Method for predicting quality of ready-mixed concrete, quality prediction program, method for producing ready-mixed concrete, and device for predicting quality of ready-mixed concrete

Abstract

To improve the accuracy of quality prediction while avoiding complication of work involved in quality prediction when performing quality prediction using a prediction model.SOLUTION: Provided is a method for predicting the quality of ready-mixed concrete, including: an acquisition step of acquiring input information including first information relating to at least one of the power load value of a mixer that produces ready-mixed concrete by mixing concrete materials or that stirs the ready-mixed concrete, vibrations caused by the falling or flowing down of the ready-mixed concrete, and an image of the ready-mixed concrete, and second information relating to the target quality of the ready-mixed concrete when it is used; and a prediction step of predicting the quality of the ready-mixed concrete based on a prediction model that has been constructed in advance by machine learning to output quality information that indicates the quality of the ready-mixed concrete in response to the input of the input information, and the input information acquired in the acquisition step.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to a method for predicting quality of ready-mixed concrete, a quality prediction program, and a quality prediction device for ready-mixed concrete. [Background technology]

[0002] Patent Document 1 discloses a method for predicting the quality of ready-mixed concrete using a prediction model. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-124304 Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a ready-mixed concrete quality prediction method, a quality prediction program, and a ready-mixed concrete quality prediction device that can improve the accuracy of quality prediction while avoiding the complexity of work associated with quality prediction when performing quality prediction using a prediction model. [Means for solving the problem]

[0005] [1] A method for predicting the quality of fresh concrete, comprising: an acquisition step of acquiring input information including first information relating to at least one of the power load value of a mixer that produces fresh concrete by mixing concrete materials or that mixes the fresh concrete, vibrations caused by the falling or flowing down of the fresh concrete, and an image of the fresh concrete, and second information relating to the target quality of the fresh concrete when it is used; a prediction step of predicting the quality of the fresh concrete based on a prediction model that has been constructed in advance by machine learning to output quality information that indicates the quality of the fresh concrete in response to the input of the input information, and the input information acquired in the acquisition step.

[0006] [2] The method for predicting the quality of ready-mixed concrete according to [1] above, wherein the quality of the ready-mixed concrete includes one or more qualities of slump, slump flow, and air content.

[0007] [3] The quality prediction method for ready-mixed concrete described in [2] above, wherein the quality of the ready-mixed concrete includes two or more qualities of slump, slump flow, and air content, and the prediction model is constructed to output the two or more qualities in response to the input of the input information.

[0008] [4] A method for predicting the quality of ready-mixed concrete according to any one of [1] to [3] above, wherein the prediction model is constructed by machine learning using a neural network that does not perform an operation to normalize the input information or an operation to cause some connections in the fully connected layer to be missing.

[0009] [5] A method for predicting the quality of ready-mixed concrete according to any one of [1] to [4] above, wherein the second information includes information indicating the target quality of the ready-mixed concrete at the time of shipment in addition to information indicating the target quality of the ready-mixed concrete at the time of use.

[0010] [6] The method for predicting the quality of ready-mixed concrete according to any one of [1] to [5] above, wherein the prediction model is constructed by machine learning using a neural network, and the machine learning using a neural network used to construct the prediction model uses one selected from the group consisting of Adam, AdamBelief, Adamax, AdaBound, Adagrad, AMSGRAD, AMSBound, RMSprop, SgdW, Momentum, and Nesterov as the weight update formula.

[0011] [7] A method for predicting the quality of ready-mixed concrete according to any one of [1] to [6] above, wherein the prediction model is constructed by machine learning using a neural network, and the machine learning using the neural network used to construct the prediction model uses a loss function such that the loss value L(a) is always less than or equal to the absolute value of the error a.

[0012] [8] A quality prediction program that causes a computer to execute the method for predicting the quality of ready-mixed concrete according to any one of [1] to [7] above.

[0013] [9] A quality prediction device for fresh concrete, comprising: an input information acquisition unit that acquires input information including first information relating to at least one of the power load value of a mixer that produces fresh concrete by mixing concrete materials or that stirs the fresh concrete, vibrations caused by the falling or flowing down of the fresh concrete, and an image of the fresh concrete, and second information relating to the target quality of the fresh concrete when it is used; a prediction model that has been constructed in advance by machine learning to output quality information that indicates the quality of the fresh concrete in response to the input of the input information; and a prediction calculation unit that predicts the quality of the fresh concrete based on the input information acquired by the input information acquisition unit. [Effects of the Invention]

[0014] According to the present disclosure, there are provided a ready-mixed concrete quality prediction method, a quality prediction program, and a ready-mixed concrete quality prediction device that can improve the accuracy of quality prediction while avoiding the complexity of work associated with quality prediction when making quality predictions using a prediction model. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a schematic diagram showing an example of a ready-mix concrete manufacturing system. [Figure 2] FIG. 2 is a block diagram illustrating an example of a functional configuration of the control device. [Figure 3] FIG. 3 is a diagram illustrating data relating to power load values. [Figure 4] FIG. 4 is a block diagram illustrating an example of a hardware configuration of the control device. [Figure 5] Fig. 5(a) is a diagram showing an example of a processing flow in the learning phase, and Fig. 5(b) is a diagram showing an example of a processing flow in the evaluation phase. [Figure 6] Figures 6(a) and 6(b) are schematic diagrams showing an example of the calculation process using a prediction model, and Figure 6(c) is a schematic diagram showing an example of the calculation process using a neural network. [Figure 7] FIG. 7 is a graph showing an example of a loss function. [Figure 8] FIG. 8 is a graph showing an example of the comparison result between the predicted value and the correct value. DETAILED DESCRIPTION OF THE INVENTION

[0016] An embodiment will be described below with reference to the drawings. In the description, identical elements or elements having identical functions are given the same reference numerals, and duplicated explanations will be omitted. Figure 1 shows a schematic diagram of a ready-mixed concrete manufacturing system equipped with a quality prediction device according to one embodiment.

[0017] [Ready-mix concrete manufacturing system] First, an overview of a ready-mixed concrete manufacturing system will be described. The manufacturing system 1 shown in Fig. 1 is a system for manufacturing ready-mixed concrete. The manufacturing system 1 mixes concrete materials to manufacture ready-mixed concrete.

[0018] The concrete materials used in the manufacturing system 1 include cement, admixtures, coarse aggregate, fine aggregate, water, and admixtures. Examples of coarse aggregate include gravel, crushed stone, slag coarse aggregate, lightweight coarse aggregate, recycled coarse aggregate, recovered aggregate, and coarse aggregates made from a mixture of these. Examples of gravel include mountain gravel, land gravel, river gravel, and sea gravel. Examples of slag coarse aggregate include blast furnace slag aggregate, ferronickel slag aggregate, electric arc furnace oxidizing slag aggregate, and coal gasification slag aggregate. Examples of lightweight coarse aggregate include natural lightweight aggregate, by-product lightweight aggregate, and artificial lightweight aggregate. Examples of coarse aggregate include crushed rock or crushed limestone.

[0019] Examples of fine aggregates include sand, crushed sand, slag fine aggregate, lightweight fine aggregate, recycled fine aggregate, recovered aggregate, and fine aggregates made from mixtures of these. Sand includes mountain sand, land sand, river sand, and sea sand. Slag fine aggregates include blast furnace slag aggregate, ferronickel slag aggregate, copper slag aggregate, electric furnace oxidizing slag aggregate, and coal gasification slag aggregate. Lightweight fine aggregates include natural lightweight aggregate, by-product lightweight aggregate, and artificial lightweight aggregate.

[0020] Examples of rock types for 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 serpentinite. Sedimentary rocks include conglomerate, sandstone, shale, slate, and tuff. Metamorphic rocks include gneiss and schist.

[0021] The manufacturing system 1 loads the manufactured ready-mixed concrete onto a transport vehicle 200. After the ready-mixed concrete has been loaded onto the transport vehicle 200, the transport vehicle 200 transports the ready-mixed concrete to the site where the ready-mixed concrete will be used (for example, a construction site). Examples of the transport vehicle 200 include an agitator vehicle (mixer vehicle) or a dump truck. The manufacturing system 1 may manufacture ready-mixed concrete from concrete materials so as to meet a target quality (required quality) set for each site. For example, an operator of the manufacturing system 1 determines the mix of concrete materials so as to meet the target quality set for each site, and inputs operating instructions to the manufacturing system 1.

[0022] The target quality set for each site is different from the quality of the ready-mixed concrete produced by the manufacturing system 1 before it is shipped (at the time of shipment). For example, in the manufacturing system 1, the quality of the ready-mixed concrete produced by the manufacturing system 1 before it is shipped is controlled (inspected, etc.) so that the target quality set for each site is met. In the present disclosure, the target quality set for each site is referred to as the "target quality at the time of use of ready-mixed concrete." The time of use of ready-mixed concrete corresponds to the time when the ready-mixed concrete is received at the site. The target quality at the time of use of ready-mixed concrete is set, for example, as shown in (1) to (3) below.

[0023] (1) Japanese Industrial Standards (National Standards) In one example, the target quality of the ready-mixed concrete when it is used includes a target value for at least one quality of slump, slump flow, and air content. The target values ​​for slump, slump flow, and air content at the site may be specified by a purchaser or an orderer in accordance with "Table 1 - Types and classifications of ready-mixed concrete" in "JIS A 5308:2019 (Ready-mixed concrete)" or "JIS A 5308:2024 (Ready-mixed concrete)." (2) Building Standards Act (Law) In addition to the target quality specified in the JIS, the Building Standards Act, Article 37, Paragraph 1, Item 2, may also set target quality standards for designated building materials that are subject to certification by the Minister of Land, Infrastructure, Transport and Tourism. Ready-mixed concrete that does not conform to the JIS standards can be used in buildings if it has been certified by the Minister of Land, Infrastructure, Transport and Tourism. This means that ready-mixed concrete with target qualities not specified in the JIS standards (for example, a slump of 23 cm, a slump flow of 65 cm, etc.) can be used in buildings (such as the foundations, main structures, and areas important for safety, fire prevention, or hygiene). (3) Standards established by academic societies If there is no mention of it in the above-mentioned JIS, the target quality when using ready-mixed concrete may be set based on the technical standards established by each academic society, such as the "Standard Specifications for Concrete" established by the Japan Society of Civil Engineers, a public interest incorporated association, or the "Standard Specifications for Building Construction and Commentary JASS5 Reinforced Concrete Works" established by the Architectural Institute of Japan, a general incorporated association. Note that "JIS A 5308:2019 (Ready-Mixed Concrete)" or "JIS A 5308:2024 (Ready-Mixed Concrete)" described in (1) corresponds to the "Japanese Industrial Standards Designated by the Minister of Land, Infrastructure, Transport and Tourism" as defined in Article 37, Paragraph 1, Item 1 of the Building Standards Act. Therefore, the second information regarding the target quality of ready-mixed concrete during use may be the target quality of designated building materials as defined in Article 37, Paragraph 1, Item 1 of the Building Standards Act. Alternatively, it may be the target quality of designated building materials subject to certification by the Minister of Land, Infrastructure, Transport and Tourism as defined in Article 37, Paragraph 1, Item 2 of the same Act as described in (2). It may also be the target quality set by standards established by academic societies, such as the "Standard Specifications for Concrete" or "Standard Specifications for Building Works and Commentary JASS5 Reinforced Concrete Works" as described in (3).

[0024] In order to manage the quality of ready-mixed concrete before it is shipped, a target quality of ready-mixed concrete at the time of shipment may be determined based on the target quality of ready-mixed concrete at the time of use. The target quality of ready-mixed concrete at the time of shipment may be set according to in-house standards or the like established for each factory. In setting the target quality of ready-mixed concrete at the time of shipment, at least one piece of information may be taken into consideration: the condition (quality) of the materials used during production, the season (temperature), the type of concrete, the target quality at the time of use, and the transportation time. The target quality of ready-mixed concrete at the time of shipment is set, for example, by adding a value established by the in-house standards to the target quality of ready-mixed concrete at the time of use.

[0025] The manufacturing system 1 includes, for example, a manufacturing apparatus 100 and a control device 10. The manufacturing apparatus 100 is an apparatus that manufactures ready-mixed concrete based on operation instructions from the control device 10. The manufacturing apparatus 100 manufactures ready-mixed concrete by mixing concrete materials. The manufacturing apparatus 100 includes, for example, a material storage area 101, a transport device 104, a storage bottle 111, a measuring bottle 112, a collection hopper 113, a mixer 114, and a loading hopper 115.

[0026] The material storage yard 101 is a place where concrete materials are stored. The material storage 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, for example, a silo 102 that stores coarse aggregate, a silo 102 that stores fine aggregate, and a silo 102 that stores cement.

[0027] The transporting device 104 is a device that transports concrete materials stored in the multiple silos 102 to the storage bins 111. 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 the control device 10, a specific material from among the various concrete materials is transferred to the transporting device 104 and transported to the storage bins 111.

[0028] The storage bottles 111 temporarily store various types of concrete materials. The various types of concrete materials are transported (conveyed) to the storage bottles 111 from the material storage area 101 by the transport device 104. The storage bottles 111 are configured to individually store various types of concrete materials. Hereinafter, "concrete materials" may be simply referred to as "materials." The various materials stored in the storage bottles 111 are supplied to the measuring bottles 112 as needed.

[0029] The measuring bottle 112 is disposed below the storage bottle 111. The measuring bottle 112 operates based on operational instructions from the control device 10, and individually measures various materials. When the measuring bottle 112 detects the target amount of material instructed by the control device 10, 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 the various materials discharged from the measuring bottle 112 and supplies the collected various materials to the mixer 114. Note that the manufacturing apparatus 100 does not necessarily have to be equipped with the collecting hopper 113, and the various materials may be supplied to the mixer 114 from the measuring bottle 112.

[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, etc. In other words, the mixer 114 produces ready-mixed concrete by mixing the concrete materials. The ready-mixed concrete is discharged from the bottom of the mixer 114 into the loading hopper 115. The mixer 114 may be a tilting mixer, a horizontal single-shaft mixer, a horizontal twin-shaft mixer, or a pan-type mixer. The mixer 114 includes, for example, two stirring members 114a and a mixer drive unit 114b.

[0031] The agitating members 114a are members that agitate the various materials supplied to the mixer 114. The two agitating members 114a are arranged side by side inside the main body (container portion) of the mixer 114 and are rotatable. Each of the two agitating members 114a includes a rotation shaft that extends horizontally in one direction. The mixer driving unit 114b rotates the rotation shaft of each of the two agitating members 114a based on an operation instruction from the control device 10. The mixer driving unit 114b includes, for example, a driving source such as a motor that applies driving force to the agitating members 114a. An opening and closing port is provided at the bottom of the main body of the mixer 114 for discharging the produced ready-mixed concrete into the loading hopper 115.

[0032] 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.

[0033] The manufacturing apparatus 100 described above is an example of a ready-mixed concrete manufacturing apparatus, and the ready-mixed concrete manufacturing apparatus may be configured in any way as long as it is capable of mixing concrete materials using a mixer and manufacturing ready-mixed concrete.

[0034] In this disclosure, a unit of ready-mixed concrete produced by one mixing in the mixer 114 and loaded onto the transport vehicle 200 is defined as "one batch." The process executed by the manufacturing system 1 for producing one batch of ready-mixed concrete is defined as "batch processing." In one example, one to three batches of ready-mixed concrete are loaded onto one transport vehicle 200. For example, when two batches of ready-mixed concrete are loaded onto one transport vehicle 200, two batch processes according to the same manufacturing conditions are performed at different times (in different orders).

[0035] <Control device (quality prediction device)> The control device 10 is a device that controls the manufacturing equipment 100. The control device 10 is configured with one or more computers. When the control device 10 is configured with multiple computers, these computers are connected to each other so that they can communicate with each other. The control device 10 controls the manufacturing equipment 100 in accordance with set operating conditions. At least some of the operating conditions may be determined by instructions from an operator such as a worker.

[0036] An input device 12 and a monitor 14 may be connected to the control device 10. The input device 12 is a device that inputs information indicating instructions from a worker or the like to the control device 10. The input device 12 may be any device that can input desired information, and may be a keyboard (keypad), an operation panel, or a mouse. The monitor 14 is a device that displays information from the control device 10 to a worker or the like. The monitor 14 may be any device that can display graphics, and may be a liquid crystal display. The input device 12 and the monitor 14 may be integrated, such as a touch panel. The control device 10, the input device 12, and the monitor 14 may be integrated, such as a tablet computer (tablet terminal).

[0037] In addition to controlling the manufacturing apparatus 100, the control device 10 may have a function of predicting the quality of ready-mixed concrete manufactured by the manufacturing apparatus 100. In this case, the control device 10 constitutes a quality prediction device that predicts the quality of ready-mixed concrete (ready-mixed concrete quality prediction device). In the following description, the quality of ready-mixed concrete predicted by the control device 10 is the quality after it has been manufactured by the manufacturing apparatus 100 and before it is shipped to the site (i.e., the quality of the ready-mixed concrete at the time of shipment).

[0038] The quality of fresh concrete to be predicted by the control device 10 may include one or more qualities of slump, slump flow, and air content. The quality of fresh concrete to be predicted by the control device 10 may include two or more qualities of slump, slump flow, and air content. The quality of fresh concrete to be predicted by the control device 10 may be one quality of slump, slump flow, and air content, or may be two or more qualities of slump, slump flow, and air content.

[0039] The control device 10 is configured to execute at least an acquisition step and a prediction step. The acquisition step is a step of acquiring input information including information related to the power load value of the mixer 114 and information related to the target quality at the time of use of the ready-mixed concrete whose quality is to be predicted (prediction target). The prediction step is a step of predicting the quality of the ready-mixed concrete to be predicted based on a prediction model previously constructed by machine learning so as to output quality information indicating the quality of the ready-mixed concrete in response to the input of the input information, and the input information acquired in the acquisition step.

[0040] 2 shows an example of functional components (hereinafter referred to as "functional blocks") included in the control device 10. The control device 10 has, for example, as functional blocks, an operation control unit 22, an operation information acquisition unit 24, a target quality information acquisition unit 26, a model construction unit 30, a model holding unit 32, a prediction calculation unit 28, and a display output unit 34. The processing executed by these functional blocks corresponds to the processing executed by the control device 10.

[0041] The operation control unit 22 controls the manufacturing apparatus 100 to manufacture ready-mixed concrete in accordance with predetermined operating conditions. At least some of the operating conditions may be determined by an operator, such as a worker, each time ready-mixed concrete is manufactured. The operation control unit 22 may control the mixer driving unit 114b of the mixer 114 so that the rotation speed of the mixer driving unit 114b follows a target rotation speed defined in the operating conditions. When controlling the mixer driving unit 114b, the operation control unit 22 may adjust the power (e.g., current value) supplied to the mixer driving unit 114b. If the ready-mixed concrete to be manufactured is hard, the power load value tends to be large, and if the ready-mixed concrete to be manufactured is soft, the power load value tends to be small.

[0042] The operation information acquisition unit 24 acquires information related to operations when producing ready-mixed concrete. The operation information acquisition unit 24 acquires information related to the power load value of the mixer 114 (hereinafter referred to as "first information"). The power load value of the mixer 114 may be a value indicating the power (kW) itself supplied to the mixer 114, or may be a value indicating the current value (A) supplied to the mixer 114. Alternatively, the power load value of the mixer 114 may be replaced with a value indicating the load hydraulic pressure (MPa). The information related to the power load value of the mixer 114 may be continuous time-series data while the mixer 114 is operating during the processing of one batch, or may be statistical data obtained from the time-series data.

[0043] FIG. 3 schematically illustrates time-series data relating to the power load value of the mixer 114 in one batch of processing. The time-series data relating to the power load value is, for example, data obtained by repeatedly measuring the power (kW) supplied to the mixer 114 at a predetermined sampling period. The operation information acquisition unit 24 may calculate (acquire) as statistical data at least one selected from the group consisting of a fluctuation range (difference between the maximum value and the minimum value), a decline range (difference between the maximum value and the final value), a total value within an arbitrarily set time period, an average value, a standard deviation, a coefficient of variation, a median, a first quartile, a third quartile, kurtosis, and skewness. The operation information acquisition unit 24 may calculate at least one of a minimum value and a maximum value as statistical data in addition to at least one selected from the above group. The statistical data acquired by the operation information acquisition unit 24 may include statistical values ​​obtained by calculation using two or more power load values ​​included in the time-series data.

[0044] In the graph shown in FIG. 3, "P1" represents the initial value in the time-series data. The initial value P1 is the power load value at the start of mixing in the time-series data. "P2" represents the minimum value in the time-series data. The minimum value P2 is the minimum power load value after the time when the initial value P1 is obtained. Note that the power load value at the start of mixing (initial value P1) may also be the minimum. "P3" represents the maximum value in the time-series data. The maximum value P3 is the maximum power load value after the time when the initial value P1 is obtained. "P4" represents the final value in the time-series data. The final value P4 is the power load value at the time when the operation control unit 22 determines that the condition for terminating mixing by the mixer 114 is met. For example, when a predetermined time has elapsed since the start of driving the agitating member 114a, the operation control unit 22 determines that the above condition is met and stops driving the agitating member 114a.

[0045] The target quality information acquisition unit 26 acquires information related to the target quality of the ready-mixed concrete when it is used (hereinafter referred to as "second information"). When the quality to be predicted by the control device 10 includes slump, the target quality information acquisition unit 26 may acquire, as the second information, information indicating a target value of slump when the ready-mixed concrete is used. When the quality to be predicted by the control device 10 includes slump flow, the target quality information acquisition unit 26 may acquire, as the second information, information indicating a target value of slump flow when the ready-mixed concrete is used. When the quality to be predicted by the control device 10 includes air content, the target quality information acquisition unit 26 may acquire, as the second information, information indicating a target value of air content when the ready-mixed concrete is used. The target quality information acquisition unit 26 may further acquire, as the second information, information indicating the target quality at the time of shipment of the ready-mixed concrete. That is, the second information may include information indicating the target quality at the time of shipment of the ready-mixed concrete in addition to information indicating the target quality at the time of use of the ready-mixed concrete.

[0046] The target quality information acquisition unit 26 acquires the second information, for example, based on input from an operator such as a worker via the input device 12. In one example, the target quality information acquisition unit 26 acquires the second information along with operating conditions related to the production of ready-mixed concrete to be produced. The target quality information acquisition unit 26 may acquire the second information based on input from an operator such as a worker via the input device 12 at the timing when quality prediction is performed by the control device 10. The operation information acquisition unit 24 and the target quality information acquisition unit 26 described above function as input information acquisition units that acquire input information including the first information and the second information.

[0047] The model construction unit 30 constructs a model for predicting the quality of ready-mixed concrete (hereinafter referred to as "prediction model M"). The prediction model M is a model that outputs quality information (quality value) indicating the quality of ready-mixed concrete in response to input of input information including the first information and second information. The model construction unit 30 constructs the prediction model M by machine learning based on the input information and the correct quality value associated with the input information. The prediction model M may be constructed to output, as quality information, one or more predicted values ​​of a predicted value of slump, a predicted value of slump flow, and a predicted value of air content. The prediction model M may be constructed to output, as quality information, a predicted value of the ratio of slump flow to slump (slump flow / slump), instead of or in addition to the one or more predicted values.

[0048] Machine learning is a technique in which a machine (computer) autonomously finds laws or rules by repeatedly learning based on given information. A prediction model M can be constructed using an algorithm and a data structure. A 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 and nerves. There are no particular limitations on the specific algorithm of machine learning used when constructing a prediction model M. A neural network has, for example, 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, thereby improving prediction accuracy.

[0049] The model construction unit 30 may autonomously construct a prediction model M for predicting the quality of ready-mixed concrete by performing machine learning using data provided as input for machine learning and correct data (correct values ​​of slump, etc.) that are the output of the machine learning. The input for the machine learning is various data sets of input information including first information and second information. The output of the machine learning is data (numerical values) that indicate the quality of the ready-mixed concrete. The model construction unit 30 iteratively learns a model that outputs predicted values ​​of slump, etc., using multiple combinations of data sets of input information and correct values ​​of slump, etc.

[0050] The stage of autonomously constructing the prediction model M corresponds to the learning phase. The learning phase may be performed before the production phase in which ready-mix concrete is manufactured, or may be performed at an early stage of the production phase. The model storage unit 32 stores the prediction model M constructed by the model construction unit 30. The prediction model M, which is a trained model, may be transferable between computers. Therefore, the prediction model M constructed in the control device 10 may be used in another manufacturing system different from the manufacturing system 1, and the model storage unit 32 may store the prediction model M constructed in the other manufacturing system.

[0051] In the evaluation phase, the prediction calculation unit 28 predicts the quality of the ready-mixed concrete to be predicted based on the input information acquired by the operation information acquisition unit 24 and the target quality information acquisition unit 26 (input information acquisition unit) and the prediction model M. The prediction calculation unit 28 inputs the acquired input information into the prediction model M and acquires a predicted value output from the prediction model M. The input information acquired in the evaluation phase (input information for evaluation) is information about the unknown quality of the ready-mixed concrete.

[0052] The display output unit 34 outputs information (quality value) indicating the quality predicted by the prediction calculation unit 28 to the monitor 14. As a result, the predicted value of quality is displayed on the monitor 14, and an operator such as a worker can grasp the predicted value of the quality of the ready-mixed concrete (manufactured ready-mixed concrete) that is the prediction target.

[0053] As shown in Fig. 4, the control device 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 at least a quality prediction program that causes a computer to execute the acquisition step and the prediction step. The storage 53 stores a quality prediction program for configuring each functional block of the control device 10.

[0054] The memory 52 is composed of one or more volatile memory devices such as a random access memory. The memory 52 temporarily stores a quality prediction 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 control device 10 by executing the quality prediction 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 to and from the input device 12, the monitor 14, the mixer 114, etc. in response to a request from the processor 51.

[0055] The timer 55 measures the elapsed time by, for example, counting reference pulses at a fixed interval. The circuit 50 is not necessarily limited to one in which each function is configured by a program. For example, the circuit 50 may have at least some of its functions configured by a dedicated logic circuit or an ASIC (Application Specific Integrated Circuit) that integrates such dedicated logic circuits. The quality prediction program may be provided by being permanently recorded on a tangible recording medium such as a CD-ROM, a DVD-ROM, or a semiconductor memory. Alternatively, the quality prediction program may be provided via a communication network as a data signal superimposed on a carrier wave.

[0056] [Ready-mix concrete manufacturing method] Next, an example of a method for producing ready-mixed concrete executed in the production system 1 will be described. The method for producing ready-mixed concrete includes a production process and a quality prediction process. The production process is a process for producing ready-mixed concrete. The quality prediction process is a process for predicting the quality of the ready-mixed concrete produced in the production process. The quality prediction process may be executed during a period that overlaps with at least a portion of the period during which the production process is repeatedly executed.

[0057] The manufacturing process includes, for example, a transporting process, a weighing process, a feeding process, a mixing process, a discharging process, and a loading process. In the transporting process, various types of concrete materials are transported to storage bottles 111 by a transporting device 104, and the various materials are individually supplied to the storage bottles 111. In the weighing process, the various materials are individually supplied from the storage bottles 111 to measuring bottles 112, and the various materials are weighed in the measuring bottles 112. In the weighing process, when the measured amount of each material reaches a predetermined set amount, the material is discharged into a collecting hopper 113. In the feeding process, after all types of materials have been collected in the collecting hopper 113, the materials in the collecting hopper 113 are fed (supplied) into a mixer 114.

[0058] In the mixing process, multiple types of concrete materials are mixed in the mixer 114. In the mixing process, the control device 10 may control the mixer driving unit 114b in accordance with predetermined operating conditions. In the mixing process, the power supplied from the control device 10 to the mixer driving unit 114b may be adjusted so that the rotation speed of the mixer driving unit 114b follows a target rotation speed.

[0059] In the discharging process, after mixing of the concrete materials in the mixer 114 is completed, the ready-mixed concrete is discharged from the mixer 114 into the loading hopper 115. In the loading process, the ready-mixed concrete discharged into the loading hopper 115 is loaded onto the transport vehicle 200.

[0060] The quality prediction process (quality prediction method) includes a model construction process in a learning phase and a quality evaluation process in an evaluation phase. In the quality prediction process, the model construction process is executed before the quality evaluation process. An example of the model construction process and an example of the quality evaluation process will be described below.

[0061] (Model building process) 5(a) is a flowchart showing an example of a series of processes executed in the model construction step. This model construction step is executed before the manufacturing process is executed in the manufacturing apparatus 100, or at an early stage after the manufacturing process is started. In this model construction step, for example, ready-mixed concrete actually manufactured in the manufacturing apparatus 100 is used as ready-mixed concrete for learning.

[0062] In the model building process, step S11 is first executed. In step S11, for example, an operator such as a worker prepares learning data for machine learning. The learning data is made up of a plurality of data sets. Each of the plurality of data sets includes input information (learning input information) including the first information and the second information obtained when the learning ready-mixed concrete is produced, and a correct value of quality information (for example, slump) associated with the input information.

[0063] The correct value of the quality information may be a value obtained by actually measuring the quality of the ready-mixed concrete for learning. In one example, after the ready-mixed concrete for learning is loaded onto the transport vehicle 200, a portion of the ready-mixed concrete is extracted by a worker or the like. The slump, slump flow, air content, etc. of the extracted ready-mixed concrete are then measured by the worker or the like, and at least a portion of these actual measured values ​​are used as the correct values ​​in the learning data.

[0064] Next, step S12 is executed. In step S12, for example, the model construction unit 30 of the control device 10 constructs a prediction model M by performing machine learning using the learning data (plurality of data sets) prepared in step S11. The model construction unit 30 may construct the prediction model M by machine learning using a neural network.

[0065] 6(a) and 6(b) each schematically show a prediction model M constructed by the model construction unit 30. The prediction model M shown in FIG. 6(a) is a model that outputs a single quality prediction value in response to input information. The prediction model M shown in FIG. 6(b) is a model that outputs two or more types of quality prediction values ​​in response to input information. In the present disclosure, machine learning performed so that the prediction model M outputs a single quality prediction value (a prediction value of only one type of quality) is referred to as "single-task learning." Furthermore, machine learning performed so that the prediction model M outputs two or more types of quality prediction values ​​is referred to as "multi-task learning."

[0066] The model construction unit 30 may construct the prediction model M by performing single-task learning. In this case, the model construction unit 30 may construct a prediction model M for each type of quality. For example, the model construction unit 30 constructs two or more models from among a prediction model M that outputs a predicted value of slump, a prediction model M that outputs a predicted value of slump flow, and a prediction model M that outputs a predicted value of air volume. The model construction unit 30 may construct the prediction model M by performing multi-task learning. For example, the model construction unit 30 constructs a prediction model M (one prediction model M) that outputs a predicted value for each of two or more qualities of slump, slump flow, and air volume. The model construction unit 30 may construct a prediction model M (one prediction model M) that outputs a ratio of slump flow to slump in addition to one or more qualities of slump, slump flow, and air volume.

[0067] An example of the prediction model M will be described below using simplified formulas for ease of understanding. The prediction model M constructed by the model construction unit 30 can be simply expressed, for example, as in the following formulas (1) and (2).

number

number

[0068] In equation (2), Y represents the output value of quality, and in a prediction model M constructed by single-task learning, it is the output value of a single quality. In a prediction model M constructed by multi-task learning, Y is the output value of one of two or more types of quality, and equations (1) and (2) are calculated for each type of quality. N is an integer equal to or greater than two and represents the number of pieces of input data. x represents various input values ​​included in the input data, and the input data corresponds to the above-mentioned input information, and the input data includes at least a value related to the power load value included in the first information (e.g., two or more statistics) and a value indicating the target quality included in the second information.

[0069] wi is a weight (coefficient), and b is a bias term (coefficient). f(U) represents the activation function. The activation function can be a linear function (identity function) or a nonlinear function such as a polynomial, absolute value, step function, sigmoid function, hardsigmoid function, logsigmoid function, softmax function, logsoftmax function, softmin function, softplus function, softsign function, tanh function, tanhShrink function, hardtanh function, tanhexp function, ReLU function, ReLU6 function, Leaky-ReLU function, PReLU function, ELU function, SELU function, CELU function, Swith function, Mish function, or ACON function.

[0070] The model construction unit 30 may use training data to repeatedly evaluate the error and loss value between Y (predicted value) obtained by equation (2) and the correct value of quality, and determine the weight wi and bias term b in equation (1) so as to minimize the error. The model construction unit 30 may use any type of loss function as a function for evaluating the error between Y (output value from an intermediate model at an intermediate stage in constructing the prediction model M) obtained by equation (2) and the correct value of quality. For example, the model construction unit 30 may use one loss function selected from the group consisting of Huber loss function (HuberLoss), mean absolute error (MAE), and ε-insensitive loss function (ε-insensitiveloss) as the loss function.

[0071] The Huber loss function can be expressed, for example, as in the following formula (3). The ε-allowable loss function can be expressed, for example, as in the following formula (4). L(a) is the loss value, and a is the error between the predicted value and the correct value. δ and ε are parameters that can be set arbitrarily, and are set, for example, to 1.0.

number

number

[0072] FIG. 7 illustrates various loss functions. Specifically, FIG. 7 shows the relationship between the error a and the loss value L(a) for the Huber loss function (δ=1.0), the mean absolute error, and the ε-allowable loss function (ε=0.5), as well as the relationship between the error a and the loss value L(a) for the mean squared error (MSE). In the graph of FIG. 7, the horizontal axis represents the error a, and the vertical axis represents the loss value L(a). In the mean squared error, when the error a exceeds 1, the loss value L(a) becomes larger than the absolute value of the error a. However, in the other three loss functions, the relationship in which the loss value L(a) is equal to or smaller than the absolute value of the error a holds regardless of the value of the error a. From the viewpoint of improving prediction accuracy, it is preferable to use a loss function that always makes the loss value L(a) equal to or smaller than the absolute value of the error a. The mean absolute error or the ε-allowable loss function may be used as a function that always makes the loss value L(a) equal to or smaller than the absolute value of the error a. Alternatively, by setting δ of the Huber loss function to 1.0 or less, it is possible to use it as a function in which the loss value L(a) is always less than or equal to the absolute value of the error a.

[0073] The model construction unit 30 may repeatedly update the weights wi using a gradient method so as to minimize the error and loss value evaluated by the loss function. The model construction unit 30 may use any type of update formula (weight update formula) when updating the weights wi. For example, the model construction unit 30 uses one selected from the group consisting of Adam, AdamBelief, Adamax, AdaBound, Adagrad, AMSGRAD, AMSBound, RMSprop, SgdW, Momentum, and Nesterov as the weight update formula. The weight update formula is also referred to as an optimization algorithm or an optimization method.

[0074] The model construction unit 30 may construct the prediction model M by machine learning using a neural network that does not perform an operation to normalize the input information and an operation to delete some connections in the fully connected layer. The operation to normalize the input information refers to an operation (batch normalization) that normalizes (standardizes) each value included in the input information that is input to the prediction model M so that the average is 0 and the standard deviation is 1.

[0075] The operation of dropping some connections in the fully connected layer means that, when performing machine learning using a neural network, learning is performed while deactivating an arbitrary proportion of nodes (dropout). Figure 6(c) shows a schematic diagram of the calculation process of the prediction model M when some connections in the fully connected layer are dropped (when dropout is performed). Note that the model construction unit 30 may construct the prediction model M by machine learning using a neural network that performs at least one of an operation to normalize input information and an operation to drop some connections in the fully connected layer.

[0076] 5(a), after step S12 is executed, step S13 is executed. In step S13, for example, the model holding unit 32 stores the prediction model M constructed in step S12. This completes the model construction process.

[0077] (Quality evaluation process) 5(b) is a flowchart showing an example of a series of processes executed in the quality evaluation process. This quality evaluation process is executed, for example, during a period overlapping at least a part of the period during which the manufacturing process is executed by the manufacturing apparatus 100.

[0078] In the quality evaluation process, first, the control device 10 executes step S21. In step S21, for example, the control device 10 waits until the evaluation timing arrives, which is the timing for evaluating the quality of the ready-mixed concrete to be evaluated. The ready-mixed concrete to be evaluated is also the ready-mixed concrete to be manufactured by the manufacturing apparatus 100. The evaluation timing may be predetermined to a certain time period in a day, or may be predetermined to the timing of executing a certain number of batch processes in a day. The evaluation timing may also be the timing when an instruction to perform the evaluation is received from an operator such as a worker.

[0079] Next, the control device 10 executes step S22. In step S22, for example, the operation information acquisition unit 24 and the target quality information acquisition unit 26 acquire input information including the first information (information related to the power load value) and the second information (information related to the target quality) when the ready-mixed concrete to be evaluated was produced. The input information acquired in step S22 is input information for evaluation in which quality information (for example, slump) is unknown.

[0080] Next, the control device 10 executes step S23. In step S23, for example, the prediction calculation unit 28 predicts quality information of the ready-mixed concrete to be evaluated based on the input information acquired in step S22 and the prediction model M held in the model holding unit 32. In one example, the prediction calculation unit 28 inputs the input information acquired in step S22 into the prediction model M, and acquires a predicted value of one or more quality types among slump, slump flow, and air content output from the prediction model M.

[0081] Next, the control device 10 executes step S24. In step S24, for example, the display output unit 34 displays the predicted quality value acquired in step S23 on the monitor 14. This allows an operator such as a worker to check the predicted quality value.

[0082] This completes the quality evaluation process. The control device 10 may execute the series of processes of steps S21 to S24 each time one batch of ready-mixed concrete is produced (each time a batch process is performed). The control device 10 may execute the series of processes of steps S21 to S24 each time multiple batches of ready-mixed concrete are produced (each time multiple batch processes are performed).

[0083] [Variations] The series of processes shown in Figures 5(a) and 5(b) are examples and can be modified as appropriate. In the series of processes, one step and the next step may be executed in parallel, or some steps may be executed in an order different from that of the example described above. Steps different from those of the example described above may be executed instead of or in addition to at least some of the steps of the series of processes described above.

[0084] The first information may include at least one of the initial value, minimum value, maximum value, and final value in the time-series data related to the power load value. The input information acquired by the control device 10 (input information acquisition unit) and used as an input to the prediction model M may include information related to mixing by the mixer 114 (information other than the power load value). Examples of the information related to mixing include the amount of concrete mixed for one batch, the mixing time, the time at which the power load value reaches its maximum value, and the time from when the power load value reaches its maximum value until the fresh concrete is discharged from the mixer 114. The input information used as an input to the prediction model M may include the nominal strength, information indicating the type of cement, information indicating the type of admixture, information indicating the type of fine aggregate, information indicating the type of coarse aggregate, and information indicating the amount of additive added.

[0085] The first information included in the input information that is input to the prediction model M may be information related to vibrations caused by the falling or flowing down of ready-mixed concrete instead of the power load value of the mixer 114. The information related to vibrations may be information related to vibrations caused by the falling or flowing down of ready-mixed concrete from the mixer 114. As shown in FIG. 1 , the manufacturing system 1 may include a vibration sensor 18.

[0086] The vibration sensor 18 is a sensor that detects vibrations (vibration magnitude) caused by the falling or flowing down of the ready-mixed concrete produced by the mixer 114. Vibrations caused by the falling or flowing down include vibrations caused by both the falling and flowing down of the ready-mixed concrete. The vibration sensor 18 may be capable of detecting the magnitude of vibrations in two or more directions caused by the falling or flowing down of the ready-mixed concrete. The vibration sensor 18 is attached to the loading hopper 115, for example, to detect the magnitude of vibration of the loading hopper 115. The vibration sensor 18 may be installed on either side wall of the loading hopper 115. The ready-mixed concrete discharged from the mixer 114 may fall against the side wall on which the vibration sensor 18 is installed.

[0087] The vibration sensor 18 may be any type of sensor as long as it is capable of detecting the magnitude of vibration of the loading hopper 115. The vibration sensor 18 is, for example, a sensor that detects the acceleration of the loading hopper 115. The vibration sensor 18 may detect acceleration in each of two directions along the side wall of the loading hopper 115 that are perpendicular to each other, and acceleration in a direction perpendicular to the side wall of the loading hopper 115. The vibration sensor 18 may detect acceleration in each direction at a predetermined sampling period. The vibration sensor 18 outputs information indicating the detection results to the control device 10.

[0088] Among the input information to be input to the prediction model M, the information relating to vibration may be time series data of the detection values ​​by the vibration sensor 18 obtained during a period including the time when the ready-mixed concrete is discharged into the loading hopper 115 (hereinafter referred to as the "discharge period"). The information relating to vibration may be a statistical quantity obtained from the time series data instead of or in addition to the time series data during the discharge period.

[0089] The first information included in the input information that is input to the prediction model M may be information relating to an image of ready-mixed concrete instead of the power load value of the mixer 114. The information relating to the image of ready-mixed concrete is information relating to an image obtained by capturing an image of ready-mixed concrete being manufactured in the manufacturing apparatus 100. As shown in FIG. 1 , the manufacturing system 1 may include an image sensor 16.

[0090] The image sensor 16 is a sensor (camera) that captures images of ready-mixed concrete during production. In the present disclosure, capturing images of ready-mixed concrete during production in the production apparatus 100 includes capturing images of ready-mixed concrete after it has been produced in the mixer 114, as well as capturing images of the ready-mixed concrete being produced in the mixer 114. Capturing images of ready-mixed concrete after it has been produced in the mixer 114 includes capturing images of the ready-mixed concrete in the loading hopper 115 and capturing images of the ready-mixed concrete being poured from the loading hopper 115 into the transport vehicle 200. The image data obtained by the image sensor 16 may be either still image data or video data. The image sensor 16 may perform imaging based on an operation instruction from the control device 10. The image sensor 16 outputs the image data obtained by the imaging to the control device 10.

[0091] The image sensor 16 may be arranged so as to be able to capture an image of the ready-mixed concrete being produced in the mixer 114. The image sensor 16 may be arranged so as to be able to capture an image of the ready-mixed concrete stored in the space within the loading hopper 115. When there is a possibility that the ready-mixed concrete will rebound in the mixer 114 or the loading hopper 115, the image sensor 16 may be arranged in a position where the image is less likely to be affected by the rebounded ready-mixed concrete. The image sensor 16 may be arranged so as to be able to capture an image of the ready-mixed concrete being discharged from the loading hopper 115. The manufacturing system 1 may include two or more image sensors 16 provided at two or more different locations.

[0092] In addition to the prediction of the quality of ready-mixed concrete by the control device 10, the quality of ready-mixed concrete may be measured periodically (for example, several times a day) in the manufacturing apparatus 100. In this case, the prediction model M may be updated based on the actual measurement value of the quality of the ready-mixed concrete and input information at the time the actual measurement value was obtained (for example, information related to the power load value or an image of the ready-mixed concrete). In the prediction step, the quality of the ready-mixed concrete may be predicted using the updated prediction model M. Note that even when the updated prediction model M is used, the step of predicting the quality of the ready-mixed concrete is still performed based on the prediction model M and the input information acquired in the acquisition step.

[0093] The first information included in the input information acquired by the input information acquisition unit of the control device 10 and used as an input to the prediction model M may be information relating to two or more of vibrations caused by the falling or flowing down of fresh concrete from the mixer 114, an image of the fresh concrete, and a power load value of the mixer 114. As described above, the first information included in the input information acquired by the input information acquisition unit of the control device 10 and used as an input to the prediction model M may be information relating to at least one of vibrations caused by the falling or flowing down of fresh concrete from the mixer 114, an image of the fresh concrete, and a power load value of the mixer 114.

[0094] The manufacturing system 1 may include, as a functional block, a quality prediction device (ready-mixed concrete quality prediction device) that has at least an operation information acquisition unit 24, a target quality information acquisition unit 26, a prediction calculation unit 28, and a model storage unit 32, separate from the control device 10. A computer that constitutes the quality prediction device may be communicably connected to the control device 10. Hereinafter, a quality prediction device that has at least the operation information acquisition unit 24, the target quality information acquisition unit 26, the prediction calculation unit 28, and the model storage unit 32 will be simply referred to as a "quality prediction device."

[0095] In the above example, the control device 10 functioning as a quality prediction device predicts the quality of ready-mixed concrete after it has been produced by the production apparatus 100 and before it is shipped to the construction site. The timing at which the quality prediction device predicts the quality is not limited to this example. The quality prediction device may also predict the quality of ready-mixed concrete while it is being transported to the construction site where the ready-mixed concrete will be used (including upon arrival at the construction site). For example, the transport vehicle 200 is provided with a mixer 204 that mixes the ready-mixed concrete (see FIG. 1), and the input information acquisition unit of the quality prediction device acquires information related to the power load value of the mixer 204 as at least part of the first information. Note that the mixer 204 in the transport vehicle 200, such as an agitator vehicle, is also referred to as a drum. As described above, at least part of the first information may be information related to the production of ready-mixed concrete by mixing concrete materials, or the power load value of the mixer (114, 204) that mixes the ready-mixed concrete after production.

[0096] In the above example, ready-mixed concrete is manufactured at a location (manufacturing apparatus 100) separate from the construction site. The location where ready-mixed concrete is manufactured is not limited to this example. Concrete materials (for example, concrete materials excluding water) may be transported to the construction site by a transport vehicle, and ready-mixed concrete may be manufactured at the construction site. At that time, water may be added to the concrete materials transported by the transport vehicle by a mixer provided on the transport vehicle, and the materials may be mixed to manufacture ready-mixed concrete. The quality prediction device may predict the quality of ready-mixed concrete at the construction site when the ready-mixed concrete is manufactured at the construction site. The input information acquisition unit of the quality prediction device may acquire, as at least part of the first information, information related to the power load value of the mixer provided on the transport vehicle when ready-mixed concrete is manufactured at the construction site.

[0097] In one example of the various examples described above, at least some of the features described in other examples may be combined.

[0098] [Verification of prediction results using the prediction model] Next, we will explain the results of verifying the prediction results of quality information using a prediction model M that inputs input information including the first information and the second information, using a dataset in which the correct values ​​are known.

[0099] (Impact of target quality) The influence of second information, which indicates the target quality of ready-mixed concrete when used, was examined. For this examination, 2,765 training datasets were prepared to construct a predictive model using machine learning, and 789 evaluation datasets, in which the correct values ​​were known, were prepared for evaluation. In the training datasets and evaluation datasets, various input values ​​contained in the input information were associated with the correct values ​​of the quality information. Statistics obtained from time-series data related to power load values ​​were used as the first information of the input information in the training datasets and evaluation datasets. Using the 2,765 training datasets, a predictive model M was constructed using input information including the first information and the second information. A predictive model M was constructed using multi-task learning to output slump, slump flow, and air content.

[0100] To verify the impact of the second information on prediction accuracy, a comparison model was constructed using the same 2,765 training datasets, excluding the second information from the input information. The impact of the second information on prediction accuracy was evaluated for slump, slump flow, and air volume. Using 789 evaluation datasets, the prediction results of the model M and the comparison model were compared with the correct values ​​in the evaluation dataset. The model prediction results were defined as correct when they fell within the range obtained by adding a specified tolerance to the correct value in the evaluation dataset, and the accuracy rate was used as the evaluation index. Figure 8 shows a graph illustrating the results of verifying the impact of the second information.

[0101] Regarding the verification results for slump in Figure 8, when the tolerance is "±0.5 cm," datasets whose prediction results (predicted values) by the model are within a range of ±0.5 cm of the correct value are considered correct, and the percentage of datasets determined to be correct is shown as the accuracy rate (%). Accuracy rates (%) are also calculated similarly when the tolerance is "±1.0 cm," "±1.5 cm," "±2.0 cm," and "±2.5 cm." "Yes" indicates the evaluation result using prediction model M, which includes second information (target quality) in its input information, and "No" indicates the evaluation result using a comparison model, which does not include second information in its input information. It can be seen that the accuracy rate (%) when predicting slump using prediction model M is higher than when predicting slump using the comparison model.

[0102] Regarding the verification results of slump flow in Figure 8, as with the verification of slump, the tolerance was changed to "±2.5 cm," "±3.0 cm," "±5.0 cm," and "±7.5 cm," and the accuracy rate (%) was calculated for each tolerance. As for slump flow, it can be seen that the accuracy rate (%) when predicting slump flow using prediction model M is higher than when predicting slump flow using the comparison model.

[0103] As with the slump verification, the accuracy rate (%) of the air content verification results in Figure 8 was calculated for each tolerance, changing it to ±0.3%, ±0.5%, ±1.0%, and ±1.5%. It can be seen that the accuracy rate (%) of the air content prediction using prediction model M is also higher than that of the air content prediction using the comparative model.

[0104] (Effect of Batch Normalization and Dropout) When constructing a model for predicting the quality information of fresh concrete, we examined the effects of batch normalization, an operation that normalizes input information, and dropout, an operation that drops some data in the fully connected layer. We constructed a prediction model M while varying the presence or absence of these operations and the dropout rate when dropping some data. We then calculated the accuracy rate (%) of the allowable discrimination for slump, slump flow, and air content. The 2,765 training datasets and the 789 evaluation datasets described above were used in the verification. The accuracy rate (%) of the allowable discrimination for slump is shown in Table 1 below, the accuracy rate (%) of the allowable discrimination for slump flow is shown in Table 2 below, and the accuracy rate (%) of the allowable discrimination for air content is shown in Table 3 below.

[0105] [Table 1]

[0106] [Table 2]

[0107] [Table 3]

[0108] In the conditions of Tables 1 to 3, "BN" represents Batch Normalization (a normalization operation), "DO" represents Dropout (an operation that causes some connections to be missing), and "P" represents the missing rate in Dropout. "BN, DO not used" indicates that prediction model M was constructed by training with a neural network that does not include Batch Normalization or Dropout. Columns with only "BN" listed indicate that prediction model M was constructed by training with a neural network that includes Batch Normalization but does not include Dropout. Columns with only "DO" listed indicate that prediction model M was constructed by training with a neural network that includes Dropout but does not include Batch Normalization. Columns with "BN+DO" indicate that prediction model M was constructed by training with a neural network that includes Batch Normalization and Dropout.

[0109] The results shown in Tables 1 and 2 indicate that there is no significant difference in the accuracy rate (%) for slump and slump flow depending on whether or not batch normalization and dropout are used.The results shown in Table 3 indicate that the accuracy rate (%) for air volume tends to be higher when batch normalization and dropout are not used than when at least one of batch normalization and dropout is used.

[0110] (Influence of the type of weight update formula) We verified the effect of the type of weight update formula used when building a model to predict quality information of fresh concrete. We built a prediction model M while changing the type of weight update formula, and then calculated the accuracy rate (%) of the allowable discrimination for air content. In the verification, we used the above-mentioned 2,765 training datasets and the above-mentioned 789 evaluation datasets. The verification results are shown in Tables 4 and 5 below.

[0111] [Table 4]

[0112] [Table 5]

[0113] In Table 5, "(×0.01)" indicates that machine learning was performed after multiplying each value included in the input information in the training dataset by 0.01 so that each value falls within the range of -1 to 1. The results shown in Tables 4 and 5 show that when one selected from the group consisting of Adam, AdamBelief, Adamax, AdaBound, Adagrad, AMSGRAD, AMSBound, RMSprop, SgdW, Momentum, and Nesterov is used as the weight update formula, the accuracy rate (%) is higher than when AdamW, Lars, Adadelta, and Sgd are used. Although the data is not shown, the accuracy rate (%) for each update formula shown in Tables 4 and 5 for slump and slump flow was calculated. When Lars and Sgd were used, the accuracy rate (%) was lower than when other update formulas were used.

[0114] (Influence of loss function type) The effect of the type of loss function used when constructing a model for predicting quality information of fresh concrete was examined. A prediction model M was constructed while varying the type of loss function, and the accuracy rate (%) of the allowable discrimination was calculated for each of slump, slump flow, and air content. The function shown in the above-mentioned formula (3) was used as the Huber loss function, with the value of δ set to 1.0. The function shown in the above-mentioned formula (4) was used as the ε-allowable loss function, with the value of ε set to 1.0. The above-mentioned 2,765 training datasets and the above-mentioned 789 evaluation datasets were used in the verification. The verification results are shown in Tables 6, 7, and 8 below.

[0115] [Table 6]

[0116] [Table 7]

[0117] [Table 8]

[0118] The results shown in Tables 6, 7, and 8 indicate that when one selected from the group consisting of the Huber loss function, mean absolute error, and ε-tolerant loss function is used as the loss function, the accuracy rate (%) is higher than when mean squared error (MSE) is used. The difference between mean squared error and other loss functions is that when the error is large, the loss value is large. The results shown in Tables 6, 7, and 8 confirm that selecting a loss function whose loss value is always less than the absolute value of the error is preferable from the perspective of improving prediction accuracy.

[0119] (Influence of learning method) The impact of the learning method when constructing a model for predicting quality information of fresh concrete was verified. The accuracy rate (%) was compared between a case where prediction models M (prediction models M for each of the three qualities) were constructed individually using single-task learning for slump, slump flow, and air content, and a case where prediction models M were constructed using multi-task learning to output predicted values ​​for all three qualities together. The verification used the 2,765 training datasets and the 789 evaluation datasets mentioned above. The verification results are shown in Tables 9, 10, and 11 below.

[0120] [Table 9]

[0121] [Table 10]

[0122] [Table 11]

[0123] In the multi-task learning column of Table 9, the accuracy rate (%) is calculated using the output value for slump from prediction model M. In the multi-task learning column of Table 10, the accuracy rate (%) is calculated using the output value for slump flow from prediction model M, and in the multi-task learning column of Table 11, the accuracy rate (%) is calculated using the output value for air volume from prediction model M. The results shown in Tables 9, 10, and 11 show that there is no significant difference in the accuracy rate (%) whether single-task learning or multi-task learning is used as the learning method.

[0124] Summary of this disclosure The method for predicting the quality of fresh concrete described above includes an acquisition step of acquiring input information including first information relating to at least one of the power load value of a mixer (114, 204) that produces fresh concrete by mixing concrete materials or mixes the fresh concrete, vibrations caused by the falling or flowing down of fresh concrete, and an image of the fresh concrete, and second information relating to the target quality of the fresh concrete when it is used; and a prediction step of predicting the quality of the fresh concrete based on a prediction model (M) previously constructed by machine learning to output quality information indicating the quality of the fresh concrete in response to input of the input information, and the input information acquired in the acquisition step.

[0125] When ready-mixed concrete is manufactured (for example, when it is manufactured in a factory or the like where the manufacturing system (1) is installed), a target quality (at the site) for the ready-mixed concrete to be manufactured at the time of use is specified, and ready-mixed concrete is manufactured to meet that target quality. As described above, it has been discovered that by using such a target quality as one of the input information for the prediction model (M) constructed by machine learning, the accuracy of quality prediction can be improved. It is easy to obtain the target quality as information. Therefore, in the above method, when predicting quality using the prediction model (M), it is possible to improve the accuracy of quality prediction while avoiding the complication of work associated with quality prediction.

[0126] In the above-described method for predicting the quality of ready-mixed concrete, the quality of the ready-mixed concrete may include one or more qualities of slump, slump flow, and air content. In this case, it is possible to easily manage whether the slump, slump flow, or air content of the produced ready-mixed concrete can satisfy the target quality when the ready-mixed concrete is used.

[0127] In the above-described method for predicting the quality of ready-mixed concrete, the quality of ready-mixed concrete may include two or more qualities selected from slump, slump flow, and air content. The prediction model (M) may be constructed to output two or more qualities in response to input information. As described above, it has been found that there is no significant difference in prediction accuracy between single-task learning to construct a prediction model (M) that outputs only one quality and multi-task learning to construct a prediction model M that outputs two or more qualities. By constructing the prediction model (M) using multi-task learning as in the above method, it is possible to simplify the work required to construct the model while maintaining prediction accuracy.

[0128] In the quality prediction method for ready-mixed concrete described above, the prediction model (M) may be constructed by machine learning using a neural network that does not perform calculations to normalize input information and calculations to delete some connections in the fully connected layer. Generally, in machine learning using a neural network, it is considered preferable to perform calculations to normalize input information and calculations to delete some connections in the fully connected layer from the standpoint of stabilizing learning and preventing overlearning. However, as described above, the presence or absence of these calculations does not significantly affect prediction accuracy, and for certain qualities (air content), it has been shown that prediction accuracy tends to be higher when these calculations are not performed. Therefore, by constructing a prediction model (M) using the above method, it is possible to simplify the work required to construct the model while maintaining prediction accuracy.

[0129] In the quality prediction method for ready-mixed concrete described above, the second information may include information indicating a target quality at the time of shipment of the ready-mixed concrete, in addition to information indicating a target quality at the time of use of the ready-mixed concrete. In a factory or the like where the production system (1) is installed, the target quality at the time of shipment is set so as to satisfy the target quality at the time of use of the ready-mixed concrete (i.e., the required quality at the time of acceptance). Therefore, the target quality at the time of shipment correlates with the target quality at the time of use of the ready-mixed concrete. In the above method, the target quality at the time of shipment is further included in the input information of the prediction model (M), thereby further improving the accuracy of quality prediction.

[0130] In the quality prediction method for ready-mixed concrete described above, the prediction model (M) may be constructed by machine learning using a neural network. In the machine learning using a neural network when constructing the prediction model (M), one selected from the group consisting of Adam, AdamBelief, Adamax, AdaBound, Adagrad, AMSGRAD, AMSBound, RMSprop, SgdW, Momentum, and Nesterov may be used as the weight update equation. As described above, it has been found that using these update equations improves prediction accuracy compared to using other update equations. Therefore, the above method can further improve prediction accuracy.

[0131] In the above-described method for predicting the quality of ready-mixed concrete, the prediction model (M) may be constructed by machine learning using a neural network. In the machine learning using a neural network for constructing the prediction model (M), a function may be used as the loss function such that the loss value L(a) is always less than or equal to the absolute value of the error a. As described above, it has been found that the use of such a loss function results in higher prediction accuracy than when other loss functions are used. Therefore, the above-described method can further improve prediction accuracy.

[0132] The quality prediction program described above is a program for causing a computer to execute the quality prediction method. This quality prediction program can cause a computer to execute the quality prediction method, so that when predicting quality using a prediction model (M), it is possible to improve the accuracy of quality prediction while avoiding the complexity of work involved in quality prediction.

[0133] The quality prediction device (10) described above includes an input information acquisition unit (24, 26) that acquires input information including first information related to at least one of a power load value of a mixer (114, 204) that mixes concrete materials to produce ready-mixed concrete or mixes the ready-mixed concrete, vibrations caused by the falling or flowing of the ready-mixed concrete, and an image of the ready-mixed concrete, and second information related to a target quality of the ready-mixed concrete when it is used; a prediction model (M) that is pre-constructed by machine learning to output quality information indicating the quality of the ready-mixed concrete in response to input of the input information; and a prediction calculation unit (28) that predicts the quality of the ready-mixed concrete based on the input information acquired by the input information acquisition unit (24, 26). As with the quality prediction method described above, when predicting quality using the prediction model (M), the quality prediction device (10) can improve the accuracy of the quality prediction while avoiding the complexity of the work involved in quality prediction. [Explanation of symbols]

[0134] 1... manufacturing system, 10... control device, 24... operation information acquisition unit, 26... target quality information acquisition unit, 28... prediction calculation unit, 30... model construction unit, M... prediction model, 100... manufacturing apparatus, 114... mixer, 114a... stirring member, 114b... mixer drive unit, 204... mixer.

Claims

1. an acquisition step of acquiring input information including first information relating to at least one of a power load value of a mixer that produces ready-mixed concrete by mixing concrete materials or that mixes the ready-mixed concrete, vibrations caused by the falling or flowing down of the ready-mixed concrete, and an image of the ready-mixed concrete, and second information relating to a target quality of the ready-mixed concrete when it is used; a prediction step of predicting the quality of the ready-mixed concrete based on a prediction model constructed in advance by machine learning so as to output quality information indicating the quality of the ready-mixed concrete in response to input of the input information, and the input information acquired in the acquisition step; A method for predicting the quality of ready-mix concrete, including:

2. The quality of the fresh concrete includes one or more qualities of slump, slump flow, and air content; The method for predicting the quality of ready-mixed concrete according to claim 1.

3. The quality of the fresh concrete includes two or more qualities of slump, slump flow, and air content, The prediction model is constructed to output the two or more types of quality in response to input of the input information. The method for predicting the quality of ready-mixed concrete according to claim 2.

4. The prediction model is constructed by machine learning using a neural network that does not perform an operation to normalize the input information and an operation to delete some connections in a fully connected layer. The method for predicting the quality of ready-mixed concrete according to claim 1.

5. The second information includes information indicating the target quality at the time of shipment of the ready-mixed concrete in addition to information indicating the target quality at the time of use of the ready-mixed concrete. The quality prediction method for ready-mixed concrete according to any one of claims 1 to 4.

6. The prediction model is constructed by machine learning using a neural network, and the machine learning using the neural network for constructing the prediction model uses one weight update formula selected from the group consisting of Adam, AdamBelief, Adamax, AdaBound, Adagrad, AMSGRAD, AMSBound, RMSprop, SgdW, Momentum, and Nesterov. The method for predicting the quality of ready-mixed concrete according to any one of claims 1 to 4.

7. The prediction model is constructed by machine learning using a neural network, and the machine learning using the neural network for constructing the prediction model utilizes a loss function such that the loss value L(a) is always equal to or less than the absolute value of the error a. The method for predicting the quality of ready-mixed concrete according to any one of claims 1 to 4.

8. A quality prediction program that causes a computer to execute the ready-mixed concrete quality prediction method according to any one of claims 1 to 4.

9. an input information acquisition unit that acquires input information including first information relating to at least one of a power load value of a mixer that produces ready-mixed concrete by mixing concrete materials or that mixes the ready-mixed concrete, vibrations caused by the falling or flowing down of the ready-mixed concrete, and an image of the ready-mixed concrete, and second information relating to a target quality of the ready-mixed concrete when it is used; a prediction calculation unit that predicts the quality of the ready-mixed concrete based on a prediction model that is constructed in advance by machine learning so as to output quality information that indicates the quality of the ready-mixed concrete in response to input of the input information, and the input information acquired by the input information acquisition unit; A ready-mixed concrete quality prediction device comprising:

Images