Method for estimating particle size distribution of granulated particles, method for manufacturing granulated particles, and apparatus for manufacturing granulated particles

Abstract

A method for estimating the particle size distribution of a particle is a method for estimating the particle size distribution of a particle using a particle manufacturing apparatus (1) equipped with an aggregator (40) that aggregates a particle from a sintering raw material containing a plurality of raw materials. The particle size distribution estimation method includes a step of obtaining an aggregation condition including a mixing ratio of a plurality of raw materials included in the sintering raw material and a moisture content of the sintering raw material when the aggregator (40) aggregates the particle; a step of calculating parameters of a distribution function that fits the particle size distribution of the particle aggregated by the aggregator (40) based on the aggregation condition; and a step of estimating the particle size distribution using the distribution function and parameters.

Description

Technology Field

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

[0002] In the sintering ore manufacturing process, sintering raw materials, including iron ore, pulverized coke, and CaO (calcium oxide), are not used as they are but are aggregated into granular particles before use. Granular particles are particles formed by aggregating the sintering raw materials into granular forms using an aggregator such as a drum mixer.

[0003] After the sintering raw materials are aggregated into coarse particles, they are loaded onto the pallets of a sintering machine used to produce sintered ore. In the sintering process using a sintering machine, it is important to improve permeability. Since permeability in a sintering machine depends on the size and porosity of the coarse particles, it is required to estimate the particle size distribution of the coarse particles with high precision.

[0004] For example, Patent Document 1 discloses an apparatus for estimating the distribution of a target raw material in the height direction in a sintered raw material layer based on target raw material particle size distribution information indicating the distribution of the particle size of a target raw material, target raw material presence information indicating the distribution of the particle size of a target raw material in a pseudo-particle (assemblaged particle) assembled by a plurality of raw materials including the target raw material, and pseudo-particle distribution information indicating the distribution of the particle size of the pseudo-particle in the height direction of a sintered raw material layer in which the pseudo-particles are stacked. Prior art literature

[0005] Japanese Patent Publication No. 2020-12185 The problem to be solved

[0006] The particle size distribution of the aggregated particles depends on the mixing conditions of the raw materials and the moisture content during aggregation. The estimation method described in Patent Document 1 does not take into account the mixing conditions of the raw materials and the moisture content during aggregation, so when the mixing conditions of the raw materials and the moisture content during aggregation change, it was difficult to estimate the distribution in the height direction of the target raw materials with high precision.

[0007] The object of the present disclosure is to provide a method for estimating the particle size distribution of aggregated particles, a method for manufacturing aggregated particles, and an apparatus for manufacturing aggregated particles, which can estimate the particle size distribution of aggregated particles with high precision. means of solving the problem

[0008] A method for estimating the particle size distribution of aggregated particles related to one embodiment of the present disclosure is,

[0009] A method for estimating the particle size distribution of granulated particles using a granulated particle manufacturing apparatus equipped with a granulator for granulating granulated particles from sintering raw materials comprising a plurality of raw materials,

[0010] A step of obtaining a granulation condition including the mixing ratio of the plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the granulator granulates the granulated particles, and

[0011] A step of calculating parameters of a distribution function that fits the particle size distribution of the assembled particles assembled by the assembly machine based on the above assembly conditions, and

[0012] It includes a step of estimating the particle size distribution using the above distribution function and the above parameters.

[0013] A method for manufacturing aggregated particles related to one embodiment of the present disclosure manufactures aggregated particles using the particle size distribution estimation method.

[0014] An assembly particle manufacturing device related to one embodiment of the present disclosure is,

[0015] A granulator for granulating particles from sintering raw materials containing multiple raw materials, and

[0016] The assembly machine comprises a control device for estimating the particle size distribution of the assembled particles assembled by the assembly machine, and

[0017] The above control device is,

[0018] A granulation condition is obtained that includes the mixing ratio of the plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the granulator granulates the granulated particles, and

[0019] Based on the above assembly conditions, parameters of a distribution function that fits the particle size distribution of the assembled particles assembled by the assembly machine are calculated, and

[0020] The particle size distribution is estimated using the above distribution function and the above parameters. Effects of the invention

[0021] According to the method for estimating the particle size distribution of aggregated particles, the method for manufacturing aggregated particles, and the apparatus for manufacturing aggregated particles related to the present disclosure, the particle size distribution of aggregated particles can be estimated with high precision. Brief explanation of the drawing

[0022] FIG. 1 is a schematic diagram showing an example of the configuration of an assembled particle manufacturing apparatus related to one embodiment of the present disclosure. FIG. 2 is a schematic diagram illustrating an example of the configuration of a control device related to one embodiment of the present disclosure. FIG. 3 is a flowchart showing a sequence example of a method for estimating the particle size distribution of assembled particles related to one embodiment of the present disclosure. Figure 4 is a diagram showing the measured values ​​of the particle size distribution in the example. Figure 5 is a diagram showing the correlation between the measured and calculated values ​​of the particle size distribution in the example. Specific details for implementing the invention

[0023] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings.

[0024] FIG. 1 is a schematic diagram showing an example of the configuration of an assembly particle manufacturing apparatus (1) related to one embodiment of the present disclosure.

[0025] The assembly particle manufacturing device (1) is equipped with a control device (10), a plurality of mixing tanks (20-1 to 20-3), a water supply device (30), and an assembly machine (40).

[0026] Subsequently, regarding the mixing tanks (20-1 to 20-3), if there is no need to distinguish them specifically, they may be simply referred to and described as “mixing tanks (20).” Furthermore, in this embodiment, the case in which the agglomerated particle manufacturing device (1) is equipped with three mixing tanks (20-1 to 20-3) is described as an example, but the number of mixing tanks (20) equipped by the agglomerated particle manufacturing device (1) is not limited to three. The number of mixing tanks (20) equipped by the agglomerated particle manufacturing device (1) may be two, or four or more.

[0027] The device for manufacturing aggregated particles (1) is a device for manufacturing aggregated particles from a sintering 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, pulverized coke, etc. The iron-containing raw material may be, for example, iron ore. The CaO-containing raw material may be, for example, limestone. In this embodiment, the case in which the plurality of raw materials included in the sintering raw material are an iron-containing raw material, a CaO-containing raw material, and pulverized coke is described as an example.

[0028] The aggregate particles produced by the aggregate particle manufacturing device (1) are, for example, returned to a sintering machine and become sintered ore by being sintered in the sintering machine. The sintered ore is used in the ironmaking process.

[0029] The control device (10) can communicate with the mixing tank (20-1 to 20-3), the water supply device (30), and the assembly machine (40). The control device (10) controls the mixing tank (20-1 to 20-3), the water supply device (30), and the assembly machine (40). In FIG. 1, the dashed line connecting the control device (10) and the mixing tank (20-1 to 20-3), the water supply device (30), and the assembly machine (40) indicates that the control device (10) can communicate with the mixing tank (20-1 to 20-3), the water supply device (30), and the assembly machine (40), and that the control device (10) can control the mixing tank (20-1 to 20-3), the water supply device (30), and the assembly machine (40).

[0030] Details regarding the configuration and function of the control device (10) will be described later.

[0031] The mixing tank (20) supplies raw materials included in the sintering raw materials to the agglomerator (40). The amount of raw materials supplied by the mixing tank (20) to the agglomerator (40) is controlled by the control device (10).

[0032] The mixing tanks (20-1 to 20-3) each supply different types of raw materials to the granulator (40). In the example shown in FIG. 1, the mixing tank (20-1) supplies iron-containing raw materials to the granulator (40). The mixing tank (20-2) supplies CaO-containing raw materials to the granulator (40). The mixing tank (20-3) supplies powdered coke to the granulator (40).

[0033] The moisture supply device (30) supplies moisture to the assembly machine (40) to be added to the raw materials when the mixing tank (20-1 to 20-3) supplies the raw materials to the assembly machine (40). The amount of moisture supplied by the moisture supply device (30) to the assembly machine (40) is controlled by the control device (10).

[0034] The aggregator (40) aggregates aggregate particles from a sintering raw material containing a plurality of raw materials. Here, the sintering raw material includes a plurality of raw materials supplied from a mixing tank (20-1 to 20-3) and water supplied from a water supply device (30). In the case of the example shown in FIG. 1, the sintering raw material supplied to the aggregator (40) includes an iron-containing raw material, a CaO-containing raw material, pulverized coke, and water.

[0035] The assembler (40) can be any assembler capable of manufacturing assembled particles, for example, a drum mixer.

[0036] The aggregated particles assembled by the aggregator (40) are, for example, returned to a sintering machine and used as raw materials for manufacturing sintered ore.

[0037] FIG. 2 is a schematic diagram showing an example of the configuration of a control device (10) related to one embodiment of the present disclosure. The control device (10) may be a general-purpose computer such as a workstation or a personal computer, or a dedicated computer configured to function as a control device (10) of an assembly particle manufacturing device (1).

[0038] The control device (10) is equipped with a control unit (11), an input unit (12), an output unit (13), a memory unit (14), and a communication unit (15).

[0039] The control unit (11) includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or a GPU (graphics processing unit), or a dedicated processor specialized for a specific processing. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0040] The control unit (11) reads programs, data, etc. stored in the memory unit (14) and executes various functions. The control unit (11) controls the mixing tank (20), the water supply device (30), and the assembly machine (40).

[0041] The control unit (11) can function as a raw material information acquisition unit (111), an assembly condition acquisition unit (112), a particle size distribution estimation unit (113), and a guidance information acquisition unit (114) by executing a program read from the memory unit (14).

[0042] The processing performed by the raw material information acquisition unit (111), assembly condition acquisition unit (112), particle size distribution estimation unit (113), and guidance information acquisition unit (114) will be described later.

[0043] The input unit (12) includes one or more input interfaces that detect user input and acquire input information based on user operation. The input unit (12) includes, for example, a physical key, a capacitive key, a touch screen formed integrally with the display of the output unit (13), or a microphone that receives voice input.

[0044] The output unit (13) includes one or more output interfaces that output information to notify the user. The output unit (13) includes, for example, a display that outputs information as an image, a speaker that outputs information as a voice, 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.

[0045] The memory unit (14) is, for example, a flash memory, a hard disk, an optical memory, etc. Part of the memory unit (14) may be outside the control unit (10). In this case, part of the memory unit (14) may be a hard disk, a memory card, etc. connected to the control unit (10) through any interface.

[0046] The memory unit (14) stores programs for the control unit (11) to execute each function, data used by the program, etc.

[0047] 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) can communicate with other terminal devices, etc. through the communication unit (15).

[0048] Next, the processing performed by the raw material information acquisition unit (111), assembly condition acquisition unit (112), particle size distribution estimation unit (113), and guidance information acquisition unit (114) is described.

[0049] The raw material information acquisition unit (111) acquires information regarding the raw materials supplied by each mixing tank (20) to the agglomerator (40). The raw material information acquisition unit (111) acquires information such as the components of the raw materials, the particle size of the raw materials, and the mixing amount of the raw materials. The information on the components of the raw materials is information on the composition of the components of the raw materials. The information on the particle size of the raw materials is information indicating the size of the granules of the raw materials. The information on the mixing amount of the raw materials is information indicating the amount of raw materials supplied by the mixing tank (20) to the agglomerator (40).

[0050] In the case of the example shown in Fig. 1, the raw material information acquisition unit (111) acquires information on the composition of the raw material, the particle size of the raw material, and the amount of the raw material for each of the iron-containing raw material, the CaO-containing raw material, and the powdered coke supplied by the mixing tank (20-1 to 20-3) to the granulator (40).

[0051] The raw material information acquisition unit (111) can acquire information regarding the raw materials supplied by each mixing tank (20) to the assembly machine (40) through input operation by the operator to the input unit (12). Additionally, the raw material information acquisition unit (111) may acquire information regarding the raw materials supplied by each mixing tank (20) to the assembly machine (40) by receiving information input by the operator to another terminal device through the communication unit (15). Additionally, the raw material information acquisition unit (111) may acquire information regarding the mixing amount of the raw materials from the set value set in the mixing tank (20).

[0052] The assembly condition acquisition unit (112) acquires information regarding the raw materials supplied by each mixing tank (20) to the assembly machine (40) from the raw material information acquisition unit (111), including the composition of the raw materials, the particle size of the raw materials, and the amount of the raw materials mixed. Based on the information regarding the amount of each raw material mixed obtained, the assembly condition acquisition unit (112) calculates the mixing ratio of multiple raw materials included in the sintering raw materials.

[0053] The assembly condition acquisition unit (112) acquires information on the moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particles. The moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particles is obtained from the moisture content of each raw material and the moisture supplied to the assembly machine (40) from the moisture supply device (30). The moisture content of each raw material is measured, for example, using an infrared moisture meter. The assembly condition acquisition unit (112) can acquire the information on the moisture content by inputting it to the input unit (12) by an operator. Additionally, the assembly condition acquisition unit (112) may acquire the information on the moisture content by receiving the information input by the operator to another terminal device through the communication unit (15). Additionally, the assembly condition acquisition unit (112) may acquire the information on the moisture content from a set value set in the moisture supply device (30).

[0054] The assembly condition acquisition unit (112) acquires information regarding the assembly machine (40), such as the fill rate of the assembly machine (40), the rotational speed of the assembly machine (40), and the estimated residence time in the assembly machine (40). The assembly condition acquisition unit (112) can acquire information regarding the assembly machine (40) by inputting it to the input unit (12) by an operator. Additionally, the assembly condition acquisition unit (112) may acquire information regarding the assembly machine (40) by receiving information input by an operator to another terminal device through the communication unit (15). Additionally, the assembly condition acquisition unit (112) may acquire information regarding the assembly machine (40) from a set value set in the assembly machine (40).

[0055] The assembly condition acquisition unit (112) outputs the acquired assembly condition to the particle size distribution estimation unit (113). The assembly condition that the assembly condition acquisition unit (112) outputs to the particle size distribution estimation unit (113) includes, at least, the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particles. The assembly condition may additionally include information on the composition of the raw material, the particle size of the raw material, the packing ratio of the assembly machine (40), the rotational speed of the assembly machine (40), and the estimated residence time in the assembly machine (40).

[0056] The particle size distribution estimation unit (113) estimates the particle size distribution of the assembled particles assembled by the assembly machine (40) based on the assembly conditions acquired from the assembly condition acquisition unit (112). First, the particle size distribution estimation unit (113) calculates the parameters of a distribution function that fits the particle size distribution of the assembled particles assembled by the assembly machine (40) based on the assembly conditions acquired from the assembly condition acquisition unit (112). Subsequently, the particle size distribution estimation unit (113) substitutes the calculated parameters into a distribution function that fits the particle size distribution of the assembled particles assembled by the assembly machine (40), and estimates the particle size distribution of the assembled particles assembled by the assembly machine (40) using the distribution function with the parameters substituted.

[0057] The particle size distribution estimation unit (113) can calculate the parameters by using a parameter estimation model corresponding to each parameter when calculating each parameter of a distribution function that fits the particle size distribution of the assembled particles. The parameter estimation model may be stored in a memory unit (14).

[0058] The parameter estimation model can be a multiple regression model, a trained machine learning model, etc.

[0059] If the parameter estimation model is a multiple regression model, for example, the mixing ratio of multiple raw materials included in the sintering raw material and the moisture content of the sintering raw material when the aggregator (40) aggregates the aggregate particles may be explanatory variables, and one of the parameters of the distribution function may be the objective variable.

[0060] If the parameter estimation model is a machine learning model, for example, it may be a machine learning model that has completed learning, taking as input the mixing ratio of multiple raw materials included in the sintering raw material and the moisture content of the sintering raw material when the aggregator (40) aggregates the aggregate particles, and taking as output one of each parameter of the distribution function.

[0061] Such multiple regression models or machine learning models can be stored in memory units (14) by using a data set in which the mixing ratio of multiple raw materials included in the sintering raw materials, the moisture content of the sintering raw materials when the aggregator (40) aggregates the aggregate particles, and the actual values ​​of the parameters of the distribution function are set as one set. Additionally, the machine learning model that has completed learning can be machine learned in advance and stored in memory units (14) by using a data set in which the mixing ratio of multiple raw materials included in the sintering raw materials, the moisture content of the sintering raw materials when the aggregator (40) aggregates the aggregate particles, and the actual values ​​of one of the parameters of the distribution function are set as one set. The actual values ​​of the parameters of the distribution function can be obtained by fitting the distribution function to the curve of the particle size distribution of the aggregate particles, the particle size distribution of which is already known.

[0062] The distribution function that the particle size distribution estimator (113) fits to the particle size distribution of the coarse particles can be a Rosin-Rammler distribution function, a normal distribution function, a two-term distribution function, etc. If the distribution function is made to be distributed only in the first quadrant, it is possible to prevent negative values ​​from appearing in the distribution of the coarse particles. For example, the Rosin-Rammler distribution function is a distribution function distributed only in the first quadrant.

[0063] When the distribution function is a rosin-Lammer distribution function, the rosin-Lammer distribution function can be expressed as shown in the following equation (1).

[0064] [Mathematical Formula 1]

[0065]

[0066] However, in Equation (1), d p represents the particle size of the coarse particles, β represents the particle size characteristic index, and n represents the number of homogeneities.

[0067] If the distribution function is a rosin-Lammer distribution function as shown in Equation (1), the particle size distribution estimator (113) calculates β and n as parameters as shown in Equation (1).

[0068] The particle size distribution estimation unit (113) can estimate the particle size distribution of the assembled particles assembled by the assembler (40) by calculating parameters β and n and substituting parameters β and n into the rosin-Lammer distribution function shown in Equation (1).

[0069] The particle size distribution estimation unit (113) can output the estimated particle size distribution of the assembled particles to the output unit (13) and display it on the output unit (13).

[0070] When the distribution function is a normal distribution function, the particle size distribution estimator (113) calculates the mean, standard deviation, skewness, and kurtosis as parameters.

[0071] The particle size distribution estimation unit (113) can estimate the particle size distribution of the assembled particles assembled by the assembler (40) by calculating the mean, standard deviation, skewness, and kurtosis, which are parameters of the normal distribution function, and substituting the mean, standard deviation, skewness, and kurtosis into the normal distribution function.

[0072] When the distribution function is a two-term distribution function, the particle size distribution estimator (113) calculates the probability P and the number of trials N as parameters.

[0073] The particle size distribution estimation unit (113) can estimate the particle size distribution of the assembled particles assembled by the assembler (40) by calculating the probability P and the number of trials N, which are parameters of the two-term distribution function, and substituting the probability P and the number of trials N into the two-term distribution function.

[0074] The guidance information acquisition unit (114) does not estimate the particle size distribution of the assembled particles assembled by the assembler (40), but rather calculates assembly conditions to make the particle size distribution of the assembled particles assembled by the assembler (40) into a target particle size distribution.

[0075] The guidance information acquisition unit (114) calculates assembly conditions based on the input parameters when parameters for achieving a target particle size distribution are input. For example, if the distribution function fitting the particle size distribution is a Rosin-Lammer distribution function, parameters β and n of the Rosin-Lammer distribution function corresponding to the target particle size distribution are input to the guidance information acquisition unit (114). The guidance information acquisition unit (114) inputs various assembly conditions, for example, into a parameter estimation model and determines whether the output parameters match the input parameters. The guidance information acquisition unit (114) performs this operation for parameters β and n, and specifies the assembly conditions for which it is determined that the output parameters match the input parameters for both parameters β and n as assembly conditions that can achieve a target particle size distribution. In this way, the guidance information acquisition unit (114) calculates assembly conditions based on input parameters β and n. The assembly conditions calculated by the guidance information acquisition unit (114) may include, for example, the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particles.

[0076] The guidance information acquisition unit (114) can acquire parameters β and n by input operation to the input unit (12) by an operator. Additionally, the guidance information acquisition unit (114) may acquire parameters β and n by receiving information input by an operator to another terminal device through the communication unit (15).

[0077] The guidance information acquisition unit (114) outputs the calculated assembly conditions to the output unit (13).

[0078] The output unit (13) outputs assembly conditions obtained from the guidance information acquisition unit (114). For example, if the output unit (13) includes a display, the output unit (13) displays assembly conditions obtained from the guidance information acquisition unit (114) on the display.

[0079] An operator who acknowledges the assembly conditions displayed on the display can manufacture assembled particles with a target particle size distribution by setting the assembly conditions and operating the assembly particle manufacturing device (1).

[0080] Alternatively, the guidance information acquisition unit (114) may automatically set the calculated assembly conditions as assembly conditions when operating the assembly particle manufacturing device (1). By doing so, the assembly particle manufacturing device (1) can automatically set assembly conditions to make the particle size distribution of the assembly particles assembled by the assembly machine (40) a target particle size distribution, and manufacture the assembly particles.

[0081] In addition, in FIG. 2, the case where the control unit (11) has the function of a guidance information acquisition unit (114) was explained as an example, but the control unit (11) does not have to have the function of a guidance information acquisition unit (114). However, if the control unit (11) has the function of a guidance information acquisition unit (114), it becomes easier to manufacture assembled particles with a target particle size distribution, so it is preferable for the control unit (11) to have the function of a guidance information acquisition unit (114).

[0082] Referring to the flowchart shown in FIG. 3, a method for estimating particle size distribution performed by the assembly particle manufacturing device (1) related to the present embodiment will be described.

[0083] In step S101, the control unit (11) of the control device (10) obtains assembly conditions including the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the aggregator (40) aggregates the aggregate particles.

[0084] In step S102, the control unit (11) calculates parameters of a distribution function that fits the particle size distribution of the assembled particles assembled by the assembler (40) based on the acquired assembly conditions. The distribution function may be a rosin-lamber distribution function, a normal distribution function, a two-term distribution function, etc.

[0085] In step S103, the control unit (11) substitutes the calculated parameters into a distribution function that fits the particle size distribution of the assembled particles, and estimates the particle size distribution of the assembled particles assembled by the assembler (40) using said distribution function. The control unit (11) outputs the estimated particle size distribution of the assembled particles to the output unit (13) and can display it on the output unit (13).

[0086] (Example)

[0087] FIGS. 4 and FIGS. 5 show examples of when the particle size distribution is estimated using an aggregate particle manufacturing device (1). FIG. 4 is a table showing the particle size distribution of aggregate particles and the carbon ratio for each particle size when aggregate particles are manufactured under various conditions. FIG. 5 is a graph comparing the measured value of the particle size distribution of aggregate particles with the calculated value of the particle size distribution estimated using an aggregate particle manufacturing device (1).

[0088] 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 assembly machine (40). In addition, a total of 8 kg of sintered raw materials mixed at various mixing ratios were used. A moisture supply device (30) added a predetermined amount of moisture to the raw materials supplied from the mixing tank (20). In addition, a rosin-Lammer distribution function was used as the distribution function. Furthermore, as a parameter estimation model, a machine learning model that takes the mixing ratio of raw materials A, B, C and pulverized coke, the particle size of pulverized coke, and the moisture content as inputs and outputs a parameter β, and a machine learning model (SPSS manufactured by IBM) that takes the mixing ratio of raw materials A, B, C and pulverized coke, the particle size of pulverized coke, and the moisture content as inputs and outputs a parameter n were used to obtain the parameters β and n of the rosin-Lammer distribution function.

[0089] As shown in Fig. 4, measurements were performed under 24 conditions from T1 to T24. Fig. 4 shows the mixing ratio, pulverized coke particle size, and moisture as conditions. In addition, the particle size distribution of coarse particles is shown as a measured value.

[0090] 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 with a different brand from raw material A. Raw material C is iron ore from Australia. In addition, regarding the particle size distribution of pulverized coke, "-2 mm" indicates the proportion of pulverized coke with a diameter of less than 2 mm. "-1 mm" indicates the proportion of pulverized coke with a diameter of less than 1 mm. In addition, regarding the particle size distribution of coarse particles, "+8.0" indicates the proportion of coarse particles with a diameter greater than 8.0 mm. "2.8-8.0" indicates the proportion of coarse particles with a diameter of 2.8 mm or more and 8.0 mm or less. "-2.8" indicates the proportion of coarse particles with a diameter less than 2.8 mm. In addition, regarding the carbon ratio by particle size, "+8.0" indicates the proportion of carbon with a diameter greater than 8.0 mm. "2.8-8.0" indicates the proportion of carbon with a diameter of 2.8 mm or more and 8.0 mm or less. "-2.8" indicates the proportion of carbon with a diameter of less than 2.8 mm.

[0091] A machine learning model was trained using the performance data shown in Figure 4 to generate a trained machine learning model, and parameters β and n were obtained using this. Then, the particle size of the assembled particles was estimated using the rosin-Lammer distribution function of parameters β and n.

[0092] FIG. 5 is a graph showing the correlation between the calculated value and the measured value of the particle size distribution estimated using the aggregate particle manufacturing device (1). FIG. 5 shows three graphs. From the top, there is a graph comparing the measured value and the calculated value of aggregate particles with a diameter greater than 8.0 mm, a graph comparing the measured value and the calculated value of aggregate particles with a diameter between 2.8 mm and 8.0 mm, and a graph comparing the measured value and the calculated value of aggregate particles with a diameter less than 2.8 mm. The horizontal axis represents the measured value. The vertical axis represents the calculated value.

[0093] Referring to FIG. 5, the measured values ​​and the calculated values ​​of the particle size distribution estimated using the agglomerated particle manufacturing device (1) show a high correlation, indicating that the agglomerated particle manufacturing device (1) estimates the particle size distribution with high precision. In the graph of agglomerated particles with a diameter greater than 8.0 mm, the coefficient of determination (R 2 ) is, R 2 = 0.7959. For the graph of coarse particles with a diameter of 2.8 mm or more and 8.0 mm or less, the coefficient of determination is R 2 = 0.8056. In the graph for coarse particles with a diameter of less than 2.8 mm, the coefficient of determination is R 2 = 0.9122.

[0094] As described above, in the assembly particle manufacturing apparatus (1) related to the present embodiment and the method for estimating the particle size distribution of an assembly particle using the assembly particle manufacturing apparatus (1) related to the present embodiment, the control device (10) obtains assembly conditions including the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particle, and based on the obtained assembly conditions, calculates parameters of a distribution function that fits the particle size distribution of the assembly particle assembled by the assembly machine (40), and estimates the particle size distribution using the calculated parameters and the distribution function. In this way, since the particle size distribution of the assembly particle is estimated based on assembly conditions including the mixing ratio of a plurality of raw materials and the moisture content of the sintering raw material, the assembly particle manufacturing apparatus (1) related to the present embodiment can estimate the particle size distribution of the assembly particle by considering the mixing ratio of a plurality of raw materials and the moisture content of the sintering raw material. Accordingly, the particle size distribution of the agglomerated particles using the agglomerated particle manufacturing device (1) related to the present embodiment and the method for estimating the particle size distribution of the agglomerated particles using the agglomerated particle manufacturing device (1) related to the present embodiment can estimate the particle size distribution of the agglomerated particles with high precision after considering the mixing ratio of a plurality of raw materials and the moisture content of the sintering raw materials.

[0095] The present disclosure is not limited to the embodiments described above. For example, a plurality of blocks described in the block diagram may be integrated, or a single block may be divided. Instead of executing a plurality of steps described in the flowchart in a chronological order according to the description, they may be executed in parallel or in a different order depending on the processing power of the device executing each step, or as necessary. Furthermore, modifications are possible without departing from the spirit of the present disclosure.

[0096] For example, in the embodiment described above, the particle size distribution estimation unit (113) was explained as an example of calculating parameters of a distribution function based on the mixing ratio of multiple raw materials included in the sintering raw material and the moisture content of the sintering raw material when the aggregator (40) aggregates the aggregated particles. However, the particle size distribution estimation unit (113) can calculate parameters of a distribution function based on the particle size of the pulverized coke in addition to the mixing ratio and moisture content of the multiple raw materials. That is, the aggregation conditions may additionally include the particle size of the pulverized coke in addition to the mixing ratio and moisture content of the multiple raw materials. By considering the particle size of the pulverized coke, the particle size distribution estimation unit (113) can estimate the particle size distribution of the aggregated particles with higher precision. Furthermore, the particle size distribution estimation unit (113) may calculate parameters of a distribution function by considering the particle size of other raw materials instead of, or in addition to, the particle size of the pulverized coke. In addition, the particle size distribution estimation unit (113) may calculate parameters of the distribution function based on the information of each raw material's components in addition to the mixing ratio and moisture content of the multiple raw materials.

[0097] For example, in the embodiment described above, the particle size distribution estimation unit (113) was explained as an example of calculating parameters of a distribution function based on the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the aggregator (40) aggregates the aggregated particles. However, the particle size distribution estimation unit (113) can calculate parameters of a distribution function based additionally on at least one of the packing ratio of the aggregator (40), the rotational speed of the aggregator (40), and the estimated residence time in the aggregator (40), in addition to the mixing ratio of the plurality of raw materials and the moisture content. That is, the aggregation conditions may additionally include at least one of the packing ratio of the aggregator (40), the rotational speed of the aggregator (40), and the estimated residence time in the aggregator (40), in addition to the mixing ratio of the plurality of raw materials and the moisture content. By considering the packing rate of the assembly machine (40), the rotational speed of the assembly machine (40), and the estimated residence time in the assembly machine (40), the particle size distribution estimation unit (113) can estimate the particle size distribution of the assembled particles with higher precision.

[0098] For example, in the embodiment described above, the case where the sintering raw material includes an iron-containing raw material, a CaO-containing raw material, and pulverized coke was explained as an example; however, the sintering raw material only needs to include an iron-containing raw material and pulverized coke. That is, the sintering raw material does not need to include a CaO-containing raw material.

[0099] For example, in the embodiment described above, the guidance information acquisition unit (114) was explained as an example of calculating assembly conditions including the mixing ratio of a plurality of raw materials included in the sintering raw material and the moisture content of the sintering raw material when the assembly machine (40) assembles the assembly particles. However, the assembly conditions calculated by the guidance information acquisition unit (114) may additionally include the particle size of the powdered coke in addition to the mixing ratio of the plurality of raw materials and the moisture content. Explanation of the symbols

[0100] 1: Assembly particle manufacturing device 10: Control unit 11: Control unit 12 : Input section 13 : Output section 14 : Memory 15 : Communications Department 20 : Mixing tank 30: Moisture supply device 40 : Assembler 111 : Raw Material Information Acquisition Department 112 : Assembly Condition Acquisition Section 113 : Particle size distribution estimation section 114: Guidance Information Acquisition Department

Claims

Claim 1 A method for estimating the particle size distribution of a granulated particle using a granulated particle manufacturing apparatus equipped with a granulator for granulating granulated particles from a sintering raw material comprising a plurality of raw materials, comprising: a step of obtaining a granulation condition including a mixing ratio of the plurality of raw materials included in the sintering raw material and a moisture content of the sintering raw material when the granulator granulates the granulated particle; a step of calculating a parameter of a distribution function that fits the particle size distribution of the granulated particle granulated by the granulator based on the granulation condition; and a step of estimating the particle size distribution using the distribution function and the parameter, wherein the distribution function is a distribution function distributed only in the first quadrant, and the step of calculating the parameter calculates the parameter using a multiple regression model, wherein the multiple regression model takes the mixing ratio and the moisture content as explanatory variables and the parameter as an objective variable, or calculates the parameter using a machine learning model that has completed training, wherein the machine learning model takes the mixing ratio and the moisture content as inputs and the parameter as an output. Claim 2 A method for estimating the particle size distribution of assembled particles, wherein, in claim 1, the distribution function is a rosin-Lammer distribution function. Claim 3 A method for estimating the particle size distribution of coarse particles, wherein the plurality of raw materials includes iron-containing raw materials and pulverized coke. Claim 4 A method for estimating the particle size distribution of assembled particles according to claim 1, wherein the assembly conditions further include at least one of the packing rate of the assembly machine, the rotational speed of the assembly machine, and the estimated residence time in the assembly machine. Claim 5 A method for estimating the particle size distribution of a particle according to claim 1, further comprising a step of calculating the aggregation conditions to make the particle size distribution of the aggregated particle into a target particle size distribution. Claim 6 A method for manufacturing aggregated particles, wherein the aggregated particles are manufactured using the aggregated conditions for making the aggregated particle size distribution calculated in the method for estimating the particle size distribution of aggregated particles described in claim 5 into a target particle size distribution. Claim 7 An apparatus for manufacturing aggregated particles, comprising: an aggregator for aggregating aggregated particles from a sintering raw material containing a plurality of raw materials; and a control device for estimating the particle size distribution of the aggregated particles aggregated by the aggregator; wherein the control device acquires aggregation conditions including a mixing ratio of the plurality of raw materials included in the sintering raw material and a moisture content of the sintering raw material when the aggregator aggregates aggregated particles; wherein, based on the aggregation conditions, the control device calculates parameters of a distribution function that fits the particle size distribution of the aggregated particles aggregated by the aggregator; wherein the particle size distribution is estimated using the distribution function and the parameters; wherein the distribution function is a distribution function distributed only in the first quadrant; wherein, when calculating the parameters, the control device calculates the parameters using a multiple regression model, wherein the multiple regression model uses the mixing ratio and the moisture content as explanatory variables and the parameters as objective variables, or calculates the parameters using a machine learning model that has completed training, wherein the machine learning model takes the mixing ratio and the moisture content as inputs and the parameters as outputs. Claim 8 delete

Images