Method for estimating particle size distribution of granulated particles, method for producing granulated particles, and device for producing granulated particles

Abstract

This method for estimating the particle size distribution of granulated particles uses a granulated particle production apparatus 1 that is provided with a granulator 40 that produces granulated particles from a sintering raw material containing a plurality of raw materials. The particle size distribution estimation method comprises: a step for acquiring the granulation conditions, including the blending proportions of the plurality of raw materials contained in the sintering raw material and the water content of the sintering raw material at the point the granulator 40 produces the granulated particles; a step for calculating, based on the granulation conditions, the parameters of a distribution function that fits to the particle size distribution of the granulated particles produced by the granulator 40; and a step for estimating the particle size distribution using the distribution function and the parameters.

Description

[Technical field]

[0001] The present disclosure relates to a method for estimating particle size distribution of granulated particles, a method for producing granulated particles, and an apparatus for producing granulated particles. [Background technology]

[0002] In the sintering process, the raw materials for sintering, including iron ore, fine coke, and CaO (calcium oxide), are not used as is, but are granulated into granules. Granules are made by granulating the raw materials for sintering into granules using a granulator such as a drum mixer.

[0003] After granulating the raw materials for sintering, they are loaded into the pallets of a sintering machine to produce sintered ore. In the sintering process using a sintering machine, it is important to improve the air permeability. Since the air permeability in a sintering machine depends on the size and porosity of the granulated particles, it is required to accurately estimate the particle size distribution of the granulated particles.

[0004] For example, Patent Document 1 discloses an apparatus for estimating a height direction distribution of a target raw material in a sintering raw material layer based on target raw material particle size distribution information showing the particle size distribution of the target raw material, target raw material abundance information showing the particle size distribution of the target raw material in pseudo-particles (granulated particles) granulated from a plurality of raw materials including the target raw material, and pseudo-particle distribution information showing the particle size distribution of the pseudo-particles in the height direction of the sintering raw material layer in which the pseudo-particles are stacked. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2020-12185 A Summary of the Invention [Problem to be solved by the invention]

[0006] The particle size distribution of granulated particles also depends on the blending conditions of the raw materials, the moisture content at the time of granulation, etc. The estimation method described in Patent Document 1 does not take into account the blending conditions of the raw materials and the moisture content at the time of granulation, and when the blending conditions of the raw materials and the moisture content at the time of granulation change, it is difficult to accurately estimate the distribution in the height direction of the target raw materials.

[0007] An object of the present disclosure is to provide a method for estimating the particle size distribution of granulated particles, a method for producing granulated particles, and an apparatus for producing granulated particles, which are capable of accurately estimating the particle size distribution of granulated particles. [Means for solving the problem]

[0008] A method for estimating a particle size distribution of granulated particles according to an embodiment of the present disclosure includes: A method for estimating a particle size distribution of granulated particles using a granulated particle manufacturing apparatus including a granulator that granulates granulated particles from a sintering raw material containing a plurality of raw materials, comprising: A step of acquiring granulation conditions including a blending ratio of the plurality of raw materials contained in the sintering raw material and a moisture content of the sintering raw material when the granulator granulates the granulated particles; Calculating parameters of a distribution function that fits to a particle size distribution of the granulated particles granulated by the granulator based on the granulation conditions; estimating the particle size distribution using the distribution function and the parameters; Includes.

[0009] A granulated particle manufacturing method according to an embodiment of the present disclosure manufactures granulated particles using the above-described particle size distribution estimation method.

[0010] An apparatus for producing granulated particles according to an embodiment of the present disclosure includes: A granulator that granulates granulated particles from a sintering raw material containing a plurality of raw materials; A control device that estimates a particle size distribution of the granulated particles produced by the granulator; Equipped with The control device includes: Acquire granulation conditions including a blending ratio of the plurality of raw materials contained in the sintering raw material and a moisture content of the sintering raw material when the granulator granulates the granulated particles; Calculating parameters of a distribution function that fits to a particle size distribution of the granulated particles granulated by the granulator based on the granulation conditions; The particle size distribution is estimated using the distribution function and the parameters. Effect of the Invention

[0011] According to the method for estimating particle size distribution of granulated particles, the method for producing granulated particles, and the device for estimating particle size distribution of granulated particles disclosed herein, it is possible to estimate the particle size distribution of granulated particles with high accuracy. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating a configuration example of a granulated particle manufacturing apparatus according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating a configuration example of a control device according to an embodiment of the present disclosure. [Diagram 3] 1 is a flowchart showing an example of a procedure for a particle size distribution estimation method for granulated particles according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a diagram showing measured values ​​of particle size distribution in the examples. [Diagram 5] FIG. 1 is a diagram showing the correlation between measured and calculated particle size distribution values ​​in Examples. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0014] FIG. 1 is a diagram illustrating a schematic configuration example of a granulated particle manufacturing apparatus 1 according to an embodiment of the present disclosure.

[0015] The granulated particle manufacturing apparatus 1 includes a control device 10, a plurality of blending tanks 20-1 to 20-3, a moisture supplying device 30, and a granulator 40.

[0016] Hereinafter, blending tanks 20-1 to 20-3 may be simply referred to as "blending tank 20" when there is no particular need to distinguish between them. In the present embodiment, the granulated particle manufacturing apparatus 1 is described as having three blending tanks 20-1 to 20-3, but the number of blending tanks 20 included in the granulated particle manufacturing apparatus 1 is not limited to three. The number of blending tanks 20 included in the granulated particle manufacturing apparatus 1 may be two, or may be four or more.

[0017] The granulated particle manufacturing apparatus 1 is an apparatus for manufacturing granulated particles from a sintered raw material containing a plurality of raw materials. The plurality of raw materials may include, for example, an iron-containing raw material, a CaO (calcium oxide)-containing raw material, and coke powder. The iron-containing raw material may be, for example, iron ore. The CaO-containing raw material may be, for example, limestone. In this embodiment, a case where the plurality of raw materials contained in the sintered raw material are an iron-containing raw material, a CaO-containing raw material, and coke powder will be described as an example.

[0018] The granulated particles produced by the granulated particle production apparatus 1 are, for example, transported to a sintering machine and sintered in the sintering machine to become sintered ore. The sintered ore is used in the pig iron making process.

[0019] The control device 10 can communicate with the blending tanks 20-1 to 20-3, the moisture supplying device 30, and the granulator 40. The control device 10 controls the blending tanks 20-1 to 20-3, the moisture supplying device 30, and the granulator 40. In FIG. 1, the dashed lines connecting the control device 10 to the blending tanks 20-1 to 20-3, the moisture supplying device 30, and the granulator 40 indicate that the control device 10 can communicate with the blending tanks 20-1 to 20-3, the moisture supplying device 30, and the granulator 40, and that the control device 10 can control the blending tanks 20-1 to 20-3, the moisture supplying device 30, and the granulator 40.

[0020] The configuration and functions of the control device 10 will be described in detail later.

[0021] The blending tank 20 supplies the raw materials contained in the sintering raw materials to the granulator 40. The amount of raw materials supplied from the blending tank 20 to the granulator 40 is controlled by the control device 10.

[0022] The blending tanks 20-1 to 20-3 each supply a different type of raw material to the granulator 40. In the example shown in Fig. 1, the blending tank 20-1 supplies an iron-containing raw material to the granulator 40. The blending tank 20-2 supplies a CaO-containing raw material to the granulator 40. The blending tank 20-3 supplies coke powder to the granulator 40.

[0023] The moisture supplying device 30 supplies moisture to the granulator 40 to be added to the raw materials when the blending tanks 20-1 to 20-3 supply the raw materials to the granulator 40. The amount of moisture supplied to the granulator 40 by the moisture supplying device 30 is controlled by the control device 10.

[0024] The granulator 40 granulates granulated particles from the sintering raw material containing a plurality of raw materials. Here, the sintering raw material contains a plurality of raw materials supplied from the blending tanks 20-1 to 20-3 and moisture supplied from the moisture supplying device 30. In the case of the example shown in Fig. 1, the sintering raw material supplied to the granulator 40 contains an iron-containing raw material, a CaO-containing raw material, coke powder, and moisture.

[0025] Granulator 40 may be any granulator capable of producing granulated particles, but may be, for example, a drum mixer.

[0026] The granulated particles produced by the granulator 40 are, for example, transported to a sintering machine and used as a raw material for producing sintered ore.

[0027] 2 is a diagram illustrating a schematic configuration example of the control device 10 according to an embodiment of the present disclosure. The control device 10 may be a general-purpose computer such as a workstation or a personal computer, or may be a dedicated computer configured to function as the control device 10 of the granulated particle manufacturing apparatus 1.

[0028] The control device 10 includes a control unit 11, an input unit 12, an output unit 13, a storage unit 14, and a communication unit 15.

[0029] The control unit 11 includes at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a central processing unit (CPU) or a graphics processing unit (GPU), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a field-programmable gate array (FPGA) or an application specific integrated circuit (ASIC).

[0030] The control unit 11 reads the programs, data, etc. stored in the storage unit 14 and executes various functions. The control unit 11 controls the blending tank 20, the water supplying device 30, and the granulator 40.

[0031] The control unit 11 can execute a program read from the memory unit 14 to cause the control unit 11 to function as a raw material information acquisition unit 111, a granulation condition acquisition unit 112, a particle size distribution estimation unit 113, and a guidance information acquisition unit 114.

[0032] The processes executed by the raw material information acquisition unit 111, the granulation condition acquisition unit 112, the particle size distribution estimation unit 113, and the guidance information acquisition unit 114 will be described later.

[0033] The input unit 12 includes one or more input interfaces that detect a user input and acquire input information based on a user operation. The input unit 12 includes, for example, physical keys, capacitive keys, a touch screen that is integral with the display of the output unit 13, or a microphone that accepts voice input.

[0034] The output unit 13 includes one or more output interfaces that output information to notify a user. The output unit 13 includes, for example, a display that outputs information as an image, a speaker that outputs information as sound, etc. The display included in the output unit 13 may be, for example, an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, etc.

[0035] The storage unit 14 is, for example, a flash memory, a hard disk, an optical memory, etc. A part of the storage unit 14 may be outside the control device 10. In this case, the part of the storage unit 14 may be a hard disk, a memory card, etc. connected to the control device 10 via an arbitrary interface.

[0036] The storage unit 14 stores programs for the control unit 11 to execute each function, data used by the programs, and the like.

[0037] The communication unit 15 includes at least one of a communication module corresponding to wired communication and a communication module corresponding to wireless communication. The control device 10 is capable of communicating with other terminal devices and the like via the communication unit 15.

[0038] Next, the processes executed by the raw material information acquisition unit 111, the granulation condition acquisition unit 112, the particle size distribution estimation unit 113, and the guidance information acquisition unit 114 will be described.

[0039] The raw material information acquisition unit 111 acquires information on the raw materials supplied from each blending tank 20 to the granulator 40. The raw material information acquisition unit 111 acquires information such as the ingredients of the raw materials, the particle size of the raw materials, and the blending amount of the raw materials. The information on the ingredients of the raw materials is information on the composition of the raw materials. The particle size information of the raw materials is information indicating the size of the particles of the raw materials. The information on the blending amount of the raw materials is information indicating the amount of raw materials supplied from the blending tank 20 to the granulator 40.

[0040] In the example shown in FIG. 1, the raw material information acquisition unit 111 acquires information on the components of the raw materials, the particle size of the raw materials, and the blending amounts of the raw materials for each of the iron-containing raw materials, the CaO-containing raw materials, and the coke fines supplied from the blending tanks 20-1 to 20-3 to the granulator 40.

[0041] The raw material information acquisition unit 111 may acquire information on the raw materials supplied from each blending tank 20 to the granulator 40 by an operator's input operation to the input unit 12. The raw material information acquisition unit 111 may also acquire information on the raw materials supplied from each blending tank 20 to the granulator 40 by receiving information input by an operator to another terminal device via the communication unit 15. The raw material information acquisition unit 111 may also acquire information on the blending amount of raw materials from a setting value set in the blending tank 20.

[0042] The granulation condition acquisition unit 112 acquires information on the components of the raw materials, the grain size of the raw materials, and the blending amount of the raw materials from the raw material information acquisition unit 111 as information on the raw materials supplied from each blending tank 20 to the granulator 40. The granulation condition acquisition unit 112 calculates the blending ratio of the multiple raw materials contained in the sintering raw material based on the acquired information on the blending amount of each raw material.

[0043] The granulation condition acquisition unit 112 acquires information on the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles. The moisture content of the sintering raw material when the granulator 40 granulates the granulated particles is calculated from the moisture content of each raw material and the moisture supplied from the moisture supply device 30 to the granulator 40. The moisture content of each raw material is measured, for example, using an infrared moisture meter. The granulation condition acquisition unit 112 may acquire the moisture content information by an input operation by an operator to the input unit 12. In addition, the granulation condition acquisition unit 112 may acquire the moisture content information by receiving information input by an operator to another terminal device via the communication unit 15. In addition, the granulation condition acquisition unit 112 may acquire the moisture content information from a setting value set in the moisture supply device 30.

[0044] The granulation condition acquisition unit 112 acquires information on the granulator 40, such as the space factor of the granulator 40, the rotation speed of the granulator 40, and the estimated residence time in the granulator 40. The granulation condition acquisition unit 112 may acquire the information on the granulator 40 by an input operation by an operator to the input unit 12. The granulation condition acquisition unit 112 may also acquire the information on the granulator 40 by receiving information input by an operator to another terminal device via the communication unit 15. The granulation condition acquisition unit 112 may also acquire the information on the granulator 40 from the setting values ​​set in the granulator 40.

[0045] The granulation condition acquisition unit 112 outputs the acquired granulation conditions to the particle size distribution estimation unit 113. The granulation conditions output by the granulation condition acquisition unit 112 to the particle size distribution estimation unit 113 include at least the blending ratio of the multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles. The granulation conditions may further include information on the components of the raw materials, the particle size of the raw materials, the space factor of the granulator 40, the rotation speed of the granulator 40, and the estimated residence time in the granulator 40.

[0046] The particle size distribution estimation unit 113 estimates the particle size distribution of the granulated particles granulated by the granulator 40 based on the granulation conditions acquired from the granulation condition acquisition unit 112. First, the particle size distribution estimation unit 113 calculates parameters of a distribution function that fits to the particle size distribution of the granulated particles granulated by the granulator 40 based on the granulation conditions acquired from the granulation condition acquisition unit 112. Next, the particle size distribution estimation unit 113 substitutes the calculated parameters into a distribution function that fits to the particle size distribution of the granulated particles granulated by the granulator 40, and estimates the particle size distribution of the granulated particles granulated by the granulator 40 using the distribution function into which the parameters have been substituted.

[0047] When calculating each parameter of the distribution function that fits the particle size distribution of the granulated particles, the particle size distribution estimation unit 113 may calculate the parameter using a parameter estimation model corresponding to each parameter. The parameter estimation model may be stored in the storage unit 14.

[0048] The parameter estimation model may be a multiple regression model, a trained machine learning model, etc.

[0049] When the parameter estimation model is a multiple regression model, it may be a multiple regression model in which, for example, the mixing ratio of multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles are explanatory variables, and one of the parameters of the distribution function is the objective variable.

[0050] When the parameter estimation model is a machine learning model, it may be, for example, a trained machine learning model that takes as input the mixing ratio of multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles, and outputs one of the parameters of the distribution function.

[0051] Such a multiple regression model or machine learning model may be obtained in advance by using a data set that includes the blending ratio of multiple raw materials contained in the sintering raw material, the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles, and the actual value of the parameters of the distribution function, and stored in the storage unit 14. In addition, the trained machine learning model may be obtained in advance by machine learning using a data set that includes the blending ratio of multiple raw materials contained in the sintering raw material, the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles, and the actual value of one of the parameters of the distribution function, and stored in the storage unit 14. The actual value of the parameter of the distribution function can be obtained by fitting the distribution function to the curve of the particle size distribution of the granulated particles whose particle size distribution is known.

[0052] The distribution function that the particle size distribution estimation unit 113 fits to the particle size distribution of the granulated particles may be a Rosin-Rammler distribution function, a normal distribution function, a binomial distribution function, or the like. If the distribution function is a distribution function that is distributed only in the first quadrant, it is possible to prevent negative values ​​from appearing in the distribution of the granulated particles. For example, the Rosin-Rammler distribution function is a distribution function that is distributed only in the first quadrant.

[0053] When the distribution function is the Rosin-Rammler distribution function, the Rosin-Rammler distribution function can be expressed as the following equation (1).

number

[0054] When the distribution function is a Rosin-Rammler distribution function as shown in formula (1), the particle size distribution estimation unit 113 calculates β and n shown in formula (1) as parameters.

[0055] After calculating the parameters β and n, the particle size distribution estimation unit 113 can estimate the particle size distribution of the granulated particles granulated by the granulator 40 by substituting the parameters β and n into the Rosin-Rammler distribution function shown in formula (1).

[0056] The particle size distribution estimation unit 113 may output the estimated particle size distribution of the granulated particles to the output unit 13 and cause the output unit 13 to display it.

[0057] When the distribution function is a normal distribution function, the particle size distribution estimation unit 113 calculates the mean, standard deviation, skewness, and kurtosis as parameters.

[0058] The particle size distribution estimation unit 113 calculates the mean, standard deviation, skewness, and kurtosis, which are parameters of the normal distribution function, and then substitutes the mean, standard deviation, skewness, and kurtosis into the normal distribution function to estimate the particle size distribution of the granulated particles granulated by the granulator 40.

[0059] When the distribution function is a binomial distribution function, the particle size distribution estimation unit 113 calculates the probability P and the number of trials N as parameters.

[0060] The particle size distribution estimation unit 113 calculates the probability P and the number of trials N, which are parameters of the binomial distribution function, and then substitutes the probability P and the number of trials N into the binomial distribution function to estimate the particle size distribution of the granulated particles granulated by the granulator 40.

[0061] The guidance information acquisition unit 114 does not estimate the particle size distribution of the granulated particles granulated by the granulator 40, but calculates the granulation conditions for making the particle size distribution of the granulated particles granulated by the granulator 40 a target particle size distribution.

[0062] When the parameters for achieving the target particle size distribution are input, the guidance information acquisition unit 114 calculates the granulation conditions based on the input parameters. For example, when the distribution function to be fitted to the particle size distribution is a Rosin-Rammler distribution function, the parameters β and n of the Rosin-Rammler distribution function having a shape corresponding to the target particle size distribution are input to the guidance information acquisition unit 114. For example, the guidance information acquisition unit 114 inputs various granulation conditions to a parameter estimation model and judges whether the output parameters match the input parameters. The guidance information acquisition unit 114 performs this operation for the parameters β and n, and specifies the granulation conditions for which it is determined that the output parameters match the input parameters for both the parameters β and n as granulation conditions that can achieve the target particle size distribution. In this way, the guidance information acquisition unit 114 calculates the granulation conditions based on the input parameters β and n. The granulation conditions calculated by the guidance information acquisition unit 114 may include, for example, the blending ratio of multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles.

[0063] The guidance information acquisition unit 114 may acquire the parameters β and n through an input operation by an operator to the input unit 12. In addition, the guidance information acquisition unit 114 may acquire the parameters β and n by receiving information input by an operator to another terminal device via the communication unit 15.

[0064] The guidance information acquisition unit 114 outputs the calculated granulation conditions to the output unit 13.

[0065] The output unit 13 outputs the granulation conditions acquired from the guidance information acquisition unit 114. For example, when the output unit 13 includes a display, the output unit 13 displays the granulation conditions acquired from the guidance information acquisition unit 114 on the display.

[0066] An operator visually checking the granulation conditions displayed on the display can set the granulation conditions and operate the granulated particle production apparatus 1 to produce granulated particles with a target particle size distribution.

[0067] Alternatively, the guidance information acquisition unit 114 may automatically set the calculated granulation conditions as the granulation conditions when operating the granulated particle manufacturing apparatus 1. In this way, the granulated particle manufacturing apparatus 1 can automatically set the granulation conditions for making the particle size distribution of the granulated particles granulated by the granulator 40 a target particle size distribution, and manufacture the granulated particles.

[0068] 2, the control unit 11 has the function of the guidance information acquisition unit 114, but the control unit 11 does not have to have the function of the guidance information acquisition unit 114. However, when the control unit 11 has the function of the guidance information acquisition unit 114, it becomes easier to manufacture granulated particles with a target particle size distribution, so it is preferable that the control unit 11 has the function of the guidance information acquisition unit 114.

[0069] A particle size distribution estimation method executed by the granulated particle manufacturing apparatus 1 according to this embodiment will be described with reference to the flowchart shown in FIG.

[0070] In step S101, the control unit 11 of the control device 10 acquires granulation conditions including the blending ratio of multiple raw materials contained in the sintering raw materials and the moisture content of the sintering raw materials when the granulator 40 granulates the granulated particles.

[0071] In step S102, the control unit 11 calculates, based on the acquired granulation conditions, parameters of a distribution function that fits to the particle size distribution of the granulated particles granulated by the granulator 40. The distribution function may be a Rosin-Rammler distribution function, a normal distribution function, a binomial distribution function, or the like.

[0072] In step S103, the control unit 11 substitutes the calculated parameters into a distribution function that fits the particle size distribution of the granulated particles, and uses the distribution function to estimate the particle size distribution of the granulated particles granulated by the granulator 40. The control unit 11 may output the estimated particle size distribution of the granulated particles to the output unit 13 and cause the output unit 13 to display it.

[0073] (Example) 4 and 5 show examples of estimating particle size distribution using the granulated particle manufacturing apparatus 1. Fig. 4 is a table showing measured values ​​of particle size distribution and carbon ratio for each particle size of granulated particles produced under various conditions. Fig. 5 is a graph comparing the measured particle size distribution of granulated particles with the calculated particle size distribution estimated using the granulated particle manufacturing apparatus 1.

[0074] In the measurement shown in this embodiment, a drum mixer with a diameter of 0.3 m and a length of 0.4 m was used as the granulator 40. A total of 8 kg of sinter raw materials mixed at various mixing ratios were used. The moisture supplying device 30 added a predetermined amount of moisture to the raw materials supplied from the blending tank 20. The distribution function was a rosin-Rammler distribution function. The parameters β and n of the rosin-Rammler distribution function were obtained using a machine learning model in which the mixing ratio of raw materials A, B, C and coke fines, the particle size of the coke fines, and the moisture content are input as parameter estimation models, and a machine learning model in which the mixing ratio of raw materials A, B, C and coke fines, the particle size of the coke fines, and the moisture content are input, and a parameter n is output (IBM's SPSS).

[0075] As shown in Fig. 4, measurements were performed under 24 different conditions, T1 to T24. Fig. 4 shows the blending ratio, coke fine particle size, and moisture as conditions, and also shows the particle size distribution of the granulated particles as measured values.

[0076] In the blending ratio shown in FIG. 4, raw material A is iron ore from South America. Raw material B is iron ore from South America of a different brand from raw material A. Raw material C is iron ore from Australia. In addition, in the coke fine particle size, "-2mm" indicates the ratio of coke fines with a diameter of less than 2 mm. "-1mm" indicates the ratio of coke fines with a diameter of less than 1 mm. In addition, in the particle size distribution of the granulated particles, "+8.0" indicates the ratio of granulated particles with a diameter of more than 8.0 mm. "2.8-8.0" indicates the ratio of granulated particles with a diameter of 2.8 mm or more and 8.0 mm or less. "-2.8" indicates the ratio of granulated particles with a diameter of less than 2.8 mm. In addition, in the carbon ratio by particle size, "+8.0" indicates the ratio of carbon with a diameter of more than 8.0 mm. "2.8-8.0" indicates the ratio of carbon with a diameter of 2.8 mm or more and 8.0 mm or less. "-2.8" indicates the percentage of carbon with a diameter less than 2.8 mm.

[0077] A machine learning model was trained using the performance data shown in Figure 4 to generate a trained machine learning model, which was then used to determine the parameters β and n. The particle size of the granulated particles was then estimated using the Rosin-Rammler distribution function of the parameters β and n.

[0078] Fig. 5 is a graph showing the correlation between the calculated particle size distribution estimated using the granulated particle manufacturing apparatus 1 and the measured values. Fig. 5 shows three graphs. From the top, it is a graph comparing the measured values ​​and calculated values ​​of granulated particles with a diameter size of more than 8.0 mm, a graph comparing the measured values ​​and calculated values ​​of granulated particles with a diameter size of 2.8 mm or more and 8.0 mm or less, and a graph comparing the measured values ​​and calculated values ​​of granulated particles with a diameter size of less than 2.8 mm. The horizontal axis is the measured values. The vertical axis is the calculated values.

[0079] Referring to FIG. 5, there is a high correlation between the measured values ​​and the calculated particle size distribution estimated using the granulated particle manufacturing apparatus 1, and it is understood that the granulated particle manufacturing apparatus 1 can estimate the particle size distribution with high accuracy. In the graph of granulated particles with a diameter exceeding 8.0 mm, the coefficient of determination (R 2 ) is R 2 = 0.7959. In the graph for granulated particles with diameters between 2.8 mm and 8.0 mm, the coefficient of determination is R 2 = 0.8056. In the graph for granulated particles with diameters less than 2.8 mm, the coefficient of determination is R 2 =0.9122.

[0080] As described above, in the granulated particle manufacturing apparatus 1 according to the present embodiment and the method for estimating the particle size distribution of granulated particles using the granulated particle manufacturing apparatus 1 according to the present embodiment, the control device 10 acquires granulation conditions including the blending ratio of multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles, calculates parameters of a distribution function that fits the particle size distribution of the granulated particles granulated by the granulator 40 based on the acquired granulation conditions, and estimates the particle size distribution using the calculated parameters and distribution function. In this way, since the particle size distribution of the granulated particles is estimated based on the granulation conditions including the blending ratio of multiple raw materials and the moisture content of the sintering raw material, the granulated particle manufacturing apparatus 1 according to the present embodiment can estimate the particle size distribution of the granulated particles taking into account the blending ratio of multiple raw materials and the moisture content of the sintering raw material. Therefore, the granulated particle manufacturing apparatus 1 of this embodiment and the method for estimating the particle size distribution of granulated particles using the granulated particle manufacturing apparatus 1 of this embodiment can accurately estimate the particle size distribution of granulated particles while taking into account the blending ratio of multiple raw materials and the moisture content of the sintering raw material.

[0081] The present disclosure is not limited to the above-described embodiments. For example, multiple blocks shown in the block diagram may be integrated, or one block may be divided. Instead of executing multiple steps shown in the flowchart in chronological order as described, each step may be executed in parallel or in a different order depending on the processing capacity of the device executing each step, or as necessary. Other modifications are possible without departing from the spirit of the present disclosure.

[0082] For example, in the above embodiment, the particle size distribution estimation unit 113 calculates the parameters of the distribution function based on the blending ratio of the raw materials contained in the sintering raw materials and the moisture content of the sintering raw materials when the granulator 40 granulates the granulated particles. However, the particle size distribution estimation unit 113 may calculate the parameters of the distribution function based on the particle size of the coke fines in addition to the blending ratio and moisture content of the raw materials. That is, the granulation conditions may further include the particle size of the coke fines in addition to the blending ratio and moisture content of the raw materials. The particle size distribution estimation unit 113 can estimate the particle size distribution of the granulated particles with higher accuracy by considering the particle size of the coke fines. The particle size distribution estimation unit 113 may calculate the parameters of the distribution function by considering the particle size of other raw materials instead of or in addition to the particle size of the coke fines. Furthermore, the particle size distribution estimation unit 113 may calculate the parameters of the distribution function based on information on the components of each raw material in addition to the blending ratio and moisture content of the multiple raw materials.

[0083] For example, in the above embodiment, the particle size distribution estimation unit 113 calculates the parameters of the distribution function based on the blending ratio of the multiple raw materials contained in the sintering raw material and the moisture content of the sintering raw material when the granulator 40 granulates the granulated particles. However, the particle size distribution estimation unit 113 may calculate the parameters of the distribution function based on at least one of the space factor of the granulator 40, the rotation speed of the granulator 40, and the estimated residence time in the granulator 40 in addition to the blending ratio and moisture content of the multiple raw materials. That is, the granulation conditions may further include at least one of the space factor of the granulator 40, the rotation speed of the granulator 40, and the estimated residence time in the granulator 40 in addition to the blending ratio and moisture content of the multiple raw materials. By considering the space factor of the granulator 40, the rotation speed of the granulator 40, and the estimated residence time in the granulator 40, the particle size distribution estimation unit 113 can estimate the particle size distribution of the granulated particles with higher accuracy.

[0084] For example, in the above embodiment, the sintering raw material includes the iron-containing raw material, the CaO-containing raw material, and the coke powder, but the sintering raw material may include the iron-containing raw material and the coke powder. In other words, the sintering raw material does not need to include the CaO-containing raw material.

[0085] For example, in the above-described embodiment, the guidance information acquisition unit 114 sets the following as the granulation conditions: An example has been given of calculating granulation conditions including the blending ratio of multiple raw materials contained in the sintering raw materials and the moisture content of the sintering raw materials when the granulator 40 granulates the granulated particles, but the granulation conditions calculated by the guidance information acquisition unit 114 may further include the particle size of the powdered coke in addition to the blending ratio and moisture content of the multiple raw materials. [Explanation of symbols]

[0086] 1 Granulated particle manufacturing equipment 10 Control device 11 Control section 12 Input section 13 Output section 14 Storage section 15 Communications Department 20 Blending tank 30 Moisture supply device 40 Granulator 111 Raw material information acquisition department 112 Granulation condition acquisition unit 113 Particle size distribution estimation section 114 Guidance information acquisition unit

Claims

1. A method for estimating a particle size distribution of granulated particles using a granulated particle manufacturing apparatus including a granulator that granulates granulated particles from a sintering raw material containing a plurality of raw materials, comprising: A step of acquiring granulation conditions including a blending ratio of the plurality of raw materials contained in the sintering raw material and a moisture content of the sintering raw material when the granulator granulates the granulated particles; Calculating parameters of a distribution function that fits to a particle size distribution of the granulated particles granulated by the granulator based on the granulation conditions; estimating the particle size distribution using the distribution function and the parameters; Including, The step of calculating the parameters includes: Calculating the parameters using a multiple regression model; The multiple regression model uses the blending ratio and the water content as explanatory variables and the parameters as objective variables, or Calculating the parameters using a trained machine learning model; The machine learning model has the blending ratio and the moisture content as input and the parameters as output, thereby estimating a particle size distribution of granulated particles.

2. The method for estimating a particle size distribution of granulated particles according to claim 1 , wherein the distribution function is a distribution function that is distributed only in a first quadrant.

3. The method for estimating a particle size distribution of granulated particles according to claim 1 , wherein the distribution function is a Rosin-Rammler distribution function.

4. The method for estimating a particle size distribution of granulated particles according to claim 1 , wherein the plurality of raw materials include an iron-containing raw material and coke fines.

5. The method for estimating a particle size distribution of granulated particles according to claim 1 , wherein the granulation conditions further include at least one of a space factor of the granulator, a rotation speed of the granulator, and an estimated residence time in the granulator.

6. The method for estimating a particle size distribution of granulated particles according to claim 1 , further comprising a step of calculating the granulation conditions for making the particle size distribution of the granulated particles a target particle size distribution.

7. A method for producing granulated particles, comprising the steps of: producing the granulated particles using the granulation conditions for making the particle size distribution of the granulated particles a target particle size distribution, the target particle size distribution being calculated by the method for estimating particle size distribution of granulated particles according to claim 6.

8. A granulator that granulates granulated particles from a sintering raw material containing a plurality of raw materials; A control device that estimates a particle size distribution of the granulated particles produced by the granulator; Equipped with The control device includes: Acquire granulation conditions including a blending ratio of the plurality of raw materials contained in the sintering raw material and a moisture content of the sintering raw material when the granulator granulates the granulated particles; Calculating parameters of a distribution function that fits to a particle size distribution of the granulated particles granulated by the granulator based on the granulation conditions; estimating the particle size distribution using the distribution function and the parameters; When calculating the parameters, the control device Calculating the parameters using a multiple regression model; The multiple regression model uses the blending ratio and the water content as explanatory variables and the parameters as objective variables, or Calculating the parameters using a trained machine learning model; The machine learning model has the blending ratio and the moisture content as input and the parameters as output, of the granulated particle manufacturing apparatus.

Images