Information processing device, information processing system, and information processing method

Abstract

To provide an information processing device that can set appropriate control conditions from among a plurality of candidates, taking into consideration the energy consumption of a heating device.SOLUTION: The information processing device is an information processing device that generates control conditions for a heating device that heats a temperature-controlled object based on generation input parameters 103a, and includes: a control condition generating unit 53 that generates a plurality of control condition candidates 103bn for the heating device based on the generation input parameters 103a acquired from an information acquiring unit 52; a candidate acquisition unit 54 that acquires the plurality of control condition candidates 103bn; an evaluation unit 55 that performs performance evaluation of a plurality of heating devices corresponding to cases where the heating devices are controlled according to the plurality of control condition candidates 103bn acquired by the candidate acquisition unit 54; and an output processing unit 56 that outputs a new control condition 103c from among the plurality of control condition candidates 103bn acquired by the candidate acquisition unit 54 based on the performance evaluation performed by the evaluation unit.SELECTED DRAWING: Figure 7

Description

[Technical field]

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

[0002] Conventionally, a preform to be blow-molded into a hollow container by a blow molding device is subjected to a heat treatment while being transported, using a heating device equipped with a plurality of infrared heaters (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] WO2014 / 208693A1 [Patent Document 2] Patent No. 6838202 Summary of the Invention [Problem to be solved by the invention]

[0004] When performing heat treatment on a temperature-controlled object such as the above-mentioned preform using a heating device, it has been required to set detailed control conditions such as the heater output conditions in the heating device and the conveying speed when the temperature-controlled object passes through the heating space. Patent Document 2 describes a technology for changing input parameters to optimize the energy efficiency or operation efficiency of a blow molding machine. However, the technology described in Patent Document 2 receives outputs from a sensor and an inspection system and determines input parameters in response to the received outputs, so there is a risk of mismatching between the outputs from the sensor and inspection system and the input parameters.

[0005] In view of the above-mentioned problems, the present invention aims to provide an information processing device, an information processing system, and an information processing method that can evaluate the performance of a heating device and set appropriate control conditions from among multiple candidates. [Means for solving the problem]

[0006] In order to achieve the above object, an information processing device includes: An information processing device that generates control conditions for a heating device that heats a temperature-controlled object based on input parameters for generation, An information acquisition unit that acquires the generation input parameters; a control condition generating unit that generates a plurality of the control condition candidates for the heating device based on the input parameters for control condition generation acquired from the information acquiring unit; a candidate acquisition unit that acquires the plurality of control condition candidates generated by the control condition generation unit; an evaluation unit that performs performance evaluation of a plurality of the heating devices corresponding to cases where the heating devices are controlled according to the plurality of control condition candidates acquired by the candidate acquisition unit; an output processing unit that outputs a new control condition from the plurality of control condition candidates acquired by the candidate acquisition unit based on the performance evaluation performed by the evaluation unit; Equipped with. Effect of the Invention

[0007] According to the information processing device of the present invention, it is possible to perform a performance evaluation of the heating device and set appropriate control conditions from among a plurality of candidates.

[0008] Other objects, configurations and effects will become apparent from the detailed description of the invention described below. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is an overall configuration diagram showing an example of a container molding system 100. [Diagram 2] 1 is a schematic diagram showing a heating system 1 of a first embodiment. [Diagram 3] FIG. 1 is a side view showing a heating device 10 of a first embodiment. [Figure 4] FIG. 1 is a configuration diagram showing a machine learning device 40 according to a first embodiment. [Diagram 5]FIG. 2 is a conceptual diagram showing elements of machine learning performed by a machine learning device 40 of the first embodiment. [Figure 6] 1 is a configuration diagram showing an information processing device 50 according to a first embodiment. [Figure 7] 2 is a configuration diagram showing a first example of an information processing control unit 51 according to the first embodiment. FIG. [Figure 8] FIG. 13 is a diagram illustrating an example of random noise. [Figure 9] 11 is a configuration diagram showing a second example of the information processing control unit 51 in the first embodiment. FIG. [Figure 10] FIG. 9 is a diagram showing the hardware configuration of a computer 900. [Figure 11] 4 is a flowchart showing a machine learning method performed by the machine learning device of the first embodiment. [Figure 12] 8 is a flowchart showing an information processing method of the first example information processing control unit shown in FIG. 7. [Figure 13] 9 is a flowchart showing an information processing method of the second example information processing control unit shown in FIG. 8. [Figure 14] FIG. 11 is a schematic diagram showing a heating device and a transport device according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings. In the following, the scope necessary for the explanation to achieve the object of the present invention will be shown in a schematic manner, and the scope necessary for the explanation of the relevant parts of the present disclosure will be mainly explained, and the parts that are omitted from the explanation will be referred to as publicly known techniques.

[0011] (Configuration of container molding system 100) 1 is a schematic diagram showing an example of a container molding system 100. The container molding system 100 functions as a production system that produces a hollow molded body 140 by blow molding using a mold 121. In this embodiment, a case will be mainly described in which a container (PET bottle) is produced as one form of the hollow molded body 140 from a preform 200, which is one form of a molded body made of polyethylene terephthalate (PET), by a biaxial stretch blow molding method.

[0012] The container molding system 100 has as its main components an injection molding apparatus 110, a preform removal apparatus 111, a preform transport conveyor 112, a preform supply apparatus 113, a blow molding apparatus 120, a molded body removal apparatus 114, a molded body transport conveyor 115, and a rejection conveyor 116.

[0013] In the container molding system 100, when synthetic resin, which is a raw material, is fed into an injection molding device 110, a preform 200 is molded by the injection molding device 110. The preform 200 is removed from the injection molding device 110 by a preform removal device 111 and transferred to a preform transport conveyor 112, and is heated to a predetermined temperature while flowing along the preform transport conveyor 112. Then, when the preforms 200 are sequentially supplied to a blow molding device 120 by a preform supply device 113, the preforms 200 are molded into a molded body 140 (PET bottle) by the blow molding device 120. The molded body 140 is removed from the blow molding device 120 by a molded body removal device 114 and transferred to a molded body transport conveyor 115, and as it flows along the molded body transport conveyor 115, it is passed through, for example, an attachment device that attaches a shrink film or a label to the molded body 140, a filling device that fills the molded body 140 with a beverage, a molding device ... The product is then conveyed to a subsequent process such as a seaming device that seams a lid around the product 140 .

[0014] When the blow molding apparatus 120 is molding the molded body 140 from the preform 200, if a pressure abnormality such as a burst is detected, the molded body 140 in which the pressure abnormality was detected is not transferred to an output line (in the example of Figure 1, the molded body transport conveyor 115) that transports normal molded bodies 140 to a subsequent process, but is transferred to a rejection conveyor 116 by the molded body removal apparatus 114.

[0015] (Heating system 1 and heating device of the first embodiment) Fig. 2 is a schematic diagram showing the heating system 1 of the first embodiment. Fig. 3 is a side view showing the heating device 10 of the first embodiment. The heating system 1 includes the heating device 10, a machine learning device 40, an information processing device 50, a control device 60, and a network 70 connecting the respective devices.

[0016] The heating system 1 is provided in a production system for producing containers such as PET bottles. The containers are produced by molding a preform 200, which is produced from a raw material of the container, with a blow molding device (not shown).

[0017] When molding the preform 200 using a blow molding machine, it is necessary to preheat the preform 200 in order to improve the moldability of the preform 200. The heating system 1 of the present disclosure is a system that handles the pre-process of the blow molding machine, and is a system that heats the preform 200 as a temperature control target.

[0018] The preforms 200 are molded from container raw materials by an injection molding machine (not shown). The molded preforms 200 are successively carried into the heating system 1 and heated. The heated preforms 200 are successively fed to a blow molding device in the next process and molded into containers.

[0019] The heating device 10 has a heating device main body 11, a plurality of heaters 14 as heat sources arranged in the heating device main body 11, a heater power supply (not shown) that supplies power to each heater 14, a blower device 17 arranged in the heating device main body 11, and a conveying device 30.

[0020] In the heating device main body 11, a heating passage 12, which is a long tunnel-shaped space, is formed along the longitudinal direction. The heating passage 12 is large enough for the preform 200 to pass through. The preform 200 can pass from the inlet side of the heating passage 12 to the outlet side. The transportation of the preform 200 in the heating passage 12 will be described later.

[0021] Each heater 14 is a long near-infrared heater. Each heater 14 is arranged along the longitudinal direction of the heating passage 12. Note that, for each heater 14, not only a long near-infrared heater but also a different type of heater can be used.

[0022] Each heater 14 can heat the preform 200 in the heating passage 12 in the heating device body 11. Each heater 14 is electrically connected to a heater power supply, and can heat the inside of the heating device body 11 by the power supplied from the heater power supply. Therefore, the heating space of the heating device 10 is defined by the heating device body 11.

[0023] The heater power supply can adjust the amount of power supplied to each heater 14 according to a command from the control device 60. Each heater 14 radiates an amount of heat according to the amount of power supplied thereto. By controlling the amount of power supplied to each heater 14, the amount of heat radiated from each heater 14 can be controlled.

[0024] The blower device 17 has a blower 18 which is an air source, a blower duct 19, and a blower power source (not shown). The blower 18 is disposed on the inlet side of the heating passage 12. The blower duct 19 is a pipe-shaped object.

[0025] The longitudinal direction of the air blower duct 19 is aligned with the longitudinal direction of the heating passage 12 and is disposed within the heating passage 12. One open end of the air blower duct 19 opens toward the outside of the heating device 10 at the inlet side of the heating passage 12, and the other open end of the air blower duct 19 opens toward the outside of the heating device 10 at the outlet side of the heating passage 12.

[0026] A plurality of through holes (not shown) are formed in the air duct 19. The blower 18 is connected to the open end of the air duct 19 on the inlet side. The blower 18 can send air into the air duct 19 from the open end of the air duct 19 on the inlet side.

[0027] The air sent into the air duct 19 by the blower 18 flows through the air duct 19. The air flowing through the air duct 19 is further sent into the heating passage 12 through a plurality of through holes, and is also released into the atmosphere from the open end of the air duct 19 on the outlet side. That is, the air sent by the blower 18 is sent into the heating space via the air duct 19.

[0028] The blower power supply can control the amount of power supplied to the blower 18 according to a command from the control device 60. The control device 60 controls the amount of power supplied to the blower 18, thereby controlling the blower 18 and the flow rate of air sent into and flowing through the air duct 19.

[0029] The conveying device 30 has a conveying device main body 31 and a conveying control unit 32. The conveying device main body 31 is a conveyor. The conveying device main body 31 can support a plurality of preforms 200. The conveying device main body 31 is disposed so that the supported preforms 200 pass through the heating passage 12.

[0030] The conveying device body 31 can rotatably support the multiple preforms 200 in an upright state. The conveying device body 31 has a rotation mechanism (not shown) and can impart a rotational motion to each of the multiple preforms 200 in an upright state. Therefore, the conveying device body 31 can convey the preforms 200 through the heating passage 12 while imparting a rotational motion to the upright preforms 200. That is, each preform 200 supported by the conveying device body 31 can pass through the heating space while rotating in an upright state.

[0031] The transport control unit 32 can control the transport speed of the transport device main body 31 based on a command from the control device 60. By controlling the transport speed of the transport device main body 31, the time during which the preform 200 stays in the heating passage 12 can be controlled. In addition, the transport control unit 32 can control the rotation speed of the rotational motion of the preform 200 by controlling the rotation mechanism of the transport device main body 31 based on a command from the control device 60. That is, the transport control unit 32 can control at least one of the transport speed of the transport device main body 31 and the rotation speed of the rotational motion of the preform 200 based on a command from the control device 60.

[0032] (Machine learning device 40 of the first embodiment) Fig. 4 is a configuration diagram showing a machine learning device 40 of the first embodiment. Fig. 5 is a conceptual diagram showing elements of machine learning performed by the machine learning device 40 of the first embodiment. The machine learning device 40 is a device that operates as a main part of the learning phase of machine learning, and has a machine learning control unit 41, a machine learning communication unit 42, a learning data storage unit 43, and a machine learning model storage unit 44.

[0033] The machine learning control unit 41 generates a learning model 45 that can obtain output information corresponding to input information. The machine learning control unit 41 uses one or more pieces of learning data 46 to generate the learning model 45. The learning data 46 is composed of learning input parameters 102a and learning control conditions 102b that are control conditions for the heating device 10 corresponding to the learning input parameters 102a.

[0034] The learning data 46 is data used as training data, verification data, and test data, which are teacher data in supervised learning. The learning control conditions 102b are data used as answer labels in supervised learning. The learning input parameters 102a and the learning control conditions 102b, which are control conditions of the heating device 10 corresponding to the learning input parameters 102a, represent data in a state in which the input parameters 101a prepared by the operator and the control conditions 101 of the heating device 10 corresponding to the input parameters 101a are stored in the learning data storage unit 43 as the learning data 46.

[0035] The input parameters 101a and control conditions 101b prepared by the operator, and the learning data storage unit 43 in which the learning data 46 are stored will be described later.

[0036] The machine learning control unit 41 can cause the learning model 45 to learn the correlation between the learning input parameters 102a and the learning control conditions 102b in one or more pieces of learning data 46. In this way, the machine learning control unit 41 can generate a learned learning model 45.

[0037] A neural network structure is adopted for the learning model 45. The learning model 45 has an input layer 45a, an intermediate layer 45b, and an output layer 45c. The input layer 45a has neurons whose number corresponds to the number of parameters of the learning input parameters 102a. The output layer 45c has neurons whose number corresponds to the number of conditions of the learning control conditions 102b.

[0038] Between each layer, there are synapses (not shown) that connect each neuron. Each synapse can be assigned a weight.

[0039] The machine learning control unit 41 adjusts a weight parameter group consisting of the weights of each synapse by machine learning. The weight parameter group is reflected in the learning model 45.

[0040] In the machine learning control unit 41, each parameter of the learning input parameters 102a is input to each neuron of the input layer 45a, and a learning result control condition 102c of the heating device 10 corresponding to the learning input parameters 102a is output through the learning model 45. The machine learning control unit 41 examines the value of the learning result control condition 102c, and adjusts the weight of each synapse based on the examination result.

[0041] When the learning model 45 is configured as a regression model, the learning control conditions 102b are output as numerical values ​​normalized to a predetermined range (e.g., 0 to 1). When the learning model 45 is configured as a classification model, the learning control conditions 102b are output as scores (accuracies) for each class as numerical values ​​normalized to a predetermined range (e.g., 0 to 1).

[0042] The learning data storage unit 43 can store a plurality of pieces of learning data 46 as a database. The specific configuration of the database constituting the learning data storage unit 43 can be designed as appropriate.

[0043] An operator uses an operation terminal (not shown) to input input parameters 101a and control conditions 101b corresponding to the input parameters 101a to the learning data storage unit 43. The input parameters 101a and the control conditions 101b input to the learning data storage unit 43 are stored as learning input parameters 102a and learning control conditions 102b, respectively. Therefore, the learning control conditions 102b correspond to the learning input parameters 102a. As a result, one learning data 46 is stored.

[0044] Data in a known heating operation is used for the learning input parameters 102a and the learning control conditions 102b. That is, as the input parameters 101a and the control conditions 101b input to the learning data storage unit 43 as the basis of the learning input parameters 102a and the learning control conditions 102b, the input parameters 101a and the control conditions 101b in a known heating operation are input.

[0045] The known heating operation is preferably a past heating operation using the heating device 10. The data actually used in the past heating operation using the heating device 10 is data having a track record of subsequent production of containers using a blow molding machine.

[0046] That is, the data actually used in the past heating operation is data that can produce a container having a shape accuracy within an allowable range. Therefore, since the correlation between the input parameters 101a and the control conditions 101b actually used in the past heating operation is valid, it is desirable to use such data as the learning data 46 for machine learning.

[0047] As the data for known heating operations, in addition to data actually used in past heating operations, for example, data generated by simulation or data created by a skilled worker may be used.

[0048] The input parameters 101a are parameters taken into consideration for calculating control conditions 101b for controlling each device of the heating system 1. The input parameters 101a are parameters related to the preform 200, parameters related to the heating device 10, and parameters related to the relationship between the preform 200 and the heating device 10.

[0049] Specifically, the input parameters 101a are composed of at least one of material information, shape information, initial temperature information, target temperature distribution information of the heating device 10, and thermal environment information of the heating device 10 of the preform 200. The material information of the preform 200 is at least one of the light transmittance, reflectance, and refractive index of the preform 200, the L value which is color lightness information, the RGB value as color information, density information, specific heat information, and thermal conductivity information.

[0050] The material information can be obtained in advance by measuring the preform 200. As a method for measuring the material information, a well-known method can be appropriately adopted.

[0051] The shape information of the preform 200 is at least one of design drawing information as shape information read from the design drawing of the preform 200, shape image information as shape information read from a shape image, dimensional information, and shape tracing measurement / scanning information. When the shape information is read from the design drawing of the preform 200, the design drawing of the preform 200 is provided to a computer in advance, and the computer reads the shape information of the preform 200 from the design drawing, thereby obtaining the shape information of the preform 200.

[0052] The shape image is image information captured by an imaging device. When reading shape information from a shape image, the shape information of the preform 200 can be obtained from the image information. The dimensional information can be obtained by having an operator input required information of the dimensions of the preform 200 in advance. The shape tracing measurement / scanning information is the shape information of the preform 200 grasped by scanning the shape of the preform 200 with a well-known scanning device.

[0053] The initial temperature information of the preform 200 can be obtained by measuring the temperature of the preform 200 before the preform 200 is subjected to the heating system 1. The target temperature distribution information of the heating device 10 is information indicating an ideal temperature distribution inside the heating passage 12 during the heating operation. The ideal temperature distribution inside the heating passage 12 can be calculated and obtained by a prior analysis or the like.

[0054] The thermal environment information of the heating device 10 is at least one of the following: distance information from each heater 14 of the heating device 10 to the preform 200, arrangement position, irradiation direction, and irradiation angle information of each heater 14, dimensional information of the heating device 10, thermal diffusion information to the outside of the heating device 10, and ambient temperature and humidity information of the heating device 10. The distance in the distance information from each heater 14 of the heating device 10 to the preform 200 is the distance in the direction perpendicular to the conveying direction of the preform 200.

[0055] Information on the distance between the preform 200 and each heater 14 can be obtained by an operator calculating and inputting the distance in advance, or by inputting the respective design drawings into a computer and analyzing them on the computer. Information on the arrangement position, irradiation direction, and irradiation angle of each heater 14 can be obtained by inputting the design drawings of the heating device 10 into a computer and analyzing them on the computer. Information on the thermal diffusion outside the heating device 10 can be obtained by simulation analysis on a computer, etc. Information on the ambient temperature and humidity of the heating device 10 can be obtained by measuring the temperature and humidity around the heating device 10.

[0056] The dimensional information of the heating device 10 can be obtained in advance by an operator inputting necessary dimensional values ​​among the dimensions of the heating device 10.

[0057] The control conditions 101b are control conditions for the heating device 10, the blower device 17, the transport device 30, etc. Specifically, the control conditions are an output command value for the blower 18, an output command value for the transport device 30, and an output command value for each heater 14.

[0058] Each output command value is an arbitrary value between 0 and 100. Each output command value is the output value of each device when the maximum output of the corresponding device is set to 100. Note that the command to each heater 14 may not only be an output command value which is an arbitrary value between 0 and 100, but also an ON / OFF command for each heater 14. Furthermore, the command to each heater 14 may be the time of an ON command for each heater 14, the time of an OFF command, or the ratio of the time of the ON command to the time of the OFF command.

[0059] The machine learning control unit 41 can extract any one or more pieces of learning data 46 from the multiple pieces of learning data 46 stored in the learning data storage unit 43, and use them for machine learning.

[0060] The machine learning model storage unit 44 is a database that stores the trained learning model 45 generated by the machine learning control unit 41, that is, the adjusted weighting parameter group.

[0061] The machine learning communication unit 42 is a communication interface unit. The machine learning communication unit 42 is connected to an external device via a network 70, and is capable of transmitting and receiving various types of data. The trained learning model 45 stored in the machine learning model storage unit 44 is provided to the information processing device 50 via the network 70, a storage medium, or the like.

[0062] In addition, in FIG. 4, the learning data storage unit 43 and the machine learning model storage unit 44 are shown as separate storage units, but these may be configured as a single storage unit.

[0063] (Information processing device 50 of the first embodiment) 6 is a schematic diagram showing an information processing device 50 according to the first embodiment. The information processing device 50 is a device that operates as a main body of the inference phase of machine learning. The information processing device 50 uses the learning model 45 generated by the machine learning device 40 to generate new control conditions 103c for the heating device 10 corresponding to newly input input parameters for generation 103a.

[0064] The information processing device 50 has an information processing control unit 51, an information processing model storage unit 57, and an information processing communication unit 58. The information processing control unit 51 has an information acquisition unit 52, a control condition generation unit 53, a candidate acquisition unit 54, an evaluation unit 55, and an output processing unit 56.

[0065] The information acquisition unit 52 acquires the generation input parameters 103a input by the worker via an operation terminal (not shown). The generation input parameters 103a are input parameters for a new heating operation, which is a heating operation in which a new heating device 10 is used for heating.

[0066] The control conditions for a new heating job using the heating device 10 corresponding to the generation input parameters 103a are set as new control conditions 103c.

[0067] The control condition generation unit 53 generates new control conditions 103c by inputting the generation input parameters 103a acquired by the information acquisition unit 52 to the learning model 45. The output processing unit 56 outputs the new control conditions 103c generated by the control condition generation unit 53 to the information processing communication unit 58.

[0068] The candidate acquisition unit 54 acquires a plurality of control condition candidates 103b generated by the control condition generation unit 53. The evaluation unit 55 performs performance evaluation of the heating device 10 for the plurality of control condition candidates 103b acquired by the candidate acquisition unit 54. The evaluation unit 55 of this embodiment obtains energy consumption as one of the performance evaluation items. The output processing unit 56 outputs new control conditions 103c based on energy consumption as a performance evaluation item from the control condition candidates 103b. Note that the output processing unit 56 may select a control condition that minimizes the energy consumption of the heating device 10 from the plurality of control condition candidates 103b evaluated by the evaluation unit 55 as the new control condition 103c.

[0069] The evaluation unit 55 may also use the amount of overshoot or the amount of hunting as an item for performance evaluation. The output processing unit 56 may select the control condition with the smallest amount of overshoot or hunting as the new control condition 103c. The amount of overshoot is the maximum temperature that exceeds the target temperature during the heating process, and the amount of hunting is the temperature amplitude when the temperature oscillates up and down just before reaching the target temperature.

[0070] The information processing model storage unit 57 is a database that stores the trained learning models 45 used by the control condition generation unit 53. The information processing model storage unit 57 can store a plurality of trained learning models 45 input from the machine learning device 40.

[0071] Each of the multiple learning models 45 is a multiple number of trained models that differ, for example, in the number and configuration of the intermediate layer 45, the machine learning method, the type of data included in the learning input parameters 102a, the type of data included in the learning control conditions 102b, etc.

[0072] The information processing model storage unit 57 may be substituted with a storage unit of an external computer such as a server-type computer or a cloud-type computer. In that case, the control condition generation unit 53 can access the storage unit of the external computer to acquire the learning model 45.

[0073] The information processing and communication unit 58 is communicably connected to devices outside the heating system 1 via the network 70. The information processing and communication unit 58 is a communication interface unit that transmits and receives various data. The information processing and communication unit 58 can output the new control condition 103c output by the output processing unit 56 to the information processing and communication unit 58.

[0074] 2 to continue the explanation. The control device 60 can control each device of the heating system 1. The control device 60 can control each device of the heating system 1 based on the new control condition 103c transmitted from the information processing device 50.

[0075] The control device 60 outputs an output command value for the blower 18 among the new control conditions 103c to the blower power supply. The blower power supply controls the blower 18 based on the input output command value. This makes it possible to control the flow rate of air flowing through the blower duct 19.

[0076] The control device 60 outputs an output command value for the transport device 30 among the new control conditions 103c to the transport control unit 32. The transport control unit 32 controls the transport device 30 based on the input output command value. This makes it possible to control at least one of the transport speed of the transport device main body 31 and the rotation speed of the rotational motion of the preform 200.

[0077] The control device 60 outputs the output command value for each heater 14 in the new control condition 103c to the heater power supply. The heater power supply controls each heater 14 based on the input output command value. This makes it possible to control the output of each heater 14.

[0078] (First example of the information processing control unit 51 in the first embodiment) 7 is a configuration diagram showing a first example of the information processing control unit 51 of the first embodiment. In the information processing control unit 51, the control condition generating unit 53 obtains control condition candidates 103bn for the generation input parameters 103a acquired by the information acquiring unit 52 using the learning model 45 stored in the information processing model storage unit 57. The control condition generating unit 53 of this embodiment has an information adding unit 53a that adds multiple pieces of additional information 53an such as variations in size, shape, material, etc., or random noise, etc., to the generation input parameters 103a. Note that the variations in size, shape, material, etc., or random noise, etc., are preferably within a predetermined minute range.

[0079] (Example of random noise) Fig. 8 shows an example of random noise. Fig. 8(a) shows an example of random selection from a uniform distribution, and Fig. 8(b) shows an example of random selection from a normal distribution. Fig. 8(c) shows an example of random selection from an arbitrary distribution. The example of random noise shown in Fig. 8 shows a case where the target value is X and the noise tolerance is ±n.

[0080] The example shown in Fig. 8(a) is a case where noise is randomly selected from a uniform distribution within the range of Xn to X+n for a target value X. The example shown in Fig. 8(b) is a case where noise is randomly selected from a normal distribution within the range of Xn to X+n for a target value X. The example shown in Fig. 8(c) is a case where noise is randomly selected from an arbitrary distribution within the range of Xn to X+n for a target value X.

[0081] The control condition generating unit 53 generates a plurality of control condition candidates 103bn. For example, the first additional information 53a1 is added to the generation input parameters 103a, and the first control condition candidate 103b1 is generated using the learning model 45. In addition, the second additional information 53a1 is added to the generation input parameters 103a, and the first control condition candidate 103b1 is generated. 3a2 and obtains a second control condition candidate 103b2 by using the learning model 45. That is, generally speaking, the n-th additional information 53an is added to the generation input parameters 103a and the n-th control condition candidate 103bn is obtained by using the learning model 45. The multiple control condition candidates 103b1 to 103bn generated by the control condition generation unit 53 are acquired by the candidate acquisition unit 54.

[0082] The evaluation unit 55 obtains the energy consumption of the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. The evaluation unit 55 may select a new control condition 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54 based on the energy consumption. For example, the evaluation unit 55 may select the smallest energy consumption from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54, and set it as the new control condition 103c. Alternatively, the evaluation unit 55 may select a candidate with the smallest overshoot amount or hunting amount, and set it as the new control condition 103c. Note that the user may select the new control condition 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. The output processing unit 56 outputs the new control condition 103c.

[0083] In this way, according to the information processing control unit 51 of the first example, the candidate acquisition unit 54 acquires the multiple control condition candidates 103bn generated by the control condition generation unit 53, the evaluation unit 55 performs performance evaluation of the multiple heating devices 10 corresponding to the cases where each heating device 10 is controlled by the multiple control condition candidates 103bn acquired, and the output processing unit 56 outputs new control conditions 103c from the multiple control condition candidates 103bn, so that it is possible to set control conditions taking into consideration the energy consumption and temperature control stability of the heating device 10. In addition, the output processing unit 56 outputs the control condition candidate 103b that minimizes the energy consumption, overshoot amount, or hunting amount found by the evaluation unit 55 from among the multiple control condition candidates 103bn as the new control condition 103c, so that it is possible to select appropriate control conditions.

[0084] In the first example, each control condition candidate 103bn was obtained by inputting multiple generation input parameters 103a into the learning model 45. However, it may be configured so that one control condition candidate 103bn is obtained by inputting generation input parameters 103a to which one additional information 53an has been added, without using the learning model 45, using an arithmetic formula, a map, a table, or the like.

[0085] (Second example of the information processing control unit 51 in the first embodiment) FIG. 9 is a configuration diagram showing a second example of the information processing control unit 51 of the first embodiment. In the information processing control unit 51, the control condition generating unit 53 obtains a control condition candidate 103b using the learning model 45 stored in the information processing model storage unit 57 for the generation input parameters 103a obtained by the information acquisition unit 52. The control condition generating unit 53 of this embodiment obtains a plurality of control condition candidates 103bn using a plurality of learning models 45 for the generation input parameters 103a. The plurality of learning models 45n are learned by changing at least one of the following: a change in hyperparameter, a change in learning method, and a change in learning data. The change in hyperparameter may be achieved by changing the number or configuration of the intermediate layer 45b. The change in learning method may be achieved by changing the method itself, such as deep learning or random forest. The change in learning data may be achieved by using a plurality of different types of learning data.

[0086] For example, a first control condition candidate 103b1 is obtained by using a first learning model 451 for the generation input parameters 103a. A second control condition candidate 103b2 is obtained by using a second learning model 452 for the generation input parameters 103a. In other words, generally speaking, an n-th control condition candidate 103bn is obtained by using an n-th learning model 45n for the generation input parameters 103a. The multiple control condition candidates 103b1 to 103bn generated by the control condition generation unit 53 are acquired by the candidate acquisition unit 54.

[0087] The evaluation unit 55 obtains the energy consumption of the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. The evaluation unit 55 may select a new control condition 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54 based on the energy consumption. For example, the evaluation unit 55 may select a control condition with the smallest energy consumption, overshoot amount, or hunting amount from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. The user may select the new control condition 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. The output processing unit 56 outputs the new control condition 103c.

[0088] In this way, according to the information processing control unit 51 of the second example, the candidate acquisition unit 54 acquires the multiple control condition candidates 103bn generated by the control condition generation unit 53, the evaluation unit 55 calculates the energy consumption of the multiple heating devices 10 corresponding to the cases where each of the heating devices 10 is controlled according to the multiple control condition candidates 103bn acquired, and the output processing unit 56 outputs the new control condition 103c from the multiple control condition candidates 103bn, so that the control condition can be set in consideration of the energy consumption and temperature control stability of the heating device 10. In addition, the output processing unit 56 outputs the control condition candidate 103b that minimizes the energy consumption, overshoot amount, or hunting amount calculated by the evaluation unit 55 from among the multiple control condition candidates 103bn as the new control condition 103c, so that an appropriate control condition can be selected.

[0089] (Hardware configuration of computer 900) 10 is a hardware configuration diagram of the computer 900. The machine learning device 40 and the information processing device 50 of the heating system 1 are configured by a general-purpose or dedicated computer 900.

[0090] The computer 900 includes a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication interface unit 922, an external device interface unit 924, an input / output device interface unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0091] The processor 912 is composed of one or more arithmetic processing devices (CPU (Central Processing Unit), MPU (Micro-processing unit), DSP (digital signal processor), GPU (Graphics Processing Unit), etc.) and operates as a control unit that oversees the entire computer 900.

[0092] The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0093] The input device 916 is, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is, for example, a sound output device including voice, a vibration device, etc., and functions as an output unit. The display device 918 is, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit.

[0094] The input device 916 and the display device 918 may be integrated, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD (Solid State Drive), etc., and functions as a storage unit. The storage device 920 stores various data required for the execution of the operating system and the program 930. The data is stored.

[0095] The communication interface unit 922 is connected to a network 940 such as the Internet or an intranet by wire or wirelessly, and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication standard. The network 940 may be the same as the network 70.

[0096] The external device interface unit 924 is connected to an external device 950 such as a camera, printer, scanner, or reader / writer by wire or wirelessly, and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication standard.

[0097] The input / output device interface unit 926 is connected to input / output devices 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data between the input / output devices 960, such as detection signals from sensors and control signals to actuators.

[0098] The media input / output unit 928 is constituted by a drive device such as a DVD drive, a CD drive, etc., and reads and writes data from and to a medium 970, which is a storage medium such as a DVD or a CD.

[0099] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. Note that the program 930 may be stored in the memory 914 instead of the storage device 920.

[0100] The program 930 may be recorded in a medium 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by downloading it over a network 940 via the communication interface unit 922.

[0101] Furthermore, the computer 900 may realize various functions that are realized by the processor 912 executing the program 930 using hardware such as an FPGA or an ASIC.

[0102] The computer 900 is, for example, a stationary computer or a portable computer, and is an electronic device of any form. The computer 900 may be a client-type computer, a server-type computer, or a cloud-type computer. The computer 900 may be applied to devices other than the machine learning device 40 and the information processing device 50 of the heating system 1.

[0103] (Machine learning methods) 11 is a flowchart showing a machine learning method performed by the machine learning device 40 of the first embodiment. Here, the machine learning method will be described. First, an operator inputs one or more pieces of learning data 46 in advance and stores them in the learning data storage unit 43. The number of pieces of learning data 46 to be stored is set taking into consideration the inference accuracy required for the ultimately obtained learning model 45.

[0104] In the machine learning method, a learning model preparation step is performed as step S100. The machine learning control unit 41 prepares a pre-learning learning model 45. In the prepared learning model 45, the weight of each synapse is set to an initial value.

[0105] Next, a machine learning process is performed in step S110. In the machine learning process, first, a learning data acquisition process is performed in step S111. The machine learning control unit 41 randomly acquires one piece of learning data 46 from the multiple pieces of learning data 46 stored in the learning data storage unit 43.

[0106] Next, an inference result output step is performed as step S112. The machine learning control unit 41 inputs the learning input parameters 102a included in the acquired piece of learning data 46 to the input layer 45a of the prepared learning model 45. As a result, the learning result control condition 102c is output as an inference result from the output layer 45c of the learning model 45.

[0107] The learning result control condition 102c output as the inference result is generated by the learning model 45 before or during learning. Therefore, the learning result control condition 102c is different from the learning control condition 102b, which is the correct label included in the learning data 46.

[0108] Next, a weight adjustment step is performed as step S113. The machine learning control unit 41 compares the learning control condition 102b in the learning data 46 acquired in step S111, which is the correct label, with the learning result control condition 102c output as the inference result in step S112. Based on the comparison, the machine learning control unit 41 performs back propagation, which is a process of adjusting the weight of each synapse, and performs machine learning.

[0109] As a result, the machine learning control unit 41 causes the learning model 45 to learn the correlation between the learning input parameters 102a and the learning control conditions 102b.

[0110] Next, a machine learning end determination step is performed as step S114. The machine learning control unit 41 determines whether a predetermined learning end condition is satisfied. This determination is performed based on, for example, an evaluation value of an error function based on the learning control condition 102b, which is the correct label, and the learning result control condition 102c, the remaining number of unlearned learning data 46 stored in the learning data storage unit 43, and the like.

[0111] In step S114, if the machine learning control unit 41 determines that the learning end condition is not satisfied and to continue the machine learning, that is, if the answer is No in step S114, the process returns to step S111. In this manner, the processes of steps S111 to S114 are performed multiple times on the unlearned learning data 46 for the learning model 45 being trained.

[0112] On the other hand, in step S114, if the machine learning control unit 41 determines that the learning end condition is satisfied and that the machine learning is to be ended, that is, if step S114 is Yes, the process proceeds to step S120.

[0113] Then, in step S120, a trained model storage step is performed. The machine learning control unit 41 stores the trained learning model 45 in which the weights of each synapse have been adjusted, i.e., the learning model 45 reflecting the adjusted weight parameter group, in the machine learning model storage unit 44. This ends the machine learning method.

[0114] (First example of information processing method) Fig. 12 is a flowchart showing the information processing method of the information processing control unit 51 of the first example shown in Fig. 7. A method of generating new control conditions 103c for the heating system 1 by the information processing device 50 will be described.

[0115] First, in step S200, a generation input parameter acquisition process is performed. In the force parameter acquisition step, an operator inputs the generation input parameters 103a to the information processing device 50, and the information acquisition unit 52 acquires the generation input parameters 103a.

[0116] Next, a generation step is performed as step S210. The generation step includes an addition step as step S211. First, as step S211, the control condition generation unit 53 executes an addition step of adding a plurality of minute additional information 53an such as variations in size, shape, material, etc., or random noise to the generation input parameters 103a acquired in step S200. Next, in the generation step, the generation input parameters 103a to which the additional information 53an has been added are input to the learning model 45. As a result, the control condition generation unit 53 generates a plurality of control condition candidates 103bn corresponding to the generation input parameters 103a.

[0117] Next, an output candidate acquisition step is performed as step S220. In the output candidate acquisition step, the candidate acquisition unit 54 acquires the multiple control condition candidates 103b1-103bn generated by the control condition generation unit 53. Then, an evaluation step is performed as step 230. In the evaluation step, the evaluation unit 55 calculates an evaluation function of the energy consumption, the amount of overshoot, the amount of hunting, or the like of the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54.

[0118] In addition, as the evaluation step, the evaluation unit 55 may select new control conditions 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. For example, the evaluation unit 55 may select new control conditions 103c having the smallest energy consumption, overshoot amount, or hunting amount from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. Also, a user may select new control conditions 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54.

[0119] Next, an output process step is performed as step S240. As the output process, the output processing unit 56 transmits the new control condition 103c selected in step S230 to the control device 60. This completes the generation and output of the new control condition 103c.

[0120] The control device 60 can control each device of the heating system 1 based on the new control condition 103c input from the output processing unit 56.

[0121] In this way, according to the information processing method of the information processing control unit 51 of the first example, a plurality of control condition candidates 103bn are acquired, energy consumption of a plurality of heating devices 10 corresponding to cases where each of the heating devices 10 is controlled according to the acquired plurality of control condition candidates 103bn is calculated, and new control conditions 103c are output from the plurality of control condition candidates 103bn, so that control conditions can be set in consideration of the energy consumption, overshoot amount, or hunting amount of the heating device 10. Furthermore, among the plurality of control condition candidates 103bn, the control condition candidate 103b that minimizes the energy consumption, overshoot amount, or hunting amount is output as the new control condition 103c, so that appropriate control conditions can be selected.

[0122] (Second example of information processing method) Fig. 13 is a flowchart showing an information processing method of the information processing control unit 51 of the second example shown in Fig. 9. A method of generating new control conditions 103c for the heating system 1 by the information processing device 50 will be described.

[0123] First, a generation input parameter acquisition step is performed as step S300. In the generation input parameter acquisition step, an operator inputs the generation input parameters 103a to the information processing device 50, whereby the information acquisition unit 52 acquires the generation input parameters 103a.

[0124] Next, a generating step is performed as step S310. The generation input parameters 103a acquired in step S200 are input to a plurality of learning models 45. In this way, the control condition generating unit 53 generates a plurality of control condition candidates 103bn corresponding to the generation input parameters 103a.

[0125] Next, an output candidate acquisition step is performed as step S320. In the output candidate acquisition step, the candidate acquisition unit 54 acquires the multiple control condition candidates 103b1-103bn generated by the control condition generation unit 53. Then, an evaluation step is performed as step 330. In the evaluation step, the evaluation unit 55 calculates the energy consumption, the overshoot amount, or the hunting amount of the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54.

[0126] In addition, as the evaluation step, the evaluation unit 55 may select new control conditions 103c from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. For example, the evaluation unit 55 may select new control conditions 103c having the smallest energy consumption, overshoot amount, or hunting amount from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54. Also, a user may select new control conditions from the multiple control condition candidates 103b1-103bn acquired by the candidate acquisition unit 54.

[0127] Next, an output process step is performed as step S340. As the output process, the output processing unit 56 transmits the new control condition 103c selected in step S330 to the control device 60. This completes the generation and output of the new control condition 103c.

[0128] The control device 60 can control each device of the heating system 1 based on the new control condition 103c input from the output processing unit 56.

[0129] In this way, according to the information processing method of the information processing control unit 51 of the second example, a plurality of control condition candidates 103bn are acquired, performance evaluation is performed on a plurality of heating devices 10 corresponding to cases where each heating device 10 is controlled using the acquired plurality of control condition candidates 103bn, and new control conditions 103c are output from the plurality of control condition candidates 103bn, so that it is possible to set control conditions taking into consideration the energy consumption of the heating device 10. Furthermore, among the plurality of control condition candidates 103bn, the control condition candidate 103b that minimizes the energy consumption, the amount of overshoot, or the amount of hunting is output as the new control condition 103c, so that it is possible to select appropriate control conditions.

[0130] (Heating device 10 of the second embodiment) FIG. 14 is a schematic diagram showing the heating device 10 and the transport device 30 of the second embodiment. The second embodiment differs from the first embodiment in that the learning control conditions 102b and the new control conditions 103c include the time of the annealing treatment performed on the preform 200. That is, the learning control conditions 102b and the new control conditions 103c in the second embodiment are the learning control conditions 102b and the new control conditions 103c in the first embodiment with the time of the annealing treatment added. In addition, the heating device 10 differs from the first embodiment in that it has two heating device bodies 11 and five transport device bodies 31. The other configurations are the same as those in the first embodiment, so the description will be omitted.

[0131] The heating device 10 has a first heating device body 11a disposed on the upstream side and a second heating device body 11b disposed on the downstream side of the first heating device body 11a. The specific configurations of the first heating device body 11a and the second heating device body 11b are similar to the specific configuration of the heating device body 11 in the first embodiment, so the description will be omitted.

[0132] The conveying device 30 has an upstream conveying device body 31a, a first conveying device body 31b, an intermediate conveying device body 31c, a second conveying device body 31d, and a downstream conveying device body 31e. The specific configurations of the first conveying device body 31c, the second conveying device body 31d, and the downstream side conveying device body 31e are similar to the specific configuration of the conveying device body 31 in the first embodiment, so the description will be omitted.

[0133] The upstream conveying device body 31a, the first conveying device body 31b, the intermediate conveying device body 31c, the second conveying device body 31d, and the downstream conveying device body 31e are arranged so as to be connected in order. The preform 200 conveyed by the upstream conveying device body 31a is conveyed from the upstream conveying device body 31a to the first conveying device body 31b, the intermediate conveying device body 31c, the second conveying device body 31d, and the downstream conveying device body 31e in this order.

[0134] The first conveying device body 31b is disposed at a position where the preform 200 supported by the first conveying device body 31b passes through the heating passage 12 of the first heating device body 11a. The second conveying device body 31d is disposed at a position where the preform 200 supported by the second conveying device body 31d passes through the heating passage 12 of the second heating device body 11b.

[0135] In this embodiment, in order to perform an annealing process on the preform 200, the preform 200 is left in a state where it is removed from the heating passage 12. Specifically, with the preform 200 placed on the intermediate conveying device body 31c, control is performed such that the conveying speed of the intermediate conveying device body 31c is slowed down or the conveying of the intermediate conveying device body 31c is temporarily stopped.

[0136] Therefore, when the time for annealing the preform 200, that is, the time for removing the preform 200 from the heating space, is output as the new control condition 103c, the control device 60 executes control such as slowing down the conveying speed of the intermediate conveying device main body 31c or temporarily stopping the conveying of the intermediate conveying device main body 31c according to the time. The control device 60 causes the preform 200 on the intermediate conveying device main body 31c to remain on the intermediate conveying device main body 31c for a time equivalent to the time for annealing. That is, the annealing process is performed on the preform 200 by placing it outside the heating space of the heating device 10.

[0137] The energy consumption changes when the time, speed, etc. of the annealing treatment performed on the preform 200 is changed. Therefore, it is preferable to use the time, speed, etc. of the annealing treatment as new control conditions.

[0138] In this way, according to the information processing device 50 of the second embodiment, the time for the annealing treatment performed on the preform 200 can be appropriately set in consideration of the energy consumption of the heating device 10.

[0139] This embodiment can also be provided in the form of an information processing program, which is a program that causes the computer 900 to function as each unit of the information processing device 50, or an information processing program, which is a program that causes the computer 900 to execute each step of an information processing method.

[0140] The present disclosure is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention. All such modifications are included in the technical concept of the present invention.

[0141] Various aspects of this embodiment will be described below as supplementary notes.

[0142] (Appendix 1) An information processing device that generates control conditions for a heating device that heats a temperature-controlled object based on input parameters for generation, An information acquisition unit that acquires the generation input parameters; a control condition generating unit that generates a plurality of control condition candidates for the heating device based on the input parameters for control condition generation acquired from the information acquiring unit; a candidate acquisition unit that acquires the plurality of control condition candidates generated by the control condition generation unit; an evaluation unit that performs performance evaluation of a plurality of the heating devices corresponding to cases where the heating devices are controlled according to the plurality of control condition candidates acquired by the candidate acquisition unit; an output processing unit that outputs a new control condition from the plurality of control condition candidates acquired by the candidate acquisition unit based on the performance evaluation performed by the evaluation unit; Equipped Information processing device. (Appendix 2) The performance evaluation item is energy consumption. 2. An information processing device according to claim 1. (Appendix 3) The output processing unit outputs, as the new control condition, the control condition candidate that minimizes the energy consumption among the plurality of control condition candidates. 3. An information processing device according to claim 2. (Appendix 4) 2. The information processing device according to claim 1, wherein the performance evaluation item is at least one of an amount of overshoot and an amount of hunting with respect to a target temperature. (Appendix 5) The information processing device according to claim 4, wherein the output processing unit outputs, as the new control condition, the control condition candidate in which the amount of overshoot or the amount of hunting is smallest, from among the plurality of control condition candidates. (Appendix 6) The generation input parameters are: Material information of the temperature control target; Shape information of the temperature control target; Initial temperature information of the temperature control object; Target temperature distribution information of the heating device, and The thermal environment information of the heating device is at least one of 2. An information processing device according to claim 1. (Appendix 7) The material information is Information on the light transmittance, reflectance, and refractive index of the object to be temperature controlled; Lightness information of the color of the temperature control target; Color information of the temperature control target; Density information of the temperature control target; Specific heat information of the temperature control target; and At least one of the thermal conductivity information of the temperature control target, 7. The information processing device according to claim 6. (Appendix 8) The shape information is Design drawing information of the temperature control object; Shape image information of the temperature control target; Dimensional information of the temperature control target; and At least one of the following: shape tracing measurement / scanning information of the temperature control object; 7. The information processing device according to claim 6. (Appendix 9) The thermal environment information is Distance information from a heat source of the heating device to the temperature control target; Information on the arrangement position, irradiation direction, and irradiation angle of the heat source of the heating device; Dimensional information of the heating device, thermal diffusion information to the outside of the heating device, and At least one of the following: 7. The information processing device according to claim 6. (Appendix 10) The heating device includes a heating device body that defines a heating space, a conveying device that conveys the temperature control target while rotating the temperature control target within the heating space, and a blowing device; The air blowing device has an air blowing source and an air blowing tube for blowing air from the air blowing source into the heating space, The control condition is an output command value of a heat source of the heating device; The time of the annealing treatment performed on the temperature control target; The flow rate of the air flowing through the air duct; The conveying speed of the conveying device, and and the rotation speed of the rotational motion of the temperature control target. 2. An information processing device according to claim 1. (Appendix 11) The control condition generating unit an information adding unit that adds a plurality of pieces of additional information to the generation input parameters; The information addition unit generates the plurality of control condition candidates based on the plurality of input parameters for generation to which the additional information has been added. 2. An information processing device according to claim 1. (Appendix 12) The control condition generation unit generates the plurality of control condition candidates by inputting the generation input parameters to a learning model that learns, by machine learning, a correlation between the learning input parameters and learning control conditions that are control conditions of the heating device corresponding to the learning input parameters. 2. An information processing device according to claim 1. (Appendix 13) The control condition generating unit generates a plurality of the control condition candidates by inputting the generation input parameters to a plurality of the learning models. 13. The information processing device according to claim 12. (Appendix 14) The learning model is created by changing at least one of a hyperparameter, a learning method, and a learning data. 14. The information processing device according to claim 13. (Appendix 15) An information processing system that generates a learning model for generating control conditions of a heating device that heats a temperature control target, and generates control conditions of the heating device that heats a temperature control target by inputting generation input parameters to the learning model, a machine learning device that includes a learning data storage unit that stores one or more pieces of learning data, a machine learning control unit that causes the learning model to learn based on the one or more pieces of learning data, and a machine learning model storage unit that stores the learned learning model, each piece of learning data being composed of learning input parameters and learning control conditions that are control conditions for the heating device corresponding to the learning input parameters, and the learning model learning a correlation between the learning input parameters in the learning data and the learning control conditions; an information acquisition unit for acquiring the generation input parameters, an information processing device having a control condition generation unit that generates a plurality of control condition candidates for the heating device by inputting parameters, a candidate acquisition unit that acquires the plurality of control condition candidates generated by the control condition generation unit, an evaluation unit that performs a performance evaluation of a plurality of the heating devices corresponding to cases where each of the heating devices is controlled using the plurality of control condition candidates acquired by the candidate acquisition unit, and an output processing unit that outputs a new control condition from the plurality of control condition candidates acquired by the candidate acquisition unit based on the performance evaluation performed by the evaluation unit; Equipped Information processing system. (Appendix 16) An information processing method for generating control conditions for a heating device that heats a temperature-controlled object based on input parameters for generation, comprising: An information acquisition step of acquiring the generation input parameters; a generation step of generating a plurality of the control condition candidates for the heating device based on the input parameters for control condition generation acquired in the information acquisition step; an output candidate acquisition step of acquiring the plurality of control condition candidates generated in the generation step; an evaluation step of performing performance evaluation of a plurality of the heating devices corresponding to cases where the heating devices are controlled using the plurality of control condition candidates acquired in the output candidate acquisition step; an output processing step of outputting a new control condition from the plurality of control condition candidates acquired in the output candidate acquisition step based on the performance evaluation performed in the evaluation step; have Information processing methods. (Appendix 17) The generating step generates the plurality of control condition candidates by inputting the generation input parameters to a learning model that has learned, by machine learning, a correlation between a learning input parameter and a learning control condition that is a control condition of the heating device corresponding to the learning input parameter. 17. The information processing method according to claim 16. [Explanation of symbols]

[0143] 1 heating system, 10 heating device, 11 heating device main body, 11a first heating device main body, 11b second heating device main body, 12 heating passage (heating space), 14 heater (heat source), 17 blower, 18 blower (blow source), 19 blower pipe, 30 conveying device, 31 conveying device main body, 31a upstream conveying device main body, 31b first conveying device main body, 31c intermediate conveying device main body, 31d second conveying device main body, 31e downstream conveying device main body, 32 conveying control unit, 40 machine learning device, 41 machine learning control unit, 42 machine learning communication unit, 43 learning data storage unit, 44 machine learning model storage unit, 45 learning model, 45a input layer, 45b intermediate layer, 45c output layer, 46 learning data, 50 information processing device, 51 information processing control unit, 52 information acquisition unit, 53 Control condition generation unit, 54 candidate acquisition unit, 55 evaluation unit, 56 output processing unit, 57 information processing model storage unit, 58 information processing communication unit, 60 control device, 70 network, 101a input parameters, 101b control conditions, 102a learning input parameters, 102b learning control conditions, 102c learning result control conditions, 103a generation input parameters, 103b control condition candidates, 103c new control conditions, 200 Preform (temperature controlled), 900 computer, 910 bus, 912 processor, 914 memory, 916 input device, 917 output device, 918 display device, 920 storage device, 922 communication interface unit, 924 external device interface unit, 926 input / output device interface unit, 928 media input / output unit, 930 program, 940 network, 950 external device, 960 input / output device, 970 media.

Claims

1. An information processing device that generates control conditions for a heating device that heats a temperature-controlled object based on input parameters for generation, An information acquisition unit that acquires the generation input parameters; a control condition generating unit that generates a plurality of control condition candidates for the heating device based on the input parameters for control condition generation acquired from the information acquiring unit; a candidate acquisition unit that acquires the plurality of control condition candidates generated by the control condition generation unit; an evaluation unit that performs performance evaluation of a plurality of the heating devices corresponding to cases where the heating devices are controlled according to the plurality of control condition candidates acquired by the candidate acquisition unit; an output processing unit that outputs a new control condition from the plurality of control condition candidates acquired by the candidate acquisition unit based on the performance evaluation performed by the evaluation unit; Equipped Information processing device.

2. The information processing apparatus according to claim 1 , wherein the performance evaluation item is energy consumption.

3. The output processing unit outputs, as the new control condition, the control condition candidate that minimizes the energy consumption among the plurality of control condition candidates. The information processing device according to claim 2 .

4. The information processing apparatus according to claim 1 , wherein the performance evaluation item is at least one of an amount of overshoot and an amount of hunting with respect to a target temperature.

5. The information processing apparatus according to claim 4 , wherein the output processing unit outputs, as the new control condition, the control condition candidate that minimizes the amount of overshoot or the amount of hunting, from among the plurality of control condition candidates.

6. The generation input parameters are: Material information of the temperature control target; Shape information of the temperature control target; Initial temperature information of the temperature control target; Target temperature distribution information of the heating device, and The thermal environment information of the heating device is at least one of The information processing device according to claim 1 .

7. The material information is Information on the light transmission, reflection, and refractive index of the object to be temperature controlled; Lightness information of the color of the temperature control target; Color information of the temperature control target; Density information of the temperature control target; Specific heat information of the temperature control target; and At least one of the thermal conductivity information of the temperature control target, The information processing device according to claim 6.

8. The shape information is Design drawing information of the temperature control object; Shape image information of the temperature control target; Dimensional information of the temperature control target; and At least one of the shape tracing measurement and scanning information of the temperature control object. One of them is The information processing device according to claim 6.

9. The thermal environment information is Distance information from a heat source of the heating device to the temperature control target; Information on the arrangement position, irradiation direction, and irradiation angle of the heat source of the heating device; Dimensional information of the heating device, thermal diffusion information to the outside of the heating device, and At least one of the following: The information processing device according to claim 6.

10. The heating device includes a heating device body that defines a heating space, a conveying device that conveys the temperature control target while rotating the temperature control target within the heating space, and an air blowing device; The air blowing device has an air blowing source and an air blowing tube for blowing air from the air blowing source into the heating space, The control condition is An output command value of a heat source of the heating device; The time of the annealing treatment performed on the temperature control target; The flow rate of the air flowing through the air duct; The conveying speed of the conveying device, and and the rotation speed of the rotational motion of the temperature control target. The information processing device according to claim 1 .

11. The control condition generating unit an information adding unit that adds a plurality of pieces of additional information to the generation input parameters; The information addition unit generates the plurality of control condition candidates based on the plurality of input parameters for generation to which the additional information has been added. The information processing device according to claim 1 .

12. The control condition generation unit generates the plurality of control condition candidates by inputting the generation input parameters to a learning model that learns, by machine learning, a correlation between the learning input parameters and learning control conditions that are control conditions of the heating device corresponding to the learning input parameters. The information processing device according to claim 1 .

13. The control condition generating unit generates a plurality of the control condition candidates by inputting the generation input parameters to a plurality of the learning models. The information processing device according to claim 12.

14. The learning model is created by changing at least one of a hyperparameter, a learning method, and a learning data. The information processing device according to claim 13.

15. An information processing system that generates a learning model for generating control conditions of a heating device that heats a temperature control target, and generates control conditions of the heating device that heats a temperature control target by inputting generation input parameters to the learning model, The present invention includes a learning data storage unit that stores one or more pieces of learning data, a machine learning control unit that causes the learning model to learn based on the one or more pieces of learning data, and a machine learning model storage unit that stores the learned learning model, and each of the learning data includes learning input parameters and learning control parameters that are control conditions of the heating device corresponding to the learning input parameters. and a learning model including: a machine learning device configured to learn a correlation between the learning input parameters in the learning data and the learning control conditions; an information processing device including an information acquisition unit that acquires the generation input parameters, a control condition generation unit that generates a plurality of control condition candidates for the heating device by inputting the generation input parameters to the learning model, a candidate acquisition unit that acquires the plurality of control condition candidates generated by the control condition generation unit, an evaluation unit that performs a performance evaluation of a plurality of the heating devices corresponding to cases where each of the heating devices is controlled using the plurality of control condition candidates acquired by the candidate acquisition unit, and an output processing unit that outputs new control conditions from the plurality of control condition candidates acquired by the candidate acquisition unit based on the performance evaluation performed by the evaluation unit; Equipped Information processing system.

16. An information processing method for generating control conditions for a heating device that heats a temperature-controlled object based on input parameters for generation, comprising: An information acquisition step of acquiring the generation input parameters; a generation step of generating a plurality of the control condition candidates for the heating device based on the input parameters for control condition generation acquired in the information acquisition step; an output candidate acquisition step of acquiring the plurality of control condition candidates generated in the generation step; an evaluation step of performing performance evaluation of a plurality of the heating devices corresponding to cases where the heating devices are controlled using the plurality of control condition candidates acquired in the output candidate acquisition step; an output processing step of outputting a new control condition from the plurality of control condition candidates acquired in the output candidate acquisition step based on the performance evaluation performed in the evaluation step; have Information processing methods.

17. The generating step generates the plurality of control condition candidates by inputting the generation input parameters to a learning model that has learned, by machine learning, a correlation between a learning input parameter and a learning control condition that is a control condition of the heating device corresponding to the learning input parameter. The information processing method according to claim 16.

Images