Production support method, production support program, and production support apparatus

Abstract

To facilitate managing the quality of ready-mixed concrete.SOLUTION: A production support method includes: a quality prediction step of predicting the quality related to a grain size of aggregate to be evaluated; and composition calculation step of calculating a corrected value for the composition of concrete in accordance with a result predicted in the quality prediction step. The quality prediction step includes: an evaluation information acquisition step of acquiring evaluation input information based on captured image data obtained by imaging the aggregate to be evaluated; and a prediction step of calculating a fineness modulus of the aggregate to be evaluated, on the basis of the evaluation input information and a prediction model which is constructed to output a value indicating the fineness modulus in accordance with an input of input information, by machine learning based on the input information based on learning image data obtained by imaging aggregate for learning and based on a ground truth value of fineness modulus associated with the input information.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present disclosure relates to a manufacturing support method, a manufacturing support program, and a manufacturing support apparatus. [Background technology]

[0002] Patent Document 1 discloses a method for estimating the particle size distribution of soil. Patent Document 2 discloses a method for estimating the quality of aggregate. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-117625 [Patent Document 2] JP 2021-135199 A Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a production support method, a production support program, and a production support device that are useful for facilitating quality control of ready-mix concrete. [Means for solving the problem]

[0005] [1] A method for supporting a manufacturing device that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, the method comprising: a quality prediction step of predicting quality related to the grain size of the aggregate to be evaluated; and a mix calculation step of calculating a correction value for the concrete mix depending on a prediction result in the quality prediction step, the quality prediction step including: an evaluation information acquisition step of acquiring evaluation input information based on image data obtained by imaging the aggregate to be evaluated; and a prediction step of calculating the coarse grain ratio of the aggregate to be evaluated based on the evaluation input information and a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training and a ground truth value of the coarse grain ratio associated with the input information, the prediction model being constructed so as to output a value indicating the coarse grain ratio in response to input of the input information. It is also conceivable to use the value actually measured using a sieve to calculate the correction value of the concrete mix and then adjust the mix. On the other hand, it is not practical to actually measure the quality of the particle size using a sieve because it takes time. In contrast, in the above-mentioned manufacturing support method, a predicted value of the quality of the particle size is obtained from image data using the prediction model M, and a correction value for correcting the mix is ​​calculated according to the predicted value. The quality prediction work using the prediction model M is much simpler than the case of actual measurement, which takes about a few seconds, and it is also easy to increase the frequency of obtaining the predicted value. As a result, even if the concrete mix is ​​adjusted according to the quality of the aggregate, the work man-hours do not increase significantly. Therefore, it is useful for facilitating the quality control of ready-mix concrete.

[0006] [2] A method for supporting a manufacturing device that produces ready-mix concrete by mixing concrete materials including fine aggregate and coarse aggregate, the manufacturing support method including: a quality prediction step of predicting quality related to the granularity of the aggregate to be evaluated; and a mix calculation step of calculating a correction value for the concrete mix depending on a prediction result in the quality prediction step, the quality prediction step including: an evaluation information acquisition step of acquiring evaluation input information based on image data obtained by imaging the aggregate to be evaluated; and a prediction step of calculating a value indicating the quality of the aggregate to be evaluated based on the evaluation input information and a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training and on the ground-truth values ​​of the mass fraction of each of a plurality of granularity classifications of the aggregate associated with the input information, the prediction model being constructed so as to output a value indicating the mass fraction for each classification included in the plurality of granularity classifications in response to input of the input information, and the evaluation input information. This manufacturing support method, like the method described in [1] above, is useful for facilitating quality control of ready-mix concrete.

[0007] [3] The manufacturing support method described in [2] above, wherein the value indicating the quality is the coarse aggregate ratio, the amount of oversized aggregate, or the amount of undersized aggregate. In this case, the mix proportions of the concrete material can be appropriately adjusted (corrected).

[0008] [4] The manufacturing support method according to any one of the above [1] to [3], wherein the mixture is a fine aggregate ratio, a bulk volume of coarse aggregate, or a unit water content of concrete. In this case, it becomes possible to adjust the quality related to the aggregate grading so that it falls within an appropriate control range.

[0009] [5] A manufacturing support method according to any one of the above [1] to [4], wherein in the prediction step, the coarse aggregate ratio of the aggregate to be evaluated is calculated, and the mixture is a fine aggregate ratio or a coarse aggregate bulk volume, and in the mixture calculation step, if the predicted result of the coarse aggregate ratio in the quality prediction step is smaller than a reference value, the correction value is calculated in accordance with the difference between the predicted result of the coarse aggregate ratio and the reference value so that the ratio of the amount of fine aggregate to the amount of the entire aggregate is reduced, and if the predicted result of the coarse aggregate ratio in the quality prediction step is larger than the reference value, the correction value is calculated in accordance with the difference between the predicted result of the coarse aggregate ratio and the reference value so that the ratio of the amount of fine aggregate to the amount of the entire aggregate is increased. In this case, it becomes possible to adjust the coarse aggregate ratio of the aggregate being evaluated so that it falls within an appropriate control range.

[0010] [6] The manufacturing support method according to any one of [1] to [5] above, further comprising a recording step of: calculating a coarse aggregate ratio of the aggregate to be evaluated in the prediction step; and recording the prediction result of the coarse aggregate ratio and the captured image data after associating the captured image data with the prediction result of the coarse aggregate ratio each time the coarse aggregate ratio of the aggregate to be evaluated is calculated in the quality prediction step. In this case, the user can easily grasp information regarding the input that is the factor that resulted in the prediction result of the coarse grain ratio.

[0011] [7] The manufacturing support method according to any one of [1] to [6] above, further comprising an imaging step of imaging the aggregate to be evaluated multiple times, and a quality prediction output step, wherein in the prediction step, a coarse aggregate ratio of the aggregate to be evaluated is calculated, the evaluation information acquisition step and the prediction step are performed for each of the multiple images, and in the quality prediction output step, an average value of the calculation results of the coarse aggregate ratio in the prediction step for each of the multiple images is output as a prediction result of the coarse aggregate ratio. In this case, even if there are variations in imaging and prediction, a stable calculation result of the predicted value can be obtained.

[0012] [8] The manufacturing support method according to any one of the above [1] to [7], wherein in the prediction step, a coarse aggregate ratio of the aggregate to be evaluated is calculated, and the manufacturing support method further includes an actual measurement information acquisition step of acquiring an actual measurement value of the coarse aggregate ratio obtained from an aggregate to be measured which corresponds to the aggregate to be evaluated and image data of the aggregate to be measured which is associated with the actual measurement value, and a model updating step of updating the prediction model based on the data acquired in the actual measurement information acquisition step. In this case, by using the actual measured value of the coarse grain ratio, it is possible to easily update the model, which may improve the prediction accuracy.

[0013] [9] A program for supporting a manufacturing device that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, the program causing a computer to execute a quality prediction step of predicting quality related to the grain size of the aggregate to be evaluated, and a mix calculation step of calculating a correction value for the concrete mix depending on a prediction result in the quality prediction step, the quality prediction step including: an evaluation information acquisition step of acquiring evaluation input information based on image data obtained by imaging the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training and a ground truth value of the coarse grain ratio corresponding to the input information, the prediction model being constructed to output a value indicating the coarse grain ratio depending on input information, and a prediction step of calculating the coarse grain ratio of the aggregate to be evaluated based on the evaluation input information. This manufacturing support program, like the method described in [1] above, is useful for facilitating quality control of ready-mix concrete.

[0014]

[10] A program for supporting a manufacturing device that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, the program causing a computer to execute a quality prediction step of predicting quality related to the granularity of an aggregate to be evaluated, and a mix calculation step of calculating a correction value for the concrete mix depending on a prediction result in the quality prediction step, the quality prediction step including: an evaluation information acquisition step of acquiring evaluation input information based on image data obtained by imaging the aggregate to be evaluated; and a prediction step of calculating a value indicating the quality of the aggregate to be evaluated based on the evaluation input information and a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training, and on the ground-truth values ​​of the mass fractions of each of a plurality of granularity classifications of the aggregate associated with the input information, the prediction model being configured to output a value indicating the mass fraction for each classification included in the plurality of granularity classifications in accordance with the input of the input information, and the evaluation input information. This manufacturing support program, like the method described in [2] above, is useful for facilitating quality control of ready-mix concrete.

[0015]

[11] A device for supporting a manufacturing device that produces ready-mix concrete by mixing concrete materials including fine aggregate and coarse aggregate, the device comprising: a quality prediction unit that predicts quality related to the grain size of the aggregate to be evaluated; and a mix calculation unit that calculates a correction value for the concrete mix in accordance with a prediction result by the quality prediction unit. The quality prediction unit has: an evaluation information acquisition unit that acquires evaluation input information based on captured image data obtained by imaging the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training and on a ground truth value of the coarse grain ratio corresponding to the input information, the prediction model being configured to output a value indicating the coarse grain ratio in accordance with input of the input information; and a prediction calculation unit that calculates the coarse grain ratio of the aggregate to be evaluated based on the evaluation input information. This manufacturing support device is useful for facilitating quality control of ready-mix concrete, similar to the method described in [1] above.

[0016]

[12] A device for supporting a manufacturing device that produces ready-mix concrete by mixing concrete materials including fine aggregate and coarse aggregate, the device comprising: a quality prediction unit that predicts quality related to the granularity of the aggregate to be evaluated; and a mix calculation unit that calculates a correction value for the concrete mix in accordance with a prediction result by the quality prediction unit, wherein the quality prediction unit has: an evaluation information acquisition unit that acquires evaluation input information based on image data obtained by imaging the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for training and on the ground-truth values ​​of the mass fraction of each of a plurality of granularity classifications of the aggregate associated with the input information, so as to output a value indicating the mass fraction for each classification included in the plurality of granularity classifications in accordance with the input of the input information; and a prediction calculation unit that calculates the value indicating the quality of the aggregate to be evaluated based on the evaluation input information. This manufacturing support device, like the method described in [2] above, is useful for facilitating quality control of ready-mix concrete. Effect of the Invention

[0017] According to the present disclosure, there are provided a production support method, a production support program, and a production support device that are useful for facilitating quality control of ready-mix concrete. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is a schematic diagram illustrating a ready-mix concrete production system and a production support device. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of the manufacturing support device. [Diagram 3] FIG. 3 is a block diagram illustrating an example of a functional configuration of the manufacturing support device. [Figure 4] Fig. 4(a) is a schematic diagram showing an example of a predictive calculation using a predictive model, and Fig. 4(b) is a cross-sectional view showing a schematic diagram of acquiring image data for learning. [Diagram 5] FIG. 5 is a diagram showing an example of image data for learning. [Figure 6] 6(a) and 6(b) are graphs showing an example of the comparison result between the predicted value and the correct value. [Figure 7] FIG. 7 is a flowchart illustrating an example of a process executed by the manufacturing support device. [Figure 8] FIG. 8 is a schematic diagram showing an example of a display screen on a monitor. [Figure 9] 9(a) and 9(b) are flowcharts illustrating an example of processing executed by the manufacturing support device. [Figure 10] FIG. 10 is a flowchart illustrating an example of a process executed by the manufacturing support device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] Hereinafter, an embodiment will be described with reference to the drawings. In the description, the same elements or elements having the same functions are given the same reference numerals, and duplicated descriptions will be omitted. Fig. 1 shows a schematic diagram of a manufacturing support device according to an embodiment and a ready-mix concrete manufacturing system in which the manufacturing support device is used.

[0020] [Ready-mix concrete manufacturing system] First, an overview of a ready-mix concrete manufacturing system will be described. A manufacturing system 100 (manufacturing device) shown in Fig. 1 is a system that manufactures ready-mix concrete. The manufacturing system 100 kneads and mixes concrete materials to manufacture (produce) ready-mix concrete.

[0021] The concrete materials used in the manufacturing system 100 include cement, admixtures, coarse aggregates, fine aggregates, water, and admixtures. Examples of the coarse aggregates include gravel, crushed stone, slag coarse aggregates, lightweight coarse aggregates, recycled coarse aggregates, reclaimed aggregates, and coarse aggregates made by mixing these. Examples of the gravel include mountain gravel, land gravel, river gravel, and sea gravel. Examples of the slag coarse aggregates include blast furnace slag aggregates, ferronickel slag aggregates, electric furnace oxidized slag aggregates, and coal gasification slag aggregates. Examples of the lightweight coarse aggregates include natural lightweight aggregates, by-product lightweight aggregates, and artificial lightweight aggregates. The coarse aggregates may include crushed rock, or limestone crushed stone.

[0022] Examples of fine aggregates include sand, crushed sand, slag fine aggregate, lightweight fine aggregate, recycled fine aggregate, recovered aggregate, and fine aggregates made by mixing these. Sand includes mountain sand, land sand, river sand, sea sand, etc. Slag fine aggregates include blast furnace slag aggregate, ferro-nickel slag aggregate, copper slag aggregate, electric furnace oxidized slag aggregate, coal gasification slag aggregate, etc. Lightweight fine aggregates include natural lightweight aggregate, by-product lightweight aggregate, artificial lightweight aggregate, etc.

[0023] Examples of rock types of crushed stone and crushed sand include igneous rocks, sedimentary rocks, metamorphic rocks, quartzite, limestone, domalite, and peridotite. Igneous rocks include granite, diorite, gabbro, porphyrite, diabase, rhyolite, andesite, basalt, and serpentine. Sedimentary rocks include conglomerate, sandstone, shale, slate, and tuff. Metamorphic rocks include gneiss and schist. In the present disclosure, coarse aggregate and fine aggregate may be collectively referred to as "aggregate". In this case, "aggregate" refers to coarse aggregate, fine aggregate, or both coarse aggregate and fine aggregate.

[0024] The manufacturing system 100 loads the manufactured ready-mix concrete onto a transport vehicle 200. After the ready-mix concrete is loaded, the transport vehicle 200 transports the ready-mix concrete to a site (e.g., a construction site) where the ready-mix concrete is to be used. Examples of the transport vehicle 200 include an agitator vehicle (mixer vehicle) or a dump truck. The manufacturing system 100 may manufacture ready-mix concrete from concrete materials so as to satisfy a target quality (required quality) set for each site. In one example, the target quality of the ready-mix concrete includes a target value for slump or slump flow. The manufacturing system 100 includes, for example, a material storage yard 101, a transport device 104, and a manufacturing device 110.

[0025] The material yard 101 is a place where concrete materials are stored. The material yard 101 includes a plurality of silos 102. The plurality of silos 102 are containers that store at least a portion of the concrete materials by material type. The plurality of silos 102 include a silo 102 that stores coarse aggregate, a silo 102 that stores fine aggregate, and a silo 102 that stores cement.

[0026] The transporting device 104 is a device that transports the concrete materials stored in the multiple silos 102 to the manufacturing device 110. The transporting device 104 includes, for example, a belt conveyor that transports the concrete materials. The transporting device 104 may transport the concrete materials by type at different times. In one example, based on an operation instruction from a control device included in the manufacturing system 100, a specific material from among the various concrete materials is transferred to the transporting device 104 and transported to the manufacturing device 110.

[0027] The manufacturing apparatus 110 is an apparatus for manufacturing ready-mixed concrete by mixing concrete materials including aggregate. The manufacturing apparatus 110 includes, for example, a storage bottle 111, a measuring bottle 112, a collecting hopper 113, a mixer 114, and a loading hopper 115.

[0028] Storage bottle 111 temporarily stores various types of concrete materials. Various types of concrete materials are transported (conveyed) to storage bottle 111 from material storage yard 101 by transport device 104. Storage bottle 111 is configured to store various types of concrete materials individually. Hereinafter, "concrete material" may be simply referred to as "material". Various materials stored in storage bottle 111 are supplied to measuring bottle 112 as necessary.

[0029] The measuring bottle 112 is disposed below the storage bottle 111. The measuring bottle 112 operates based on an operation command from the control device, and weighs each material individually. When the measuring bottle 112 detects a target amount of material instructed by the control device, it supplies the material to the collecting hopper 113. When water is supplied to the measuring bottle 112, an admixture may be mixed into the water. The collecting hopper 113 is disposed below the measuring bottle 112. The collecting hopper 113 collects each material discharged from the measuring bottle 112, and supplies the collected materials to the mixer 114. Note that the collecting hopper 113 does not have to be provided, and in this case, each material is supplied from the measuring bottle 112 to the mixer 114.

[0030] The mixer 114 is disposed below the collecting hopper 113. The mixer 114 is a device that mixes concrete materials. The mixer 114 produces ready-mixed concrete by mixing (kneading) aggregate, cement, water, admixtures, and the like. The ready-mixed concrete is discharged from the bottom of the mixer 114 into the loading hopper 115. The loading hopper 115 is disposed below the mixer 114, and temporarily stores the ready-mixed concrete. The loading hopper 115 supplies the temporarily stored ready-mixed concrete to the transport vehicle 200.

[0031] The manufacturing system 100 described above is one example of a ready-mix concrete manufacturing system, and the ready-mix concrete manufacturing system may be configured in any manner as long as it is capable of mixing concrete materials and manufacturing ready-mix concrete.

[0032] [Manufacturing support equipment] The production support device 1 is a device that supports the production of ready-mix concrete by the production system 100. The production support device 1 predicts the quality (e.g., coarse aggregate ratio) related to the grain size of the aggregate to be evaluated, and calculates a correction value for the concrete mix according to the predicted quality. The production support device 1 is also a quality prediction device that predicts the above quality.

[0033] The manufacturing support device 1 is configured with one or more computers. The computer configuring the manufacturing support device 1 may be a personal computer, a tablet computer (tablet terminal), a smartphone, a wearable device, a workstation, a server computer, or a general-purpose computer. The manufacturing support device 1 may be connected to a communication network via a wired or wireless connection. When the manufacturing support device 1 is configured with two or more computers, the computers are connected to each other so as to be able to communicate with each other via a wired, wireless, or communication network.

[0034] The manufacturing support device 1 includes, for example, a main body 10, an input device 12, a monitor 14, and a camera 16. The main body 10 is a device (computer main body) that executes the main functions of the computer that constitutes the manufacturing support device 1.

[0035] The input device 12 is a device for inputting information to the main body 10. The input device 12 may be any device capable of inputting desired information, and specific examples thereof include operation interfaces such as a keypad, a mouse, and an operation controller.

[0036] The monitor 14 is a device for displaying information output from the main body 10. The monitor 14 may be any device capable of displaying graphics, a specific example of which is a liquid crystal panel. The monitor 14 and the input device 12 may be integrated as a touch panel.

[0037] The camera 16 is a device capable of capturing an image of the aggregate. The camera 16 captures an image of the aggregate to generate image data. The camera 16 is, for example, a digital camera that captures an image of the imaging range based on visible light, or a video camera. The image data generated by the camera 16 is used to predict the quality of the aggregate. When the camera 16 generates a video of the imaging target, still images included in the video may be acquired as image data.

[0038] The camera 16 may be disposed in the manufacturing system 100 so as to be able to capture an image of an aggregate at a specific location. For example, the camera 16 may be disposed so as to be able to capture an image of an aggregate being transported by the transport device 104. The camera 16 may be portable, and a user such as a worker may carry the camera 16 to an imaging position. The camera 16 may be mounted on a mobile body such as a drone, and the camera 16 may capture an image at any location in the manufacturing system 100 by a user operating the mobile body, etc.

[0039] In the manufacturing support device 1, the main body 10, the input device 12, the monitor 14, and the camera 16 may be integrated into one device, such as a smartphone with a built-in (mounted) camera or a tablet computer with a built-in camera. In one example, the manufacturing support device 1 is configured by installing an application for predicting the quality of aggregate on a smartphone.

[0040] As shown in FIG. 2, the main body 10 includes a circuit 50. The circuit 50 includes a processor 51, a memory 52, a storage 53, and an input / output port 54. The storage 53 is configured with one or more non-volatile memory devices such as a flash memory or a hard disk. The storage 53 stores a manufacturing support program that causes a computer to execute at least a quality prediction process and a composition calculation process. In addition to the quality prediction process and the composition calculation process, the manufacturing support program may cause the computer to further execute one or more processes among a result output process, a recording process, an imaging process, a quality prediction output process, an actual measurement information acquisition process, and a model update process. Details of these processes will be described later. The storage 53 stores a manufacturing support program for configuring each functional block of the main body 10.

[0041] The memory 52 is composed of one or more volatile memory devices such as a random access memory. The memory 52 temporarily stores a manufacturing support program loaded from the storage 53. The processor 51 is composed of one or more arithmetic devices such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The processor 51 configures each functional block of the main body 10 by executing the manufacturing support program loaded into the memory 52. ​​The calculation results by the processor 51 are temporarily stored in the memory 52. ​​The input / output port 54 inputs and outputs information between the input device 12, the monitor 14, the camera 16, etc. in response to a request from the processor 51.

[0042] The manufacturing support program may be provided in a state where it is fixedly recorded on a tangible recording medium such as a CD-ROM, a DVD-ROM, or a semiconductor memory. Alternatively, the manufacturing support program may be provided via a communication network as a data signal superimposed on a carrier wave. The main body 10 (manufacturing support device 1) may be composed of a plurality of computers communicably connected to each other. At least a part of the main body 10 (manufacturing support device 1) may be a part of a control device included in the manufacturing system 100.

[0043] 3 shows an example of functional components (referred to as "functional blocks" in this disclosure) included in the main body 10. The main body 10 includes, as functional blocks, a quality prediction unit 21, a blend calculation unit 42, and a result output unit 44. The processes executed by these functional blocks correspond to the processes executed by the main body 10 (manufacturing support device 1).

[0044] The quality prediction unit 21 is configured to predict quality related to the granularity of the aggregate to be evaluated. The granularity-related quality predicted by the quality prediction unit 21 is, for example, the coarse aggregate ratio of the aggregate, the excessively large aggregate amount, or the excessively small aggregate amount. The quality prediction unit 21 may predict two or more types of quality related to these three types of granularity. The quality prediction unit 21 (quality prediction device) has a user input acquisition unit 22, an image data acquisition unit 24, an evaluation information acquisition unit 26, a prediction model holding unit 28, and a prediction calculation unit 30. The processing executed by these functional blocks corresponds to the processing executed by the quality prediction unit 21 (manufacturing support device 1).

[0045] The user input acquisition unit 22 is configured to acquire user input information indicating an input from a user required for predicting the quality of the aggregate to be evaluated. The user input acquisition unit 22 may acquire the user input information based on a user input to an interface screen displayed on the monitor 14.

[0046] The image data acquisition unit 24 is configured to acquire image data generated by capturing an image of the aggregate to be evaluated (hereinafter, referred to as "captured image data"). The image data acquisition unit 24 acquires captured image data (captured image) captured by the camera 16.

[0047] The evaluation information acquiring unit 26 is configured to acquire evaluation input information based on captured image data acquired by capturing an image of the aggregate to be evaluated. The evaluation information acquiring unit 26 may acquire, for example, the captured image data as is as the evaluation input information, or may acquire image data acquired by performing a predetermined processing on the captured image data as the evaluation input information. A user input may determine whether or not to process the captured image data in order to obtain the evaluation input information, and how to process the captured image data.

[0048] The prediction model holding unit 28 is configured to hold a model (hereinafter, referred to as "prediction model M") for predicting the coarse grain ratio of the aggregate to be evaluated. The prediction model M is a model constructed by machine learning based on input information based on learning image data (learning image data) obtained by imaging the learning aggregate and a ground truth value of a quality value related to the quality of the aggregate associated with the input information, so as to output a predicted value of the quality value in response to the input of the input information. The quality value is, for example, the coarse grain ratio, the mass fraction for each grain size division included in the grain size division of the aggregate, or both the coarse grain ratio and the mass fraction for each grain size division. The construction of the prediction model M will be described later. In addition to the quality value, the prediction model M may further output the amount of oversized grains and the amount of undersized grains as quality values.

[0049] Machine learning refers to a method in which a machine (computer) autonomously finds laws or rules by repeatedly learning based on given information. The prediction model M can be constructed using an algorithm and a data structure. The prediction model M is realized, for example, using a neural network, which is an information processing model that mimics the mechanism of the human brain. There is no particular limitation on the specific algorithm of the machine learning performed when constructing the prediction model M. The neural network has an input layer, one or more intermediate layers, and an output layer. By including one or more intermediate layers, a more complex prediction model M can be constructed, and prediction accuracy can be improved.

[0050] The prediction model M may be constructed by machine learning using a convolutional neural network (CNN). The prediction model M is constructed by machine learning based on the correct value of the quality value. The prediction model M may output only the coarse grain ratio, only a value indicating the mass fraction for each grain size division included in the multiple grain size divisions, or both the coarse grain ratio and the mass fraction for each grain size division, as the quality value, according to the input information. When outputting the mass fraction for each grain size division, the prediction model M outputs multiple values ​​each indicating a mass fraction for the multiple grain size divisions. The following illustrates an example in which the prediction model M outputs both the coarse grain ratio and the mass fraction for each grain size division.

[0051] The prediction model M is constructed to predict the above quality value, for example, by performing machine learning using data provided as input for machine learning and correct answer data (correct answer value of the above quality value) of the machine learning output. The input for the machine learning is various data sets of input information based on learning image data obtained by imaging the learning aggregate. In the various data sets of input information, at least the image data included in the input information is different from each other. The output of the machine learning is data (numerical value) indicating a quality value such as the coarse grain ratio. When constructing the prediction model M, a model that outputs a predicted value of the above quality value is iteratively trained using multiple combinations of input information and correct answer values ​​such as the coarse grain ratio.

[0052] The stage in which the prediction model M is autonomously constructed corresponds to the learning phase. The learning phase may be performed before the production phase in which ready-mix concrete is manufactured in the manufacturing system 100, or may be performed at an early stage of the production phase. The prediction model M, which is a trained model, is portable between computers. Therefore, the prediction model M constructed in another device may be stored in the prediction model holding unit 28. The stage in which the quality prediction unit 21 predicts the coarse particle ratio of the aggregate to be evaluated using the prediction model M corresponds to the evaluation phase.

[0053] The prediction calculation unit 30 is configured to input evaluation input information to the prediction model M and obtain a predicted value output from the prediction model M. For example, the prediction calculation unit 30 obtains a predicted value indicating the coarse grain ratio from the prediction model M. The prediction calculation unit 30 may also obtain a plurality of predicted values ​​indicating mass fraction values ​​for a plurality of grain size divisions from the prediction model M. The prediction calculation unit 30 may calculate the coarse grain ratio from a predicted value (a plurality of predicted values) regarding the mass fraction for each grain size division. For reliability evaluation, the prediction calculation unit 30 may obtain both the coarse grain ratio and a plurality of predicted values ​​each indicating a mass fraction value from the prediction model M and compare the coarse grain ratio predicted for each prediction model M. As described above, the calculation (prediction) of the coarse grain ratio is performed by two different methods using the prediction model M, so that the reliability of the predicted value of the coarse grain ratio can be evaluated. The amount of excessive grains and the amount of excessive grains, which will be described later, may be calculated from the predicted value (a plurality of predicted values) of the mass fraction for each grain size division.

[0054] The mix calculation unit 42 is configured to calculate a correction value for the mix of concrete according to the prediction result by the prediction calculation unit 30. For example, the mix calculation unit 42 may calculate at least one correction value of the fine aggregate ratio of the aggregate to be managed (aggregate used in the manufacturing system 100), the bulk volume of the coarse aggregate, or the unit water content of the concrete in order to manufacture concrete according to the standard mix according to the prediction result of the coarse aggregate ratio by the prediction calculation unit 30. A specific example of the calculation of the correction value by the mix calculation unit 42 will be described later (will be described in the mix calculation process described later). In this embodiment, correcting the concrete mix includes correcting, modifying, and changing the concrete mix. Correcting (sometimes called modifying) the concrete mix means reviewing the mix in response to daily quality fluctuations in the concrete raw materials and concrete quality fluctuations. Modifying the concrete mix means reviewing the mix based on short- to medium-term quality fluctuations in the concrete raw materials and concrete quality fluctuations. Changing the concrete mix means reviewing the mix based on long-term quality fluctuations in the concrete raw materials and concrete quality fluctuations.

[0055] The result output unit 44 outputs at least the calculation result of the correction value by the blend calculation unit 42. The result output unit 44 may output the calculation result of the correction value by the blend calculation unit 42 to the monitor 14 of its own device (manufacturing support device 1) to display the calculation result on the monitor 14. The result output unit 44 may output the calculation result of the correction value to a monitor of another device to display the calculation result on the monitor. The result output unit 44 may display the prediction result by the prediction calculation unit 30 (for example, the predicted value of the coarse grain ratio) on the monitor 14 or the like in addition to the calculation result of the correction value by the blend calculation unit 42. The result output unit 44 may output the calculation result of the correction value by the blend calculation unit 42 to a manufacturing device in the manufacturing system 100 instead of a monitor.

[0056] <Prediction model M> Here, the prediction model M used to predict the coarse grain ratio will be further described with reference to Figs. 4 and 5. In the learning phase for constructing the prediction model M, aggregate of the same type as the aggregate that is used in the manufacturing system 100 and can be evaluated is used as the learning aggregate. Fig. 4(a) shows a schematic diagram of the calculation process for predicting the coarse grain ratio using the prediction model M from the image Im, which is input information. The input of the prediction model M is the image Im, and the output of the prediction model M is the predicted value of the mass fraction of each of the multiple grain size classes and the predicted value of the coarse grain ratio.

[0057] When constructing the prediction model M, learning data for machine learning is prepared. The learning data includes various image data (input information) obtained by imaging the learning aggregate, and answer data associated with each of the various image data. In preparing the learning images, for example, various aggregates whose mass fractions for each granularity classification are known are prepared. The above various aggregates do not mean different types of aggregate, but mean the same type of aggregates with different granularities.

[0058] In one example, various types of learning aggregates are individually imaged by camera 130 in a stacked state on measurement sheet 132 (see FIG. 4(b)). A stacked state (piled state) refers to a state in which some particles contained in the aggregate overlap other particles when viewed vertically from above. By individually imaging the various types of aggregates by camera 130, learning image data is obtained for each type of aggregate. Camera 130 may be a digital camera, and images an area including the stacked aggregates from a position a predetermined distance away from the aggregates on measurement sheet 132 (for example, a predetermined position above).

[0059] The sheet 132 may be a rubber sheet. As shown in FIG. 4(b), the sheet 132 may be a sheet formed to be curved in imitation of the belt conveyor of the conveying device 104, or may be a sheet formed in a flat shape, unlike the example shown in FIG. 4(b). The amount of aggregate placed on the sheet 132 is not particularly limited, but may be about 1 kg to 10 kg. FIG. 4(b) shows a schematic example of aggregate piled up on the sheet 132, and shows piled up states when the amount of aggregate is 2 kg, 5 kg, and 8 kg. Note that the sheet 132 may be a container other than a rubber sheet. If it is a container with a rim, it is preferable from the viewpoint that it can be used to uniformly adjust the size of the captured aggregate by correcting the size of the image data based on the distance calculation result after calculating the distance from the camera to the aggregate.

[0060] In one example, samples of various aggregates are prepared under the conditions shown in Table 1 below, and images for learning are obtained by photographing the prepared samples. The mass fraction and coarse aggregate ratio for each grain size division of the various aggregates prepared under the conditions shown in Table 1 are known, and the known values ​​are the correct answer data for machine learning.

[0061] [Table 1]

[0062] The coarse grain ratio (FM) is calculated, for example, by the following formula (1) specified in the Standard Method for Concrete. In the measurement specified in the "Standard Specifications for Building Construction and Commentary JASS5 Reinforced Concrete Construction", 9 sieves are used excluding the 80 mm sieve in formula (1). The coarse grain ratio predicted in this disclosure may be specified by any method.

number

[0063] In Table 1, this means that aggregates of 10 levels of gradation (coarse aggregate ratio) are prepared. Category I represents a gradation category of particles smaller than 2.5 mm. Category I includes particles that cannot be retained on a 2.5 mm sieve. Category II represents a gradation category of particles 2.5 mm or larger and smaller than 5 mm. Category II includes particles that can be retained on a 2.5 mm sieve but cannot be retained on a 5 mm sieve. Category III represents a gradation category of particles 5 mm or larger and smaller than 10 mm. Category III includes particles that can be retained on a 5 mm sieve but cannot be retained on a 10 mm sieve. Category IV represents a gradation category of particles 10 mm or larger and smaller than 20 mm. Category IV includes particles that can be retained on a 10 mm sieve but cannot be retained on a 20 mm sieve.

[0064] For level 1, the coarse aggregate ratio can be calculated from the mass fractions of each grain size category (mass fractions of each of categories I to IV) as follows. For level 1 aggregate, the mass percentages of the sample that are retained on the 80 mm, 40 mm, and 20 mm sieves are 0, the mass percentages of the sample that are retained on the 10 mm sieve are 85, and the mass percentages of the sample that are retained on the 5 mm sieve are 100 (=15+85). Also, since all the grains are retained on the 5 mm sieve, the mass percentages of the sample that are retained on the 2.5 mm, 1.2 mm, 600 μm, 300 μm, and 150 μm sieves are 100. Therefore, the coarse aggregate ratio is calculated as shown in the following formula (2).

number

[0065] For levels 2 to 10, the coarse aggregate ratio is calculated in the same manner as for level 1. The conditions of the learning aggregate shown in Table 1 are merely examples, and the number of levels, the coarse aggregate ratio and mass fraction for each grading class at each level, and the method of setting the grading classes may be set arbitrarily. As with the multiple grading classes shown in Table 1, the grading classes in multiple classes including the smallest class (<150 μm) may be combined into one grading class. Grain sizes above a certain class (e.g., 20 to 40 mm) may not be included in multiple grading classes. Also, unlike the setting method in Table 1, grain sizes below a certain class (e.g., 1.2 to 2.5 μm) may not be included in multiple grading classes.

[0066] FIG. 5 shows images T1 to T10 obtained by imaging learning aggregates prepared according to the conditions of each of levels 1 to 10 in Table 1. Level n (n is an integer from 1 to 10) corresponds to image Tn. For example, image T1 is obtained by imaging learning aggregates prepared according to level 1. Learning aggregates according to each level n contain grains of multiple grain size divisions. In this way, learning aggregates may be prepared so as to contain grains of two or more grain size divisions, and input information may be prepared based on image data obtained by imaging the learning aggregates.

[0067] For each level n, multiple images Tn in which the states (more specifically, pile states) of the learning aggregate are different from each other may be prepared. In one example, a first image is taken with the learning aggregate placed on the measurement sheet 132, to obtain one image Tn. Then, the learning aggregate is temporarily removed from the sheet 132, and the same learning aggregate (same sample) is placed again on the sheet 132 so that the pile state of the multiple grains is different from that in the first image. Then, a second image is taken. By repeating the above-mentioned image taking, multiple images Tn may be prepared for each level n.

[0068] One data set is composed of one image Tn and the correct answer data of the mass fraction and the coarse grain ratio at the level n associated with the image Tn. As learning data, a plurality of data sets each consisting of a combination of the image Tn and the correct answer data of the mass fraction and the coarse grain ratio are prepared. Then, a prediction model M is constructed by performing machine learning using such learning data. The prediction model M constructed as described above outputs, for example, four mass fraction values ​​and a coarse grain ratio value for four grain size classifications.

[0069] Focusing on the point that the prediction model M outputs a value of the coarse grain ratio, the prediction model M is a model constructed by machine learning based on input information based on learning image data obtained by imaging the learning aggregate and the correct value of the coarse grain ratio associated with the input information, so as to output a value indicating the coarse grain ratio in response to the input of the input information. Focusing on the point that the prediction model M outputs a value of the mass fraction for each grain size division, the prediction model M is a model constructed by machine learning based on input information based on learning image data obtained by imaging the learning aggregate and the correct value of the mass fraction for each of the multiple grain size divisions of the aggregate associated with the input information, so as to output a value indicating the mass fraction for each of the multiple grain size divisions in response to the input of the input information.

[0070] In order to verify the method of predicting the coarse aggregate ratio using the prediction model M based on machine learning using a convolutional neural network, a comparison was made between the prediction results by the prediction model M and the correct values ​​using a dataset in which the correct values ​​were known. For the learning aggregate, 10 levels of aggregate with different coarse aggregate ratios were prepared according to the conditions in Table 1 above. For each level, images were taken 10 times indoors with the aggregate piled up on the measurement sheet 132 in different states, to obtain 10 images.

[0071] In addition, a total of 100 images (10 levels x 10 shots) were prepared according to the standard conditions shown in Table 2 below. As a result, 100 data sets were prepared as learning data, each of which corresponds to an image and a correct answer value.

[0072] [Table 2]

[0073] The prediction model M was constructed using 80 of the 100 datasets, and 20 datasets were used for validation. At each level, 8 data were used for model construction, and 2 datasets were used for validation. In the validation using 20 datasets, the prediction results calculated using the image and the prediction model M for each dataset were compared with the correct values ​​such as the coarse grain rate associated with the image. The prediction model M was constructed using a convolutional neural network with 6 intermediate layers consisting of a convolutional layer and a pooling layer, followed by 4 fully connected layers. The Huber function was used as the loss function. In each dataset, the number of images was increased by the Image Augmentation layer.

[0074] FIG. 6(a) is a graph showing the relationship between the predicted values ​​of the mass ratio (%) in the divisions III and IV in Table 1 and the corresponding correct values ​​of the mass fraction (%). In the graph shown in FIG. 6(a), the horizontal axis is the correct value of the mass fraction, and the vertical axis is the predicted value of the mass fraction output from the prediction model M. The prediction results in division III (5 mm to 10 mm) are plotted with △ marks, and the prediction results in division IV (10 mm to 20 mm) are plotted with ◯ marks. A solid line where the correct value and the predicted value match is drawn, and the closer the plotted results are to the line, the higher the prediction accuracy. From the results shown in FIG. 6(a), the prediction results are plotted near the line, and it can be seen that the mass ratio can be predicted with high accuracy by the prediction model M. Note that the coarse particle ratio can be calculated from the mass fraction, so if the mass fraction can be predicted with high accuracy by the prediction model M, the coarse particle ratio can also be predicted with high accuracy.

[0075] FIG. 6(b) is a graph showing the relationship between the predicted value of the coarse grain ratio output from the prediction model M and the correct value of the coarse grain ratio. In the graph shown in FIG. 6(b), the horizontal axis is the correct value of the coarse grain ratio, and the vertical axis is the predicted value of the coarse grain ratio output from the prediction model M. The prediction results are plotted with square marks. The solid line is the line where the correct value and the predicted value match, and a dashed upper limit line shifted vertically by +0.10 from the solid line and a lower limit line shifted vertically by -0.10 are drawn. The prediction results included in the area between the upper limit line and the lower limit line are defined as being within the allowable range. With reference to the error in the coarse grain ratio allowed in current ready-mix concrete plants, a range of ±0.10 was set as the allowable range. It can be seen that all of the prediction results using the prediction model M are included in the allowable range, and the prediction model M can predict the coarse grain ratio with high accuracy.

[0076] [Manufacturing support method] 7 and 8, a manufacturing support method executed in the manufacturing support device 1 will be described. Hereinafter, the manufacturing support method for supporting the manufacturing of ready-mix concrete by the manufacturing system 100 will be described using an example in which the manufacturing support device 1 is configured by a smartphone with a camera. This manufacturing support method includes, for example, a quality prediction step, a mix calculation step, and a result output step. These steps may be executed by corresponding functional blocks in the manufacturing support device 1.

[0077] The quality prediction process is a process of predicting quality related to the granularity of the aggregate to be evaluated. In the quality prediction process, for example, the coarse aggregate ratio of the aggregate to be evaluated is predicted as the quality related to the granularity. The quality prediction process includes, for example, an imaging data acquisition process, an evaluation information acquisition process, and a prediction process.

[0078] The imaging data acquisition step is a step of acquiring imaging image data (captured image) obtained by imaging an aggregate to be evaluated, the quality of which related to the grain size of the prediction target is unknown. The evaluation information acquisition step is a step of acquiring evaluation input information based on the above-mentioned captured image data. For example, as the evaluation input information, the captured image data is acquired as it is, or image data after processing the captured image is acquired.

[0079] The prediction process is a process of calculating a value indicating quality related to gradation (e.g., coarse aggregate ratio) based on the prediction model M and evaluation input information. In the prediction process, the evaluation input information may be input to the prediction model M, and a predicted value output from the prediction model M regarding the coarse aggregate ratio may be obtained. In the prediction process, the evaluation input information may be input to the prediction model M, and a predicted value output from the prediction model M regarding the mass fraction may be obtained for each gradation class. In the prediction process, the coarse aggregate ratio of the aggregate to be evaluated may be calculated from the predicted value of the mass fraction for each gradation class. For example, the coarse aggregate ratio is calculated from the predicted value of the mass fraction for each gradation class according to the above formula (1).

[0080] The mix ratio calculation step is a step of calculating a correction value for the mix ratio of concrete in accordance with the prediction result in the quality prediction step. Examples of the mix ratio of concrete include the fine aggregate ratio, the bulk volume of coarse aggregate, and the unit water content of concrete. The correction value for one of these three types of mix ratios may be calculated, or the correction values ​​for two or more types of mix ratios may be calculated. The fine aggregate ratio is the absolute volume ratio of fine aggregate to the total aggregate (fine aggregate + coarse aggregate) in concrete, and is expressed as a percentage (%), for example. The bulk volume of coarse aggregate is the absolute volume ratio of fine aggregate to the total aggregate (fine aggregate + coarse aggregate) in concrete. 3 The unit water content of concrete is the volume of the coarse aggregate when making it. 3 The mass of water per unit area is the mass of water per unit area. Hereinafter, a concrete mix proportion will be described by way of example in which a correction value for the fine aggregate ratio is calculated. In the mix proportion calculation step, for example, a correction value for the fine aggregate ratio is calculated according to the predicted value of the coarse aggregate ratio in the quality prediction step. The correction value for the fine aggregate ratio may be the fine aggregate ratio itself, or may be an increase or decrease from the standard value of the fine aggregate ratio.

[0081] In the mixture calculation step of the above manufacturing support method, a correction value for the mixture of fine aggregate percentage is calculated according to the predicted value of the coarse aggregate percentage of the aggregate to be evaluated. The calculation of the correction value includes calculating the correction value as a standard value when the fine aggregate percentage does not need to be changed, or calculating the correction value with an increase or decrease range of zero.

[0082] In the mix calculation step, when the predicted value of the coarse aggregate ratio deviates from the reference value, a correction value may be calculated as follows. When the predicted value of the coarse aggregate ratio (prediction result) is smaller than the reference value, a correction value of the fine aggregate ratio may be calculated according to the difference between the predicted value of the coarse aggregate ratio and the reference value, so that the ratio of the amount of fine aggregate to the total amount of aggregate becomes smaller. When the predicted value of the coarse aggregate ratio (prediction result) is larger than the reference value, a correction value of the fine aggregate ratio may be calculated according to the difference between the predicted value of the coarse aggregate ratio and the reference value, so that the ratio of the amount of fine aggregate to the total amount of aggregate becomes larger.

[0083] The result output process is a process of outputting the calculation result of the correction value in the mix ratio calculation process. For example, the calculation result of the mix ratio correction value is output to the monitor 14 or the like, or to a control device in the manufacturing system 100. When the calculation result of the correction value is displayed on the monitor 14, a user such as an operator may view the result and change the set value of the concrete mix ratio as necessary. Alternatively, the control device in the manufacturing system 100 may adjust the set value of the concrete mix ratio according to the calculation result of the correction value.

[0084] 7 shows a series of processes executed in the manufacturing support method. The manufacturing support device 1 first executes steps S11 and S12. In step S11, for example, the image data acquisition unit 24 of the quality prediction unit 21 acquires captured image data obtained by capturing an image of the aggregate to be evaluated. In step S12, for example, the evaluation information acquisition unit 26 acquires evaluation input information to be input information to the prediction model M based on the captured image data obtained in step S11.

[0085] Next, the manufacturing support device 1 executes step S13. In step S13, for example, the prediction calculation unit 30 calculates a predicted value of the coarse grain ratio as a predicted value of quality based on the prediction model M and the evaluation input information obtained in step S12. The prediction calculation unit 30 may calculate the predicted value of the coarse grain ratio based on the predicted value of the coarse grain ratio directly output from the prediction model M and the predicted value of the coarse grain ratio calculated from the mass ratio for each grain size class output from the prediction model M (for example, by calculating an average value).

[0086] Next, the manufacturing support device 1 executes step S14. In step S14, for example, the mix calculation unit 42 calculates a correction value for the mix of concrete (for example, fine aggregate ratio) according to the coarse aggregate ratio calculated in step S13. As described in the mix calculation process above, the mix calculation unit 42 may calculate a correction value for the mix of the fine aggregate ratio so that the coarse aggregate ratio of the aggregate to be managed falls within an allowable range after the mix is ​​changed.

[0087] Next, the manufacturing support device 1 executes step S15. In step S15, for example, the result output unit 44 causes the monitor 14 to display the correction value calculated in step S14 and the prediction result in step S13. FIG. 8 illustrates a screen displayed on the monitor 14 by executing step S15. The result output unit 44 may cause the monitor 14 to display information 82b indicating the predicted value of the coarse aggregate ratio and information 82c indicating the corrected value of the fine aggregate ratio. The information 82c may include a standard value of the fine aggregate ratio. The result output unit 44 may cause the monitor 14 to display a captured image 84 related to the captured image data obtained in step S11, in addition to the information 82b and the information 82c.

[0088] [Variations] The mix calculation unit 42 may calculate a correction value for the coarse aggregate bulk volume instead of the fine aggregate ratio. For example, the mix calculation unit 42 calculates the correction value so that the corrected coarse aggregate bulk volume becomes smaller as the predicted value of the coarse aggregate ratio increases, and calculates the correction value so that the corrected coarse aggregate bulk volume becomes larger as the predicted value of the coarse aggregate ratio decreases. When the predicted value of the coarse aggregate ratio (prediction result) is smaller than a reference value, the correction value for the coarse aggregate bulk volume may be calculated in accordance with the difference between the predicted value of the coarse aggregate ratio and the reference value so that the ratio of the amount of fine aggregate to the amount of the entire aggregate becomes smaller. When the predicted value of the coarse aggregate ratio (prediction result) is larger than the reference value, the correction value for the coarse aggregate bulk volume may be calculated in accordance with the difference between the predicted value of the coarse aggregate ratio and the reference value so that the ratio of the amount of fine aggregate to the amount of the entire aggregate becomes larger.

[0089] The mix ratio calculation unit 42 may calculate a correction value for the unit water content of concrete instead of the fine aggregate ratio. For example, the mix ratio calculation unit 42 calculates the correction value so that the corrected unit water content becomes smaller as the predicted value of the coarse aggregate ratio increases, and calculates the correction value so that the corrected unit water content becomes larger as the predicted value of the coarse aggregate ratio decreases.

[0090] The prediction calculation unit 30 may calculate at least one of the amount of oversized aggregate (mass fraction of 5 mm or more in the fine aggregate [S]) and the amount of undersized aggregate (mass fraction of 5 mm or less in the coarse aggregate [G]) as a predicted value of the quality related to the gradation, instead of or in addition to the coarse aggregate ratio. The amount of oversized aggregate and the amount of undersized aggregate can be obtained from the mass fraction of each gradation class. The prediction calculation unit 30 may calculate the amount of oversized aggregate and the amount of undersized aggregate from the mass fraction for each granularity class output from the prediction model M. The mix calculation unit 42 may calculate a correction value for the mix of concrete according to the predicted value of the amount of oversized aggregate, or may calculate a correction value for the mix of concrete according to the predicted value of the amount of undersized aggregate.

[0091] For example, the concrete mix is ​​calculated as follows according to the amount of oversized aggregate and the amount of undersized aggregate. The mix calculation unit 42 calculates the concrete mix (calculates the corrected value of the amount of fine aggregate or coarse aggregate) based on the amount of oversized fine aggregate and the amount of undersized coarse aggregate, the quality of which is predicted using the prediction model M. For example, the concrete mix can be calculated by the following formulas (3) and (4).

number

number

[0092] In formulas (3) and (4), the symbols have the following meanings. S: Corrected fine aggregate amount (kg / m 3 ) G: Corrected amount of coarse aggregate (kg / m 3 ) S0: Standard mix fine aggregate unit amount (kg / m 3 ) G0: Standard mix unit coarse aggregate amount (kg / m 3 ) ·a: Excessive grain (%) ·b: Undersized grains (%)

[0093] In the manufacturing support method using the manufacturing support device 1, a recording step may be further executed. The recording step is a step of associating the captured image data with the prediction result of the coarse aggregate ratio and recording the captured image data each time the coarse aggregate ratio of the evaluation target is calculated in the quality prediction step. That is, in the recording step, for each prediction of the coarse aggregate ratio of the evaluation target, the captured image data (captured image) used in the prediction and the predicted value of the coarse aggregate ratio in the prediction are recorded after being linked to each other. For example, such linked data may be recorded (stored) in the manufacturing support device 1 itself.

[0094] The type of aggregate to be evaluated may be different in the repeated predictions of the coarse aggregate ratio (multiple predictions). In the recording step, in addition to the predicted value of the coarse aggregate ratio and the captured image data, other information such as the date of prediction, the environment at the time of prediction (weather, etc.), or the type of aggregate to be evaluated may be linked and recorded. The main body 10 of the manufacturing support device 1 may have, as a functional block, a result recording unit 46 that executes the recording step.

[0095] 9(a), the manufacturing support device 1 executes step S21. In step S21, for example, the result recording unit 46 waits until the prediction calculation unit 30 executes a prediction of the coarse grain rate. Next, the manufacturing support device 1 executes step S22. In step S22, for example, the result recording unit 46 records the prediction result of the coarse grain rate by the prediction calculation unit 30 and the captured image data used when the prediction result was obtained in a state in which they are associated with each other.

[0096] When there is an inquiry request from a user, the manufacturing support device 1 may display the information recorded in the recording process on the monitor 14, or may generate a file listing the information recorded in the recording process. By viewing the information recorded in the recording process, the user can easily understand the prediction result and the captured image when the prediction result was obtained.

[0097] In the manufacturing support method by the manufacturing support device 1, a performance information acquisition step and a model update step may be further executed. The performance information acquisition step is a step of acquiring an actual measurement value of the coarse aggregate ratio obtained from an aggregate to be measured (an aggregate of the same type as the aggregate to be evaluated) corresponding to an aggregate to be evaluated (an aggregate to be predicted using the prediction model M and an aggregate to be managed by the user) and image data of the aggregate to be measured, which is associated with the actual measurement value. The actual measurement value of the coarse aggregate ratio is a value obtained by taking a part of the aggregate as a sample and having an operator actually measure the coarse aggregate ratio using a sieve. For example, in a current ready-mix concrete plant, the coarse aggregate ratio of the aggregate to be managed is actually measured at least once a week. In the performance information acquisition step, for example, the actual measurement value and image data associated with the actual value are acquired based on an input by a user.

[0098] The model updating process is a process of updating the prediction model M based on the data obtained in the actual measurement information acquisition process (the data set of the actual measurement values ​​and image data). The model updating process may be executed when one data set is obtained, or may be executed when two or more data sets are obtained. The actual measurement values ​​become correct answer data in machine learning, and information based on the image data becomes input information for learning. In the model updating process, for example, a newly obtained data set is added to the learning data used up to that point, and machine learning is executed again to update the prediction model M. In updating the prediction model M, as an example, the coefficients in the prediction model M are adjusted.

[0099] The main body 10 of the manufacturing support device 1 may have, as functional blocks, an actual measurement information acquisition unit 36 ​​that executes a performance information acquisition step, and a model update unit 38 that executes a model update step. As shown in Fig. 9(b), the manufacturing support device 1 executes step S31. In step S31, for example, the model update unit 38 waits until the actual measurement information acquisition unit 36 ​​acquires performance information (the user inputs performance).

[0100] Next (after the performance information is acquired), the manufacturing support device 1 executes step S32. In step S32, for example, the model update unit 38 determines whether or not an update condition for updating the model is satisfied. The model update unit 38 may determine that the update condition is satisfied when a predetermined number of data sets including actual measurements and image data are newly acquired. The predetermined number is, for example, determined in advance by a user. If the predetermined number is not met, the model update unit 38 may determine that the update condition is not satisfied. If it is determined that the update condition is not satisfied (step S32: NO), the process executed by the manufacturing support device 1 returns to step S31.

[0101] If it is determined that the update condition is satisfied (step S32: YES), the process executed by the manufacturing support device 1 proceeds to step S33. In step S33, for example, the model update unit 38 updates the prediction model M (more specifically, the part of the prediction model M that is related to the direct prediction of the coarse grain ratio) using one or more of the above data sets acquired by the actual measurement information acquisition unit 36. As described above, by acquiring actual measurement values ​​that are periodically measured and image data when the actual measurement values ​​are obtained, learning data for machine learning can be easily obtained.

[0102] In the imaging support method by the manufacturing support device 1, an imaging step and a quality prediction output step may be further executed. The imaging step is a step of performing imaging of the aggregate to be evaluated multiple times. In each of the multiple imaging steps, the aggregate to be evaluated is imaged by the camera 16. In the multiple imaging steps, different samples of the same type of aggregate may be imaged by the camera 16. The different samples include different individual particles contained in the aggregate, as well as different piled states of the same individual. In the multiple imaging steps, the same sample of the same type of aggregate (samples with the same piled state) may be imaged by the camera 16. In the imaging step, for example, while the belt conveyor of the transport device 104 is operating, continuous imaging is performed by the camera 16 from a fixed position. The continuous imaging also includes the camera 16 acquiring video data.

[0103] For each of the multiple imaging operations, the evaluation information acquisition step (acquiring evaluation input information based on captured image data) and the prediction step (predicting the coarse grain ratio using the evaluation input information and the prediction model M) are executed. That is, for each imaging operation, evaluation input information is obtained from the captured image data, and the coarse grain ratio is predicted using the evaluation input information and the prediction model M.

[0104] The quality prediction output step is a step of outputting an average value of the calculation results of the coarse grain ratio in the prediction step for each of the multiple imaging times as a prediction result of the coarse grain ratio. For example, in the case of performing imaging three times, a value obtained by arithmetically averaging the predicted value of the coarse grain ratio obtained in the first imaging time, the predicted value of the coarse grain ratio obtained in the second imaging time, and the predicted value of the coarse grain ratio obtained in the third imaging time is output as a final prediction result (prediction value). In the quality prediction output step, the average value may be output to the monitor 14 or may be output to a control device in the manufacturing system 100. The result output unit 44 may execute the quality prediction output step.

[0105] As shown in FIG. 10, the manufacturing support device 1 executes step S51. In step S51, for example, the manufacturing support device 1 (main body 10) waits until a user issues an instruction to execute a prediction. Next, the manufacturing support device 1 executes steps S52 and S53. In step S52, for example, the user uses the camera 16 (or a smartphone constituting the manufacturing support device 1) to capture an image of a sample obtained from the aggregate to be evaluated. This results in captured image data related to the sample. In step S53, for example, the prediction calculation unit 30 calculates a predicted value of the coarse grain ratio of the aggregate to be evaluated using evaluation input information based on the captured image data obtained in step S52 and the prediction model M.

[0106] Next, the manufacturing support device 1 executes step S54. In step S54, for example, the manufacturing support device 1 (main body 10) judges whether or not the set of step S52 and step S53 has been executed a set number of times. If it is judged in step S54 that the set has not been executed the set number of times (step S54: NO), the manufacturing support device 1 executes the set of step S52 and step S53 again. The set number of times is, for example, preset by the user.

[0107] If it is determined in step S54 that the set of step S52 and step S53 has been executed a set number of times (step S54: YES), the manufacturing support device 1 executes step S55. In step S55, for example, the result output unit 44 calculates a calculated average of the predicted values ​​calculated for each repeated execution of step S53, and outputs the calculated average value to the monitor 14 or the like. As described above, by calculating an average of multiple predicted values ​​in multiple predictions (imaging) and outputting the average value, rather than a predicted value in a single prediction, it is possible to reduce the influence of a certain moment or under certain conditions and obtain a stable predicted value.

[0108] The series of processes shown in each of Fig. 7 etc. are examples and can be changed as appropriate. In the series of processes shown in each of Fig. 7 etc., the manufacturing support device 1 may execute one step and the next step in parallel, may execute some steps in an order different from the example shown in Fig. 7 etc., or may execute steps with contents different from the example shown in Fig. 7 etc.

[0109] A computer that realizes the functional blocks included in the quality prediction unit 21 and a computer that realizes the functional blocks not included in the quality prediction unit 21 may be separate entities. Any of the various functional blocks illustrated in FIG. 3 may be an element included in the quality prediction unit 21. Some of the functional blocks described as elements included in the quality prediction unit 21 do not need to be elements included in the quality prediction unit 21.

[0110] The manufacturing support device 1 may be a server connected to a terminal device such as a smartphone that can be operated by a user via a communication network. The result output unit 44 included in the manufacturing support device 1 may display various information on a monitor of a terminal device that is a device other than the manufacturing support device 1. The manufacturing support device 1 as the server may exchange information with the terminal device by presenting to the user a Web page or the like that can be viewed and accessed from the terminal device operated by the user. Alternatively, instead of a Web page, an application that cooperates with the manufacturing support device 1 may be prepared in the terminal device, and the manufacturing support device 1 as the server may provide information to the terminal device.

[0111] The above-mentioned prediction model M is an example, and the prediction model M may be any model as long as it can output at least a plurality of predicted values ​​of mass fractions for a plurality of gradation classes or coarse aggregate ratios from information based on image data of aggregates. The input data to the prediction model M may include, in addition to the evaluation input information, information indicating physical quantities that may affect the mass fraction or coarse aggregate ratio.

[0112] In one example among the various examples described above, at least a part of the matters described in the other examples may be combined. [Explanation of symbols]

[0113] 1... manufacturing support device, 14... monitor, 21... quality prediction section, 26... evaluation information acquisition section, 30... prediction calculation section, 36... actual measurement information acquisition section, 38... model update section, 42... blend calculation section, 46... result recording section, M... prediction model.

Claims

1. A method for supporting a manufacturing device that mixes concrete materials including fine aggregates and coarse aggregates to manufacture ready-mix concrete, comprising the steps of: A quality prediction step of predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation step of calculating a correction value for the mixture of concrete according to the prediction result in the quality prediction step, The quality prediction step includes: an evaluation information acquisition step of acquiring evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and a correct value of the coarse aggregate ratio associated with the input information, so as to output a value indicating the coarse aggregate ratio in response to input of the input information, and a prediction step of calculating the coarse aggregate ratio of the aggregate to be evaluated based on the evaluation input information; Manufacturing support methods.

2. A method for supporting a manufacturing device that mixes concrete materials including fine aggregates and coarse aggregates to manufacture ready-mix concrete, comprising the steps of: A quality prediction step of predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation step of calculating a correction value for the mixture of concrete according to the prediction result in the quality prediction step, The quality prediction step includes: an evaluation information acquisition step of acquiring evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and on a correct answer value of the mass fraction of each of a plurality of granularity classifications of the aggregate associated with the input information, so as to output a value indicating a mass fraction for each classification included in the plurality of granularity classifications in response to input of the input information, and a prediction process for calculating a value indicating the quality of the aggregate to be evaluated based on the evaluation input information; Manufacturing support methods.

3. The manufacturing support method according to claim 2 , wherein the value indicating the quality is a coarse aggregate ratio, an amount of excessively large aggregate, or an amount of excessively small aggregate.

4. The manufacturing support method according to any one of claims 1 to 3, wherein the mixture is a fine aggregate ratio, a bulk volume of coarse aggregate, or a unit water content of concrete.

5. In the prediction step, a coarse aggregate ratio of an aggregate to be evaluated is calculated, The mix ratio is the fine aggregate ratio or the coarse aggregate bulk volume, In the formulation calculation step, When the predicted result of the coarse aggregate ratio in the quality prediction step is smaller than a reference value, the correction value is calculated according to the difference between the predicted result of the coarse aggregate ratio and the reference value so that the ratio of the amount of fine aggregate to the amount of the whole aggregate is reduced; The manufacturing support method according to any one of claims 1 to 3, wherein, when the predicted result of the coarse aggregate rate in the quality prediction step is greater than the reference value, the correction value is calculated so that the ratio of the amount of fine aggregate to the amount of total aggregate is increased according to the difference between the predicted result of the coarse aggregate rate and the reference value.

6. In the prediction step, a coarse aggregate ratio of an aggregate to be evaluated is calculated, The manufacturing support method according to any one of claims 1 to 3, further comprising a recording step of recording the prediction result of the coarse aggregate ratio and the captured image data after corresponding the prediction result of the coarse aggregate ratio to the captured image data each time the coarse aggregate ratio of the aggregate to be evaluated is calculated in the quality prediction step.

7. An imaging step of imaging the aggregate to be evaluated a plurality of times; and a quality prediction output step, In the prediction step, a coarse aggregate ratio of an aggregate to be evaluated is calculated, The evaluation information acquisition step and the prediction step are performed for each of the multiple imaging steps, The manufacturing support method according to any one of claims 1 to 3, wherein in the quality prediction output process, an average value of the calculation results of the coarse grain rate in the prediction process for each of the multiple imaging operations is output as a prediction result of the coarse grain rate.

8. In the prediction step, a coarse aggregate ratio of an aggregate to be evaluated is calculated, The manufacturing support method includes: an actual measurement information acquisition step of acquiring an actual measurement value of a coarse aggregate ratio obtained from an actual measurement target aggregate corresponding to the aggregate to be evaluated, and image data of the actual measurement target aggregate associated with the actual measurement value; 4. The manufacturing support method according to claim 1, further comprising: a model updating step of updating the prediction model based on data obtained in the actual measurement information obtaining step.

9. A program for supporting a manufacturing device that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, A quality prediction step of predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation step of calculating a correction value for the mixture of concrete according to the prediction result in the quality prediction step; Run the following on your computer: The quality prediction step includes: an evaluation information acquisition step of acquiring evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and a correct answer value of the coarse aggregate ratio associated with the input information, so as to output a value indicating the coarse aggregate ratio in response to input of the input information, and a prediction step of calculating the coarse aggregate ratio of the aggregate to be evaluated based on the evaluation input information; Manufacturing Assistance Program.

10. A program for supporting a manufacturing device that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, A quality prediction step of predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation step of calculating a correction value for the mixture of concrete according to the prediction result in the quality prediction step; Run the following on your computer: The quality prediction step includes: an evaluation information acquisition step of acquiring evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and on a correct answer value of the mass fraction of each of a plurality of granularity classifications of the aggregate associated with the input information, so as to output a value indicating a mass fraction for each classification included in the plurality of granularity classifications in response to input of the input information, and a prediction process for calculating a value indicating the quality of the aggregate to be evaluated based on the evaluation input information; Manufacturing Assistance Program.

11. An apparatus for supporting a manufacturing apparatus that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, a quality prediction unit for predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation unit that calculates a correction value for the mixture of concrete according to the prediction result by the quality prediction unit, The quality prediction unit an evaluation information acquisition unit that acquires evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and a correct value of the coarse grain ratio associated with the input information, so as to output a value indicating the coarse grain ratio in response to the input of the input information; and a prediction calculation unit that calculates the coarse grain ratio of the aggregate to be evaluated based on the evaluation input information. Manufacturing support equipment.

12. An apparatus for supporting a manufacturing apparatus that mixes concrete materials including fine aggregate and coarse aggregate to manufacture ready-mix concrete, a quality prediction unit for predicting quality related to the granularity of the aggregate to be evaluated; A mixture calculation unit that calculates a correction value for the mixture of concrete according to the prediction result by the quality prediction unit, The quality prediction unit an evaluation information acquisition unit that acquires evaluation input information based on captured image data obtained by capturing an image of the aggregate to be evaluated; a prediction model constructed by machine learning based on input information based on learning image data obtained by imaging an aggregate for learning and on a correct value of a mass fraction for each of a plurality of granularity classifications of the aggregate associated with the input information, so as to output a value indicating a mass fraction for each classification included in the plurality of granularity classifications in response to input of the input information; and a prediction calculation unit that calculates a value indicating the quality of the aggregate to be evaluated based on the evaluation input information. Manufacturing support equipment.

Images