Kneaded body quality prediction model generation method and quality prediction program

Abstract

To provide a kneaded body quality prediction model generation method for generating a quality prediction model of a kneaded body whose prediction accuracy is maintained even when a region to be imaged is displaced, and a quality prediction program for executing quality prediction of a kneaded body by the quality prediction model generated in the same method.SOLUTION: A kneaded body quality prediction model generation method comprises: a step (A) for receiving input of learning input data which includes multiple pieces of image data acquired by an imaging part which images a kneaded body which is kneaded and mixed by a kneading part and quality related data which is data related to quality of the kneaded body after kneading; a step (B) for cutting out a main region being a prescribed region in the image data for generating main region image data; a step (C) for cutting out a sub region whose part is overlapped to the main region in the image data for generating at least one piece of sub region image data; and (D) a step for receiving input of the main region image data, the sub region image data, and the quality related data and performing machine learning.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a quality prediction model generating method and a quality prediction program, and more particularly to a quality prediction model generating method and a quality prediction program for a kneaded body. [Background technology]

[0002] A kneaded body is a mixture of liquid materials such as water, materials such as powder, and solid materials such as aggregates, for example, a mixture of water, hydraulic hardening materials such as cement, fly ash, and blast furnace slag, and aggregates. Specific examples of the kneaded body include fresh concrete, fresh mortar, geopolymer, and fresh paste. The properties required for the kneaded body vary depending on the purpose of use and the environment of the site where it is used. Therefore, in the conventional manufacturing process of the kneaded body, the kneaded state was visually checked based on intuition and experience so that the kneaded body to be manufactured would meet the required properties, and then the product was shipped.

[0003] One of the important characteristics related to the quality of a concrete mixture is the slump value. The slump value is a value used as an index of the consistency of concrete before hardening, and generally, when an unhardened concrete mixture is shipped or unloaded, it is evaluated and inspected to see if its slump value is within the required range.

[0004] The evaluation results and inspection results of the slump value of the kneaded body are the standard for judging whether the manufactured kneaded body can be shipped or used at the unloading site. Therefore, it is expected that the slump value of the kneaded body can be predicted with high accuracy, as far as possible, without depending on the feeling or experience of the worker, before the kneaded body is shipped from the manufacturing plant.

[0005] Therefore, in recent years, in order to predict the slump value of a kneaded body with higher accuracy, a method has been proposed for predicting the slump value of a kneaded body using a prediction model generated by machine learning that applies training data that associates image data of the kneaded body in the kneading section with the slump value (see Patent Document 1 below). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2020-144132 A Summary of the Invention [Problem to be solved by the invention]

[0007] The prediction method described in Patent Document 1 can predict the slump value of the kneaded body with sufficiently high accuracy. Therefore, the present inventors have been actively studying how to further improve the accuracy of the prediction method described in Patent Document 1 and how to introduce the method to each production base, and have found the following problem.

[0008] The inventors prepared a quality prediction model capable of predicting quality-related indices based on the fluidity of the kneaded body, such as the slump value, or other quality-related indices of the kneaded body with sufficient prediction accuracy, and applied the model to devices installed at each production site to confirm whether the quality can be predicted with the expected accuracy. However, depending on the production site, the prediction accuracy may vary to an unacceptable extent.

[0009] Through extensive research, the inventors have discovered that the above results are caused by mechanical vibrations or sudden external forces occurring in the kneading section, or errors in machine control, which displace the area that the imaging section that captures the kneaded body attempts to capture, and the image data that is applied to the trained model for prediction ends up being image data that captures a position different from the area that was originally intended to be captured.

[0010] In view of the above problems, the present invention aims to provide a quality prediction model creation method for a kneaded body that can create a quality prediction model for a kneaded body in which prediction accuracy is maintained even when the area to be imaged is displaced, and a quality prediction program that performs quality prediction of a kneaded body using the quality prediction model created by the method. [Means for solving the problem]

[0011] The method for creating a quality prediction model of a kneaded body of the present invention includes the steps of: A step (A) of receiving input of learning input data including a plurality of image data acquired by an imaging unit that captures an image of the kneaded body being kneaded in the kneading unit and quality-related data that is data related to the quality of the kneaded body after kneading; A step (B) of extracting a main region, which is a predetermined region, from the image data to generate main region image data; (C) extracting a sub-region from the image data, the sub-region partially overlapping the main region, to generate at least one sub-region image data; The method further comprises a step (D) of inputting the main region image data, the sub-region image data, and the quality-related data and performing machine learning.

[0012] In this specification, the term "image data" is used to include still image data and video data. Video data is a collection of image data acquired at a specific frame rate, and still image data can be acquired by extracting one frame from video data. Therefore, video data and still image data are collectively referred to as "image data."

[0013] The mixing section is a component where the mixture is mixed, and includes a housing in which the mixture is housed and a stirring member for mixing the mixture. For example, the mixing section in the case of a mixture containing cement such as fresh concrete corresponds to a mixer in a ready-mixed concrete plant (concrete plant) or a concrete product plant, or an on-site plant installed at a construction site.

[0014] The quality prediction model created by the above-mentioned creation method is not based on learning input data in which only main region image data is associated with quality-related data, but on learning input data in which main region image data, sub-region image data surrounding the main region image data, and quality-related data are associated.

[0015] Therefore, the quality prediction model created by the above-mentioned creation method can predict quality in response to the displacement even if the region where the image data used for prediction is acquired is displaced from the region corresponding to the main region due to mechanical vibration, external force, or machine control error, because the quality prediction model has learned to associate the features appearing in the sub-region located around the main region with the quality-related data. In other words, the quality prediction model can maintain a relatively high prediction accuracy in quality prediction of the kneaded body compared to conventional quality prediction models, even if the imaging region is displaced due to mechanical vibration or external force.

[0016] In the above quality prediction model creation method, The step (C) includes extracting a plurality of the sub-regions, which are mutually different regions, from the image data to generate a plurality of the sub-region image data; The step (D) may be a method of performing machine learning based on the main region image data, the plurality of sub-region image data, and the quality-related data.

[0017] Furthermore, in the above quality prediction model creation method, The plurality of sub-regions may be regions positioned by shifting a predetermined number of pixels from the main region in at least one direction of pixel arrangement in the image data.

[0018] The quality prediction model created by the above-mentioned method can respond to different displacements of the imaging region due to mechanical vibrations, external forces, etc., because the model has been trained to associate the features appearing in the sub-regions corresponding to the respective displaced positions of the main region with the quality-related data, thereby making it possible to more reliably maintain high prediction accuracy.

[0019] The predetermined number of pixels is arbitrary. As a mere example, when the objective is to comprehensively acquire image data and respond to any displacement, the sub-regions may be regions shifted by one pixel from the main region. When the objective is to prioritize the arithmetic processing speed and reduce the image data to be applied to the quality prediction model, the sub-regions may be regions shifted by five pixels from the main region. Furthermore, it is assumed that the sub-regions are regions shifted by a predetermined number of pixels in two directions that define the pixel arrangement direction, that is, regions shifted not only in the vertical and horizontal directions but also in the diagonal direction.

[0020] The above quality prediction model creation method includes the following steps: A step (E) of identifying a structure region in which the structure of the kneading unit is reflected in the image data based on the magnitude of the change in luminance over time in the image data; The method may further include a step (F) of determining, as the main region, a region located in the vicinity of the structure region identified in the step (E).

[0021] The structural body of the kneading section corresponds to, for example, the rotating shaft of the mixer, the stirring blade, or a connecting portion thereof.

[0022] In addition, in this specification, the term "vicinity of the structure region" is used to mean any of (1) parts of both rotating shafts, (2) at least one part of the tip portions of the multiple agitator blades, and (3) at least one part of the fixed portions of the rotating shaft and the multiple agitator blades, as well as an area into which the kneaded body or the material of the kneaded body may be reflected.

[0023] According to the above method, even when the material of the kneaded body is scattered and the area where the structure is reflected is difficult to distinguish from the appearance, the area where the structure is reflected can be relatively accurately determined. Moreover, the larger the movement of the kneaded body, the more likely the characteristics of the kneaded body during kneading are to appear. And, the quality prediction model created by the above-mentioned creation method can determine, as the main area, the area near the structure where the kneaded body that moves relatively greatly due to the kneading operation is likely to be reflected.

[0024] The quality prediction program of the present invention is A program executed by a computer to predict the quality of a kneaded body, A step of photographing the kneaded body being kneaded in the kneading section to obtain a plurality of image data; inputting the plurality of image data into the quality prediction model; and outputting quality-related information regarding the quality-related data corresponding to the plurality of image data. Effect of the Invention

[0025] According to the present invention, a quality prediction model creation method for a kneaded body is provided that can create a quality prediction model for a kneaded body that maintains prediction accuracy even when the area to be imaged is displaced, and a quality prediction program is provided that performs quality prediction of a kneaded body using the quality prediction model created by the method. [Brief description of the drawings]

[0026] [Figure 1] FIG. 1 is a block diagram showing an overall configuration of an embodiment of a quality prediction model creation system. [Diagram 2] 1 is a diagram showing a schematic view of a scene in a mixer in which a kneaded material is being mixed. [Diagram 3] 1 is a diagram showing a schematic view of a scene in a mixer in which a kneaded material is being mixed. [Figure 4] 1 is a diagram virtually expressing pixel regions for image data of a shooting region. [Diagram 5]10 is a flowchart showing a processing operation for creating learning input data executed by a calculation processing unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] The method for creating a quality prediction model for a kneaded body of the present invention will be described below with reference to the drawings as appropriate. Note that the drawings are all schematic illustrations, and the numbers on the drawings do not necessarily correspond to the actual numbers.

[0028] The method for creating a quality prediction model of a kneaded body of the present invention is a method for creating a quality prediction model of a kneaded body by performing machine learning based on image data obtained by an imaging unit photographing the kneaded body being kneaded in a mixer corresponding to a kneading unit, and learning input data including quality-related data of the kneaded body. Note that, although the following embodiment will be described on the premise that the quality information data is a slump value, the quality information data may be other information.

[0029] Specifically, the quality prediction data is data including information on the fluidity of the mixture (for example, slump and slump flow). The quality prediction information of fresh concrete in the following description of the embodiment is a slump value, but other information related to the quality of fresh concrete may be adopted. The quality prediction model generated by the quality prediction model creation system 1 of the embodiment described below can capture changes in the state of fresh concrete more accurately, and therefore can adequately predict indices related to the consistency and fluidity of fresh concrete. Furthermore, the quality prediction model generated by the quality prediction model creation system 1 can predict other qualities besides the indices related to the consistency and fluidity of fresh concrete based on the above associations.

[0030] First, the relationship between information extracted from image data (hereinafter referred to as "image extraction information") and the quality of the mixture will be described. As described above, the mixture is a mixture of liquid materials such as water, materials such as powder, and solid materials such as aggregates, for example, a mixture of water and construction materials such as cement, fly ash, and blast furnace slag. Specific examples of the mixture include fresh concrete, fresh mortar, geopolymer, and fresh paste.

[0031] [Image extraction information] The image extraction information is information extracted from image data of the kneaded body being kneaded in the kneading section, and is an element for grasping the viscosity, water content, etc. of the kneaded body and predicting the state of the kneaded body after a predetermined time has passed. Therefore, quality prediction information related to the predicted value of the quality of the kneaded body can be associated with the image extraction information.

[0032] Therefore, by applying a quality prediction model for predicting the quality of a kneaded body generated by machine learning using learning input data including image extraction information and learning output data including quality prediction information, it is possible to predict the quality of the kneaded body to be manufactured.

[0033] Specifically, the image extraction information includes the amplitude of the surface of the kneaded body, the depth to which the kneaded body is sunk by the blades of the stirring member, the size and shape of the aggregate, etc. The image extraction information applied to the quality prediction model may be one of the above image extraction information or a combination of two or more of them.

[0034] The number of samples of teacher data used for training the trained model is preferably 100 or more, more preferably 1,000 or more, even more preferably 10,000 or more, even more preferably 50,000 or more, and particularly preferably 100,000 or more, from the viewpoint of extracting features necessary for deriving slump information from the training input data and further improving the prediction accuracy. Furthermore, the number of training times for each trained model can be, for example, 1,000 or more, but is not particularly limited.

[0035] Specifically, in the case of a kneaded body, it is preferable to obtain image data of multiple batches of the kneaded body and use it as input data for learning, but it is also acceptable to adopt image data of only one batch of the kneaded body as training data.

[0036] Next, the machine learning method used in the quality prediction model creation system of the present invention will be described. Examples of the machine learning method used in the quality prediction model creation system of the present invention include neural networks, linear regression, decision trees, support vector regression, ensemble methods, support vector machines, discriminant analysis, naive Bayes methods, nearest neighbor methods, etc. These methods may be used alone or in combination of two or more.

[0037] Among these methods, machine learning using a neural network is preferably selected from the viewpoint of being able to predict quality with higher accuracy. As the neural network, a hierarchical neural network having one or more intermediate layers between an input layer and an output layer is preferable from the viewpoint of being able to predict quality with higher accuracy.

[0038] Examples of neural networks include convolutional neural networks (CNNs) such as 3D Convolutional Neural Networks (3DCNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) neural networks (recurrent neural networks improved using LSTM).

[0039] Among these, a three-dimensional convolutional neural network (a neural network having a convolutional layer, a pooling layer, or the like as an intermediate layer) is more suitable, since it has excellent performance in the field of image recognition and is related to the time axis. A three-dimensional convolutional neural network can detect features (including features that change with time) from multiple image data acquired at different times, and create a quality prediction model capable of performing classification or regression using the features. In a convolutional neural network, the number of layers consisting of a combination of a convolutional layer and a pooling layer is preferably two or more, more preferably three or more, from the viewpoint of being able to perform prediction with higher accuracy.

[0040] In addition, as a tool for performing machine learning, for example, "TensorFlow (registered trademark)", a software library developed by Google, or "IBM Watson (registered trademark)", a system developed by IBM, can be used.

[0041] Next, a specific configuration of the quality prediction model creation system 1 will be described.

[0042] The configuration of this embodiment of the quality prediction model creation system 1 of the present invention will be described. Fig. 1 is a block diagram showing the overall configuration of one embodiment of the quality prediction model creation system 1. As shown in Fig. 1, the quality prediction model creation system 1 is composed of a data input unit 10, a calculation processing unit 11, and a model storage unit 12.

[0043] Fig. 2 is a diagram showing a schematic view of a state in the mixer 2 where the kneaded material C1 is being mixed. Fig. 3 is a diagram showing a schematic view of a state in the mixer 2 where the kneaded material C1 is being mixed, as viewed from a different direction from that in Fig. 2.

[0044] In reality, the quality prediction model creation system 1 would capture images of the inside of the mixer 2 during mixing to obtain image data. However, for ease of explanation, Figures 2 and 3 show a schematic diagram of the mixer 2 with mixing stopped so that the condition inside the mixer 2 can be easily confirmed.

[0045] 1, the data input unit 10 of this embodiment accepts input of image data d1 acquired by the imaging unit 20 as learning input data. Then, the data input unit 10 converts the image data d1 into image data d2 applicable to the arithmetic processing unit 11 and inputs it to the arithmetic processing unit 11. If the arithmetic processing unit 11 is configured to be able to process the image data d1 as is, the data input unit 10 may be configured to input the image data d1 as is to the arithmetic processing unit 11 as image data d2.

[0046] In this embodiment, the image data d1 is directly input from the imaging unit 20 to the data input unit 10, but the image data d1 input to the data input unit 10 may be data stored in a memory unit provided in a data server, a cloud server, a smartphone or a PC, or a dedicated storage device.

[0047] 3, the imaging unit 20 is fixed at a position where the height from the liquid surface when stationary is h1. The height h1 is set arbitrarily depending on the shape and size of the mixer 2, and is set within a range of 50 cm to 300 cm, for example.

[0048] The imaging unit 20 may be, for example, a camera that captures still image data at a predetermined time interval, or a video camera that captures moving image data.

[0049] 1, the arithmetic processing unit 11 includes a main region determination unit 11a, a main region image generation unit 11b, a sub-region image generation unit 11c, and a learning unit 11d. Note that the arithmetic processing unit 11 is configured by an arithmetic processing device such as a CPU or an MPU, but does not necessarily have to be configured by one device or IC chip, and may be configured by combining multiple devices or multiple IC chips.

[0050] Fig. 4 is a diagram virtually expressing the pixel P1 region for image data d2 of the photographed region 20a. For convenience of explanation, in Fig. 4, one pixel is illustrated much larger than usual. In Fig. 4, the pixels of the image data d2 are arranged along the X direction and the Y direction which are perpendicular to each other, and the axial direction of the rotation shaft 3a of the stirring member 3 is illustrated as the Y direction, and the following explanation will be based on this definition.

[0051] When the image data d2 is input, the main region determination unit 11a determines a structure region A1 in which the structure of the mixer 2 is reflected. The structure region A1 may be determined simply based on the position of the stirring member 3 reflected in the image data d2, but it is assumed that the material of the kneaded body is scattered and the stirring member 3 in the image data d2 is difficult to determine by appearance. In such a case, for example, the region in which the structure is reflected can be determined by referring to a plurality of time-series image data d2 and referring to the magnitude of the change in brightness over time. Note that, as a mere example, the structure region A1 is adopted as a fixed portion between the rotating shaft 3a and the stirring blade 3b of the stirring member 3, as shown in FIG. 4.

[0052] The main region determination unit 11a determines an area in the image data d2 to be the main region 21, which corresponds to the area indicated by the solid line in Fig. 4, and outputs image data d4 to which information on the main region 21 is added to the main region image generation unit 11b. Note that this determination process may be performed on image data obtained by cutting out a part of the image data of the shooting region 20a.

[0053] The main region image generating unit 11b cuts out the region determined as the main region 21 in the image data d4, and outputs the main region image data d3 to the learning unit 11d. Furthermore, when the generation of the main region image data d3 is completed, the main region image generating unit 11b outputs the image data d4 to the sub-region image generating unit 11c.

[0054] The sub-region image generating unit 11c determines a sub-region 22 that partially overlaps with the main region 21 in the image data d4, and generates sub-region image data d5 by cutting out the sub-region 22. The sub-region image generating unit 11c then outputs the generated sub-region image data d5 to the learning unit 11d.

[0055] The sub-region 22 may be one region or multiple regions. In this embodiment, the sub-region 22 is multiple, but in Fig. 4, only one sub-region 22 is illustrated by a dashed line in order to avoid complication of the illustration.

[0056] The sub-region 22 may be selected arbitrarily, but in this embodiment, the sub-region 22 is specifically a region of 5×5=25 pixels, the same as the main region 21, and eight regions are selected with the main region 21 as the reference (X,Y)=(-3,-3), (0,-3), (+3,-3), (-3,0), (+3,0), (-3,+3), (0,+3), (+3,+3), with the main region 21 as the reference (X,Y)=(0,0). These correspond to the regions shifted by 3 pixels in each of the X and Y directions with the main region 21 as the reference.

[0057] The number of pixels to be shifted is set arbitrarily from the viewpoint of the number of image data to be applied to the learning unit 11d and realizing an expected processing speed, but is preferably between 1 pixel and (the number of pixels in the X direction or Y direction of the main region 21 / 2).In addition, instead of setting a specific numerical value in advance, it is also possible to grasp the range in which the shooting range of the imaging unit for acquiring image data to be applied to the quality prediction model will be displaced or acquire it as measurement data, and set the number manually or automatically based on the grasped data.

[0058] As a different example from the above, in the case of a mixer whose rotation axis is grounded in a direction different from that of the mixers shown in Figures 2 and 3, natural vibrations are likely to occur in the direction perpendicular to the rotation axis. Therefore, even if the imaging unit 20 itself is fixed in a predetermined position and there is no change in position, the shooting area 20a of the imaging unit 20 may change due to deviation caused by the rotation of the mixer. When such vibrations are expected, it is preferable to set the sub-area 22 to an area that is shifted by 1 to 10 pixels in the direction perpendicular to the rotation axis.

[0059] The learning unit 11d executes machine learning based on the main region image data d3 input from the main region image generating unit 11b, the sub region image data d5 input from the sub region image generating unit 11c, and the slump value data d6 of the kneaded body depicted in the image data d1, which is one of the learning input data and is read from the data server 30. The learning unit 11d executes machine learning to generate a quality prediction model M1 and stores it in the model storage unit 12.

[0060] Next, with reference to the drawings, an operation related to the generation of image data (d3, d5) included in the learning input data in the arithmetic processing unit 11 will be described.

[0061] FIG. 5 is a flowchart showing the processing operation for creating learning input data executed by the arithmetic processing unit 11, and more specifically, a flowchart showing the process of creating image data (d3, d5) to be input to the learning unit 11d.

[0062] Image data d1 is input from the imaging unit 20 to the data input unit 10. The step of inputting this image data d1 corresponds to step (A). When image data d2 is input from the data input unit 10 to the calculation processing unit 11, creation of learning input data is started. As shown in FIG. 5, when creation of learning input data is started, the main region determination unit 11a identifies a structure region A1 in the image data d2 (step S1). This step S1 corresponds to step (E).

[0063] After the structure region A1 is specified by step S1, the main region determining unit 11a determines a region in which the kneaded body or the material of the kneaded body may be reflected, together with any one of (1) parts of both rotating shafts, (2) at least one part of the tip parts of the plurality of stirring blades, or (3) at least one part of the fixed parts of the rotating shaft and the plurality of stirring blades, as the main region 21 (step S2). This step S2 corresponds to the process (F). Note that steps S1 and S2 may not be performed, and the main region 21 may be a predetermined region in the image data d1.

[0064] The main region image generating unit 11b cuts out the region determined to be the main region 21 from the image data d4 in step S2, and generates main region image data d3 (step S3). This step S3 corresponds to process (B). The main region image generating unit 11b then outputs the main region image data d3 generated in step S3 to the learning unit 11d, and outputs the image data d4 to the sub-region image generating unit 11c.

[0065] When the image data d4 is input, the sub-region image generating unit 11c determines, as sub-regions 22, each region located at the coordinate positions as described above with respect to the main region 21 from the image data d4 (step S4). The sub-region image generating unit 11c then cuts out the regions determined as the sub-regions 22 from the image data d4 in step S4, and generates multiple sub-region image data d5 (step S5). Steps S4 and S5 correspond to process (C). The sub-region image generating unit 11c then outputs the multiple sub-region image data d5 generated in step S5 to the learning unit 11d.

[0066] Through the above steps, image data (d3, d5) to be input to the learning unit 11d is created.

[0067] By performing machine learning based on data in which the image data (d3, d5) created through the above-mentioned process is associated with quality-related data, the generated quality prediction model M1 maintains higher prediction accuracy than conventional quality prediction models, even when image data is applied that is slightly displaced from the position corresponding to the main region 21 due to mechanical vibration, external force, or machine control error, etc.

[0068] The configuration of the quality prediction model creation system 1 described above is merely an example, and the present invention is not limited to the illustrated configurations. For example, the quality prediction model creation system 1 may be realized by installing a quality prediction model creation program that executes the above-mentioned steps (S1 to S5) in a computer such as a PC. The quality prediction model creation program may be configured to cause a computer to execute the steps required by the quality prediction model creation system 1 among the above-mentioned steps (S1 to S5).

[0069] Furthermore, a computer can be configured to configure a program for predicting the quality of a mixed material by utilizing the quality prediction model created by the above-mentioned quality prediction model creation system 1. By way of example only, when installed in a computer, the program is configured to cause the computer to execute a series of operations, such as photographing a mixed material being mixed in a mixing section of a ready-mix concrete manufacturing plant or the like to obtain multiple pieces of image data, inputting the multiple pieces of image data into the quality prediction model created by the quality prediction model creation system 1, and outputting quality-related information regarding the quality-related data corresponding to the multiple pieces of image data.

[0070] It should be noted that the terms "executed by a computer" and "installed on a computer" mentioned here do not only refer to a case where one terminal executes all processing on its own, but also to a complex system that can be essentially regarded as a single computer, consisting of multiple terminals connected via a network. [Explanation of symbols]

[0071] 1: Quality prediction model creation system 2: Mixer 3: Stirring member 3a: Rotation axis 10: Data entry section 11: Processing section 11a: Judgment part 11b: Measuring section 11c: Image correction section 11d: Learning Department 12: Model storage section 20: Imaging section 20a: Shooting area 21 : Main area 22 : Sub area 30: Data Server A1: Structure area C1: Kneaded body M1: Quality prediction model

Claims

1. A step (A) of receiving input of learning input data including a plurality of image data acquired by an imaging unit that captures an image of the kneaded body being kneaded in the kneading unit and quality-related data that is data related to the quality of the kneaded body after kneading; A step (B) of extracting a main region, which is a predetermined region, from the image data to generate main region image data; (C) extracting a sub-region from the image data, the sub-region partially overlapping the main region, to generate at least one sub-region image data; A method for generating a quality prediction model of a kneaded body, comprising a step (D) of inputting the main region image data, the sub-region image data, and the quality-related data and performing machine learning.

2. The step (C) includes extracting a plurality of the sub-regions, which are mutually different regions, from the image data to generate a plurality of the sub-region image data; The method for generating a quality prediction model of a kneaded body according to claim 1, characterized in that the step (D) comprises performing machine learning based on the main region image data, the plurality of sub-region image data, and the quality-related data.

3. The method for generating a quality prediction model of a kneaded body as described in claim 2, characterized in that the multiple sub-regions are each regions shifted a predetermined number of pixels from the main region in at least one direction of pixel arrangement in the image data.

4. A step (E) of identifying a structure region in which a structure provided in the kneading unit is reflected in the image data based on a magnitude of a change in luminance over time in the image data; The method for generating a quality prediction model of a kneaded body according to any one of claims 1 to 3, further comprising a step (F) of determining, as the main region, a region located in the vicinity of the structure region identified in the step (E).

5. A program executed by a computer to predict the quality of a kneaded body, A step of photographing the kneaded body being kneaded in the kneading section to obtain a plurality of image data; A step of inputting the plurality of image data into the quality prediction model according to claim 1; and outputting quality-related information regarding the quality-related data corresponding to the plurality of image data.

Images