Information processing method and information processing device

Abstract

To provide an information processing method capable of suppressing an increase in costs required for generating molding conditions.SOLUTION: In an information processing method, molding condition information or quality information is input together with shape information and time-series information into a mathematical model that is adjusted to output quality information as output information when the molding condition information, the shape information, and the time-series information are input, based on the molding condition information that indicates molding conditions for the molding by a molding device, the shape information that indicates a shape of a molded product, the time-series information that indicates a time series of physical quantities detected by a physical quantity detection part that detects physical quantities related to fluidity of a molding material in an area within the molding device through which the molding material passes, and the quality information that indicates quality of the molded product; and output information output from the mathematical model into which the information has been input is displayed on a display part.SELECTED DRAWING: Figure 12

Description

[Technical Field]

[0001] The present disclosure relates to an information processing method and an information processing device. [Background technology]

[0002] BACKGROUND ART Research and development is being conducted on methods for forming objects using forming materials, such as injection molding and three-dimensional modeling.

[0003] In this regard, there is known an injection molding condition generation system that generates injection molding conditions using a computer including a processor and memory, in which the processor acquires a first material characteristic value of a first resin material and generates injection molding conditions for injection molding using the first resin material based on a target value of a quality parameter related to the quality of the molded product, the first material characteristic value, and a predetermined relational expression, where the predetermined relational expression is an expression that shows the relationship between the material characteristic value of the resin material, multiple injection molding conditions input to the injection molding device, and the quality parameters related to the quality of the molded product molded by the injection molding device based on the material characteristic value and each injection molding condition, and an injection molding condition generation system in which the material characteristic value of the resin material, the injection molding conditions, and the quality parameters are linked and generated based on data stored in memory (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-141495 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the injection molding condition generation system described in Patent Document 1, the first material characteristic value is detected by a sensor installed in the mold. Therefore, in this injection molding condition generation system, the first material characteristic value needs to be detected again every time the mold is changed. This undesirably increases the cost required to generate injection molding conditions. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, one aspect of the present disclosure is an information processing method comprising: an input step of inputting the modeling condition information or the quality information together with the shape information and the time-series information into a mathematical model that is adjusted to output the quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to the fluidity of the modeling material in an area of ​​the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; and a display control step of displaying the output information output from the mathematical model into which information has been input by the input step, on a display unit.

[0007] In order to solve the above-mentioned problems, one aspect of the present disclosure is an information processing device comprising: an input unit that inputs the modeling condition information or the quality information together with the shape information and the time-series information to a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to the fluidity of the modeling material in an area of ​​the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; and a display control unit that displays the output information output from the mathematical model to which information has been input by the input unit, on a display unit. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of a configuration of an information processing system 1. FIG. [Figure 2] FIG. 2 is a diagram showing an example of the configuration of a material supply device 11. [Figure 3] FIG. 3 is a perspective view showing an example of the configuration of the flat screw 130 shown in FIG. 2. [Figure 4] 3 is a plan view showing an example of the configuration of the barrel 133 shown in FIG. 2. FIG. [Figure 5] 3 is an enlarged view of a flow path 160 and a suction portion 171 shown in FIG. 2. [Figure 6] FIG. 2 is a diagram illustrating an example of input and output of a mathematical model X. [Figure 7] 10 is a diagram illustrating time-series information of the pressure in the flow path 160 of the modeling material in a dried state and time-series information of the pressure in the flow path 160 of the modeling material in a non-dried state. FIG. [Figure 8]10 is a diagram illustrating time-series information of the pressure in the suction unit 171 of the modeling material in a dried state and time-series information of the pressure in the suction unit 171 of the modeling material in a non-dried state. FIG. [Figure 9] FIG. 10 is a diagram showing an example of CAD data of a shaped product. [Figure 10] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device 20. [Figure 11] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device 20. [Figure 12] FIG. 10 is a diagram showing an example of a processing flow in which the information processing device 20 displays output information. [Figure 13] 10 is a diagram showing an example of a processing flow in which the information processing device 20 learns a mathematical model X. FIG. [Figure 14] FIG. 10 is a diagram showing an example of a processing flow in which the information processing device 20 acquires time-series information. DETAILED DESCRIPTION OF THE INVENTION

[0009] <Embodiment> Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0010] <Outline of the information processing system> First, an overview of an information processing system according to an embodiment will be described.

[0011] An information processing system according to an embodiment includes a modeling apparatus and an information processing device. The modeling apparatus models a modeled product using a modeling material. The information processing device includes an input unit and a display control unit. The input unit inputs the modeling condition information or the quality information, together with the shape information and the time-series information, to a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information indicating modeling conditions for modeling by the modeling apparatus, shape information indicating the shape of the modeled product, time-series information indicating a time series of physical quantities detected by a physical quantity detection unit that detects physical quantities related to the fluidity of the modeling material in an area within the modeling apparatus through which the modeling material passes, and quality information indicating the quality of the modeled product. The mathematical model is capable of outputting the modeling condition information as output information when the shape information, the time-series information, and the quality information are input. The display control unit controls the display unit to display the output information output from the mathematical model to which the input unit inputs information.

[0012] As a result, the information processing system according to the embodiment can prevent a user from having to repeatedly go through trial and error to obtain desired modeling conditions. Furthermore, the information processing system can detect a physical quantity related to the fluidity of a modeling material within the modeling apparatus. This means that it is not necessary to provide a detection unit for detecting the physical quantity in a mold, as in the past. As a result, the information processing system does not need to re-detect the physical quantity every time a mold is changed, and it is possible to prevent an increase in the cost required to generate modeling conditions.

[0013] The configuration of the information processing system according to the embodiment, the configuration of the information processing device included in the information processing system, and the processing performed by the information processing device will be described in detail below.

[0014] It is known that, for example, when the modeling apparatus is an injection molding apparatus, the physical quantity related to the fluidity of the modeling material is affected by the mold attached to the injection molding apparatus, individual differences between the injection molding apparatus, and modeling conditions. Therefore, in the past, in order to detect the physical quantity, it was necessary to set reference modeling conditions, which are standard modeling conditions, for each combination of an injection molding apparatus and a mold, and to repeatedly detect the physical quantity for each combination. This is time-consuming and undesirable. In contrast, the information processing system according to this embodiment detects the physical quantity related to the fluidity of the modeling material in the area within the modeling apparatus through which the modeling material passes. This means that even when the modeling apparatus is an injection molding apparatus, it is not necessary to repeatedly detect the physical quantity for each combination of an injection molding apparatus and a mold. Therefore, the information processing system can also suppress an increase in the effort and time required to determine the modeling conditions. Here, the physical quantity includes, but is not limited to, the pressure and temperature of the modeling material.

[0015] <Configuration of information processing system> The configuration of the information processing system according to the embodiment will be described below using the information processing system 1 as an example.

[0016] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system 1. As shown in FIG.

[0017] The information processing system 1 includes a modeling apparatus 10 and an information processing device 20. Note that the information processing system 1 may include other devices, other members, etc. in addition to the modeling apparatus 10 and the information processing device 20. In addition, in FIG. 1, the modeling apparatus 10 is depicted as a rectangular parallelepiped object to avoid cluttering the drawing.

[0018] The modeling apparatus 10 is connected to the information processing apparatus 20 via a network, either wired or wirelessly, so that they can communicate with each other. The network may be, for example, a local area network (LAN), a wide area network (WAN), the Internet, or another type of network. Note that the modeling apparatus 10 may be configured to be connected to the information processing apparatus 20 via a wired or wireless connection without using a network.

[0019] The modeling apparatus 10 may be any apparatus that forms a modeled article using a modeling material. For example, the modeling apparatus 10 may be an injection molding apparatus, a three-dimensional modeling apparatus such as a 3D printer, or another apparatus that forms a modeled article using a modeling material. Hereinafter, as an example, the modeling apparatus 10 will be described as an injection molding apparatus that includes a material supplying apparatus 11 that supplies plasticized resin as a modeling material and that forms a modeled article by injection molding using the modeling material supplied from the material supplying apparatus 11.

[0020] Fig. 2 is a diagram showing an example of the configuration of the material supply device 11. In Fig. 2, arrows indicating the positive directions of the mutually orthogonal X-axis, Y-axis, and Z-axis are shown. In the following, as an example, a case where the negative direction of the Z-axis coincides with the direction of gravity will be described. In addition, in the following, as an example, a case where the X-axis and Y-axis are parallel to a horizontal plane will be described. In addition, in the following, as an example, a case where the X-axis and Y-axis are orthogonal to each other will be described.

[0021] The material supply device 11 includes a material holding section 111 , a plasticizing section 112 , and a supply section 113 .

[0022] The material holding unit 111 supplies materials for generating the modeling material to the plasticizing unit 112. The material holding unit 111 is configured by, for example, a hopper. The material holding unit 111 stores materials in pellet form, powder form, etc. Examples of such materials include thermoplastic resins such as polypropylene resin (PP), polyethylene resin (PE), and polyacetal resin (POM). The material holding unit 111 supplies materials to the plasticizing unit 112 via a communication passage 120.

[0023] The plasticizing unit 112 plasticizes at least a portion of the material supplied from the material holding unit 111 to generate a paste-like modeling material with fluidity, and guides the generated modeling material to the supply unit 113. Here, plasticization is a concept that includes melting, and refers to changing from a solid to a fluid state. Specifically, in the case of a material that undergoes glass transition, plasticization refers to raising the temperature of the material to or above the glass transition point. In the case of a material that does not undergo glass transition, plasticization refers to raising the temperature of the material to or above the melting point. The plasticizing unit 112 includes a flat screw 130, a screw case 131, a drive motor 132, and a barrel 133.

[0024] The flat screw 130 is housed in a screw case 131. The top side of the flat screw 130 is connected to a drive motor 132. The flat screw 130 rotates within the screw case 131 by a rotational driving force generated by the drive motor 132. The rotation axis RX of the flat screw 130 is an axis parallel to the Z axis. The rotation speed of the flat screw 130 is controlled by a control unit (not shown) of the molding apparatus 10, which controls the rotation speed of the drive motor 132. The control unit controls the rotation speed of the drive motor 132 so that the rotation speed of the flat screw 130 becomes a value set by a user. The flat screw 130 may be configured to be driven by the drive motor 132 via a reducer. The flat screw 130 has a groove forming surface 141, on which a groove 140 is formed, on the opposite side to the top surface in a direction parallel to the rotation axis RX. The specific configuration of the flat screw 130 will be described later. The flat screw 130 may also be called a rotor or a screw.

[0025] The barrel 133 is disposed on the negative side of the flat screw 130 in the Z-axis direction. An opposing surface 150, which is the upper surface of the barrel 133, faces the groove-forming surface 141 of the flat screw 130. A communication hole 152 is formed in the center of the barrel 133, penetrating the barrel 133 in a direction parallel to the Z-axis and forming part of a flow path 151 through which the modeling material flows. A heater (not shown) is embedded in the barrel 133 to heat the material supplied to the groove 140 of the flat screw 130. For example, four rod-shaped heaters are arranged in the barrel 133 in a direction parallel to the Y-axis. In this case, these four heaters are arranged, for example, below the opposing surface 150. The temperature of each of these four heaters is controlled by the control unit of the modeling apparatus 10 described above. In other words, the temperature of each of these four heaters is individually controlled by the control unit. The control unit controls the temperature of each of the four heaters so that the temperature of each of the four heaters becomes the value set by the user.

[0026] FIG. 3 is a perspective view showing an example of the configuration of the flat screw 130 shown in FIG. 2. For this reason, FIG. 3 also shows arrows indicating the positive directions of the X-axis, Y-axis, and Z-axis. The flat screw 130 is a generally cylindrical member whose length in a direction parallel to the rotation axis RX is shorter than its length in a direction perpendicular to the rotation axis RX. A spiral groove 140 is formed around a central portion 142 in the groove-forming surface 141. The groove 140 communicates with a material inlet 143 formed on the side surface of the flat screw 130. The groove 140 forms part of a flow path 151. Material supplied from the material holding unit 111 is supplied to the groove 140 through the material inlet 143. The grooves 140 are formed by being separated by ridge portions 144. While FIG. 3 shows an example in which three grooves 140 are formed, the number of grooves 140 may be one or more. The groove 140 is not limited to a spiral shape, but may be a helical shape, an involute curve shape, or the like, or may be a shape that extends in an arc from the center portion 142 to the outer periphery.

[0027] FIG. 4 is a plan view showing an example of the configuration of the barrel 133 shown in FIG. 2. For this reason, FIG. 4 also shows arrows indicating the positive directions of the X-axis, Y-axis, and Z-axis. A plurality of guide grooves 153 are formed around the communicating hole 152 in the opposing surface 150. In the example shown in FIG. 4, six guide grooves 153 are formed around the communicating hole 152 in the opposing surface 150. Note that in FIG. 4, to avoid complication of the drawing, only two of the six guide grooves 153 are indicated by reference numerals. One end of each guide groove 153 is connected to the communicating hole 152 and extends in a spiral shape from the communicating hole 152 toward the outer periphery of the opposing surface 150. Note that one end of the guide groove 153 does not have to be connected to the communicating hole 152. Furthermore, the barrel 133 does not have to have any guide grooves 153 formed therein.

[0028] The material supplied to the groove 140 of the flat screw 130 is plasticized within the groove 140 by the rotation of the flat screw 130 and the heat of the heater, and flows along the groove 140 and is guided to the central portion 142 of the flat screw 130 as a modeling material. The pasty modeling material that has flowed into the central portion 142 and exhibits fluidity is supplied to the supply unit 113 via the communicating hole 152. Note that not all types of substances that make up the modeling material need to be plasticized in the plasticizing unit 112. It is sufficient that the modeling material is converted into a fluid state as a whole by plasticizing at least some of the types of substances that make up the modeling material.

[0029] The supply unit 113 supplies the modeling material to a mold attached to the modeling apparatus 10, which is an injection molding apparatus. The supply unit 113 includes a flow path 160, a flow rate control unit 161, a first pressure sensor 162, a first temperature sensor 163, a second pressure sensor 164, and a second temperature sensor 165. When the modeling apparatus 10 is a three-dimensional modeling apparatus, the supply unit 113 supplies the modeling material to a nozzle that injects the modeling material. In this case, the supply unit 113 may be configured to include the nozzle, or may not be configured to include the nozzle.

[0030] The flow path 160 is connected to the communication hole 152 of the barrel 133. The flow path 160 flows the modeling material produced in the plasticizing unit 112 toward a mold attached to the modeling device 10, which is an injection molding device. Note that in FIG. 2, the mold and the components between the flow path 160 and the mold are omitted to avoid cluttering the illustration.

[0031] The flow rate control unit 161 includes a flow rate adjustment unit 170 that opens and closes the flow path 160, and a suction unit 171 that sucks in the modeling material and temporarily stores it.

[0032] The flow rate adjustment unit 170 is provided in the flow path 160 and changes the opening degree of the flow path 160 by rotating within the flow path 160. In this embodiment, the flow rate adjustment unit 170 is configured as a butterfly valve. The flow rate adjustment unit 170 is driven by an actuator (not shown) that is driven under the control of the control unit of the above-mentioned modeling apparatus 10. The actuator is configured, for example, by a stepping motor or the like, but is not limited to this. The control unit can adjust the flow rate of the modeling material flowing from the plasticizing unit 112 to the flow path 160 by controlling the rotation angle of the butterfly valve using the actuator. The flow rate adjustment unit 170 can adjust the flow rate of the modeling material and can also control the on / off of the outflow of the modeling material.

[0033] The suction unit 171 is connected to the flow path 160 downstream of the flow rate adjustment unit 170. When the outflow of the modeling material to the flow path 160 is stopped, the suction unit 171 temporarily sucks the modeling material in the flow path 160, thereby preventing the modeling material from unintentionally flowing out of the flow path 160. In this embodiment, the suction unit 171 is configured by a cylinder SL that slidably houses a plunger PR. The cylinder SL is connected to the flow path 160. The suction unit 171 is driven by an actuator that is driven under the control of the control unit of the modeling device 10 described above. The actuator is configured by, for example, a stepping motor, a rack-and-pinion mechanism that converts the rotational force of the stepping motor into translational motion of the plunger PR in the cylinder SL, or the like.

[0034] Fig. 5 is an enlarged view of the flow path 160 and the suction unit 171 shown in Fig. 2. For this reason, arrows indicating the positive directions of the X-axis, Y-axis, and Z-axis are also shown in Fig. 5. However, in Fig. 5, to simplify the drawing, the portion of the flow path 160 near the flow rate adjustment unit 170 is omitted.

[0035] The first pressure sensor 162 is provided in the flow path 160 upstream of the flow rate adjustment unit 170. The first pressure sensor 162 detects the pressure of the modeling material in the flow path 160, i.e., the internal pressure of the flow path 160. The value of the internal pressure of the flow path 160 detected by the first pressure sensor 162 is transmitted to the control unit of the modeling apparatus 10 described above. Note that the flow path 160 may be configured to have two or more pressure sensors. In this case, the first pressure sensor 162 is one of these two or more pressure sensors. The first pressure sensor 162 is an example of a physical quantity detection unit and an example of a first pressure detection unit. Furthermore, the pressure detected by the first pressure sensor 162 is an example of a physical quantity related to the fluidity of the modeling material.

[0036] The first temperature sensor 163 is provided upstream of the flow rate adjuster 170 in the flow path 160. The first temperature sensor 163 is also provided downstream of the first pressure sensor 162 in the flow path 160. However, the positional relationship between the first pressure sensor 162 and the first temperature sensor 163 may be reversed or may be other positional relationships. The first temperature sensor 163 detects the temperature of the modeling material in the flow path 160, i.e., the temperature in the flow path 160. The value of the temperature in the flow path 160 detected by the first temperature sensor 163 is transmitted to the control unit of the modeling apparatus 10. The flow path 160 may be configured to have two or more temperature sensors. In this case, the first temperature sensor 163 is one of these two or more temperature sensors. The first temperature sensor 163 is an example of a physical quantity detection unit and an example of a first temperature detection unit. The temperature detected by the first temperature sensor 163 is an example of a physical quantity related to the fluidity of the modeling material.

[0037] As shown in FIG. 5 , the second pressure sensor 164 is provided in the cylinder SL that accommodates the plunger PR of the suction unit 171. The second pressure sensor 164 detects the pressure of the modeling material in the cylinder SL within the suction unit 171, i.e., the internal pressure of the cylinder SL. The value of the internal pressure of the cylinder SL detected by the second pressure sensor 164 is transmitted to the control unit of the modeling apparatus 10. Note that the cylinder SL may be configured to have two or more pressure sensors. In this case, the second pressure sensor 164 is one of these two or more pressure sensors. The second pressure sensor 164 is an example of a physical quantity detection unit and an example of a second pressure detection unit. The pressure detected by the second pressure sensor 164 is an example of a physical quantity related to the fluidity of the modeling material. The second pressure sensor 164 may be configured to be provided in the plunger PR instead of the cylinder SL.

[0038] As shown in FIG. 5 , the second temperature sensor 165 is provided in the cylinder SL that accommodates the plunger PR of the suction unit 171. The second temperature sensor 165 is provided next to the second pressure sensor 164 in the cylinder SL of the suction unit 171. However, the positional relationship between the second pressure sensor 164 and the second temperature sensor 165 may be reversed or may be other positional relationships. The second temperature sensor 165 detects the temperature of the modeling material in the cylinder SL, i.e., the temperature in the cylinder SL. The temperature value in the cylinder SL detected by the second temperature sensor 165 is transmitted to the control unit of the modeling apparatus 10. The cylinder SL may be configured to have two or more temperature sensors. In this case, the second temperature sensor 165 is one of these two or more temperature sensors. The second temperature sensor 165 is an example of a physical quantity detection unit and an example of a second temperature detection unit. The temperature detected by the second temperature sensor 165 is an example of a physical quantity related to the fluidity of the modeling material. The second temperature sensor 165 may be provided on the plunger PR instead of the cylinder SL.

[0039] Note that some or all of the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 may be configured to be provided in other areas within the modeling apparatus 10 through which the modeling material passes. For example, some or all of the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 may be configured to be provided in the barrel 133. Here, when the first pressure sensor 162 and the second pressure sensor 164 are provided in the barrel 133, they detect the pressure of the modeling material passing through the groove 140 of the flat screw 130, i.e., the internal pressure of the groove 140. Furthermore, when the first temperature sensor 163 and the second temperature sensor 165 are provided in the barrel 133, they detect the temperature of the modeling material passing through the groove 140 of the flat screw 130, i.e., the temperature within the groove 140. However, when the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 are each provided at the positions shown in FIG. 5, the noise contained in the signals output from these four sensors is suppressed.

[0040] In addition, some or all of the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 may be replaced with sensors that detect other types of physical quantities related to the fluidity of the modeling material, such as the density of the modeling material, the viscosity of the modeling material, and the fiber length distribution of the modeling material.

[0041] The molding apparatus 10 equipped with the material supply device 11 configured as described above molds a molded product by injection molding the molding material supplied from the material supply device 11.

[0042] The information processing device 20 may be, for example, a notebook PC (Personal Computer), a desktop PC, a workstation, a tablet PC, a multi-function mobile phone terminal (smartphone), a PDA (Personal Digital Assistant), etc., but is not limited to these. In the example shown in Fig. 1, the information processing device 20 is a notebook PC.

[0043] The information processing device 20 generates a mathematical model X in response to the received operation. The mathematical model X is adjusted based on the following information: modeling condition information indicating the modeling conditions for modeling of a model by the modeling device 10; shape information indicating the shape of the model; time-series information indicating the time series of physical quantities detected by a physical quantity detection unit that detects physical quantities in an area within the modeling device 10 through which the modeling material passes; and quality information indicating the quality of the model. The mathematical model X is adjusted so that quality information is output as output information when the modeling condition information, shape information, and time-series information are input; and can output the modeling condition information as output information when the shape information, time-series information, and quality information are input. Here, in this embodiment, the physical quantity detection unit is at least one of the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165. Furthermore, the reason why the three pieces of information, namely, the modeling condition information, the shape information, and the time-series information, are used as input information to the mathematical model X when the quality information is output as output information is that the quality of the modeled product modeled by the modeling apparatus 10 is determined by the modeling conditions for modeling the product by the modeling apparatus 10, the shape of the modeled product, and the time series of the physical quantities related to the fluidity of the modeling material among the physical quantities that can be detected for the modeling material. Note that in this embodiment, the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 are not provided in a mold attached to the modeling apparatus 10, but are provided within the modeling apparatus 10. Therefore, the information processing apparatus 20 does not need to provide a detection unit that detects the physical quantities in the mold. As a result, it is not necessary to re-detect the physical quantities every time the mold is changed, and this can suppress an increase in the cost required for generating modeling conditions.

[0044] In the following, as an example, a case will be described in which the mathematical model X is a supervised machine learning model. The supervised machine learning model may be, but is not limited to, a regression model, deep learning, etc. Note that instead of a supervised machine learning model, the mathematical model X may be a simple regression equation or another type of mathematical model, as long as it is adjusted based on modeling condition information, shape information, time-series information, and quality information so as to output quality information as output information when the modeling condition information, shape information, and time-series information are input, and the modeling condition information can be output as output information by inputting the shape information, time-series information, and quality information. Note that the method for generating the mathematical model X by the information processing device 20 may be a known method or a method to be developed in the future.

[0045] Here, adjusting the mathematical model X as a supervised machine learning model means learning the mathematical model X. The training data for learning the mathematical model X is quality information. Therefore, the adjustment of the mathematical model X is performed based on the modeling condition information, shape information, time-series information, and quality information. That is, the information processing device 20 learns the mathematical model X based on the modeling condition information, shape information, time-series information, and quality information. Furthermore, the information processing device 20 inputs the modeling condition information, shape information, and time-series information as input information to the trained mathematical model X, and displays the quality information output from the mathematical model X as output information. This allows the information processing device 20 to accurately estimate the quality of a molded product to be molded by injection molding based on the assumed modeling conditions. This means that the increase in cost required to find desired modeling conditions can be suppressed compared to finding desired modeling conditions by actually repeating modeling using the modeling device 10. In other words, by using the mathematical model X, the information processing device 20 can prevent the user from having to repeat trial and error to obtain desired modeling conditions. Furthermore, the information processing device 20 inputs shape information, time-series information, and quality information as input information to the trained mathematical model X, causes the mathematical model X to output modeling condition information as output information using a predetermined optimization method, and displays the modeling condition information output from the mathematical model X as output information. That is, when shape information, time-series information, and quality information are input as input information to the trained mathematical model X, the mathematical model X is used as an optimization model together with the optimization method. Note that the method of using the mathematical model X as an optimization model is a known method, and therefore detailed description thereof will be omitted. By using the mathematical model X as an optimization model in this way, the information processing device 20 can accurately estimate modeling conditions for causing the modeling apparatus 10 to model a model of desired quality. This also means that the increase in costs required to find the desired molding conditions can be suppressed compared to finding the desired molding conditions by actually repeating molding using the molding device 10.That is, the information processing device 20 can prevent the user from having to repeat trial and error to obtain desired modeling conditions. Therefore, the information processing device 20 can prevent an increase in the cost required to generate modeling conditions. Note that the predetermined optimization method is, for example, the steepest descent method, but is not limited to this.

[0046] FIG. 6 is a diagram illustrating an example of input / output of a mathematical model X. The upper part of FIG. 6 shows that when input information including modeling condition information D11, shape information D12, and time-series information D13 is input to the mathematical model X, information output from the mathematical model X as output information is quality information D21. Note that in the example shown in the upper part of FIG. 6, the input information may include information other than the quality information in addition to the modeling condition information D11, shape information D12, and time-series information D13. However, in this example, the mathematical model X outputs information including at least the quality information D21 as output information. On the other hand, the lower part of FIG. 6 shows that when input information including quality information D31, shape information D32, and time-series information D33 is input to the mathematical model X, information output from the mathematical model X as output information is modeling condition information D41. Note that in the example shown in the lower part of FIG. 6, the input information may include information other than the modeling condition information in addition to the quality information D31, shape information D32, and time-series information D33. However, in this example, the mathematical model X outputs information including at least the modeling condition information D41 as output information.

[0047] Furthermore, the information processing device 20 causes the modeling device 10 to model a modeled product using reference modeling conditions, which are standard modeling conditions, and thereby acquires time-series information indicating the time series of physical quantities detected by some or all of the first pressure sensor 162, the first temperature sensor 163, the second pressure sensor 164, and the second temperature sensor 165 during the modeling period. The modeling conditions indicated by the reference modeling conditions may be any modeling conditions as long as they are predetermined modeling conditions. However, when the information processing device 20 is repeatedly caused to acquire time-series information used when outputting certain quality information to the mathematical model X, a common reference modeling condition is used in the acquisition process. Hereinafter, for convenience of explanation, this period will be referred to as a time-series information acquisition period. Furthermore, below, as an example, a case will be described in which the information processing device 20 acquires information indicating the time series of pressure detected by the first pressure sensor 162 during the time-series information acquisition period as the time-series information. When the information processing device 20 acquires information indicating the time series of physical quantities detected by each of the multiple sensors during the time-series information acquisition period as time-series information, the information processing device 20 acquires time-series information corresponding to each physical quantity detected by each of the multiple sensors. Therefore, in this case, the information processing device 20 inputs each of the multiple time-series information into the mathematical model X. Here, as described above, the pressure detected by the first pressure sensor 162 is related to the fluidity of the modeling material, which is one of the physical quantities that can be detected for the modeling material. This can be easily understood by looking at the graphs shown in FIGS. 7 and 8. FIG. 7 is a diagram illustrating a time series of the pressure in the flow path 160 of the modeling material in a dried state and a time series of the pressure in the flow path 160 of the modeling material in a wet state. The horizontal axis of the graph shown in FIG. 7 indicates the elapsed time since the start of injection molding of the modeled product. The vertical axis of the graph indicates the pressure in the flow path 160, i.e., the pressure detected by the first pressure sensor 162. The curve F1 plotted in the graph represents the time series of pressure in the flow channel 160 of the build material in a dried state. The curve F2 plotted in the graph represents the time series of pressure in the flow channel 160 of the build material in a non-dried state.As shown in FIG. 7, the curve F2 has a different shape from the curve F1 and does not match. This is because the fluidity of the modeling material in a dried state differs from that in a wet state. Therefore, it can be considered that the difference in pressure within the flow channel 160 reflects the difference in fluidity of the modeling material. Therefore, the pressure of the modeling material within the flow channel 160 is a physical quantity related to the fluidity of the modeling material among the physical quantities detectable for the modeling material. In other words, the time-series information of the pressure of the modeling material within the flow channel 160 indicates the fluidity of the modeling material. The same applies to the pressure within the suction unit 171. FIG. 8 illustrates a time series of the pressure within the suction unit 171 for the modeling material in a dried state and a time series of the pressure within the suction unit 171 for the modeling material in a wet state. The horizontal axis of the graph shown in FIG. 8 also indicates the elapsed time since the start of injection molding of the modeled product. The vertical axis of the graph indicates the pressure within the suction unit 171, i.e., the pressure detected by the second pressure sensor 164. The curve F3 plotted in the graph indicates the time series of the pressure in the suction unit 171 of the modeling material in a dried state. The curve F4 plotted in the graph indicates the time series of the pressure in the suction unit 171 of the modeling material in a wet state. As shown in FIG. 8, the curve F4 has a different shape from the curve F2 and does not match. This also suggests that the difference in the pressure in the suction unit 171 reflects the difference in the fluidity of the modeling material. That is, the pressure of the modeling material in the suction unit 171 is also a physical quantity related to the fluidity of the modeling material among the physical quantities that can be detected for the modeling material. In other words, the time series information of the pressure of the modeling material in the suction unit 171 is information that indicates the fluidity of the modeling material.

[0048] The information processing device 20 may be configured to use the time-series information acquired in this manner as one piece of information included in the input information. In this case, the information processing device 20 inputs a vector having, as components, the physical quantities at each time indicated by the time-series information acquired from the first pressure sensor 162 into the mathematical model X. For convenience of explanation, the vector will be referred to as a time-series information vector. Hereinafter, the dimension of the time-series information vector increases as the takt time and the sampling rate increase. For example, if the takt time is 20 seconds and the sampling rate is 20 Hz, the dimension of the time-series information vector is 400. This undesirably increases the processing load of the information processing device 20. Therefore, the information processing device 20 may be configured to perform processing to reduce the dimension of the time-series information vector. For example, the information processing device 20 may be configured to use a variational autoencoder (VAE) to convert the time-series information vector into a vector having each latent variable as a component, and input the vector to the mathematical model X as the time-series information. For ease of explanation, the vector will be referred to as a latent variable vector below. The following describes, as an example, a case where the latent variable vector is input from the information processing device 20 to the mathematical model X as the time-series information. The method of converting the time-series information vector into a latent variable vector using a VAE may be a known method or a method to be developed in the future. The method of reducing the dimension of the time-series information vector may be a method using an autoencoder, principal component analysis, a self-organizing map, or the like, instead of a method using a VAE, or any other method capable of reducing the dimension of the time-series information vector.

[0049] The information processing device 20 also generates shape information based on CAD (Computer Aided Design) data of the shaped product. More specifically, the information processing device 20 calculates at least one of the following as shape characteristics of the shaped product: center of gravity, surface area, projected area, volume, average thickness, thickness variation, inertia, rotation matrix, rotation angle, and rotation radius, based on the CAD data of the shaped product, and generates information indicating the calculated at least one as shape information indicating the shape of the shaped product. For example, the information processing device 20 generates shape information based on the CAD data of the shaped product as shown in FIG. 9. FIG. 9 is a diagram showing an example of CAD data of the shaped product. The CAD data shown in FIG. 9 indicates a rectangular object MD as the shaped product. The information processing device 20 calculates the at least one of the following based on the CAD data of the object MD shown in FIG. 9, for example. The method for calculating at least one of the characteristics of the molded product, such as the center of gravity, surface area, projected area, volume, average thickness, thickness variation, inertia, rotation matrix, rotation angle, and radius of rotation, from CAD data may be a known method or a method to be developed in the future. The information processing device 20 may be configured to generate shape information based on captured images of the molded product, instead of CAD data of the molded product, or based on point cloud data of the molded product, or based on CAD data of a mold for molding the molded product, or based on other information indicating the shape of the molded product. The information processing device 20 may be configured to input, into the mathematical model X, CAD data indicating the shape of the molded product, captured images of the molded product, point cloud data of the molded product, CAD data of a mold for molding the molded product, etc., as shape information indicating the shape of the molded product. However, if the shape information is information indicating at least one of the center of gravity, surface area, projected area, volume, average thickness, thickness variation, inertia, rotation matrix, rotation angle, rotation radius, etc. of the molded product, the processing load of the information processing device 20 will be reduced.

[0050] Furthermore, the information processing device 20 acquires, from the control unit of the molding apparatus 10, information indicating at least one value of the injection speed, dwell pressure, dwell time, VP (Velocity Pressure) switching position, mold clamping pressure, rotation speed of the flat screw 130, etc. in injection molding by the molding apparatus 10, among the setting values ​​set in the control unit of the molding apparatus 10, from the control unit as molding condition information. Note that the information processing device 20 may be configured to acquire, from the control unit as molding condition information, information indicating at least one value of the injection speed, dwell pressure, dwell time, VP (Velocity Pressure) switching position, mold clamping pressure, rotation speed of the flat screw 130, mold clamping pressure in the molding apparatus 10, among the setting values ​​set in the control unit of the molding apparatus 10. In addition, when the modeling device 10 is a three-dimensional modeling device such as a 3D printer, the information processing device 20 may be configured to acquire, from the control unit of the modeling device 10, information indicating at least one of the setting values ​​set in the control unit of the modeling device 10, such as the rotation speed of the flat screw 130 during injection molding by the modeling device 10, the temperature of the barrel 133, and the temperature of the nozzle that ejects the modeling material, as modeling condition information.

[0051] As described above, the information processing device 20 can acquire each of the time-series information, shape information, and modeling condition information. Note that the method by which the information processing device 20 acquires part or all of the time-series information, shape information, and modeling condition information may be a method of acquiring them from another device via a flash memory or the like, or any other method.

[0052] Furthermore, when training the mathematical model X, the user of the information processing device 20 prepares a plurality of combinations of the three pieces of information, i.e., the modeling condition information, shape information, and time-series information, acquired by the method described above, and quality information as training data. Then, the information processing device 20 trains the mathematical model X using the plurality of combinations. Note that the method of training the mathematical model X, which is a supervised machine learning model, using the plurality of combinations may be a known method or a method to be developed in the future.

[0053] Furthermore, when acquiring quality information, the information processing device 20 acquires information indicating the results of a quality inspection of the shaped product as the quality information. The method by which the information processing device 20 acquires the quality information may be a known method or a method to be developed in the future. Furthermore, the quality information may be information that numerically represents the quality of the shaped product, information that represents the quality of the shaped product using a binary value of either good or bad, or other information that can indicate the quality of the shaped product.

[0054] <Hardware configuration of information processing device> The hardware configuration of the information processing device 20 will be described below with reference to Fig. 10. Fig. 10 is a diagram showing an example of the hardware configuration of the information processing device 20.

[0055] The information processing device 20 includes, for example, a processor 21, a storage unit 22, an input receiving unit 23, a communication unit 24, and a display unit 25. These components of the information processing device 20 are connected to each other via a bus so that they can communicate with each other. In addition, the information processing device 20 communicates with the modeling device 10 and the like via the communication unit 24.

[0056] The processor 21 is, for example, a CPU (Central Processing Unit). Instead of a CPU, the processor 21 may be another processor such as an FPGA (Field Programmable Gate Array). The processor 21 executes various programs stored in the storage unit 22. The processor 21 may be configured by a CPU included in one information processing device (in this example, the information processing device 20), or may be configured by CPUs included in multiple information processing devices.

[0057] The storage unit 22 includes, for example, a hard disk drive (HDD), a solid state drive (SSD), an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), a random access memory (RAM), etc. Note that the storage unit 22 may be an external storage device connected via a digital input / output port such as a USB instead of being built into the information processing device 20. The storage unit 22 stores various types of information, various images, various programs, etc. to be processed by the information processing device 20. For example, the storage unit 22 stores a mathematical model X. Note that the storage unit 22 may be configured with one storage device or multiple storage devices. Furthermore, the multiple storage devices may include a storage device provided in an information processing device separate from the information processing device 20. Furthermore, the storage unit 22 may be a server communicably connected to the information processing device 20 via a network.

[0058] The input receiving unit 23 is an input device such as a keyboard, a mouse, a touchpad, etc. The input receiving unit 23 may be a touch panel that is integrated with the display unit 25.

[0059] The communication unit 24 includes, for example, a digital input / output port such as a USB, an Ethernet (registered trademark) port, an antenna for wireless communication, and the like.

[0060] The display unit 25 is a display device including, for example, a liquid crystal display panel, an organic EL (ElectroLuminescence) display panel, or the like.

[0061] <Functional configuration of information processing device> The functional configuration of the information processing device 20 will be described below with reference to Fig. 11. Fig. 11 is a diagram showing an example of the functional configuration of the information processing device 20.

[0062] The information processing device 20 includes a storage unit 22, an input receiving unit 23, a communication unit 24, a display unit 25, and a control unit 26.

[0063] The control unit 26 controls the entire information processing device 20. The control unit 26 includes an acquisition unit 261, an input unit 262, a learning unit 263, a display control unit 264, and a modeling control unit 265. These functional units included in the control unit 26 are realized, for example, by the processor 21 executing various instructions (e.g., a program, commands included in the program, etc.) stored in the storage unit 22. Some or all of the functional units may be hardware functional units such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit).

[0064] The acquiring unit 261 acquires various types of information processed by the information processing device 20 from the modeling apparatus 10, the storage unit 22, etc. For example, the acquiring unit 261 acquires modeling condition information, time-series information, etc. from the modeling apparatus 10. Furthermore, for example, the acquiring unit 261 acquires shape information based on CAD data, etc. stored in the storage unit 22. Furthermore, for example, the acquiring unit 261 acquires quality information stored in the storage unit 22 from the storage unit 22.

[0065] The input unit 262 inputs, as input information, each of the modeling condition information, time series information, and shape information acquired by the acquisition unit 261, or each of the time series information, shape information, and quality information acquired by the acquisition unit 261, as input information to the mathematical model X pre-stored in the memory unit 22.

[0066] The learning unit 263 learns the mathematical model X stored in advance in the storage unit 22, and stores the learned mathematical model X in the storage unit 22.

[0067] The display control unit 264 generates an image including output information output from the mathematical model X to which input information has been input by the input unit 262, and displays the generated image on the display unit 25. Note that the target on which the display control unit 264 displays the image may be another device connected to the information processing device 20 so as to be able to communicate with the information processing device 20, instead of the display unit 25.

[0068] The modeling control unit 265 controls the modeling apparatus 10 .

[0069] <Processing by which information processing device displays output information> Hereinafter, a process in which the information processing device 20 displays output information will be described with reference to FIG. 12. FIG. 12 is a diagram illustrating an example of a process flow in which the information processing device 20 displays output information. Hereinafter, as an example, a case will be described in which the mathematical model X stored in the storage unit 22 has already been trained at a timing before the process of step S110 illustrated in FIG. 12 is performed. For convenience of explanation, each of the forming condition information, the time-series information, and the shape information acquired by the acquisition unit 261, or each of the time-series information, the shape information, and the quality information acquired by the acquisition unit 261, will be simply referred to as input information. Hereinafter, as an example, a case will be described in which the input information is stored in the storage unit 22 at the timing. Hereinafter, as an example, a case will be described in which the information processing device 20 receives a first process start operation to start the process at the timing.

[0070] After receiving the first process start operation, the input unit 262 reads out, from the storage unit 22, input information that has been stored in advance in the storage unit 22 (step S110).

[0071] Next, the input unit 262 inputs the input information read out from the storage unit 22 in step S110 to the mathematical model X stored in the storage unit 22 (step S120). As a result, the mathematical model X outputs quality information or modeling condition information as output information. However, when causing the mathematical model X to output the modeling condition information as output information, the control unit 26 causes the mathematical model X to output the output information using a predetermined optimization method. The functional unit that uses the optimization method may be the input unit 262 or another functional unit included in the control unit 26. Furthermore, the optimization method may be incorporated into the mathematical model X.

[0072] Next, the acquisition unit 261 acquires output information output from the mathematical model X to which the input information has been input by the input unit 262 in step S120 (step S130).

[0073] Next, the display control unit 264 generates an image including the output information acquired by the acquisition unit 261 from the mathematical model X in step S130, and displays the generated image on the display unit 25 (step S140). Then, the display control unit 264 ends the processing of the flowchart shown in FIG.

[0074] As described above, the information processing device 20 inputs the modeling condition information or the quality information, together with the shape information and the time-series information, as input information to the mathematical model X, and displays the output information output from the mathematical model X to which the input information has been input, on the display unit 25. This allows the information processing device 20 to suppress an increase in the cost required to generate modeling conditions.

[0075] <Processing by which an information processing device learns a mathematical model> Hereinafter, with reference to FIG. 13 , a process in which the information processing device 20 learns the mathematical model X will be described. FIG. 13 is a diagram illustrating an example of the flow of the process in which the information processing device 20 learns the mathematical model X. Hereinafter, as an example, a case in which the mathematical model X stored in the storage unit 22 has not been learned at a timing before the process of step S210 illustrated in FIG. 13 is performed will be described. Also, as an example, a case in which a plurality of pieces of learning information are stored in the storage unit 22 at that timing will be described. Each of the plurality of pieces of learning information includes the modeling condition information, the time-series information, the shape information, and the quality information, which are acquired by the acquisition unit 261. However, as described above, the quality information in the learning information is information that is treated by the learning unit 263 as training data. Also, as an example, a case in which the information processing device 20 receives a second process start operation to start the process at that timing will be described.

[0076] After receiving the second process start operation, the learning unit 263 reads out each of the plurality of pieces of learning information stored in the storage unit 22 from the storage unit 22 (step S210).

[0077] Next, the learning unit 263 learns the mathematical model X stored in the storage unit 22 using each of the multiple pieces of learning information read out from the storage unit 22 in step S210 (step S220), and stores the learned mathematical model X in the storage unit 22. Note that the method by which the learning unit 263 learns the mathematical model X in step S220 may be a known method or a method to be developed in the future. After the processing of step S220 is performed, the learning unit 263 stores the learned mathematical model X in the storage unit 22, and ends the processing of the flowchart shown in FIG.

[0078] Through the above-described processing, the information processing device 20 can learn the mathematical model X stored in the memory unit 22 so as to output quality information as output information when the forming condition information, shape information, and time-series information are input.

[0079] <Processing by which information processing device acquires time-series information> Hereinafter, a process in which the information processing device 20 acquires time-series information will be described with reference to Fig. 14. Fig. 14 is a diagram showing an example of the flow of a process in which the information processing device 20 acquires time-series information. In the following, as an example, a case in which the modeling device 10 has completed preparations to model a model at a timing before the process of step S310 shown in Fig. 14 is performed will be described. In addition, in the following, as an example, a case in which the information processing device 20 has received a third process start operation to start the process at that timing will be described.

[0080] After receiving the third process start operation, the acquisition unit 261 waits until the modeling device 10 starts modeling of a modeled product (Step S310). The method by which the acquisition unit 261 determines whether the modeling has started in Step S310 may be a known method or a method to be developed in the future.

[0081] When it is determined that the modeling of a modeled product by the modeling apparatus 10 has started (step S310-YES), the acquiring unit 261 starts acquiring information indicating the pressure detected by the first pressure sensor 162 of the modeling apparatus 10 from the first pressure sensor 162 (step S320). In FIG. 14, the processing of step S320 is indicated by "start of data acquisition."

[0082] Next, the obtaining unit 261 waits until the formation of the shaped product by the modeling apparatus 10, which was determined to have started in step S310, is completed (step S330-YES). The method by which the obtaining unit 261 determines whether the modeling has been completed in step S330 may be a known method or a method to be developed in the future.

[0083] When it is determined that the modeling of the modeled product by the modeling apparatus 10, which was determined to have started in step S310, has ended (step S330), the acquisition unit 261 ends the acquisition of information from the first pressure sensor 162, which was started in step S320 (step S340). In FIG. 14, the process of step S340 is indicated by "end of data acquisition."

[0084] Next, based on the information acquired from first pressure sensor 162 by the processes of steps S320 to S340, acquisition unit 261 generates time-series information indicating the time series of the pressure detected by first pressure sensor 162, and stores the generated time-series information in storage unit 22 (step S350). After the process of step S350 is performed, acquisition unit 261 ends the process of the flowchart shown in FIG.

[0085] As described above, the information processing device 20 can generate time-series information based on the information acquired from the first pressure sensor 162 of the modeling apparatus 10. That is, the information processing device 20 can acquire time-series information from the modeling apparatus 10.

[0086] As mentioned above, physical quantities related to the fluidity of the modeling material include the pressure and temperature of the modeling material, as well as the density, viscosity, and fiber length distribution of the modeling material. Among these, the physical quantity most related to the fluidity is the viscosity of the modeling material. However, the fluidity may vary depending on the supplier and grade. In particular, the fluidity of modeling materials made from recycled materials often varies from lot to lot. For this reason, the information processing device 20 acquires a time series of the physical quantities in the area within the modeling device 10 through which the modeling material passes, and inputs the acquired time series information into the mathematical model X. This allows the information processing device 20 to estimate optimal modeling conditions using the mathematical model X, even when modeling materials with different fluidities are used for different lots. In this sense, the information processing device 20 can also suppress increases in the cost required to generate modeling conditions.

[0087] Another known method for acquiring shape information is to acquire it from captured images of the molded product. However, this method requires time and effort to install an imaging device and capture images from multiple angles to capture the image of the molded product. In contrast, the information processing device 20 can acquire shape information from CAD data of the molded product. This means that the time and effort required for capturing images of the molded product can be reduced. In this sense, the information processing device 20 can also suppress an increase in costs required for generating the molding conditions. Furthermore, when acquiring shape information from CAD data of a mold, there is no need to manufacture the molded product itself or a model of the molded product. Therefore, when acquiring shape information from CAD data of a mold, the information processing device 20 can more reliably suppress an increase in costs required for generating the molding conditions.

[0088] The above-described contents may be combined in any manner.

[0089] Furthermore, the mathematical model X described above may be configured with two mathematical models: a first mathematical model that outputs quality information, and a second mathematical model that outputs modeling condition information. In this case, the first mathematical model is trained to output the quality information as output information when modeling condition information, shape information, and time-series information are input. In this case, the second mathematical model is trained to output the modeling condition information as output information when shape information, time-series information, and quality information are input. In this case, in step S120, when the information processing device 20 causes the first mathematical model to output the quality information as output information, it inputs the modeling condition information, shape information, and time-series information to the first mathematical model as input information, and when the information processing device 20 causes the second mathematical model to output the modeling condition information as output information, it inputs the shape information, time-series information, and quality information to the second mathematical model as input information. In step S130, when the information processing device 20 inputs input information to the first mathematical model, it acquires quality information from the first mathematical model as output information, and when the information processing device 20 inputs input information to the second mathematical model, it acquires molding condition information from the second mathematical model as output information. Here, the first mathematical model and the second mathematical model may be models replicated from one trained mathematical model, or may be independently trained mathematical models.

[0090] <Additional Notes> [1] an input step of inputting the modeling condition information or the quality information together with the shape information and the time-series information into a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to fluidity of the modeling material in an area of ​​the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; and a display control step of displaying the output information output from the mathematical model into which information is input by the input step, on a display unit. [2] The information processing method described in [1], wherein the mathematical model is trained based on the modeling condition information, the shape information, the time-series information, and the quality information so as to output the quality information as the output information when the modeling condition information, the shape information, and the time-series information are input, and is a machine learning model that can output the modeling condition information as the output information by inputting the shape information, the time-series information, and the quality information. [3] The information processing method described in [2], wherein the mathematical model is used as an optimization model based on a predetermined optimization method when the shape information, the time series information, and the quality information are input. [4] The information processing method according to [2] or [3], further comprising a learning step of learning the machine learning model stored in a storage unit so as to output the quality information as the output information when the molding condition information, the shape information, and the time-series information are input. [5] The information processing method according to any one of [1] to [4], wherein the region includes a flow path through which the modeling material passes and a suction unit that adjusts the flow rate of the modeling material in the flow path, and the physical quantity detection unit includes at least one detection unit selected from the group consisting of one or more first temperature detection units that detect a temperature in the flow path as one of the physical quantities, one or more first pressure detection units that detect a pressure in the flow path as one of the physical quantities, one or more second temperature detection units that detect a temperature in the suction unit as one of the physical quantities, and one or more second pressure detection units that detect a pressure in the suction unit as one of the physical quantities, and the input step inputs information indicating a time series of the one or more physical quantities detected by the at least one detection unit into the mathematical model as the time series information. [6] The information processing method according to any one of [1] to [5], wherein the shape information is information indicating characteristics of the shape of the shaped product, and is information indicating at least one of the center of gravity, surface area, volume, and thickness of the shaped product. [7] The information processing method described in any one of [1] to [6], wherein the modeling device comprises a plasticizing unit that plasticizes the modeling material and a flow path through which the modeling material plasticized by the plasticizing unit flows, the plasticizing unit comprises a flat screw that rotates around a rotation axis, and the modeling condition information includes at least one of the injection speed of the modeling material and the rotation speed of the flat screw. [8] an input unit that inputs the modeling condition information or the quality information together with the shape information and the time-series information to a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to the fluidity of the modeling material in a region of the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; and a display control unit that displays the output information output from the mathematical model to which information has been input by the input unit, on a display unit. [9] The information processing device described in [8], wherein the mathematical model is a machine learning model that is trained based on the modeling condition information, the shape information, the time-series information, and the quality information so as to output the quality information as the output information when the modeling condition information, the shape information, and the time-series information are input, and is capable of outputting the modeling condition information as the output information by inputting the shape information, the time-series information, and the quality information.

[10] The information processing method described in [9], wherein the mathematical model is used as an optimization model based on a predetermined optimization method when the shape information, the time series information, and the quality information are input.

[11] The information processing device according to [9] or

[10] , further comprising a learning unit that trains the machine learning model stored in a storage unit so as to output the quality information as the output information when the modeling condition information, the shape information, and the time-series information are input.

[12] The information processing device according to any one of [8] to

[11] , wherein the region includes a flow path through which the modeling material passes and a suction unit that adjusts the flow rate of the modeling material in the flow path, and the physical quantity detection unit includes at least one detection unit selected from the group consisting of one or more first temperature detection units that detect a temperature in the flow path as one of the physical quantities, one or more first pressure detection units that detect a pressure in the flow path as one of the physical quantities, one or more second temperature detection units that detect a temperature in the suction unit as one of the physical quantities, and one or more second pressure detection units that detect a pressure in the suction unit as one of the physical quantities, and the input unit inputs information indicating a time series of the one or more physical quantities detected by the at least one detection unit to the mathematical model as the time series information.

[13] The information processing device according to any one of [8] to

[12] , wherein the time-series information is information indicating the fluidity of the modeling material and is reduced-dimensional information.

[14] The information processing device according to

[13] , wherein the time series information is a latent variable reduced in dimension using a Variational Auto Encoder (VAE).

[15] The information processing device according to any one of [8] to

[14] , wherein the shape information is information indicating characteristics of the shape of the molded product, and is information indicating at least one of the center of gravity, surface area, volume, and thickness of the molded product.

[16] The information processing device described in any one of [8] to

[15] , wherein the modeling device comprises a plasticizing unit that plasticizes the modeling material and a flow path through which the modeling material plasticized by the plasticizing unit flows, the plasticizing unit comprises a flat screw that rotates around a rotation axis, and the modeling condition information includes at least one of the injection speed of the modeling material and the rotation speed of the flat screw.

[0091] The embodiments of this disclosure have been described in detail above with reference to the drawings, but the specific configuration is not limited to this embodiment, and may be changed, replaced, deleted, etc. as long as it does not deviate from the gist of this disclosure.

[0092] A program for implementing the functions of any of the components of the above-described apparatus may be recorded on a computer-readable recording medium and loaded into a computer system for execution. Here, the apparatus may be, for example, the molding apparatus 10 or the information processing apparatus 20. The term "computer system" herein includes hardware such as an operating system (OS) and peripheral devices. The term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and compact disks (CDs)-ROMs, as well as storage devices such as hard disks built into computer systems. The term "computer-readable recording medium" also includes devices that retain a program for a certain period of time, such as volatile memory within a computer system that acts as a server or client when the program is transmitted via a network such as the Internet or a communication line such as a telephone line.

[0093] The above program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by transmission waves in the transmission medium. Here, the "transmission medium" that transmits the program refers to a medium that has the function of transmitting information, such as a network such as the Internet or a communication line such as a telephone line. The program may also be a program for realizing some of the functions described above, or may be a so-called differential file or differential program that can realize the functions described above in combination with a program already recorded in the computer system. [Explanation of symbols]

[0094] 1...information processing system, 10...molding device, 11...material supply device, 20...information processing device, 21...processor, 22...memory unit, 23...input receiving unit, 24...communication unit, 25...display unit, 26...control unit, 111...material holding unit, 112...plasticizing unit, 113...supply unit, 120...communicating passage, 130...flat screw, 131...screw case, 132...drive motor, 133...barrel, 140...groove, 141...groove forming surface, 142...center portion, 14 3...material inlet, 144...ridge portion, 150...opposing surface, 151...flow path, 152...communicating hole, 153...guide groove, 160...flow path, 161...flow rate control unit, 162...first pressure sensor, 163...first temperature sensor, 164...second pressure sensor, 165...second temperature sensor, 170...flow rate adjustment unit, 171...suction unit, 261...acquisition unit, 262...input unit, 263...learning unit, 264...display control unit, 265...modeling control unit, RX...rotation axis, X...mathematical model

Claims

1. an input step of inputting the modeling condition information or the quality information together with the shape information and the time-series information into a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to fluidity of the modeling material in a region within the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; a display control step of displaying, on a display unit, the output information output from the mathematical model to which information has been input in the input step; An information processing method comprising:

2. the mathematical model is a machine learning model that is trained based on the modeling condition information, the shape information, the time-series information, and the quality information so as to output the quality information as the output information when the modeling condition information, the shape information, and the time-series information are input, and that is capable of outputting the modeling condition information as the output information by inputting the shape information, the time-series information, and the quality information. The information processing method according to claim 1 .

3. the mathematical model is used as an optimization model based on a predetermined optimization method when the shape information, the time-series information, and the quality information are input. The information processing method according to claim 2 .

4. a learning step of learning the machine learning model stored in a storage unit so as to output the quality information as the output information when the forming condition information, the shape information, and the time-series information are input; The information processing method according to claim 2 .

5. the region includes a flow path through which the build material passes; the physical quantity detection unit includes at least one detection unit selected from the group consisting of one or more first temperature detection units that detect a temperature in the flow path as one of the physical quantities, and one or more first pressure detection units that detect a pressure in the flow path as one of the physical quantities; the input step inputs information indicating a time series of the one or more physical quantities detected by the at least one detection unit to the mathematical model as the time series information; The information processing method according to claim 1 .

6. the shape information is information indicating characteristics of the shape of the shaped product, and is information indicating at least one of a center of gravity, a surface area, a volume, and a thickness of the shaped product; The information processing method according to claim 1 .

7. The molding device is a plasticizing unit that plasticizes the modeling material; a flow path through which the modeling material plasticized by the plasticizing unit flows; Equipped with The plasticizing section includes a flat screw that rotates around a rotation axis, The modeling condition information includes at least one of an injection speed of the modeling material and a rotation speed of the flat screw. The information processing method according to claim 1 .

8. an input unit that inputs the modeling condition information or the quality information together with the shape information and the time-series information to a mathematical model that is adjusted to output quality information as output information when the modeling condition information, the shape information, and the time-series information are input, based on modeling condition information that indicates modeling conditions for modeling by a modeling device that models a model using a modeling material, shape information that indicates a shape of the model, time-series information that indicates a time series of physical quantities detected by a physical quantity detection unit that detects a physical quantity related to fluidity of the modeling material in a region within the modeling device through which the modeling material passes, and quality information that indicates a quality of the model; and a display control unit that causes a display unit to display the output information output from the mathematical model to which information has been input by the input unit; An information processing device comprising:

Images