumulative oxygen supply unit supplied to the converter in the new blowing process. The present invention is also provided as a molten steel phosphorus concentration estimating device for estimating the molten steel phosphorus concentration in the converter.

According to the device for estimating the phosphorus concentration in molten steel according to the present invention, the dephosphorization rate constant is the amount of change in the phosphorus concentration in molten steel in the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter. It is defined as a proportionality constant assuming that it is proportional to concentration. Therefore, if a statistical model constructed according to this definition is used, as the inventors found, even if the blowing process is stopped in the middle of the blowing process, the estimated value of the dephosphorization rate constant can be can be calculated with high accuracy, and in turn, the phosphorus concentration in molten steel can be estimated with high accuracy.

In the device for estimating the phosphorus concentration in molten steel according to the present invention, the cumulative oxygen supply amount basic unit supplied to the converter is, for example, the cumulative blown oxygen amount basic unit blown into the converter.

Preferably, in the device for estimating phosphorus concentration in molten steel according to the present invention, the cumulative oxygen supply amount basic unit supplied to the converter is equal to the cumulative blown oxygen amount basic unit blown into the converter and the cumulative oxygen amount basic unit blown into the converter. This is the sum of the amount of oxygen generated from the auxiliary raw materials produced per unit of production.

Furthermore, in order to solve the above-mentioned problems, the present invention includes a data collection step of collecting operational data regarding blowing treatment of a converter; a statistical model construction step of constructing a statistical model, wherein the dephosphorization rate constant is such that the amount of change in phosphorus concentration in molten steel in the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is It is defined as a proportionality constant when it is assumed that it is proportional to the phosphorus concentration in the molten steel of the converter, and in the statistical model construction step, the statistical model is constructed using the operational data regarding the past blowing treatment collected in the data collection step. It is also provided as a statistical model construction method.

Further, in order to solve the above-mentioned problems, the present invention includes a data collection step of collecting operational data regarding the blowing process of a converter, the operational data is used as an explanatory variable, and the dephosphorization rate constant in the blowing process is set as an objective variable. a phosphorus concentration estimating step of estimating the phosphorus concentration in molten steel in the converter during the blowing process using a statistical model, wherein the dephosphorization rate constant is determined by the cumulative amount of phosphorus supplied to the converter. It is defined as a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the oxygen supply rate is proportional to the phosphorus concentration in the molten steel of the converter, and in the phosphorus concentration estimation step, the data collection step The estimated value of the dephosphorization rate constant in the new blowing process is calculated using the operational data regarding the new blowing process collected in the above statistical model, and the estimated value of the dephosphorization rate constant in the new blowing process is calculated. The new blowing process is performed based on the phosphorus concentration in the hot metal of the converter, the calculated estimated value of the dephosphorization rate constant, and the cumulative oxygen supply amount basic unit supplied to the converter in the new blowing process. It is also provided as a method for estimating phosphorus concentration in molten steel, which estimates the phosphorus concentration in molten steel in the converter during processing.

Moreover, in order to solve the above-mentioned problem, the present invention includes a data collection unit that collects operational data regarding the blowing process of a converter, the operational data as an explanatory variable, and a dephosphorization rate constant in the blowing process as an objective variable. a statistical model construction unit for constructing a statistical model, and a statistical model construction program for operating a computer, wherein the dephosphorization rate constant is based on the cumulative oxygen supply basic unit supplied to the converter. It is defined as a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter is proportional to the phosphorus concentration in the molten steel of the converter, and the statistical model construction unit uses the past data collected by the data collection unit. It is also provided as a statistical model construction program that constructs the statistical model using operational data regarding the blowing process.

Furthermore, in order to solve the above-mentioned problems, the present invention includes a data collection unit that collects operational data regarding the blowing process of a converter, the operational data as an explanatory variable, and a dephosphorization rate constant in the blowing process as an objective variable. a phosphorus concentration estimating unit that estimates a phosphorus concentration in molten steel in the converter during the blowing process using a statistical model; The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. and the phosphorus concentration estimating unit estimates the dephosphorization rate constant in the new blowing process using the operational data regarding the new blowing process collected by the data collecting unit and the statistical model. the phosphorus concentration in the hot metal of the converter before the new blowing process, the calculated estimated value of the dephosphorization rate constant, and the cumulative amount supplied to the converter in the new blowing process. The present invention is also provided as a phosphorus concentration estimation program in molten steel that estimates the phosphorus concentration in molten steel in the converter during the new blowing process based on the oxygen supply amount per unit.

According to the present invention, it is possible to construct a statistical model that can accurately estimate a dephosphorization rate constant. Furthermore, using this statistical model, it is possible to accurately estimate the phosphorus concentration in the molten steel in the converter during the blowing process.

1 is a diagram schematically showing a schematic configuration of a refining facility equipped with a statistical model construction device and a molten steel phosphorus concentration estimation device according to a first embodiment of the present invention. 2 is a diagram showing an example of operation data 321 shown in FIG. 1. FIG. 1 is a flowchart schematically showing steps of a method for estimating phosphorus concentration in molten steel according to a first embodiment of the present invention. 4 is a flowchart showing a specific procedure of step ST6 shown in FIG. 3. FIG. FIG. 2 is a diagram schematically showing a schematic configuration of a refining facility including a statistical model construction device and a molten steel phosphorus concentration estimating device according to a second embodiment of the present invention. 6 is a diagram illustrating an example of information 323 by brand of auxiliary raw materials illustrated in FIG. 5. FIG. FIG. 2 is a scatter diagram showing the relationship between estimated values and actual values estimated by methods for estimating phosphorus concentration in molten steel according to examples and comparative examples of the present invention.

Embodiments of the present invention (first embodiment and second embodiment) will be described below with appropriate reference to the accompanying drawings. Note that in this specification and the drawings, components having substantially the same configurations and functions are designated by the same reference numerals, and the description thereof will be omitted as appropriate.

<Principle for estimating phosphorus concentration in molten steel>
First, in this embodiment, the principle of estimating the phosphorus concentration in molten steel in a converter during blowing treatment will be explained.
In the conventional technology described in the above-mentioned Patent Document 1, etc., the time change d[P]/dt of the phosphorus concentration (hereinafter also referred to as [P] [%]) in the molten steel of the converter during the blowing process is It is assumed that the reaction is expressed by the first-order reaction formula shown in equation (1) below. That is, it is assumed that the amount of change d[P]/dt per unit time in the phosphorus concentration [P] in molten steel is proportional to the phosphorus concentration [P] in molten steel. In equation (1), k _P [sec ⁻¹ ] is a dephosphorization rate constant which is a proportionality constant. From equation (1), [P] after t [sec] has elapsed from the start of the blowing process is expressed by equation (2) below. In formula (2), [P] _ini [%] is the initial value of [P] (that is, the phosphorus concentration in the hot metal of the converter before blowing treatment).

Therefore, if an accurate dephosphorization rate constant k _P is obtained, based on the above equation (2), the phosphorus concentration [P] [%] in the molten steel after t [sec] has elapsed from the start of the blowing process can be determined with high precision. It can be estimated that However, in general, the dephosphorization rate constant k _P is not the same value for all blowing processes, but is considered to vary depending on the operational data regarding the blowing process. Therefore, for example, as disclosed in Patent Document 1, the dephosphorization rate constant k _P is estimated for each blowing process using operational data regarding the blowing process from which the phosphorus concentration in molten steel is estimated. Note that the actual value of the dephosphorization rate constant k _P is determined by the following equation (3), which is a modification of the above equation (2), after the blowing process is completed (more precisely, after the molten steel composition is determined at the end of the blowing process). ) is calculated by substituting the values on the right side of each. Here, in formula (3), [P] _ini [%] represents the phosphorus concentration in the hot metal before the blowing process, and [P] _end [%] represents the phosphorus concentration in the hot metal at the end of the blowing process. The elapsed time from the start of the blowing process to the end of the blowing process is substituted for t _end [sec]. [P] _ini and [P] _end can be obtained, for example, by analyzing a sample taken from hot metal before blowing or from molten steel after blowing.

In order to estimate the dephosphorization rate constant k _P for each blowing process, a statistical model is constructed using operational data related to the blowing process as an explanatory variable and the dephosphorization rate constant k _P as an objective variable. This statistical model can be appropriately constructed using various statistical methods, and can be expressed, for example, by a multiple regression equation shown in Equation (4) below.
Then, by substituting the operational data related to the blowing process, which is the target of estimating the phosphorus concentration in molten steel, into equation (4) as the explanatory variable X _i (i=1, 2,...,M), Different dephosphorization rate constants k _P are estimated, and by applying this estimated dephosphorization rate constant k _P to the above equation (2), it is possible to estimate the phosphorus concentration in the molten steel during the blowing process. can.
The regression coefficient a _i (i=0, 1, . . . , M), which is a parameter for estimating the dephosphorization rate constant k _P in the following equation (4), is obtained by a known multiple regression analysis method. For example, the actual value of the dephosphorization rate constant k _P in the past blowing process obtained by the above formula (3) and the explanatory variable X _i which is the operational data regarding that blowing process are corresponded for each blowing process. The regression coefficient a _i can be determined by using the training data for building the statistical model.

As described above, according to the prior art described in Patent Document 1, etc., the dephosphorization rate constant k _P is estimated by the statistical model shown in equation (4), and this estimated dephosphorization rate constant k _P is expressed by the equation By applying (2), it is possible to estimate the phosphorus concentration in molten steel during blowing.
However, as mentioned above, when performing an operation in which the blowing process is temporarily stopped in the middle of the blowing process, the length of the non-blowing time varies depending on the blowing process, so the In the conventional technique, there was a risk that the estimation error of the dephosphorization rate constant _kP and, by extension, the estimation error of the phosphorus concentration in molten steel would become large.
To solve the above problem, instead of the elapsed time t and _end from the start of the blowing process in equations (1) to (3), the oxygen supply time to the converter excluding the non-blowing time should be set. It is also possible to use However, as mentioned above, dephosphorization is a reaction in which phosphorus in molten steel is oxidized using an oxygen source in the converter and incorporated into slag, so even if the oxygen supply time is the same, If the amount of oxygen blown from a lance or the like per unit time and the amount of auxiliary raw material (oxygen-containing auxiliary raw material) input per unit time are different, the amount of dephosphorization will be different, so the dephosphorization rate constant k _P and, ultimately, It is considered difficult to accurately estimate the phosphorus concentration in molten steel.

Therefore, in this embodiment, the cumulative oxygen supply amount per unit is used instead of the elapsed time t from the start of the blowing process, _tend . Specifically, the following equations (5) to (7) are used in place of equations (1) to (3). In other words, it is assumed that the amount of change in the phosphorus concentration in molten steel [P] with respect to the cumulative oxygen supply amount unit is proportional to the phosphorus concentration in molten steel [P], and the dephosphorization rate constant k _P is defined as its proportionality constant.

In the above equations (5) and (6), O ₂ is the cumulative oxygen supply basic unit [Nm ³ /ton] (cumulative value of oxygen supply per ton of molten steel) from the start of the blowing process, and the above In Equation (7), O _2end is the cumulative oxygen supply unit [Nm ³ /ton] from the start of the blowing process to the end of the blowing process.
The actual value [(Nm ³ /ton) ⁻¹ ] of the dephosphorization rate constant k _P is calculated by substituting the respective values into the right side of the above equation (7) after the blowing process is completed. Then, similar to the conventional technology described in Patent Document 1, etc., by using learning data in which the actual value of the dephosphorization rate constant k _P in past blowing treatments is used as the objective variable, the above equation (4) is applied. Build a statistical model to show.
Then, for a new blowing process that is the target of estimating the phosphorus concentration in molten steel, the operational data obtained in the blowing process is used as the explanatory variable X _i of the statistical model constructed as shown in equation (4). By substituting the estimated value of the dephosphorization rate constant _kP , the phosphorus concentration in the hot metal before the blowing process [P] _ini , the estimated value of the calculated dephosphorization rate constant _kP , and the blowing process By substituting the cumulative oxygen supply amount basic unit O ₂ supplied in the process into the right side of the above equation (6), the phosphorus concentration in the molten steel during the blowing process can be estimated.

As described above, in this embodiment, by using the cumulative oxygen supply basic unit _O2 supplied to the converter instead of the elapsed time t from the start of the blowing process, the blowing process can be performed during the blowing process. Even when the treatment is stopped, the dephosphorization rate constant k _P and, by extension, the phosphorus concentration in molten steel can be estimated with high accuracy.

上記の式（８）において、Ｖ_Ｏ２は吹錬処理開始から吹き込まれた酸素量の累積値（累積吹き込み酸素量）［Ｎｍ^３］であり、Ｗ_ｓｔは溶鋼（溶銑）の重量［ｔｏｎ］である。ここで、溶鋼（溶銑）の重量は、溶銑の重量のみで算出しても良いが、スクラップや冷銑などの投入があり、その投入量の実績値がある場合には、転炉に装入された主原料（精錬を実施する対象）の合計値を溶鋼の重量として算出することが好ましい。本実施形態では、主原料の合計値を溶鋼の重量として算出している。 As the cumulative oxygen supply amount basic unit _O2 , for example, the cumulative oxygen amount basic unit blown into the converter can be used. The "cumulative amount of blown oxygen per unit" means the cumulative value of the amount of oxygen per unit weight of molten steel blown from the start of the blowing process, as shown in equation (8) below. The weight of molten steel in the converter is calculated by calculating the cumulative amount of oxygen blown into the converter, the cumulative amount of oxygen blown in from the tuyeres, and the cumulative amount of oxygen blown in from both the top blowing lance and the tuyeres. It corresponds to the value divided by .

In the above equation (8), V _O2 is the cumulative value of the amount of oxygen blown in from the start of the blowing process (cumulative amount of blown oxygen) [Nm ³ ], and W _st is the weight [ton] of the molten steel (hot metal). be. Here, the weight of molten steel (hot metal) may be calculated using only the weight of molten metal, but if scrap or cold pig iron is input, and there is actual value of the amount of input, it is possible to calculate the weight of molten steel (hot metal). It is preferable to calculate the total value of the main raw materials (objects to be refined) as the weight of molten steel. In this embodiment, the total value of the main raw materials is calculated as the weight of molten steel.

上記の式（９）において、Ｖ_Ｏ２は式（８）と同様に吹錬処理開始から吹き込まれた酸素量の累積値［Ｎｍ^３］であり、Ｗ_ｓｔは式（８）と同様に溶鋼（溶銑）の重量［ｔｏｎ］である。Ｖ_ａｕＯ２は副原料から発生した発生酸素量［Ｎｍ^３］である。 More preferably, as the cumulative oxygen supply unit _O2 , the cumulative oxygen supply unit blown into the converter and the auxiliary raw material ( The sum of the basic unit amount of oxygen generated from oxygen-containing auxiliary raw materials) can be used. The "unit amount of oxygen generated from auxiliary raw materials" means the amount of oxygen per unit weight of molten steel generated from auxiliary raw materials.

In the above equation (9), V _O2 is the cumulative value [Nm ³ ] of the amount of oxygen blown from the start of the blowing process, similar to the equation (8), and W _st is the cumulative value [Nm 3 ] of the amount of oxygen blown into the molten steel (similar to the equation (8)). The weight of hot metal (hot metal) is [ton]. V _auO2 is the amount of oxygen generated from the auxiliary raw material [Nm ³ ].

なお、上記の式（１０）は、複数の銘柄の副原料を投入する場合を表したものであり、銘柄毎のＷ_ａｕとＯ２_ａｕとの積の全銘柄についての総和が、副原料から発生した発生酸素量Ｖ_ａｕＯ２として算出される。ただし、本発明はこれに限るものではなく、単一銘柄の副原料を投入する場合には、当該銘柄についてのＷ_ａｕとＯ２_ａｕとの積を発生酸素量Ｖ_ａｕＯ２として算出すればよい。 The amount of oxygen V _auO2 generated from the auxiliary raw material is determined by the input amount (input weight) W _au [ton] of the auxiliary raw material and the oxygen content per unit weight of the auxiliary raw material, for example, as shown in equation (10) below. It can be calculated by multiplying the amount (oxygen content volume) by O2 _au [Nm ³ /ton].

The above formula (10) represents the case where multiple brands of auxiliary raw materials are input, and the sum of the products of W _au and O2 _au for each brand for all brands is the amount generated from the auxiliary raw materials. It is calculated as the generated oxygen amount V _auO2 . However, the present invention is not limited to this, and when a single brand of auxiliary raw material is introduced, the product of W _au and O2 _au for the brand may be calculated as the generated oxygen amount V _auO2 .

<First embodiment>
In the first embodiment of the present invention, the cumulative amount of oxygen blown into the converter is used as the cumulative amount of oxygen supplied per unit O ₂ . That is, the cumulative oxygen supply basic unit O ₂ is calculated according to the above-mentioned equation (8).
FIG. 1 is a diagram schematically showing a schematic configuration of a refining facility equipped with a statistical model construction device and a molten steel phosphorus concentration estimation device according to a first embodiment of the present invention.
As shown in FIG. 1, the refining equipment 100 of the first embodiment includes a converter equipment 10, a measurement control device 20, and a calculation device 30. In the first embodiment, the calculation device 30 also functions as a statistical model construction device and a molten steel phosphorus concentration estimation device according to the present invention. The computing device 30 accumulates operation data regarding the blowing process while repeating the operation of the blowing process in the converter, and constructs a statistical model. Further, after the statistical model is constructed and becomes available, the computing device 30 uses the statistical model to estimate the phosphorus concentration in the molten steel during the blowing process, and if necessary, after the blowing process is completed. The statistical model is updated using the obtained operational data. Each component of the refining equipment 100 will be specifically explained below.

The converter equipment 10 includes a converter 11 , a top blowing lance 12 , a flue 13 , a tuyere 14 , and a charging device having a charging chute 15 . In the converter equipment 10, a top blow lance 12 inserted from the furnace mouth of the converter 11 blows oxygen gas G1 into the hot metal MS in the converter 11. In the decarburization reaction that occurs in the blowing process, carbon in the hot metal MS reacts with the oxygen gas G1 to generate CO gas or CO ₂ gas, and these gases are discharged via the flue 13. The hot metal MS that has undergone the blowing process is sent to the next process as molten steel MI. Further, in the blowing process, phosphorus and silicon in the hot metal MS also react with the oxygen gas G1 or the auxiliary materials contained in the slag SL, and are taken into the slag SL and stabilized. On the other hand, a bottom blowing gas G2 such as nitrogen gas or argon gas is blown from the tuyere 14 to stir the hot metal MS and promote the above reaction. From the charging chute 15 of the charging device, auxiliary materials AM including oxygen-containing auxiliary materials such as quicklime and limestone constituting the slag SL, and sintered ore for supplying oxygen to the hot metal MS are charged into the converter 11. . In addition, when the auxiliary raw material AM is a powder, it is also possible to blow it together with the oxygen gas G1 using the top blowing lance 12.

The measurement control device 20 performs various measurements related to the refining process in the converter equipment 10 and controls the refining process.
Specifically, the measurement control device 20 includes a sublance 21, an exhaust gas analyzer 22, an exhaust gas flow meter 23, and a slag level meter 28 as a measurement system. The sublance 21 is inserted from the furnace mouth of the converter 11 together with the top blowing lance 12, and is used for component analysis of the molten steel MI by immersing a measuring device installed at the tip into the molten steel MI at a predetermined timing during the blowing process. Collect samples of molten steel MI and measure the carbon concentration and temperature of the molten steel MI. In the following description, measurement using such a sublance 21 is also referred to as sublance measurement. The exhaust gas analyzer 22 analyzes the components of the gas exhausted via the flue 13. Specifically, the exhaust gas analyzer 22 measures the concentrations of CO, CO ₂ and O ₂ contained in the exhaust gas (the concentration of each component is referred to as exhaust gas component concentration). On the other hand, the exhaust gas flow meter 23 measures the flow rate of gas discharged via the flue 13 (referred to as exhaust gas flow rate). The slag level meter 28 measures the level of slag SL in the converter 11 from the mouth of the converter 11 in a non-contact manner. The results of the sublance measurement described above, as well as the measurement results of the exhaust gas analyzer 22, exhaust gas flow meter 23, and slag level meter 28, are transmitted to the arithmetic device 30 (specifically, transmitted to the communication section 31, which will be described later).

On the other hand, the measurement control device 20 includes a lance drive device 24, an oxygen supply device 25, a bottom-blown gas supply device 26, and a charging control device 27 as a control system. The lance drive device 24 drives the top blow lance 12 in the vertical direction. Thereby, the height of the top blowing lance 12 (that is, the distance from the hot metal MS to the position where the oxygen gas G1 is supplied in the converter 11) can be adjusted. The oxygen supply device 25 supplies oxygen gas G1 to the top blow lance 12. The blown oxygen flow rate, that is, the flow rate of the supplied oxygen gas G1 per unit time is adjustable. The bottom blowing gas supply device 26 supplies the bottom blowing gas G2 to the tuyere 14. The flow rate of the supplied bottom blowing gas G2 can also be adjusted. The charging control device 27 controls charging of the auxiliary material AM from the charging chute 15 of the charging device. Specifically, the input control device 27 controls the input timing and amount of the auxiliary material AM. The operations of the lance drive device 24, oxygen supply device 25, bottom blowing gas supply device 26, and injection control device 27 described above may be controllable separately from the calculation device 30, or as shown in FIG. It may be controllable according to a control signal from the arithmetic device 30 (specifically, transmitted from the communication unit 31 described below).

The arithmetic device 30 includes a communication section 31, a storage section 32, a calculation section 33, and an input/output section 34, and is configured by, for example, a computer. The communication unit 31 is a variety of communication devices that communicate with each component of the measurement control device 20 by wire or wirelessly, and receives measurement results obtained by the measurement control device 20 and sends control signals to the measurement control device 20. Send. The communication unit 31 may be able to communicate with an external device different from the measurement control device 20.

The storage unit 32 is a storage that can store various types of data. The storage unit 32 of the first embodiment stores operational data 321 and parameters 322 regarding the blowing process of the converter 11.
FIG. 2 is a diagram showing an example of the operation data 321. In the example shown in FIG. 2, the operation data 321 is such that the charge number (CHNO) determined for each blowing process is used as a key, and various operation data related to the blowing process with the same charge number are stored in the same line. It is. The operation data 321 includes analysis performance data 3211 in which sublance measurement results and component analysis results at the end of the blowing process are stored. Note that, as in the record of CHNO=00XX in the example shown in FIG. Analysis performance data 3211 that has not been measured or whose analysis results have not yet been determined is not stored.

As described above, in the first embodiment, the cumulative oxygen supply basic unit O ₂ is calculated according to equation (8). Therefore, as the operation data 321, data items for calculating the cumulative oxygen supply amount basic unit O ₂ according to equation (8) are also stored.
Specifically, in the operation data 321, the cumulative value of the amount of oxygen blown from the start of the blowing process (cumulative amount of blown oxygen) V _O2 [Nm ³ ] shown in equation (8) is included in the top blowing lance 12. The total cumulative amount of oxygen blown from the tuyere 14 is stored. The total cumulative value is the measured value of the amount of oxygen blown (for example, if the oxygen supply device 25 or the bottom blowing gas supply device 26 is equipped with a sensor that measures the amount of oxygen, the measured value of that sensor), if any. If there are no measured values, the data collection unit 331 can calculate using the indicated values of the oxygen supply device 25 and the bottom blowing gas supply device 26. In addition, in the operation data 321, the main _raw material (smelting Stores the total weight (total weight of main raw materials) of the target (object to be carried out). The main raw materials include, for example, hot metal, scrap, and cold pig iron.

On the other hand, the parameters 322 are stored in the storage unit 32 separately from the operation data 321 organized for each blowing process (for each charge number). As described later, the parameters of the statistical model estimated by the statistical model construction unit 333 (regression coefficient a _i shown in the above-mentioned equation (4)) are stored as the parameters 322 .

The calculation unit 33 includes, for example, one or more hardware processors such as a CPU (Central Processing Unit), and one or more memories such as a RAM (Random Access Memory) and a ROM (Read Only Memory). , one or more programs stored in the memory (for example, the storage unit 32) are executed by one or more hardware processors to perform various operations. The calculation unit 33 functions as a data collection unit 331, a data preprocessing unit 332, a statistical model construction unit 333, and a phosphorus concentration estimation unit 334 by operating according to a stored program. Note that the calculation unit 33 may be a PLC (Programmable Logic Controller) or may be realized by dedicated hardware such as an ASIC (Application Specific Integrated Circuit). The functions of each section realized by the calculation section 33 will be described below.

The data collection unit 331 collects operation data 321 stored in the storage unit 32. Specifically, for example, data such as the weight of hot metal that is known before the start of the blowing process is communicated from a converter blowing database stored in an external device (not shown in FIG. 1) before the start of the blowing process. The data is acquired by the data collection unit 331 via the data collection unit 31 and stored in the corresponding item in the row of the blowing process (CHNO) of the operation data 321. After the start of the blowing process, data acquired by various measurement devices included in the measurement control device 20 are acquired by the data collection unit 331 via the communication unit 31, and the data collection unit 331 collects the operation data 321. It is stored in the corresponding item in the row of the blowing process (CHNO). Analysis performance data 3211 in the operation data 321 is collected from the converter blowing database stored in an external device through the communication unit 31 to the data collection unit 331 after the sublance measurement results and the component analysis results at the end of the blowing process are known. and is stored by the data collection unit 331 in the corresponding item in the row of the blowing process (CHNO) of the operation data 321.
The data preprocessing unit 332 performs preprocessing on the operation data 321 described above. For example, the data preprocessing unit 332 averages, cumulatively calculates, or performs various numerical processing on the data acquired by the data collection unit 331 at regular intervals from the start of the blowing process to the end of the blowing process. , the data collection unit 331 stores the data that has been preprocessed by the data preprocessing unit 332 in the corresponding item of the blowing process (CHNO) row of the operation data 321. Further, the data preprocessing unit 332 may perform data normalization processing. In the following explanation, data that has undergone preprocessing by the data preprocessing unit 332 will also be treated as operational data 321, but the storage unit 32 will store these data that have not been preprocessed and the data that have undergone preprocessing separately. may have been done.

The statistical model construction unit 333 constructs a statistical model (a statistical model expressed by the multiple regression equation shown in Equation (4) above) using the operational data as an explanatory variable and the dephosphorization rate constant k _P as an objective variable. Specifically, the statistical model construction unit 333 uses data items extracted from the operation data 321 related to past blowing processes stored in the storage unit 32 as explanatory variables, and uses the actual value of the dephosphorization rate constant k _P as an objective. Parameters (regression coefficients a _i ) of the statistical model are estimated using learning data as variables. Note that, unless otherwise mentioned, the learning data used for constructing the statistical model is past accumulated operation data 321 that has been preprocessed by the data preprocessing unit 332.
The statistical model construction unit 333 calculates the phosphorus concentration in the hot metal before the blowing process [P] _ini included in the learning data, the phosphorus concentration in the molten metal at the end of the blowing process [P] _end of the analysis performance data 3211 included in the learning data, and the cumulative oxygen supply basic unit _O2end , which is the value obtained by dividing the cumulative amount of blown oxygen _VO2 from the start of the blowing process to the end of the blowing process included in the learning data by the total weight of the main raw materials _Wst included in the learning data. , to calculate the actual value of the dephosphorization rate constant k _P in the past blowing process by substituting it into the right side of the above-mentioned equation (7). Furthermore, the statistical model construction unit 333 extracts the explanatory variable X _i from the data items included in the learning data regarding the same blowing process, uses the previously calculated actual value of the dephosphorization rate constant k _P as the objective variable, and uses the known Parameters a _i of the statistical model are estimated using a multiple regression analysis method, and the estimated parameters a _i are stored in the storage unit 32 as parameters 322 . In the first embodiment, a multiple regression analysis method is adopted as a statistical model construction method, and the data items extracted from the operation data 321 are used as explanatory variables X _i , and the dephosphorization rate constant k _P is used as an objective variable. If so, it is also possible to construct a statistical model using a known machine learning method.

The phosphorus concentration estimating unit 334 uses the operation data 321 regarding the new blowing process from which the phosphorus concentration in molten steel is to be estimated, and the statistical model constructed by the statistical model building unit 333 to estimate the removal rate in the new blowing process. Calculate the estimated value of the phosphorus rate constant _kP . Specifically, the phosphorus concentration estimating unit 334 uses the explanatory variable X _i extracted from the operation data 321 regarding the new blowing process and the parameter a _i stored in the storage unit 32 as the parameter 322 using a statistical model. (that is, the multiple regression equation shown in equation (4)), the estimated value of the dephosphorization rate constant k _P in the new blowing process is calculated.
Furthermore, the phosphorus concentration estimating unit 334 calculates the phosphorus concentration in the hot metal [P] _ini before the new blowing treatment included in the operation data 321 regarding the new blowing treatment, and the estimated value of the calculated dephosphorization rate constant k _P. , the value obtained by dividing the cumulative amount of blown oxygen V _O2 from the start of the blowing process to the present time included in the operation data 321 related to the new blowing process by the total weight of the main raw materials W _st included in the operation data 321 related to the new blowing process By substituting the cumulative oxygen supply amount basic unit O ₂ into the above-mentioned equation (6), the phosphorus concentration [P] in the molten steel at the present moment (that is, at any time during the blowing process) is estimated. For example, when the explanatory variable X _i includes a data item obtained by sublance measurement, the phosphorus concentration estimating unit 334 starts estimating the phosphorus concentration [P] in molten steel after the sublance measurement in a new blowing process, and The phosphorus concentration [P] in molten steel can be estimated at predetermined intervals until the blowing process is completed.

The input/output unit 34 includes, for example, an output device such as a display or a printer, and an input device such as a keyboard, mouse, or touch panel. The output device outputs, for example, an estimated value of the phosphorus concentration [P] in the molten steel at an arbitrary point in time during the blowing process, which is calculated by the phosphorus concentration estimation unit 334. The input device can obtain an operation input for adding or modifying data stored in the storage unit 32, for example.

FIG. 3 is a flowchart showing the general steps of a method for estimating phosphorus concentration in molten steel according to the first embodiment of the present invention, using the refining equipment 100 described above. In the example shown in FIG. 3, the process of constructing a statistical model and the process of estimating the phosphorus concentration in molten steel using the constructed statistical model are illustrated as a series of processes, but the process is not limited to this. Instead, each may be executed at different times. For example, steps ST1, ST4 to ST7 related to the process of building a statistical model and steps ST1 to ST3 related to the process of estimating the phosphorus concentration in molten steel may be executed at different timings.

As shown in FIG. 3, in the method for estimating the phosphorus concentration in molten steel according to the first embodiment, first, the data collection unit 331 collects data regarding a new blowing process, and stores it in the storage unit 32 as operation data 321 ( Step ST1 in FIG. 3). Specifically, the data collection unit 331 acquires data such as the weight of hot metal before the start of the blowing process, and acquires data such as the cumulative amount of blown oxygen, the input amount of auxiliary materials, and the concentration of exhaust gas components during the blowing process. , obtain exhaust gas flow rate, etc. When acquiring these data, the data preprocessing unit 332 performs preprocessing of the data, and the data collection unit 331 stores the data that has undergone this preprocessing as the operation data 321.
In the first embodiment, the dephosphorization rate constant k _P using the statistical model is calculated at the time when the data of the explanatory variable X _i used in the statistical model is collected among the collected operation data 321 related to the new blowing process. It becomes possible to estimate and estimate the phosphorus concentration [P] in molten steel. If a statistical model has already been constructed and can be used (“YES” in step ST2 of FIG. 3), the parameters a _i of the statistical model and the explanatory variables X _i stored in the storage unit 32 as parameters 322 are Using the data, the phosphorus concentration estimating unit 334 estimates the phosphorus concentration [P] in molten steel for a new blowing process to be estimated (step ST3 in FIG. 3). Note that the estimation result of the molten steel phosphorus concentration [P] may be output by an output device such as a display or a printer included in the input/output section 34, for example. Further, the phosphorus concentration estimating unit 334 may estimate the phosphorus concentration [P] in molten steel only once at a predetermined timing after the data of the explanatory variable X _i used in the statistical model is collected, or The estimation of the phosphorus concentration [P] in molten steel may be repeated at a cycle of .
On the other hand, if the statistical model is not available ("NO" in step ST2 in FIG. 3), the estimation of the phosphorus concentration [P] in molten steel as described above is not performed.

After the blowing process is completed, the data collection unit 331 collects analysis performance data 3211 (step ST4 in FIG. 3). For example, if a statistical model has not been constructed yet, but a sufficient number of operational data 321 regarding past blowing processes have already been accumulated in the storage unit 32 ("NO" in step ST2 of FIG. 3, and "NO" in step ST5). If “YES”), processing for building a statistical model is executed. In this case, the statistical model construction unit 333 constructs a statistical model based on the accumulated operation data 321 related to past blowing processes in accordance with the procedure described later with reference to FIG. 4 (step ST6 in FIG. 3), and estimates The parameters a _i of the statistical model obtained are stored in the storage unit 32 as parameters 322 (step ST7 in FIG. 3).

On the other hand, if a statistical model has not yet been constructed and a sufficient number of operation data 321 regarding past blowing processes have not been accumulated in the storage unit 32 ("NO" in step ST2 of FIG. 3, "NO" in step ST5), In the case of "NO"), the processing for building the statistical model is not executed, and only the accumulation of the operation data 321 is executed. In addition, after the statistical model is constructed and becomes available, it becomes possible to estimate the phosphorus concentration [P] in molten steel and execute the blowing process, so the process for constructing the statistical model is not performed. It is not necessary (in the case of "YES" in step ST2 and "NO" in step ST5 in FIG. 3). Further, for example, if a predetermined condition is satisfied, such as the blowing process performed by estimating the phosphorus concentration [P] in molten steel is repeated a predetermined number of times ("YES" in step ST2 of FIG. 3, step ST5). If the answer is "YES"), a new statistical model is constructed by using the operation data 321 regarding the new blowing treatment together with the past operation data 321 or in place of the operation data 321 regarding the past blowing treatment. Step ST6 in FIG. 3), the parameter 322 may be updated (step ST7 in FIG. 3).

FIG. 4 is a flowchart showing the specific procedure of step ST6 shown in FIG. The processing shown in FIG. 4 is executed by the statistical model construction unit 333. In this process, first, the phosphorus concentration in the hot metal before the blowing process [P] _ini and the phosphorus concentration in the molten metal at the end of the blowing process [P] _end are extracted from the accumulated operation data 321 regarding the past blowing processes. , calculate the cumulative oxygen supply unit O _2end , which is the value obtained by dividing the cumulative amount of blown oxygen V _O2 from the start of the blowing process to the end of the blowing process by the total weight W _st of the main raw materials, and calculate these by using the above formula (7 ) to calculate the actual value of the dephosphorization rate constant _kP in the past blowing process (step ST61 in FIG. 4).
Next, the accumulated operational data 321 was divided into learning data for building a statistical model and evaluation data at an arbitrary ratio (step ST62 in FIG. 4), and preprocessing was performed in the preprocessing unit 332 as necessary. Then, the explanatory variable X _i of the statistical model shown in the above equation (4) is determined (step ST63 in FIG. 4).
Which data item to use as the explanatory variable X _i from the operation data 321 can be determined, for example, based on operation knowledge or using a machine learning method such as Lasso. Then, the statistical model construction unit 333 constructs a statistical model using the explanatory variable X _i included in the learning data and the actual value of the dephosphorization rate constant k _P which is the objective variable calculated from the learning data ( Step ST64 in FIG. 4).

Finally, the statistical model construction unit 333 constructs a statistical model using the explanatory variable X _i included in the evaluation data and the actual value of the dephosphorization rate constant k _P which is the objective variable calculated from the evaluation data. Accuracy is evaluated (step ST65 in FIG. 4). Specifically, the statistical model construction unit 333 calculates, for example, the dephosphorization rate constant k P estimated by substituting the explanatory variable X _i included in the evaluation data into equation (4), and the dephosphorization rate constant k _P calculated from the evaluation data. The actual value of the dephosphorization rate constant _kP is compared, and the error between the two (standard deviation, root mean square error, etc.) is calculated. If the calculated error is within a predetermined tolerance range, the statistical model constructed in step ST64 is determined as the statistical model used to estimate the phosphorus concentration [P] in molten steel. On the other hand, if the calculated error is not within the predetermined tolerance range, for example, the operation data 321 used for building the statistical model may be changed, or the learning data and evaluation data may be changed using the same operation data 321 as before. It is conceivable to re-do the division of (step ST62 in FIG. 4) and then rebuild the statistical model (step ST64 in FIG. 4).
The parameters a _i of the statistical model calculated by the processing in step ST64 are stored in the storage unit 32 as parameters 322, as shown as step ST7 in FIG.
In addition, in order to accurately estimate the dephosphorization rate constant and, by extension, the phosphorus concentration in molten steel, it is necessary to divide the accumulated operational data 321 into learning data and evaluation data, as shown in the example shown in Fig. 4. (Step ST62 in FIG. 4), construct a statistical model using the learning data (step ST64 in FIG. 4), and evaluate the accuracy of the constructed statistical model using the evaluation data (step ST65 in FIG. 4). . However, the present invention is not limited to this, and it is also possible to create only learning data from the accumulated operation data 321 and execute only construction of a statistical model using this learning data. That is, it is also possible to omit step ST62 and step ST65 shown in FIG.

As explained above, according to the first embodiment of the present invention, the dephosphorization rate constant k _P is calculated according to the cumulative oxygen supply basic unit O ₂ (Equation (8)) supplied to the converter 11. Proportionality constant when it is assumed that the amount of change in the phosphorus concentration [P] in the molten steel in the converter 11 d[P]/dO ₂ is proportional to the phosphorus concentration in the molten steel in the converter 11 [P] with respect to the cumulative amount of blown oxygen per unit) is defined as By using a statistical model constructed according to this definition, even when the blowing process is stopped in the middle of the blowing process, it is possible to accurately calculate the estimated value of the dephosphorization rate constant _kP . As a result, the phosphorus concentration [P] in molten steel can be estimated with high accuracy.

<Second embodiment>
In the second embodiment of the present invention, the above-mentioned cumulative oxygen supply amount basic unit O ₂ is calculated from the cumulative blown oxygen amount basic unit blown into the converter and the auxiliary raw material (oxygen-containing auxiliary raw material) input into the converter. This is a form that uses the sum of the generated oxygen amount per unit. That is, the cumulative oxygen supply basic unit O ₂ is calculated according to the above-mentioned equation (9).
In the first embodiment, as described above, the cumulative oxygen supply unit V ₀₂ /W _st is used as the cumulative oxygen supply unit O ₂ , but in the converter blowing process, Oxygen-containing auxiliary raw materials may be added, and dephosphorization may also proceed due to the oxygen generated from the auxiliary raw materials. Therefore, even if the cumulative amount of blown oxygen is the same, if the amount of oxygen generated from the auxiliary raw material is different, the amount of dephosphorization is considered to be different, and as in the first embodiment, the cumulative amount of oxygen supplied per unit O ₂ If the dephosphorization rate constant k _P and the phosphorus concentration in molten steel [P] are estimated using only the cumulative blown oxygen amount basic unit V ₀₂ /W _st , the estimation accuracy may decrease. Therefore, in the second embodiment, the dephosphorization rate constant k _P and the phosphorus concentration in molten steel are determined by considering not only the cumulative blown oxygen amount basic unit V ₀₂ /W _st but also the generated oxygen amount basic unit generated from auxiliary raw materials. [P] can be estimated with even higher accuracy.

FIG. 5 is a diagram schematically showing a schematic configuration of a refining facility equipped with a statistical model construction device and a molten steel phosphorus concentration estimation device according to a second embodiment of the present invention.
As shown in FIG. 5, like the refining equipment 100 of the first embodiment, the refining equipment 100A of the second embodiment includes a converter equipment 10, a measurement control device 20, and a calculation device 30A. Similarly to the arithmetic device 30 of the first embodiment, the arithmetic device 30A of the second embodiment includes a communication section 31, a storage section 32A, an arithmetic section 33A, and an input/output section 34, and includes, for example, a computer. Consisted of.
The refining equipment 100A of the second embodiment differs from the refining equipment 100 of the first embodiment in that, in addition to the operation data 321 and parameters 322, information 323 by sub-material brand is stored in the storage unit 32A. Further, in accordance with this, the refining equipment 100 of the first embodiment is also different in that the calculation contents executed by the calculation unit 33A are different from those of the calculation unit 33 of the first embodiment.
Hereinafter, regarding the refining equipment 100A of the second embodiment, the points that are different from the refining equipment 100 of the first embodiment will be mainly explained, and the description of the same points will be omitted as appropriate.

FIG. 6 is a diagram showing an example of the information 323 by brand of auxiliary raw materials. In the example shown in FIG. 6, the auxiliary raw material brand information 323 uses the brand name of the auxiliary raw material AM as a key, and the content oxygen amount (contained oxygen volume) per unit weight of the auxiliary raw material AM of the same brand O2 _au [Nm ³ / ton] and the like are stored in the same line.

As described above, in the second embodiment, the cumulative oxygen supply basic unit O ₂ is calculated according to equation (9). That is, in the second embodiment, unlike the first embodiment, when calculating the cumulative oxygen supply amount basic unit O ₂ , the generated oxygen amount V _auO2 generated from the auxiliary raw material AM is taken into consideration.
To calculate the amount of oxygen V _auO2 generated from the auxiliary raw material AM, as shown in the above equation (10), the input amount (input weight) W _au for each brand of the auxiliary raw material AM and each brand of the auxiliary raw material AM. The amount of oxygen contained (volume of oxygen contained) per unit weight of O2 _au is used. The input amount W _au of each brand of auxiliary raw material AM is determined by calculating the total value of the input amount of each brand of auxiliary raw material AM input into the converter 11 from the input chute 15 by the data collection unit 331, and calculating the input amount W au from the operation data 321. is stored in In the example shown in FIG. 2 described above, the input amount W _au (W _auA ) of auxiliary raw material A of a certain brand and the input amount W _au (W _auB ) of auxiliary raw material B of a different brand are stored. It shows the state of being. The input amount W _au for each brand of auxiliary raw material AM is determined by using the measured value of the input amount (for example, if the input control device 27 is equipped with a sensor that measures the input amount, the measured value of that sensor), if available. , if there is no measured value, the data collection unit 331 can calculate using the instruction value of the input control device 27. The oxygen content O2 _au per unit weight for each brand of sub-material AM is determined by the data collection unit 331 via the communication unit 31 from the converter blowing database stored in an external device (not shown in FIG. 5). The information is acquired and stored by the data collection unit 331 in the corresponding item in the row of each brand of auxiliary raw material AM in the information 323 by brand of auxiliary raw material.

Similar to the statistical model construction unit 333 of the first embodiment, the statistical model construction unit 333 of the second embodiment explains data items extracted from the operation data 321 related to the past blowing process stored in the storage unit 32A. The parameters of the statistical model (regression coefficient a _i ) are estimated using learning data in which the actual value of the dephosphorization rate constant k _P is used as a variable and the objective variable is the actual value of the dephosphorization rate constant k P.
Although the statistical model construction unit 333 of the second embodiment calculates the actual value of the dephosphorization rate constant k _P according to equation (7) similarly to the statistical model construction unit 333 of the first embodiment, Unlike the statistical model construction unit 333, the cumulative oxygen supply basic unit _O2end shown in equation (7) is calculated using equation (9). That is, the statistical model construction unit 333 of the second embodiment uses the cumulative amount of blown oxygen from the start of the blowing process to the end of the blowing process included in the learning data as the cumulative oxygen supply amount basic unit _O2end shown in equation (7). V _O2 and the amount of oxygen generated from the auxiliary raw material AM from the start of the blowing process to the end of the blowing process V _auo2 (for each brand of the auxiliary raw material AM from the start of the blowing process to the end of the blowing process included in the learning data) The sum of the product of the input amount W _au and the amount of oxygen contained per unit weight O2 _au for each brand of auxiliary raw material AM included in the information 323 by brand of auxiliary raw material (the sum of the products for all brands) is calculated as the sum of the products for all brands included in the learning data. The actual value of the dephosphorization rate constant _kP is calculated by substituting the value divided by the total weight of the main raw materials _Wst .

Similar to the statistical model construction unit 333 of the first embodiment, the phosphorus concentration estimating unit 334 of the second embodiment uses explanatory variables extracted from the operation data 321 regarding the new blowing process that is the target of estimating the phosphorus concentration in molten steel. By substituting X _i and the parameter a _i stored in the storage unit 32A as the parameter 322 into a statistical model (i.e., the multiple regression equation shown in equation (4)), dephosphorization in a new blowing process can be performed. Calculate the estimated value of the rate constant _kP . The phosphorus concentration estimating unit 334 of the second embodiment, like the phosphorus concentration estimating unit 334 of the first embodiment, calculates the phosphorus concentration in the hot metal before the new blowing process included in the operation data 321 regarding the new blowing process. By substituting the concentration [P] _ini , the estimated value of the calculated dephosphorization rate constant k _P , and the cumulative oxygen supply unit O ₂ for the new blowing treatment into equation (6), the current value (i.e., The phosphorus concentration [P] in the molten steel at an arbitrary point during the blowing process is estimated.
However, unlike the phosphorus concentration estimating unit 334 of the first embodiment, the phosphorus concentration estimation unit 334 of the second embodiment calculates the cumulative oxygen supply basic unit O ₂ shown in equation (6) using equation (9). do. That is, the phosphorus concentration estimating unit 334 of the second embodiment uses the cumulative oxygen supply amount basic unit O ₂ shown in equation (6) from the start of the blowing process to the present time included in the operation data 321 regarding the new blowing process. The cumulative amount of blown oxygen V _O2 and the amount of oxygen generated from the auxiliary material AM from the start of the new blowing process to the present time V _auo2 (start of the blowing process included in the operation data 321 regarding the new blowing process) The total sum for all brands of the product of the input amount W _au for each brand of auxiliary raw material AM from 2009 to the present time and the amount of oxygen contained per unit weight O2 _au for each brand of auxiliary raw material AM included in the information 323 for each brand of auxiliary raw material AM ) is divided by the total weight of the main raw materials W _st included in the operation data 321 regarding the new blowing process, and the current phosphorus concentration in the molten steel [P] is estimated.

The method for estimating phosphorus concentration in molten steel according to the second embodiment using the refining equipment 100A described above is the method for estimating phosphorus concentration in molten steel according to the first embodiment described with reference to FIGS. 3 and 4, and the cumulative The only difference is the method of calculating the oxygen supply amount basic unit O ₂ (O _{2 end} ), and the other procedures are the same, so detailed explanation thereof will be omitted here.

According to the second embodiment of the present invention, in addition to the cumulative blown oxygen amount basic unit V ₀₂ /W _st blown into the converter 11, the generated oxygen amount basic unit generated from the auxiliary material AM input into the converter 11 By also considering the unit V _auO2 /W _st , it is possible to estimate the dephosphorization rate constant k _P with even greater precision, and in turn, it is possible to estimate the phosphorus concentration [P] in molten steel with greater precision.

Note that in both the first and second embodiments described above, the single calculation section 33, 33A has a configuration (in other words, For example, regarding a configuration in which a single calculation unit 33, 33A functions as a statistical model construction device and a molten steel phosphorus concentration estimating device according to the present invention, and executes both statistical model construction and molten steel phosphorus concentration estimation) Although described, the present invention is not limited thereto. For example, a single calculation unit includes only the statistical model construction unit 333 out of the statistical model construction unit 333 and the phosphorus concentration estimation unit 334, and the statistical model constructed by the statistical model construction unit 333 is applied to the phosphorus concentration estimation unit. It is also possible to adopt a mode in which the phosphorus concentration in molten steel is estimated by using another single calculation unit having only 334. In other words, it is also possible to adopt an embodiment in which the statistical model construction device according to the present invention and the molten steel phosphorus concentration estimation device are provided separately.

Hereinafter, an example of the results of evaluating the estimation accuracy of the method for estimating the phosphorus concentration in molten steel according to the examples and comparative examples of the present invention will be described.
The method for estimating the phosphorus concentration in molten steel according to the comparative example is a conventional estimation method described in Patent Document 1, etc., and is a method for estimating the phosphorus concentration in molten steel using the above-mentioned formulas (1) to (4). It is. The method for estimating the phosphorus concentration in molten steel according to Example 1 is the estimation method described in the first embodiment, and is a method for estimating the phosphorus concentration in molten steel using the above-mentioned formulas (4) to (8). . The method for estimating phosphorus concentration in molten steel according to Example 2 is the estimation method described in the second embodiment, and uses the above-mentioned equations (4) to (7), equation (9), and equation (10). This is a method for estimating the phosphorus concentration in molten steel.
The phosphorus concentration in the molten steel at the end of the blowing process was estimated using the estimation methods according to the comparative example and Examples 1 and 2, and each estimated value was calculated using the sample taken from the molten steel after the blowing process. Estimation accuracy was evaluated by comparing with actual values obtained through analysis.

FIG. 7 is a scatter diagram showing the relationship between estimated values and actual values estimated by the methods for estimating phosphorus concentration in molten steel according to the examples and comparative examples of the present invention. 7(a) shows the relationship between the estimated value and actual value for the comparative example, FIG. 7(b) shows the relationship between the estimated value and actual value for Example 1, and FIG. 7(c) shows the relationship between the estimated value and actual value for Example 2. The relationship between the estimated value and the actual value is shown. Table 1 also shows the error σ (standard deviation) and root mean square error (RMSE) calculated from the results shown in FIG.
The results shown in FIG. 7 and Table 1 are the results of using the operation data for 3640 blowing treatments as learning data and using the operation data for 1564 blowing treatments as evaluation data (therefore, FIG. In the scatter diagram shown in Figure 1, data for 1564 blowing treatments are plotted).

As shown in FIG. 7 and Table 1, both Examples 1 and 2 have higher estimation accuracy than the comparative example, and it can be seen that Example 2 has the highest estimation accuracy. As described above, according to the estimation method according to the present invention, it is possible to accurately estimate the phosphorus concentration in molten steel in a converter.

10... Converter equipment 11... Converter 20... Measurement control device 30, 30A... Arithmetic device 33, 33A... Arithmetic unit 100, 100A... Refining equipment 331... Data collection Section 333... Statistical model construction section 334... Phosphorus concentration estimation section MI... Molten steel

Claims (10)

a data collection department that collects operational data regarding the converter blowing process;
a statistical model construction unit that constructs a statistical model with the operational data as an explanatory variable and the dephosphorization rate constant in the blowing treatment as an objective variable,
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
The statistical model construction unit constructs the statistical model using operational data related to past blowing processes collected by the data collection unit.
Statistical model building device. The cumulative oxygen supply amount basic unit supplied to the converter is the cumulative blown oxygen amount basic unit blown into the converter,
The statistical model construction device according to claim 1. The cumulative amount of oxygen supplied to the converter is the sum of the cumulative amount of oxygen blown into the converter and the amount of oxygen generated from the auxiliary materials fed into the converter. is,
The statistical model construction device according to claim 1. a data collection department that collects operational data regarding the converter blowing process;
a phosphorus concentration estimation unit that estimates a phosphorus concentration in molten steel in the converter during the blowing process using a statistical model that uses the operational data as an explanatory variable and uses a dephosphorization rate constant in the blowing process as an objective variable; , comprising;
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
The phosphorus concentration estimating unit calculates an estimated value of the dephosphorization rate constant in the new blowing process using the operational data regarding the new blowing process collected by the data collecting unit and the statistical model. and the phosphorus concentration in the hot metal of the converter before the new blowing treatment, the calculated estimated value of the dephosphorization rate constant, and the cumulative amount of oxygen supplied to the converter in the new blowing treatment. estimating the phosphorus concentration in the molten steel of the converter during the new blowing process based on the basic unit;
Device for estimating phosphorus concentration in molten steel. The cumulative oxygen supply amount basic unit supplied to the converter is the cumulative blown oxygen amount basic unit blown into the converter,
The device for estimating phosphorus concentration in molten steel according to claim 4. The cumulative amount of oxygen supplied to the converter is the sum of the cumulative amount of oxygen blown into the converter and the amount of oxygen generated from the auxiliary materials fed into the converter. is,
The device for estimating phosphorus concentration in molten steel according to claim 4. a data collection step of collecting operational data regarding the blowing process of the converter;
a statistical model construction step of constructing a statistical model using the operational data as an explanatory variable and the dephosphorization rate constant in the blowing treatment as an objective variable;
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
In the statistical model construction step, the statistical model is constructed using operational data regarding past blowing processes collected in the data collection step.
Statistical model construction method. a data collection step of collecting operational data regarding the blowing process of the converter;
a phosphorus concentration estimating step of estimating the phosphorus concentration in molten steel in the converter during the blowing process using a statistical model using the operational data as an explanatory variable and the dephosphorization rate constant in the blowing process as an objective variable; , has
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
In the phosphorus concentration estimation step, an estimated value of the dephosphorization rate constant in the new blowing process is calculated using the operational data regarding the new blowing process collected in the data collection step and the statistical model. and the phosphorus concentration in the hot metal of the converter before the new blowing treatment, the calculated estimated value of the dephosphorization rate constant, and the cumulative amount of oxygen supplied to the converter in the new blowing treatment. estimating the phosphorus concentration in the molten steel of the converter during the new blowing process based on the basic unit;
Method for estimating phosphorus concentration in molten steel. a data collection department that collects operational data regarding the converter blowing process;
A statistical model construction program for operating a computer as a statistical model construction unit that constructs a statistical model with the operational data as an explanatory variable and the dephosphorization rate constant in the blowing process as an objective variable,
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
The statistical model construction unit constructs the statistical model using operational data related to past blowing processes collected by the data collection unit.
Statistical model building program. a data collection department that collects operational data regarding the converter blowing process;
a phosphorus concentration estimation unit that estimates a phosphorus concentration in molten steel in the converter during the blowing process using a statistical model that uses the operational data as an explanatory variable and uses a dephosphorization rate constant in the blowing process as an objective variable; , a program for estimating phosphorus concentration in molten steel for making a computer function,
The dephosphorization rate constant is a proportionality constant when it is assumed that the amount of change in the phosphorus concentration in the molten steel of the converter with respect to the cumulative oxygen supply amount basic unit supplied to the converter is proportional to the phosphorus concentration in the molten steel of the converter. is defined as
The phosphorus concentration estimating unit calculates an estimated value of the dephosphorization rate constant in the new blowing process using the operational data regarding the new blowing process collected by the data collecting unit and the statistical model. and the phosphorus concentration in the hot metal of the converter before the new blowing treatment, the calculated estimated value of the dephosphorization rate constant, and the cumulative amount of oxygen supplied to the converter in the new blowing treatment. estimating the phosphorus concentration in the molten steel of the converter during the new blowing process based on the basic unit;
Program for estimating phosphorus concentration in molten steel.

Images