Particle size class determination device, image size determination support device, method and program

Abstract

To provide a particle diameter class determination device, method and program which can determine a particle diameter class of a wider determination object, and an image size determination support device, method and program which support determination when determining the size of an image used for determination of the particle diameter class.SOLUTION: A particle diameter class determination device D according to the present invention acquires an image obtained by imaging a plurality of particles including particles with different particle diameters, and obtains each probability of each of a plurality of particle diameter classes in the acquired image with a machine-learned machine learning model that outputs such a probability that an input image is classified into the particle diameter class for each of the plurality of particle diameter classes when the particle diameters are classified as the plurality of particle diameter classes in mutually-different ranges. Here, any of respective boundary values in the ranges is a particle diameter value of a determination target, and a size of the image input to the machine learning model is a size obtained by multiplying the particle diameter value of the determination target by a prescribed constant.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention provides a particle size class determination device for determining the particle size class of a measurement object when particle sizes are divided into a plurality of particle size classes each having a different range; Na The present invention also relates to an image size determination support device, an image size determination support method, and an image size determination support program that support the determination of the size of an image used to determine the particle size class. [Background technology]

[0002] In the production of steel using blast furnaces, not only mined iron ore but also sintered ore is used. Sintered ore particles are pseudo-particles consisting of core powders, such as iron ore, limestone, and coke, and fine particles of these particles attached to the surface of the core powder. For example, fine ore with a wide particle size distribution, with a maximum diameter of approximately 15 mm, is used as raw material. Fine ore particles of less than 1 mm in size are attached to fine ore particles of 1 mm or larger in size, resulting in sintered ore particles with an average diameter of approximately 3 to 5 mm, which is produced through the so-called sintering process. In this sintering process, heat is transferred to a stack of raw materials stacked in layers by heating from above and drawing air below. Therefore, gaps are required within the stack to allow air to circulate. Sintered ore particles smaller than 2 mm typically impair air permeability and reduce sinter productivity. Therefore, there is a need to measure particle size and particle size distribution to avoid the generation of particles that impair air permeability during the sintering process.

[0003] A technique for measuring this particle size distribution is disclosed, for example, in Patent Document 1. The soil particle size distribution estimation method disclosed in Patent Document 1 estimates the particle size distribution of sampled soil using a trained model obtained by machine learning using artificial intelligence installed in a server, using as training data a large number of images of each single-particle size soil that has been sieved from raw soil and classified into multiple particle sizes, in which the image of each single-particle size soil that serves as training data is taken with a camera at a predetermined shooting distance of the surface of the single-particle size soil that has been spread evenly to a thickness that leaves no voids in a planar view, and the images are linked to the proportions of each classified particle size. The particle size distribution of the sampled soil is estimated by inputting the image taken with the camera at the predetermined shooting distance of the surface of the sampled soil that has been spread evenly to a thickness that leaves no voids in a planar view, into the trained model, and outputting the proportions of each classified particle size of the sampled soil. Then, paragraph

[0029] states, "Furthermore, soil properties also include moisture content and particle composition, but these properties can be excluded from the scope of the present invention. In this embodiment, naturally dried soil generated on site is used as the raw soil, and this raw soil is sieved to obtain single-grain particle size soils of each classified particle size that serve as training data. In addition, naturally dried raw soil generated on site that is in a state where soils of various particle sizes remain mixed is used as the collected soil (locally generated soil) for which the particle size distribution is to be estimated, and the particle size distribution can be estimated." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-117625 Summary of the Invention [Problem to be solved by the invention]

[0005] As described in paragraph

[0029] of the patent, the soil particle size distribution estimation method disclosed in Patent Document 1 can estimate particle size distribution when the measurement target is in a naturally dried state. Therefore, the soil particle size distribution estimation method disclosed in Patent Document 1 is considered unsuitable for measurement of targets that are not in a naturally dried state. In particular, in the sintering process, raw materials are mixed with water, kneaded, and then baked. Therefore, the soil particle size distribution estimation method disclosed in Patent Document 1 is considered unsuitable for measuring the particle size distribution of such materials. Furthermore, because the particles of sintered ore produced in the sintering process are pseudoparticles, it is necessary to determine the particle size of not only the powder but also the fine powder attached to the powder. However, the soil particle size distribution estimation method disclosed in Patent Document 1 may estimate the particle size distribution based only on the powder or the fine powder.

[0006] The present invention has been made in view of the above circumstances, and its object is to provide a particle size class determination device that can determine a particle size class of a wider range of determination targets, Na Furthermore, the present invention provides an image size determination support device, an image size determination support method, and an image size determination support program that support the determination of the size of an image used to determine the particle size class. [Means for solving the problem]

[0007] After extensive investigation, the inventors have found that the above object can be achieved by the present invention. That is, a particle size class determination device according to one aspect of the present invention includes an image acquisition unit that acquires an image of a plurality of particles, including particles of different particle sizes, and a particle size class processing unit that, when an image is input and particle sizes are divided into a plurality of different ranges as a plurality of particle size classes, calculates a probability of each of the plurality of particle size classes for the image acquired by the image acquisition unit using a machine learning model (first machine learning model) that has been machine-learned and outputs, for each of the plurality of particle size classes, a probability that the input image will be classified into the corresponding particle size class. One of the boundary values ​​in the plurality of ranges is a target particle size value for determination, and the size of the image input to the machine learning model is a size obtained by multiplying the target particle size value by a predetermined constant. Preferably, in the above-described particle size class determination, the target particle size value is set to the upper limit of a range corresponding to the particle size class with the smallest particle size. Preferably, in the above-described particle size class determination, the particle size class processing unit uses the calculated probabilities as the probabilities of each particle size class for the input image.

[0008] According to the inventor's findings, when particle size classes are set to three, namely, a large particle size class for large particle sizes, a small particle size class for small particle sizes, and a medium particle size class between these, if the image size is too small, an image capturing large particle sizes will not capture the entire particle, resulting in a loss of particle outline, making it difficult to extract the particles properly. In particular, if the particles are pseudo-particles, there is a risk that fine powder (an example of a second particle, described below) attached to the core powder (an example of a first particle, described below) will be extracted, making it difficult to extract the actual pseudo-particles. On the other hand, if the image size is too large, when both large and small particles are captured in the image, the outline information of the small particles may be hidden, making it difficult to extract the particles properly. Therefore, it is believed that there is an optimal image size for the target particle size value.

[0009] The particle size class determination device uses a machine learning model to determine the particle size class of an image of a plurality of particles, and thus can determine a wider range of particle size classes by performing machine learning on images of various determination targets. Since the size of the image input to the machine learning model during this determination is a size obtained by multiplying the particle size value of the determination target by a predetermined constant, the particle size class determination device can appropriately determine the particle size class. The particle size class determination device is particularly suitable when the determination target is a pseudo particle.

[0010] In another aspect, in the particle size class determination device described above, the predetermined constant is a value greater than 7 and less than 12. Preferably, in the particle size class determination device described above, the predetermined constant is a value greater than 8 and less than 11. Preferably, in the particle size class determination device described above, the predetermined constant is 10.

[0011] According to this, a particle size class determination device can be provided in which the predetermined constant is set to a value greater than 7 and less than 12.

[0012] In another aspect, in the particle size class determination device described above, the particles are pseudo-particles comprising a first particle serving as a nucleus and a second particle attached to the surface of the first particle and smaller than the first particle. Preferably, in the particle size class determination described above, the pseudo-particles are particles of sintered ore used in blast furnaces.

[0013] This provides a particle size class determination device for determining pseudo particles. Since the particle size class determination device is used to determine the particle size class of pseudo particles, the particle size class of the pseudo particles can be determined appropriately.

[0014] In another aspect, the particle size class determination device described above further comprises an illumination unit that illuminates the plurality of particles, and the image acquisition unit is an imaging unit that generates an image.

[0015] Such a particle size class determination device further includes an illumination unit and uses an imaging unit as the image acquisition unit, so that the particle size class determination device can be used, for example, on a production line in a factory, and particle size classes can be determined during production.

[0016] According to another aspect of the present invention, an image size determination assistance device is a device for assisting in determining the size of an image to be used to determine a particle size class when particle sizes are divided into a plurality of different ranges as particle size classes, the device comprising: a first data acquisition unit that acquires a predetermined training dataset; a second data acquisition unit that acquires a predetermined size determination dataset; a machine learning unit that uses the predetermined training dataset acquired by the first data acquisition unit to train a second machine learning model to which an image is input and that outputs, for each of the plurality of particle size classes, a probability that the input image will be classified into that particle size class; and an output unit that inputs the predetermined size determination dataset acquired by the second data acquisition unit into the second machine learning model trained by the machine learning unit and outputs each probability for each of the plurality of particle size classes output from the second machine learning model trained by the machine learning unit, wherein the predetermined training dataset and the predetermined size determination dataset each comprise a plurality of data groups each comprising image data of a plurality of images, and the plurality of data groups are the plurality of data groups in the predetermined training dataset are different from one another, the plurality of images in the data group are a plurality of images including images of each of the plurality of particle size classes, and the particle size class of the image is linked to each of the plurality of images in the data group, the plurality of data groups in the predetermined size determination dataset are a plurality of images including images with different content rates of particles belonging to the particle size class with the smallest particle size, and the content rate of the image is linked to each of the plurality of images in the data group, the number of the unmachined second machine learning models is the same as the number of the plurality of data groups and is provided corresponding to each of the plurality of data groups, the machine learning unit machine-learns the unmachined second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset using the plurality of images in the data group, and the output unit outputs, for each of the plurality of data groups in the predetermined size determination dataset, an image of the same size as the image in the data group,By inputting a plurality of images in the data group into a second machine learning model that has been machine-learned by the machine learning unit using the data group in the predetermined learning dataset, the probabilities for each of the plurality of particle size classes output from the second machine learning model that has been machine-learned by the machine learning unit are output.

[0017] This image size determination assistance device outputs the probability of each of the plurality of particle size classes obtained by inputting a predetermined size determination dataset into a machine-learned second learning model. A user can determine the optimal image size from among a plurality of image sizes by referring to the output probability of each of the plurality of particle size classes and the content associated with the image. Therefore, the image size determination assistance device can effectively assist a user in determining the image size. This provides an image size determination assistance device that assists in determining the size of an image used to determine a particle size class.

[0018] In another aspect, the above-mentioned particle size class determination device further includes the above-mentioned image size determination support device, and the machine learning model that has been machine-learned is a second machine learning model that has been machine-learned by the machine learning unit.

[0019] This provides a particle size class determination device with a function to assist in determining image size. The particle size class determination device is integrated with the image size determination assistance device, so that a single device can determine the image size and determine the particle size class.

[0020] Another aspect of the present invention provides a particle size class determination method, comprising: an image acquisition step of acquiring an image of a plurality of particles including particles of different particle sizes; and a particle size class processing step of inputting an image and dividing the particle sizes into a plurality of different ranges into a plurality of particle size classes, using a machine learning model that has been machine-learned to output, for each of the plurality of particle size classes, the probability that the input image will be classified into that particle size class; wherein one of the boundary values ​​in the plurality of ranges is a particle size value to be determined; and the size of the image input to the machine learning model is a size obtained by multiplying the particle size value to be determined by a predetermined constant.

[0021] Another aspect of the present invention provides a particle size class determination program, which is a computer-executable program that includes an image acquisition step of acquiring an image of a plurality of particles including particles of different particle sizes, and a particle size class processing step of inputting an image and dividing the particle sizes into a plurality of different ranges into a plurality of particle size classes, using a machine learning model that has been machine-learned to output the probability that the input image will be classified into that particle size class for each of the plurality of particle size classes. One of the boundary values ​​in the plurality of ranges is a particle size value to be determined, and the size of the image input to the machine learning model is a size obtained by multiplying the particle size value to be determined by a predetermined constant.

[0022] Such particle size class determination methods and particle size class determination programs use a machine learning model to determine the particle size class of images of multiple particles, and therefore, by performing machine learning on images of various determination targets, it is possible to determine a wider range of particle size classes for the determination targets. During this determination, the size of the image input to the machine learning model is a size obtained by multiplying the particle size value of the determination target by a predetermined constant, so the particle size class determination methods and particle size class determination programs can appropriately determine the particle size class. In particular, the particle size class determination methods and particle size class determination programs are suitable when the determination targets are pseudoparticles.

[0023] According to another aspect of the present invention, there is provided an image size determination support method for supporting the determination of the size of an image to be used in determining a particle size class when particle sizes are divided into a plurality of particle size classes into a plurality of mutually different ranges, the method comprising: a first data acquisition step of acquiring a predetermined training dataset; a second data acquisition step of acquiring a predetermined size determination dataset; a machine learning step of using the predetermined training dataset acquired in the first data acquisition step to train a second machine learning model to which an image is input and which outputs, for each of the plurality of particle size classes, a probability that the input image is classified into that particle size class; and an output step of inputting the predetermined size determination dataset acquired in the second data acquisition step into the second machine learning model trained in the machine learning step, and outputting each probability for each of the plurality of particle size classes output from the second machine learning model trained in the machine learning step, wherein the predetermined training dataset and the predetermined size determination dataset each comprise a plurality of data groups each comprising image data of a plurality of images, and the plurality of data groups each comprise image sizes of the plurality of images. the plurality of data groups in the predetermined training dataset are a plurality of images including images of each of the plurality of particle size classes, and the particle size class of the image is linked to each of the plurality of images in the data group; the plurality of data groups in the predetermined size determination dataset are a plurality of images including images of different content rates of particles belonging to the particle size class with the smallest particle size, and the content rate of the image is linked to each of the plurality of images in the data group; the number of the unmachined second machine learning models is the same as the number of the plurality of data groups and is provided corresponding to each of the plurality of data groups; the machine learning step machine-learns the unmachined second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset using the plurality of images in the data group; and the output step outputs, for each of the plurality of data groups in the predetermined size determination dataset, an image of the same size as the size of the image in the data group.By inputting a plurality of images in the data group into a second machine learning model trained by machine learning in the machine learning step using the data group in the predetermined learning dataset, the probabilities for each of the plurality of particle size classes output from the second machine learning model trained by machine learning in the machine learning step are output.

[0024] According to another aspect of the present invention, there is provided an image size determination assistance program that is executed by a computer and that assists in determining the size of an image to be used to determine a particle size class when particle sizes are divided into a plurality of particle size classes into a plurality of mutually different ranges, the program comprising: a first data acquisition step of acquiring a predetermined training dataset; a second data acquisition step of acquiring a predetermined size determination dataset; a machine learning step of using the predetermined training dataset acquired in the first data acquisition step to train a second machine learning model that receives an input of an image and outputs, for each of the plurality of particle size classes, a probability that the input image will be classified into that particle size class; and an output step of inputting the predetermined size determination dataset acquired in the second data acquisition step into the second machine learning model trained in the machine learning step, and outputting the respective probabilities for each of the plurality of particle size classes output from the second machine learning model trained in the machine learning step, wherein the predetermined training dataset and the predetermined size determination dataset each comprise image data of a plurality of images. the plurality of data groups have different image sizes, and in each of the plurality of data groups in the predetermined training dataset, the plurality of images in the data group are a plurality of images including images of each of the plurality of particle size classes, and the particle size class of the image is linked to each of the plurality of images in the data group, and in each of the plurality of data groups in the predetermined size determination dataset, the plurality of images in the data group are a plurality of images including images with different content rates of particles belonging to the particle size class with the smallest particle size, and the content rate of the image is linked to each of the plurality of images in the data group, and the number of the unmachined second machine learning models is the same as the number of the plurality of data groups and is provided corresponding to each of the plurality of data groups, and the machine learning step performs machine learning on the unmachined second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset using the plurality of images in the data group, and the output step performs, for each of the plurality of data groups in the predetermined size determination dataset,By inputting a plurality of images in the data group into a second machine learning model trained by machine learning in the machine learning step using a data group in the predetermined learning dataset having the same image size as the image size in the data group, the probabilities for each of the plurality of particle size classes output from the second machine learning model trained by machine learning in the machine learning step are output.

[0025] Such an image size determination support method and image size determination support program output the probability of each of the plurality of particle size classes obtained by inputting a predetermined size determination dataset into a machine-learned second learning model, so that a user can determine the optimal image size from among a plurality of image sizes by referring to the output probability of each of the plurality of particle size classes and the content rate associated with the image. Therefore, the image size determination support method and image size determination support program can suitably support a user in determining the image size. Therefore, an image size determination support method and image size determination support program can be provided that support the determination when determining the size of an image to be used for particle size class determination. [Effects of the Invention]

[0026] Particle size class determination device according to the present invention teeth According to the present invention, an image size determination support device, an image size determination support method, and an image size determination support program can be provided that support the determination of the size of an image used for determining the particle size class. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a block diagram showing the configuration of a particle size class determination device with an image size determination support function according to an embodiment. [Figure 2] 10 is a schematic diagram for explaining a situation in which an image acquisition unit and an illumination unit in the particle size class determination device are arranged in a production line. FIG. [Figure 3]FIG. 1 is a diagram illustrating a training dataset and a validation dataset. [Figure 4] FIG. 2 is a diagram for explaining a machine learning model in the particle size class determination device. [Figure 5] FIG. 10 is a diagram for explaining a size determination dataset. [Figure 6] 10 is a flowchart showing the operation of the particle size class determination device regarding machine learning. [Figure 7] 10 is a flowchart showing the operation of the particle size class determination device in relation to image size determination support. [Figure 8] 10 is a graph showing the correlation between the powder rate determined using a sieve and the powder rate estimated using the particle size class determination device. [Figure 9] 4 is a flowchart showing the operation of the particle size class determination device regarding particle size class determination. [Figure 10] One example is an image in which a mark is used to indicate the particle size class corresponding to the particle size value of the determination target in the image to be determined. DETAILED DESCRIPTION OF THE INVENTION

[0028] Hereinafter, one or more embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the disclosed embodiments. In addition, components with the same reference numerals in each drawing indicate the same components, and their description will be omitted as appropriate. In this specification, when referring to a general term, a reference numeral without a subscript is used, and when referring to an individual component, a reference numeral with a subscript is used.

[0029] The particle size class determination device in the embodiment includes an image acquisition unit that acquires images of multiple particles, including particles of different particle sizes, and a particle size class processing unit that, when an image is input and particle sizes are divided into multiple different ranges as multiple particle size classes, calculates the probability of each of the multiple particle size classes for the image acquired by the image acquisition unit using a machine learning model (first machine learning model) that has been machine-learned and outputs, for each of the multiple particle size classes, the probability that the input image will be classified into that particle size class. One of the boundary values ​​in the multiple ranges is a particle size value for determination, and the size of the image input to the first machine learning model is a size obtained by multiplying the particle size value for determination by a predetermined constant. The image size determination support device in the embodiment is a device that supports the determination of the size of an image to be used for particle size class determination. This image size determination assistance device includes: a first data acquisition unit that acquires a predetermined training dataset; a second data acquisition unit that acquires a predetermined size determination dataset; a machine learning unit that uses the predetermined training dataset acquired by the first data acquisition unit to train a second machine learning model that, when an image is input and particle sizes are divided into a plurality of particle size classes with different ranges, outputs, for each of the plurality of particle size classes, a probability that the input image will be classified into that particle size class; and an output unit that inputs the predetermined size determination dataset acquired by the first data acquisition unit to the second machine learning model trained by the machine learning unit, and outputs each probability for each of the plurality of particle size classes output from the second machine learning model trained by the machine learning unit. The predetermined training dataset and the predetermined validation dataset each include a plurality of data groups each containing image data of a plurality of images, and the plurality of data groups have different image sizes. In each of the plurality of data groups in the predetermined training dataset, the plurality of images in the data group include a plurality of images each containing an image of the plurality of particle size classes, and each of the plurality of images in the data group is associated with a particle size class of the image.In each of the plurality of data groups in the predetermined size determination dataset, the plurality of images in the data group are a plurality of images including images with different content rates of particles belonging to a particle size class with a smallest particle size, and the content rate of each of the plurality of images in the data group is linked to the plurality of images in the data group. The number of the unmachine-learned second machine-learning models is the same as the number of the plurality of data groups, and the models are provided corresponding to each of the plurality of data groups. The machine learning unit trains an unmachine-learned second machine-learning model corresponding to each of the plurality of data groups in the predetermined training dataset using the plurality of images in the data group. The output unit inputs the plurality of images in each of the plurality of data groups in the predetermined size determination dataset into the second machine-learning model trained by the machine learning unit using a data group in the predetermined training dataset having the same image size as the image in the data group, and outputs the probability of each of the plurality of particle size classes output from the second machine-learning model trained by the machine learning unit. Below, we will explain in more detail such a particle size class determination device, the particle size class determination method implemented therein, and the particle size class determination program implemented therein, as well as the image size determination support device, the image size determination support method implemented therein, and the image size determination support program implemented therein, using a particle size class determination device with an image size determination support function that integrates the particle size class determination device and the image size determination support device.

[0030] FIG. 1 is a block diagram showing the configuration of a particle size class determination device with an image size determination support function according to an embodiment. FIG. 2 is a schematic diagram illustrating a situation in which an image acquisition unit and an illumination unit in the particle size class determination device are arranged on a production line. FIG. 3 is a diagram illustrating a training dataset and a validation dataset. FIG. 3A shows, as an example, an image of a plurality of particles having a particle size of 2 mm or less. FIG. 3B shows, as an example, an image of a plurality of particles having a particle size of more than 2 mm but not more than 2.8 mm. FIG. 3C shows, as an example, an image of a plurality of particles having a particle size of more than 2.8 mm but not more than 4.75 mm. FIG. 3D shows how the image shown in FIG. 3A is divided into multiple parts. FIG. 3E shows how the image shown in FIG. 3B is divided into multiple parts. FIG. 3F shows how the image shown in FIG. 3C is divided into multiple parts. FIG. 3G shows, as an example, a group of images of a plurality of data groups divided by a first division size; FIG. 3H shows, as an example, a group of images of a plurality of data groups divided by a second division size; FIG. 3I shows, as an example, a group of images of a plurality of data groups divided by a third division size; and FIG. 3J shows, as an example, a group of images of a plurality of data groups divided by a fourth division size. FIG. 4 is a diagram for explaining a machine learning model in the particle size class determination device. FIG. 5 is a diagram for explaining a size determination dataset. FIG. 5A shows, as an example, a plurality of images in a data group with a powder rate of 20%; FIG. 5B shows, as an example, a plurality of images in a data group with a powder rate of 30%; FIG. 5C shows, as an example, a plurality of images in a data group with a powder rate of 40%; and FIG. 5D shows, as an example, a plurality of images in a data group with a powder rate of 50%.

[0031] The particle size class determination device D in the embodiment includes, for example, an image acquisition unit 1, an illumination unit 2, a control processing unit 3, an input unit 4, an output unit 5, an interface unit (IF unit) 6, and a memory unit 7, as shown in FIG.

[0032] The image acquisition unit 1 is connected to the control processing unit 3 and acquires images of a plurality of particles, including particles of different particle sizes, under the control of the control processing unit 3. The particles may be any particles, but in this embodiment, the particles are pseudo-particles, for example, comprising a first particle serving as a nucleus and one or more second particles smaller than the first particle and attached to the surface of the first particle. More specifically, the particles are particles of sintered ore (sintered ore particles) comprising a nucleus powder (an example of a first particle) such as iron ore, limestone, or coke, and fine particles of this powder smaller than the powder (an example of a second particle) attached to the surface of the powder. Such sintered ore is preferably used in a blast furnace. In this embodiment, the image acquisition unit 1 is, for example, an imaging unit 1 that generates images during the sintering process to acquire images of the sintered ore particles after the sintering process. As shown in FIG. 2, the imaging unit 1 is disposed above a belt conveyor BC that transports the sintered ore particles so as to obtain a bird's-eye view of the sintered ore particles on the belt conveyor BC. More specifically, the imaging unit 1 is disposed directly above the belt conveyor BC, with its optical axis aligned with the normal direction of the conveying surface (the surface on which the sintered ore particles are placed) of the belt conveyor BC. The imaging unit 1 preferably has an angle of view that allows it to capture the entire width direction (the direction perpendicular to the conveying direction) of the belt conveyor BC. By capturing images of the sintered ore particles and determining their particle size class after the sintering process, the sintering conditions for the sintering process can be adjusted according to the determination results, thereby optimizing and efficiently performing the sintering process. Such an imaging unit 1 is, for example, a digital camera that includes an imaging optical system that forms an optical image of the imaging target on a predetermined imaging plane, an area image sensor that is positioned so that its light-receiving surface is aligned with the imaging plane and that converts the optical image of the imaging target into an electrical signal, and an image processing unit that processes the output of the area image sensor to generate image data that represents the image of the imaging target.

[0033] The image acquisition unit 1 is not limited to the imaging unit 1 and may be another device. For example, the image acquisition unit 1 is an interface circuit that inputs and outputs data to and from an external device. The external device may be a storage medium, such as a USB (Universal Serial Bus) memory or an SD card (registered trademark), that stores images of multiple particles, including particles of different particle sizes. Alternatively, the external device may be a drive device that reads data from a storage medium, such as a CD-ROM (Compact Disc Read Only Memory), a CD-R (Compact Disc Recordable), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a DVD-R (Digital Versatile Disc Recordable), that stores the images. The interface circuit serving as the image acquisition unit 1 may be connected to the external device via a wired or wireless connection. Alternatively, the image acquisition unit 1 may be a communication interface circuit that transmits and receives communication signals to and from an external device, and the external device may be a server device that manages the images and is connected to the communication interface circuit via a network (such as a WAN (Wide Area Network, including a public communication network)) or a LAN (Local Area Network). With such an image acquisition unit 1, even when production is not in progress, the particle size class of the image can be determined and past sintering processes can be verified. Here, when the image acquisition unit 1 is an interface circuit or a communication interface circuit, the image acquisition unit 1 may also be used as the IF unit 6 (i.e., the IF unit 6 may be used as the image acquisition unit 1).

[0034] The illumination unit 2 is connected to the control processing unit 3 and is a device that illuminates the plurality of particles to be determined under the control of the control processing unit 3. In this embodiment, as shown in FIG. 2, the illumination unit 2 includes four illumination units, first through fourth illumination units 2-1 through 2-4, which surround the imaging unit 1 on all four sides and are arranged so as to illuminate each sintered ore particle on the belt conveyor BC. More specifically, when a virtual square is set on a virtual plane parallel to the conveying surface of the belt conveyor BC, the imaging unit 1 is arranged so that its optical axis passes through the center of the square (the intersection of two diagonals), and the first through fourth illumination units 2-1 through 2-4 are arranged one at each of the four corners (quadrangles) of the square so that their optical axes pass through the intersections where the optical axis of the imaging unit 1 intersects with the conveying surface of the belt conveyor BC. The illumination unit 2 may be turned on and off manually.

[0035] The input unit 4 is connected to the control processing unit 3 and is a device that inputs various commands, such as a command to start assistance or a command to start judgment, and various data necessary to operate the particle size class judgment device D with image size determination assistance function, such as the image size determined as a result of the assistance, to the particle size class judgment device D, and is, for example, a plurality of input switches to which predetermined functions are assigned, a keyboard, a mouse, etc. The output unit 5 is connected to the control processing unit 3 and is a device that outputs the commands and data input from the input unit 4 and the particle size class of the judgment result, etc., under the control of the control processing unit 3, and is, for example, a display device such as a CRT display, LCD (liquid crystal display) or organic EL display, or a printing device such as a printer.

[0036] The input unit 4 and the output unit 5 may be configured as a touch panel. In the case of configuring this touch panel, the input unit 4 is a position input device that detects and inputs an operation position, such as a resistive film type or a capacitive type, and the output unit 5 is a display device. In this touch panel, a position input device is provided on the display surface of the display device, and one or more input content candidates that can be input to the display device are displayed. When a user touches the display position showing the input content they want to input, the position is detected by the position input device, and the display content displayed at the detected position is input to the particle size class determination device D as the user's operation input content. With such a touch panel, the user can easily intuitively understand the input operation, and therefore a particle size class determination device D that is easy for the user to use is provided.

[0037] The IF unit 6 is connected to the control processing unit 3 and is a circuit that inputs and outputs data to and from, for example, an external device under the control of the control processing unit 3, and is, for example, an interface circuit for RS-232C, which is a serial communication method, an interface circuit using the Bluetooth (registered trademark) standard, an interface circuit using the USB standard, etc. The IF unit 6 may also be, for example, a communication interface circuit that transmits and receives communication signals to and from an external device, such as a data communication card or a communication interface circuit conforming to the IEEE802.11 standard, etc.

[0038] The input unit 4 accepts and acquires input of a predetermined training dataset and a validation dataset, which will be described later, and accepts and acquires input of a predetermined sizing dataset, which will be described later. The input unit 4 corresponds to an example of a first data acquisition unit that acquires a predetermined training dataset, and corresponds to an example of a second data acquisition unit that acquires a predetermined sizing dataset. Alternatively, the IF unit 6 acquires the predetermined training dataset from a storage medium that stores the predetermined training dataset, a recording medium that records the predetermined training dataset, or a server device that manages the predetermined training dataset. The IF unit 6 acquires the predetermined sizing dataset from a storage medium that stores the predetermined sizing dataset, a recording medium that records the predetermined sizing dataset, or a server device that manages the predetermined sizing dataset. The IF unit 6 corresponds to another example of the first data acquisition unit and another example of the second data acquisition unit.

[0039] The storage unit 7 is connected to the control processing unit 3 and is a circuit that stores various predetermined programs and various predetermined data under the control of the control processing unit 3. The various predetermined programs include, for example, a control processing program, which includes, for example, a control program that controls each of the units 1, 2, 4 to 7 of the particle size class determination device D according to the function of each unit; a machine learning program that uses a predetermined learning dataset acquired by the first data acquisition unit (input unit 4 and IF unit 6 in this embodiment) to train an unmachined second machine learning model that outputs the probability that the input image is classified into a particle size class for each of the multiple particle size classes when an image is input and particle sizes are divided into multiple different ranges; a particle size class processing program that uses a machine-learned machine learning model (first machine learning model) that outputs the probability that the input image is classified into a particle size class for each of the multiple particle size classes when an image is input and particle sizes are divided into multiple different ranges; and an image size adjustment program that adjusts the image acquired by the image acquisition unit 1 to the size of the image received by the input unit 4. In this embodiment, the first machine-learned model is a second machine-learned model trained by the machine learning program. The various types of predetermined data include, for example, images acquired by the image acquisition unit 1, a training dataset, a validation dataset and a size determination dataset (described later), and other data required to execute each of these programs. The storage unit 7 includes, for example, a non-volatile storage element such as a read-only memory (ROM) or a rewritable non-volatile storage element such as an electrically erasable programmable read-only memory (EEPROM). The storage unit 7 also includes, for example, a random access memory (RAM) that serves as a working memory for the control processing unit 3 and stores data generated during execution of the predetermined programs.The storage unit 7 may also be configured to include a hard disk device with a relatively large storage capacity.

[0040] The control processing unit 3 is a circuit that controls each of the units 1, 2, 4 to 7 of the particle size class determination device D according to the function of each unit, determines the particle size class of a plurality of particles including particles of different particle sizes based on an image of the captured particle, and assists in determining the size of the image used for determining the particle size class. The control processing unit 3 is configured, for example, with a CPU (Central Processing Unit) and its peripheral circuits. By executing a control processing program, the control processing unit 3 functionally includes a control unit 31, a machine learning unit 32, a particle size class processing unit 33, and an image size adjustment unit 34.

[0041] The control unit 11 controls each of the units 1, 2, 4 to 7 of the particle size class determination device D according to the function of each unit, and controls the particle size class determination device D as a whole.

[0042] The machine learning unit 32 uses a predetermined learning dataset acquired by the first data acquisition unit (in this embodiment, the input unit 4 or the IF unit 6) to train a second machine learning model that, when an image is input and particle sizes are divided into multiple particle size classes into multiple different ranges, outputs the probability that the input image will be classified into that particle size class for each of the multiple particle size classes.

[0043] The predetermined training dataset includes a plurality of data groups each including image data of a plurality of images. The plurality of data groups have different image sizes. In each of the plurality of data groups in the predetermined training dataset, the plurality of images in the data group are a plurality of images including an image of each of the plurality of particle size classes, and each of the plurality of images in the data group is associated with the particle size class of the image. Therefore, the machine learning unit 32 performs supervised machine learning of the untrained second machine learning model as a classification problem.

[0044] The number of the untrained second machine learning models is the same as the number of the plurality of data groups, and the untrained second machine learning models are provided corresponding to each of the plurality of data groups. For each of the plurality of data groups in the predetermined training dataset, the machine learning unit 32 trains the untrained second machine learning model corresponding to the data group by machine learning using a plurality of images in the data group.

[0045] In this embodiment, as described above, the particles are sintered ore particles after the sintering process, and the particle size class determination device D determines the particle size class based on images taken while the particles are being transported on the belt conveyor BC. According to the inventor's knowledge, multiple sintered ore particles on the belt conveyor BC are locally present with approximately the same particle size. In this embodiment, each sintered ore particle locally present with approximately the same particle size is classified into one of three particle size classes: large, medium, and small. In this embodiment, the purpose is to detect sintered ore particles that do not exceed 2 mm in size in order to efficiently operate the sintering process. Therefore, in this embodiment, the three particle size classes are defined as a particle size class (small particle size class) of particles having a particle size of 2 mm or less (i.e., sintered ore particles not exceeding 2 mm, small particle size particles) that can be separated using a sieve of JIS standard (JIS Z8801-1) by taking into account the particle sizes typically observed in the sintered ore particles, a particle size class (medium particle size class) of particles having a particle size of more than 2 mm and not more than 2.8 mm (medium particle size class), and a particle size class (large particle size class) of particles having a particle size of more than 2.8 mm and not more than 4.75 mm (large particle size particles).

[0046] According to the inventor's findings, when particle size classes are set to three particle size classes (large, medium, and small), if the image size is too small, an image capturing large particle sizes will not capture the entire particle, resulting in a loss of particle outline, making it difficult to properly extract the particles. In particular, if the particles are pseudo-particles of sintered ore, there is a risk that fine powder attached to the core powder will be extracted, making it difficult to extract the actual pseudo-particles of sintered ore. On the other hand, if the image size is too large, when large and small particles are captured in the image, the outline information of the small particles may be hidden, making it difficult to properly extract the particles. Therefore, it is believed that there is an optimal solution for the image size (image size) relative to the target particle size value. In this embodiment, the purpose is to detect sintered ore particles not exceeding 2 mm, so the target particle size value is 2 mm.

[0047] For this reason, the image sizes (image sizes) of the plurality of data groups in the predetermined training dataset are set to be different from one another by a constant multiple of the particle size value of the judgment target. Specifically, the plurality of data groups in the predetermined training dataset are four data groups, first to fourth, as means for optimal solution search, and the image size (first image size) of the first data group is set to 12 times the particle size value of the judgment target, the image size (second image size) of the second data group is set to 10 times the particle size value of the judgment target, the image size (third image size) of the third data group is set to 7 times the particle size value of the judgment target, and the image size (fourth image size) of the fourth data group is set to 5 times the particle size value of the judgment target.

[0048] More specifically, the predetermined training dataset was created as follows. In this embodiment, a predetermined validation dataset was also created along with the predetermined training dataset. The predetermined validation dataset has the same configuration as the training dataset, and is data for verifying whether the machine learning model has been properly trained (i.e., whether it can produce correct answers).

[0049] First, the sintered ore was sieved through a JIS standard sieve to prepare aggregates of small sintered ore particles (small sintered ore aggregates), aggregates of medium sintered ore particles (medium sintered ore aggregates), and aggregates of large sintered ore particles (large sintered ore aggregates).

[0050] Next, the small particle size sinter aggregate was spread out on a flat surface and photographed from directly above with a digital camera, thereby generating, for example, a 2456 x 2054 pixel image (small particle size image) as shown in Figure 3A. The same process was repeated multiple times to generate multiple small particle size images. The same process was performed for each of the medium particle size sinter aggregate and the large particle size sinter aggregate, generating multiple images of the medium particle size sinter aggregate (medium particle size images), and multiple images of the large particle size sinter aggregate (large particle size images). Figures 3B and 3C show the medium particle size image and the large particle size image, respectively.

[0051] Next, in order to make the small particle size images approximately 12 times larger, since in this embodiment 1 pixel is 0.06 mm, for example, as shown in FIG. 3D , they are divided into 411 × 375 pixel sizes, and 2842 images (small particle size divided images of the first image size) are generated by dividing the small particle size images from the plurality of small particle size images. Of these 2842 small particle size divided images of the first image size, 2085 are designated as image data belonging to the first data group in the training dataset, and each of these image data is associated with a small particle size class. Of the 2842 small particle size divided images of the first image size, 784 are designated as image data belonging to the first data group in the validation dataset, and each of these image data is associated with a small particle size class. For example, as shown in Figures 3E and 3F, similar operations were performed on each of the medium-sized images and the large-sized images, and 1,813 images (medium-sized divided images of the first image size) were generated by dividing the medium-sized images from the multiple medium-sized images, and 1,960 images (large-sized divided images of the first image size) were generated by dividing the large-sized images from the multiple large-sized images. Of these 1,813 medium-sized divided images of the first image size, 1,372 were designated as image data belonging to the first data group in the training dataset, and the remaining 441 were designated as image data belonging to the first data group in the verification dataset, and each of these image data was associated with a medium-sized class. Of these 1,960 large-sized divided images of the first image size, 1,372 were designated as image data belonging to the first data group in the training dataset, and the remaining 588 were designated as image data belonging to the first data group in the verification dataset, and each of these image data was associated with a large-sized class. As a result, for example, a first data group in the training dataset shown in FIG. 3G was generated, and a first data group in the validation dataset (not shown) was generated.

[0052] Next, the same process was performed on each of the plurality of small particle size images, the plurality of medium particle size images, and the plurality of large particle size images, but at a size of 319 x 290 pixels, which was approximately 10 times larger. As a result, for example, a second data group in the training dataset shown in FIG. 3H was generated, and a second data group in the validation dataset (not shown) was generated. The number of small particle size divided images (images obtained by dividing a small particle size image at the second image size) at the second image size, medium particle size divided images (images obtained by dividing a medium particle size image at the second image size), and large particle size divided images (images obtained by dividing a large particle size image at the second image size) at the second image size in the second data group of the training dataset was 2058, 1127, and 1372, respectively. The number of small particle size divided images at the second image size, medium particle size divided images at the second image size, and large particle size divided images at the second image size in the second data group of the validation dataset was 784, 411, and 588, respectively.

[0053] Next, the same process was performed on each of the plurality of small-grain images, the plurality of medium-grain images, and the plurality of large-grain images, but at a size of 237 × 216 pixels, so that the size was approximately seven times larger. As a result, for example, the third data group in the training dataset shown in FIG. 3I was generated, and the third data group in the validation dataset (not shown) was generated. The number of small-grain divided images (images obtained by dividing small-grain images at the third image size), medium-grain divided images (images obtained by dividing medium-grain images at the third image size), and large-grain divided images (images obtained by dividing large-grain images at the third image size) at the third image size in the third data group of the training dataset was 3,402, 1,863, and 2,268, respectively. The number of small-grain divided images (images obtained by dividing small-grain images at the third image size), medium-grain divided images (images obtained by dividing medium-grain images at the third image size), and large-grain divided images (images obtained by dividing large-grain images at the third image size) at the third image size in the third data group of the validation dataset was 1,296, 972, and 729, respectively.

[0054] Next, the same process was performed on each of the plurality of small-grain images, the plurality of medium-grain images, and the plurality of large-grain images, each with a size of 184 × 167 pixels, so that the size was approximately five times larger. As a result, for example, a fourth data group in the training dataset shown in FIG. 3J was generated, and a fourth data group in the validation dataset (not shown) was generated. The number of small-grain divided images (images obtained by dividing a small-grain image by the fourth image size), medium-grain divided images (images obtained by dividing a medium-grain image by the fourth image size), and large-grain divided images (images obtained by dividing a large-grain image by the fourth image size) in the fourth data group of the training dataset was 6,048, 3,312, and 4,032, respectively. The number of small-grain divided images (images obtained by dividing a small-grain image by the fourth image size), medium-grain divided images (images obtained by dividing a medium-grain image by the fourth image size), and large-grain divided images (images obtained by dividing a large-grain image by the fourth image size) in the fourth data group of the validation dataset was 2,304, 1,296, and 1,728, respectively.

[0055] In this embodiment, the unmachined second machine learning model includes four models: an unmachined second machine learning model according to the first data group (an unmachined second machine learning model for the first image size), an unmachined second machine learning model according to the second data group (an unmachined second machine learning model for the second image size), an unmachined second machine learning model according to the third data group (an unmachined second machine learning model for the third image size), and an unmachined second machine learning model according to the fourth data group (an unmachined second machine learning model for the fourth image size). The machine learning unit 32 performs supervised machine learning of an unmachine-learned second machine learning model for the first image size using a plurality of images of a first data group in the training dataset (a plurality of small particle size divided images of the first image size, a plurality of medium particle size divided images of the first image size, and a plurality of large particle size divided images of the first image size), performs supervised machine learning of an unmachine-learned second machine learning model for the second image size using a second data group in the training dataset (a plurality of small particle size divided images of the second image size, a plurality of medium particle size divided images of the second image size, and a plurality of large particle size divided images of the second image size), performs supervised machine learning of an unmachine-learned second machine learning model for the third image size using a third data group in the training dataset (a plurality of small particle size divided images of the third image size, a plurality of medium particle size divided images of the third image size, and a plurality of large particle size divided images of the third image size), and performs supervised machine learning of an unmachine-learned second machine learning model for the fourth image size using a fourth data group in the training dataset (a plurality of small particle size divided images of the fourth image size, a plurality of medium particle size divided images of the fourth image size, and a plurality of large particle size divided images of the fourth image size). This generates a second machine learning model that has been machine-trained for the first data group (first image size), a second machine learning model that has been machine-trained for the second data group (second image size), a second machine learning model that has been machine-trained for the third data group (third image size), and a second machine learning model that has been machine-trained for the fourth data group (fourth image size).

[0056] In this embodiment, a well-known deep learning convolutional neural network (CNN) is used as the machine learning model.

[0057] This CNN 8 is a CNN having a function of avoiding overlearning, and includes a plurality of layers of pre-processing units 81 (81-1 to 81-6) and a post-processing unit 82, as shown in FIG.

[0058] In this embodiment, the CNN 8 includes six layers of first to sixth preprocessing units 81-1 to 81-6. These first to sixth preprocessing units 81-1 to 81-6 do not necessarily have the same number of input channels and output channels, but they have the same structure, including convolutional layers 811 (811-1 to 811-6), pooling layers 812 (812-1 to 812-6), and dropout layers 813 (813-1 to 813-6). Each convolutional layer 811 (811-1 to 811-6) performs a convolution operation on the input image of that layer and extracts features of the input image. Each pooling layer 812 (812-1 to 812-6) is connected to a convolutional layer 811 (811-1 to 811-6) and reduces the size of the output (feature map) of the convolutional layer 811 (811-1 to 811-6) through a predetermined process. This predetermined process typically uses max pooling. For example, when reducing a 12x12 feature map to a 3x3 size, max pooling divides the 12x12 feature map into nine 4x4 regions, extracts the maximum value from each region, and sets it as each value of the 3x3 size. Note that, instead of the maximum value, average pooling, which calculates the average value of the region, may be used. Each dropout layer 813 (813-1 to 813-6) is connected to the pooling layer 812 (812-1 to 812-6) and prevents overfitting. The dropout layer 813 includes multiple nodes, and each time the machine learning is updated, one of the multiple nodes is randomly selected with a certain probability and deactivated (disabled). For example, the first preprocessing unit 81-1 has 16 output channels and is connected to the second preprocessing unit 81-2 via the 16 channels. The dropout layer 813 includes 16 nodes, and these 16 nodes are randomly deactivated each time the machine learning is updated. In the example shown in FIG. 4, the dropout layer 813 (813-1 to 813-6) is included in each of the preprocessing units 81-1 to 81-6, but there may be a preprocessing unit 81 that does not include a dropout layer 813. The first preprocessing unit 81-1 has one input channel and 16 output channels. The second preprocessing unit 81-2 has 16 input channels and 32 output channels.The third preprocessing unit 81-3 has 32 input channels and 64 output channels. The fourth preprocessing unit 81-4 has 64 input channels and 64 output channels. The fifth preprocessing unit 81-5 has 64 input channels and 128 output channels. The sixth preprocessing unit 81-6 has 128 input channels and 64 output channels.

[0059] The post-processing unit 82 is a neural network including a fully connected layer 821 and an output layer 822, and uses the neural network to recognize the input image input to the pre-processing unit 81 based on the processing results of the pre-processing unit 81. In this embodiment, an image of a plurality of particles is input as the input image, and the probabilities of the small particle size class, the medium particle size class, and the large particle size class for the image (the input image) are output.

[0060] Returning to FIG. 1 , the particle size class processing unit 33 receives an input image and divides particle sizes into multiple particle size classes into different ranges. The particle size class processing unit 33 calculates the probability of each of the multiple particle size classes for the image acquired by the image acquisition unit 1 using a first machine learning model that has been machine-learned and outputs the probability that the input image is classified into that particle size class. The control unit 31 outputs the probability of each of the multiple classes for the image calculated by the particle size class processing unit 33 to the output unit 5. The particle size class determination device D in this embodiment has an image size determination support function, as described above. The particle size class processing unit 33 inputs a predetermined size determination dataset acquired by the second data acquisition unit into a second machine learning model that has been machine-learned by the machine learning unit 32, thereby calculating the probability of each of the multiple classes for each image in the predetermined size determination dataset. The control unit 31 outputs the probability of each of the multiple classes for each image in the predetermined size determination dataset calculated by the particle size class processing unit 33 to the output unit 5. The second machine learning model that has been machine-learned by the machine learning unit 32 is used as the first machine learning model that has been machine-learned.

[0061] In this embodiment, as described above, the probability of the small particle size class (small particle size probability), the probability of the medium particle size class (medium particle size probability), and the probability of the large particle size class (large particle size probability) for the image are calculated and output.

[0062] The size determination data set includes a plurality of data groups each including image data of a plurality of images, the plurality of data groups having different image sizes, and the plurality of images in each of the plurality of data groups in the predetermined size determination data set include images having different content rates of particles belonging to a particle size class with a smallest particle size, and each of the plurality of images in the data group is associated with the content rate of the image.

[0063] Then, for each of the plurality of data groups in the predetermined size determination dataset, particle size class processing unit 33 inputs a plurality of images in the data group into a second machine learning model trained by machine learning unit 32 using a data group in the predetermined training dataset having the same image size as the image in the data group, thereby determining the probability of each of the plurality of particle size classes output from the second machine learning model trained by machine learning unit 32. Control unit 31 outputs to output unit 5 the probability of each of the plurality of classes for each image in the predetermined size determination dataset determined for each of the plurality of data groups by particle size class processing unit 33.

[0064] In this embodiment, the particle size classes are the small particle size class, the medium particle size class, and the large particle size class, as described above, and the particle size class with the smallest particle size is the small particle size class. Particles belonging to the smallest particle size class have a particle size of 2 mm or less when sieved through a JIS standard sieve, and the content of particles belonging to the smallest particle size class is the content of particles with a particle size of 2 mm or less. In this embodiment, these particles with a particle size of 2 mm or less are defined as "powder," and the content of "powder" in the measurement object (the ratio of powder to the entire measurement object) is defined as the "powder ratio."

[0065] The image sizes of the plurality of data groups in the predetermined size determination dataset are set to the image sizes of the plurality of data groups in the predetermined training dataset. In the above example, the plurality of data groups in the predetermined size determination dataset are four data groups, first to fourth, and the image size of the first data group (first image size) is set to 12 times the target particle size value, the image size of the second data group (second image size) is set to 10 times the target particle size value, the image size of the third data group (third image size) is set to 7 times the target particle size value, and the image size of the fourth data group (fourth image size) is set to 5 times the target particle size value.

[0066] To determine the image size, different dust ratios were set at 20%, 30%, 40% and 50%.

[0067] More specifically, the predetermined size determination data set was created as follows.

[0068] First, by using a JIS standard sieve to sieve the sintered ore, two aggregates of sintered ore particles with a fineness of 20% (20% fineness sintered ore aggregate), two aggregates of sintered ore particles with a fineness of 30% (30% fineness sintered ore aggregate), two aggregates of sintered ore particles with a fineness of 40% (40% fineness sintered ore aggregate), and two aggregates of sintered ore particles with a fineness of 50% (50% fineness sintered ore aggregate).

[0069] Next, for each of the two 20% fineness sinter aggregates, the same process as for generating small particle size images in the predetermined training dataset described above was performed to generate an image of sintered ore with a fineness of 20% (20% fineness image). The same process as for generating small particle size divided images in the predetermined training dataset described above was performed to generate images obtained by dividing the 20% fineness image into a first image size (first image size 20% fineness divided image), images obtained by dividing the 20% fineness image into a second image size (second image size 20% fineness divided image), images obtained by dividing the 20% fineness image into a third image size (third image size 20% fineness divided image), and images obtained by dividing the 20% fineness image into a fourth image size (fourth image size 20% fineness divided image). The actual fineness of each of the two 20% fineness sinter aggregates prepared above was measured separately using a sieve test according to the JIS standard. For one sintered ore aggregate with a fineness of 20%, 50 divided images with a fineness of 20% each of the first to fourth image sizes were generated, an example of which is shown in FIG. 5A.

[0070] Next, the same procedure was repeated for each of the two 30% fine sinter aggregates, generating 50 images for each of the first, second, third, and fourth image sizes, each representing a 30% fineness ratio. The fineness ratios of the two 30% fine sinter aggregates were then measured. An example of this is shown in Figure 5B.

[0071] Next, the same procedure was repeated for each of the two 40% fine sinter aggregates, generating 50 images for each of the first, second, third, and fourth image sizes, each representing a 40% fineness ratio. The fineness ratios of the two 40% fine sinter aggregates were measured, as shown in Figure 5C.

[0072] Next, the same procedure was repeated for each of the two 50% fine sinter aggregates, generating 50 images for each of the first, second, third, and fourth image sizes with a 50% fineness ratio. The fineness ratios of the two 50% fine sinter aggregates were measured, as shown in Figure 5D.

[0073] Next, the divided image of the first image size with a 20% powder rate, the divided image of the first image size with a 30% powder rate, the divided image of the first image size with a 40% powder rate, and the divided image of the first image size with a 50% powder rate are set as image data belonging to a first data group in the size determination dataset, and the divided image of the second image size with a 20% powder rate, the divided image of the second image size with a 30% powder rate, the divided image of the second image size with a 40% powder rate, and the divided image of the second image size with a 50% powder rate are set as image data belonging to a second data group in the size determination dataset. The third image size divided image with a 20% fineness ratio, the third image size divided image with a 30% fineness ratio, the third image size divided image with a 40% fineness ratio, and the third image size divided image with a 50% fineness ratio are regarded as image data belonging to the third data group in the size determination dataset, and the fourth image size divided image with a 20% fineness ratio, the fourth image size divided image with a 30% fineness ratio, the fourth image size divided image with a 40% fineness ratio, and the fourth image size divided image with a 50% fineness ratio are regarded as image data belonging to the fourth data group in the size determination dataset. In this embodiment, two each of the 20% fineness ratio sintered ore aggregate, the 30% fineness ratio sintered ore aggregate, the 40% fineness ratio sintered ore aggregate, and the 50% fineness ratio sintered ore aggregate are prepared, and accordingly, two size determination datasets are also generated.

[0074] The particle size class processing unit 33 inputs a plurality of images in a first data group in the predetermined size determination dataset into a machine-learned second machine-learning model for a first image size, thereby determining each probability of each of the plurality of particle size classes output from the machine-learned machine-learning model for the first image size, and the control unit 31 outputs each of these probabilities to the output unit 5. The particle size class processing unit 33 inputs a plurality of images in a second data group in the predetermined size determination dataset into a machine-learned second machine-learning model for a second image size, thereby determining each probability of each of the plurality of particle size classes output from the machine-learned machine-learning model for the second image size, and the control unit 31 outputs each of these probabilities to the output unit 5. The particle size class processing unit 33 inputs a plurality of images in a third data group in the predetermined size determination dataset into a machine-learned second machine-learning model for a third image size, thereby determining each probability of each of the plurality of particle size classes output from the machine-learned machine-learning model for the third image size, and the control unit 31 outputs each of these probabilities to the output unit 5. The particle size class processing unit 33 inputs multiple images in the fourth data group in the specified size determination dataset into a second machine learning model that has been machine-learned for the fourth image size, thereby calculating the probability of each of the multiple particle size classes output from the machine learning model that has been machine-learned for the fourth image size, and the control unit 31 outputs each of these probabilities to the output unit 5.

[0075] The image size adjustment unit 34 adjusts the image acquired by the image acquisition unit 1 to the image size accepted by the input unit 4. The image size adjustment unit 34 may, for example, generate one image of the image size accepted by the input unit 4 by cutting out an image area of ​​the image size accepted by the input unit 4 (for example, an image area in the center of the image) from one image acquired by the image acquisition unit 1. Alternatively, the image size adjustment unit 34 may, for example, generate multiple images of the image size accepted by the input unit 4 by cutting out multiple discontinuous image areas of the image size accepted by the input unit 4 from one image acquired by the image acquisition unit 1. In this embodiment, for example, the image size adjustment unit 34 generates multiple images of the image size accepted by the input unit 4 by dividing one image acquired by the image acquisition unit 1 into a two-dimensional matrix by the image areas of the image size accepted by the input unit 4. Then, for each of the multiple images generated by division in the image size adjustment unit 34, the particle size class processing unit 33 inputs the image into the machine-learned second machine learning model corresponding to the size of the image received by the input unit 4 as the machine-learned first machine learning model, thereby calculating the probability of each of the multiple particle size classes output from the machine-learned second machine learning model, and the control unit 31 outputs each of these probabilities to the output unit 5.

[0076] The control processing unit 3, input unit 4, output unit 5, IF unit 6 and storage unit 7 can be configured by, for example, a desktop or notebook computer.

[0077] Next, the operation of this embodiment will be described. FIG. 6 is a flowchart showing the operation of the particle size class determination device related to machine learning. FIG. 7 is a flowchart showing the operation of the particle size class determination device related to image size determination support. FIG. 8 is a graph showing the correlation between the powder rate determined using a sieve and the powder rate estimated using the particle size class determination device. FIG. 9 is a flowchart showing the operation of the particle size class determination device related to particle size class determination. FIG. 10 is an example of an image to be determined, in which a mark is used to indicate the particle size class corresponding to the particle size value of the determination target. FIGS. 10A to 10D show the image after determination, FIG. 10E shows the image before determination corresponding to FIG. 10A, FIG. 10F shows the image before determination corresponding to FIG. 10B, FIG. 10G shows the image before determination corresponding to FIG. 10C, and FIG. 10H shows the image before determination corresponding to FIG. 10D.

[0078] When the power is turned on, the particle size class determination device D with the image size determination support function configured as described above initializes each necessary part and starts operation. The control processing unit 3 is functionally configured with a control unit 31, a machine learning unit 32, a particle size class processing unit 33, and an image size adjustment unit 34 by executing the control processing program.

[0079] In machine learning of the second machine learning model, a user (operator) inputs a predetermined training data set to the particle size class determination device D with an image size determination support function via the input unit 4 or the IF unit 6. In the above example, a predetermined training data set including first to fourth data groups corresponding to the first to fourth image sizes, respectively, is input to the particle size class determination device D.

[0080] In Figure 6, first, the particle size class determination device D acquires the predetermined learning data set input via the input unit 4 or the IF unit 6 by the control unit 31 of the control processing unit 3, and stores it in the memory unit 7 (S11).

[0081] Next, the particle size class determination device D uses a plurality of images (image data) in one data group in the predetermined learning dataset to machine-learn a second machine-learning model (S12) that has not yet been machine-learned for the data group by the machine learning unit 32 of the control processing unit 3. For example, a plurality of images in a first data group (first image size) is used to machine-learn a second machine-learning model (not yet machine-learned) for the first data group.

[0082] Next, when the machine learning is completed, the particle size class determination device D causes the machine learning unit 32 to store the machine-learned second machine learning model trained for the data group in the storage unit 7 in association with (linked to) the data group (S13). In the above example, the machine-learned second machine learning model trained for the first data group is stored in the storage unit 7 in association with the first data group (e.g., an identifier for specifying and identifying the first data group (e.g., data group ID, image size ID)). The machine-learned second machine learning model may be verified using a verification dataset.

[0083] Next, the particle size class determination device D determines, via the machine learning unit 32, whether or not each of the processes S12 and S13 has been completed for all data groups (all image sizes) in the predetermined learning dataset (S14). If the result of this determination is that each of the processes has not been completed for all data groups (No), the particle size class determination device D returns to process S12 to execute each of the processes for the next data group. On the other hand, if the result of the determination is that each of the processes has been completed for all data groups (Yes), the particle size class determination device D terminates this process. Note that, if necessary, each machine-learned machine learning model corresponding to each data group may be output from the IF unit 6 to an external device.

[0084] As a result, in the above example, a machine-learned second machine learning model is generated for the first data group (for the first image size), a machine-learned second machine learning model is generated for the second data group (for the second image size), a machine-learned second machine learning model is generated for the third data group (for the third image size), and a machine-learned second machine learning model is generated for the fourth data group (for the fourth image size), and these are stored in memory unit 7.

[0085] In terms of machine learning, the particle size class determination device D operates in this way.

[0086] In assisting in image size determination, after generating a second machine learning model that has undergone machine learning, the user (operator) inputs a predetermined size determination dataset to the particle size class determination device D with an image size determination assistance function via the input unit 4 or the IF unit 6. In the above example, a predetermined size determination dataset including first to fourth data groups corresponding to the first to fourth image sizes, respectively, is input to the particle size class determination device D.

[0087] In Figure 7, first, the particle size class determination device D acquires the predetermined size determination data set input via the input unit 4 or IF unit 6 by the control unit 31 of the control processing unit 3, and stores it in the memory unit 7 (S21).

[0088] Next, the particle size class determination device D, by using the particle size class processing unit 33 of the control processing unit 3, determines each probability of each of the plurality of particle size classes by applying multiple images (image data) in one data group in the predetermined size determination dataset to a second machine learning model trained by the machine learning unit 32 as described above using a data group in the predetermined training dataset with the same image size as the image in the data group, and stores each of these probabilities in the storage unit 7 (S22). Each of the probabilities is associated with the data group (data group ID, image size ID), an image (input image) input into the machine-learned second machine learning model to determine each probability (an identifier (image ID) for specifying and identifying the image), and a content rate associated with the input image. For example, for each of the multiple images (image data) in the first data group (first image size), the image is input into the machine-learned second machine learning model for the first data group, and a small particle size probability, a medium particle size probability, and a large particle size probability for the image are determined. Each of these probabilities is associated with the data group ID, image ID, and powder content and stored in the storage unit 7.

[0089] Next, the particle size class determination device D determines whether or not process S22 has been completed for all data groups (all image sizes) in the predetermined size determination data set using the particle size class processing unit 33 (S23). If the result of this determination is that process S22 has not been completed for all data groups (No), the particle size class determination device D returns to process S22 to execute process S22 for the next data group. On the other hand, if the result of the determination is that process S22 has been completed for all data groups (Yes), the particle size class determination device D then executes process S24.

[0090] In this process S24, the particle size class determination device D causes the control unit 31 of the control processing unit 3 to output to the output unit 5 each of the multiple probabilities calculated in process S22 and stored in the memory unit 7, together with the data group (data group ID, image size ID), input image (image ID), and content rate (powder rate in the above example) associated therewith, and ends this process. Note that, if necessary, each of the multiple probabilities may be output from the IF unit 6 to an external device together with the data group (data group ID, image size ID), etc.

[0091] In aiding in the determination of image size, the particle size class determination device D operates in this manner.

[0092] In this embodiment, as described above, two size determination datasets were prepared, and the above-described processes were performed on each size determination dataset, resulting in the respective probabilities for each size determination dataset. The results are shown in FIG. 8. The horizontal axis of FIG. 8 is the fineness rate (content of small particle diameter particles) (mass %) actually measured using a JIS standard sieve. The vertical axis of FIG. 8 is the fineness rate (area %) estimated using the size determination dataset in the particle diameter class determination device D, which is the average value of the small particle diameter probability among the small particle diameter probability, medium particle diameter probability, and large particle diameter probability obtained by the particle diameter class determination device D through the above-described processes S21 to S24. For example, in the first image size, the horizontal axis represents the fineness ratio measured using a JIS sieve for a sintered ore aggregate with a fineness ratio of 20% used to generate one of the two size determination datasets. For each of 50 images in the first data group generated from this sintered ore aggregate with a fineness ratio of 20%, a small particle size probability, a medium particle size probability, and a large particle size probability for that image are calculated using a second machine learning model that has been machine-learned for the first data group. The vertical axis represents the average of the small particle size probabilities calculated for each of the 50 images. For example, in the third image size, the horizontal axis represents the fineness ratio measured using a JIS sieve for a sintered ore aggregate with a fineness ratio of 40% used to generate one of the two size determination datasets. For each of 50 images in the third data group generated from this sintered ore aggregate with a fineness ratio of 40%, a small particle size probability, a medium particle size probability, and a large particle size probability for that image are calculated using a second machine learning model that has been machine-learned for the third data group. The vertical axis represents the average of the small particle size probabilities calculated for each of the 50 images. The results for the first image size (first data group) are indicated by ◆, the results for the second image size (second data group) are indicated by ●, the results for the third image size (third data group) are indicated by ×, and the results for the fourth image size (fourth data group) are indicated by ▲.

[0093] As can be seen from the results for the third image size indicated by an X and the fourth size indicated by a ▲ in Figure 8, the average small particle size probability calculated by particle size class determination device D for both the measured powder ratios was approximately 33.3%. Therefore, with the third and fourth image sizes, particle size class determination device D determined each particle size class equally and was unable to distinguish between small, medium, and large particles, and was unable to determine the particle size class. Therefore, it is considered that the third and fourth image sizes are too small for particle size class determination.

[0094] On the other hand, as can be seen from the results for the first image size indicated by ◆ in Figure 8, the average value of the small particle size probability calculated by the particle size class determination device D for all measured powder rates is approximately 100%. Therefore, at the first image size, the particle size class determination device D determines all particles as being in the small particle size class, and is unable to distinguish between small, medium, and large particles, and is unable to determine the particle size class. Therefore, it is considered that the first image size is too large for particle size class determination.

[0095] Therefore, for determining the particle size class, the image size is within a range larger than the third image size and smaller than the first image size. That is, when the image size input to the machine learning model is a size obtained by multiplying the particle size value of the determination target by a predetermined constant, in the above description, the particle size value of the determination target is 2 mm, and the predetermined constant is a value larger than 7 and smaller than 12. Preferably, the predetermined constant is a value larger than 8 and smaller than 11. Preferably, the predetermined constant is 10.

[0096] In determining the particle size class, the user (operator) inputs the image size (or the predetermined constant) to the particle size class determination device D via the input unit 4. For example, a second image size (or 10 as the predetermined constant) is input to the particle size class determination device D. It is assumed that second machine learning models that have been trained and correspond to each of a plurality of image sizes (or the predetermined constants) are stored in advance in the storage unit 7.

[0097] 9, first, the particle size class determination device D receives input of the image size (or the predetermined constant) at the input unit 4 by the control unit 31 of the control processing unit 3, and stores the input image size (or the predetermined constant) in the storage unit 7 (S31). At this time, the illumination unit 2 is turned on.

[0098] Next, the particle size class determination device D selects a machine-learned second machine learning model corresponding to the input image size (or the specified constant) from among multiple machine-learned second machine learning models stored in the memory unit 7, using the control unit 31 of the control processing unit 3, and sets this selected machine-learned second machine learning model as the first machine learning model to be used in the particle size class processing unit 33 (S32).

[0099] Next, the particle size class determination device D causes the control unit 31 to acquire an image with the image acquisition unit 1 and store the image in the storage unit 7 (S33).

[0100] Next, the particle size class determination device D adjusts the image acquired in step S33 to the image size accepted in step S31 by the image size adjustment unit 34 of the control processing unit 3 (S34).

[0101] Next, the particle size class determination device D uses the particle size class processing unit 33 of the control processing unit 3 to input the image whose image size has been adjusted in process S34 into the machine learning model that has been set up in process S32, thereby calculating each probability for the image, and determines the particle size class with the highest probability from among the probabilities as the particle size class for the image, and stores the result of this determination in the memory unit 7 (S35).

[0102] Next, the particle size class determination device D causes the control unit 31 to output the determination result determined in step S35 to the output unit 5 (S36).

[0103] More specifically, in each of processes S34 to S36, an area of ​​the image size received in process S31 is extracted sequentially from the image acquired in process S33, as if scanning from one corner (for example, the upper left corner of the image) to the diagonal corner (in this example, the lower right corner of the image) in a so-called raster scan manner. Each time an area is extracted, the image of the extracted area is input to the machine learning model set in process S32, and each probability for the image of the extracted area is calculated. A particle size class for the image of the extracted area is determined. The result of this determination is superimposed and displayed on the image acquired in process S33 at the position of the extracted area. Here, in the determination, the calculated probabilities are directly used as the probabilities for each particle size class for the image of the extracted area. For example, as shown in each of Figures 10A to 10D, for an image of a region where the probability of a small particle size is 50% or more, a mark (□) indicating that the position of the region is determined to be a small particle size class with a probability of 50% or more is superimposed and displayed on the image acquired in process S33. The image shown in Figure 10A is an image in which the particle size class determination result (□) for the image with a 20% powder rate shown in Figure 10E is superimposed on the image with a 20% powder rate shown in Figure 10E. The image shown in Figure 10B is an image in which the particle size class determination result (□) for the image with a 30% powder rate shown in Figure 10F is superimposed on the image with a 30% powder rate shown in Figure 10F. The image shown in Figure 10C is an image in which the particle size class determination result (□) for the image with a 40% powder rate shown in Figure 10G is superimposed on the image with a 40% powder rate shown in Figure 10G. The image shown in Figure 10D is an image in which the particle size class determination result (□) for the image with a 50% powder content shown in Figure 10H is superimposed on the image with a 50% powder content shown in Figure 10H. The image acquired in process S33 is divided into regions of the image size accepted in process S31 in a two-dimensional matrix, and the particle size class is determined for each of the images of these divided regions, and the determination result (□) is added. As shown in Figure 10, the number of square marks increases as the powder content increases. In other words, as the powder content increases, the number of regions determined to be in the small particle size class with a probability of 50% or more increases.

[0104] Returning to Fig. 9, next, the particle size class determination device D determines, by the control unit 31, whether or not this process has ended. If the result of this determination is that this process has ended (Yes), the particle size class determination device D ends this process, and if the result of the determination is that this process has not ended (No), the particle size class determination device D then executes process S38. For example, if, during the execution of each of the above-mentioned processes S33 to S36, the input of a predetermined command instructing the end of the process is received at the input unit 4 (if a predetermined input switch or the like is operated), it is determined that this process has ended, and in any other case, it is determined that this process has not ended.

[0105] In step S38, the particle size class determination device D determines, via the control unit 31, whether or not it is time for the next determination. If the result of this determination is that it is time for the next determination (Yes), the particle size class determination device D returns the process to step S33 to determine the particle size class of the next image. On the other hand, if the result of the determination is that it is not time for the next determination (No), the particle size class determination device D returns the process to step S38. Therefore, step S38 is repeated until it is time for the next determination. For example, when determining the particle size class of an image at a predetermined sampling interval, it is determined that it is time for the next determination when the predetermined sampling interval has elapsed since the previous determination timing.

[0106] In the above description, input of the image size is accepted by process S31, and a machine-learned second machine learning model corresponding to this input image size is set in the particle size class processing unit 33 by process S32. However, the image size may be specified in advance, and a machine-learned second machine learning model corresponding to this may be set in advance in the particle size class processing unit 33, and these processes S31 and S32 may be omitted.

[0107] With respect to particle size class determination, the particle size class determination device D operates in this manner.

[0108] As described above, the particle size class determination device D with an image size determination assistance function according to this embodiment, and the particle size class determination method and particle size class determination program implemented therein, use a first machine learning model to determine the particle size class of an image of multiple particles. Therefore, by performing machine learning on a variety of images of particles to be determined, it is possible to determine the particle size class of a wider range of particles to be determined. During this determination, the size of the image input to the first machine learning model is a size obtained by multiplying the particle size value of the determination target by a predetermined constant. Therefore, the particle size class determination device D, particle size class determination method, and particle size class determination program can appropriately determine the particle size class. In particular, the particle size class determination device D, particle size class determination method, and particle size class determination program are suitable when the particle size to be determined is a pseudo particle.

[0109] The particle size class determination device D, particle size class determination method, and particle size class determination program further include an illumination unit 2 (2-1 to 2-4), and use an imaging unit 1 for the image acquisition unit 1, so that the particle size class determination device D, particle size class determination method, and particle size class determination program can be used, for example, on a production line within a factory, and the particle size class can be determined during production.

[0110] According to the above-described embodiment, the particle size class determination device D, particle size class determination method, and particle size class determination program can be provided, in which the predetermined constant is set to a value greater than 7 and less than 12.

[0111] According to the above-described embodiment, it is possible to provide the particle size class determination device D, particle size class determination method, and particle size class determination program for determining pseudo particles. The particle size class determination device D, particle size class determination method, and particle size class determination program are used to determine the particle size class of pseudo particles, so that the particle size class of the pseudo particles can be appropriately determined.

[0112] The particle size class determination device D with an image size determination support function and the image size determination support method and image size determination support program implemented therein in this embodiment output the respective probabilities for each of the plurality of particle size classes obtained by inputting a predetermined size determination dataset into a machine-learned second learning model. A user can determine the optimal image size from among a plurality of image sizes by referring to the respective probabilities for each of the plurality of particle size classes output and the content rate associated with the image (in the embodiment, the powder content is an example of this). Therefore, the particle size class determination device D with the image size determination support function, the image size determination support method, and the image size determination support program can effectively support the user in determining the image size. Therefore, this embodiment provides the particle size class determination device D with the image size determination support function, the image size determination support method, and the image size determination support program that support the determination of the image size used for particle size class determination.

[0113] In order to express the present invention, the present invention has been properly and sufficiently described above through the embodiments with reference to the drawings, but it should be recognized that those skilled in the art can easily change and / or improve the above-mentioned embodiments. Therefore, unless the changes or improvements made by those skilled in the art are at a level that causes departure from the scope of the claims described in the claims, such changes or improvements are interpreted as being included in the scope of the claims. [Explanation of symbols]

[0114] D. Particle size class determination device with image size determination support function 1 Image acquisition unit 2(2-1~2-4) Lighting section 3 Control processing section 4 Input section 5 Output section 6 Interface section (IF section) 7 Memory section 31 Control Unit 32 Machine Learning Department 33 Particle size class processing section 34 Image size adjustment section

Claims

1. an image acquisition unit that acquires an image of a plurality of particles including particles of different particle sizes; a particle size class processing unit that, when an image is input and particle sizes are divided into a plurality of particle size classes into a plurality of different ranges, calculates the probability of each of the plurality of particle size classes in the image acquired by the image acquisition unit using a machine learning model that has undergone machine learning and outputs, for each of the plurality of particle size classes, the probability that the input image will be classified into that particle size class; Any of the boundary values ​​in the plurality of ranges is a particle size value that is a predetermined target for judgment, The size of the image input to the machine learning model is a size obtained by multiplying the particle size value of the judgment target by a predetermined constant, the predetermined constant is greater than 7 and less than 12; The particles are pseudo-particles each comprising a first particle serving as a core and a second particle attached to the surface of the first particle and smaller than the first particle. Particle size class determination device.

2. an illumination unit that illuminates the plurality of particles; The image acquisition unit is an imaging unit that generates an image. The particle size class determination device according to claim 1 .

3. 1. An image size determination support device that supports the determination of an image size to be used for determining a particle size class when particle sizes are divided into a plurality of particle size classes each having a different range, the device comprising: a first data acquisition unit that acquires a predetermined learning dataset; a second data acquisition unit that acquires a predetermined size determination data set; a machine learning unit that uses a predetermined learning dataset acquired by the first data acquisition unit to perform machine learning on a second machine learning model that receives an input image and outputs, for each of the plurality of particle size classes, a probability that the input image is classified into the particle size class; an output unit that outputs the probabilities of each of the plurality of particle size classes output from the second machine learning model trained by the machine learning unit by inputting the predetermined size determination data set acquired by the second data acquisition unit into the second machine learning model trained by the machine learning unit, the predetermined learning dataset and the predetermined size determination dataset each include the same number of data groups each including image data of a plurality of images; The plurality of data groups have different image sizes, In each of the plurality of data groups in the predetermined learning dataset, the plurality of images in the data group are a plurality of images including images of each of the plurality of particle size classes, and each of the plurality of images in the data group is linked to the particle size class of the image; In each of the plurality of data groups in the predetermined size determination data set, the plurality of images in the data group are a plurality of images including images with different content rates of particles belonging to a particle size class with a smallest particle size, and the content rate of each of the plurality of images in the data group is linked, the number of the unmachine-learned second machine learning models is the same as the number of the plurality of data groups, and the unmachine-learned second machine learning models are provided corresponding to each of the plurality of data groups; the machine learning unit performs machine learning on a second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset, the second machine learning model being an untrained model corresponding to the data group, using a plurality of images in the data group; The output unit inputs, for each of the plurality of data groups in the predetermined size determination data set, a plurality of images in the data group into a second machine learning model that has been machine-learned by the machine learning unit using a data group in the predetermined training data set that has the same image size as the image size in the data group, and outputs each of the plurality of particle size classes output from the second machine learning model that has been machine-learned by the machine learning unit. Output the rate, Image size determination support device.

4. The image size determination support device according to claim 3 is further provided, As the machine-learned machine learning model, a second machine learning model trained by the machine learning unit is used. The particle size class determination device according to claim 1 or 2.

5. 1. An image size determination support method for supporting the determination of an image size to be used for determining a particle size class when particle sizes are divided into a plurality of particle size classes each having a different range, the method comprising: a first data acquisition step of acquiring a predetermined training data set; a second data acquisition step of acquiring a predetermined sizing data set; a machine learning process in which an image is input and a second machine learning model, which is not yet machine-learned, is trained by machine using the predetermined training data set acquired in the first data acquisition process, and which outputs, for each of the plurality of particle size classes, the probability that the input image is classified into that particle size class; an output step of inputting the predetermined size determination data set acquired in the second data acquisition step into a second machine learning model trained by machine learning in the machine learning step, and outputting the probabilities of each of the plurality of particle size classes output from the second machine learning model trained by machine learning in the machine learning step; each of the predetermined training dataset and the predetermined size determination dataset includes a plurality of data groups each including image data of a plurality of images; The plurality of data groups have different image sizes, In each of the plurality of data groups in the predetermined learning dataset, the plurality of images in the data group are a plurality of images including images of each of the plurality of particle size classes, and each of the plurality of images in the data group is linked to the particle size class of the image; In each of the plurality of data groups in the predetermined size determination data set, the plurality of images in the data group are a plurality of images including images with different content rates of particles belonging to a particle size class with a smallest particle size, and the content rate of each of the plurality of images in the data group is linked, the number of the unmachine-learned second machine learning models is the same as the number of the plurality of data groups, and the unmachine-learned second machine learning models are provided corresponding to each of the plurality of data groups; the machine learning step performs machine learning of an untrained second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset using a plurality of images in the data group; The output step outputs the probabilities of each of the plurality of particle size classes output from the second machine learning model trained in the machine learning step by inputting, for each of the plurality of data groups in the predetermined size determination data set, a plurality of images in the data group into the second machine learning model trained in the machine learning step using a data group in the predetermined training data set having the same image size as the image size in the data group. A method to help determine image size.

6. 1. An image size determination support program executed by a computer, which supports the determination of a size of an image to be used for determining a particle size class when particle sizes are divided into a plurality of particle size classes each having a different range, the program comprising: a first data acquisition step of acquiring a predetermined training data set; a second data acquisition step of acquiring a predetermined sizing data set; a machine learning process in which an image is input and a second machine learning model, which is not yet machine-learned, is trained by machine using the predetermined training data set acquired in the first data acquisition process, and which outputs, for each of the plurality of particle size classes, the probability that the input image is classified into that particle size class; an output step of inputting the predetermined size determination data set acquired in the second data acquisition step into a second machine learning model trained by machine learning in the machine learning step, and outputting the probabilities of each of the plurality of particle size classes output from the second machine learning model trained by machine learning in the machine learning step; each of the predetermined training dataset and the predetermined size determination dataset includes a plurality of data groups each including image data of a plurality of images; The plurality of data groups have different image sizes, In each of the plurality of data groups in the predetermined learning dataset, the plurality of images in the data group are a plurality of images including images of each of the plurality of particle size classes, and each of the plurality of images in the data group is linked to the particle size class of the image; In each of the plurality of data groups in the predetermined size determination data set, the plurality of images in the data group are a plurality of images including images with different content rates of particles belonging to a particle size class with a smallest particle size, and the content rate of each of the plurality of images in the data group is linked, the number of the unmachine-learned second machine learning models is the same as the number of the plurality of data groups, and the unmachine-learned second machine learning models are provided corresponding to each of the plurality of data groups; the machine learning step performs machine learning of an untrained second machine learning model corresponding to each of the plurality of data groups in the predetermined training dataset using a plurality of images in the data group; The output step outputs the probabilities of each of the plurality of particle size classes output from the second machine learning model trained in the machine learning step by inputting, for each of the plurality of data groups in the predetermined size determination data set, a plurality of images in the data group into the second machine learning model trained in the machine learning step using a data group in the predetermined training data set having the same image size as the image size in the data group. A program to help determine image size.

Images