Information processing device, information processing method, information processing program, and method for manufacturing molded articles

Abstract

To continuously produce molded products with the desired quality. [Solution] The information processing device (2) includes an identification unit (201) that identifies each polymer fed into each hopper of an extruder used in the manufacture of molded products made by blending multiple polymers, and a quality prediction unit (203) that predicts the quality of the molded product using a quality prediction model (211) in which the quality of the molded product is the objective variable and the blending ratio when blending the multiple polymers identified by the identification unit is included as at least one of the explanatory variables.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing apparatus, an information processing method, an information processing program, and a method for manufacturing a molded article. [Background Art]

[0002] Conventionally, when manufacturing a product by blending a plurality of raw materials, a technique for controlling the blending ratio so as to satisfy a desired quality is known (for example, Patent Document 1). Patent Document 1 discloses that: "While a provisional blending amount determining means 26 determines provisional blending amounts of respective raw materials to be blended, based on raw material data of the respective raw materials acquired by an acquiring means 20, a predicted value calculation means 28 calculates a maximum predicted value and a minimum predicted value of a control component in each of the raw materials for each control component. Further, a correction value determining means 30 determines a correction value for correcting at least one of the maximum predicted value and the minimum predicted value such that at least the maximum predicted value falls within a range between an upper limit target value and a lower limit target value determined by a target value determining means 24. Then, based on the correction value, a blending amount determining means 32 obtains correction amounts for the provisional blending amounts, and determines the blending amount of each raw material necessary for obtaining a target blend from the correction amounts and the provisional blending amounts." A raw material blending planning system is disclosed. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2003-005803 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] In recent years, environmental problems caused by waste plastics have been highlighted. Among them, marine pollution caused by waste plastics is serious, and the spread of biodegradable polymers that decompose in natural environments is expected.

[0005] While various biodegradable polymers are known, polyhydroxyalkanoates, in particular, are attracting attention as a material that can solve the above-mentioned problems because they are produced and accumulated as energy storage substances within the cells of microbial species, and can undergo biodegradation not only in soil but also in seawater.

[0006] Because the production process of polyhydroxyalkanoates relies on biochemical processes, differences in physical properties can occur between batches of polymers produced under similar conditions. One example of a problem arising from this phenomenon is the following: Consider the case of producing molded products (e.g., pellets) using polymers as raw materials with an extruder. Generally, an extruder is equipped with 3 to 4 hoppers, into which each polymer is fed in combination and mixing ratio according to the formulation. As mentioned above, since the physical properties of polymers vary from batch to batch, switching polymer batches may adversely affect the quality of the pellets. Therefore, in order to produce pellets of stable quality, it is desirable to adjust the mixing ratio according to the combination of polymer batches. However, adjusting the mixing ratio while monitoring batch changes during continuous production is not practical as it increases the workload and can lead to errors. Therefore, in order to ensure the quality of the pellets, one method is to stop production when a batch changes, but this leads to a decrease in productivity.

[0007] Furthermore, while the blending ratio is determined based on past performance according to the physical properties of the lot, it is necessary to conduct a quality evaluation to ensure that the pellet quality does not deviate from the specifications, and in order to reduce the risk of deviation from specifications, this also makes continuous production difficult.

[0008] Furthermore, lots that have been used intermittently become difficult to use when the remaining amount is low, and this also contributes to taking up valuable storage space.

[0009] However, Patent Document 1 does not address these problems.

[0010] One aspect of this disclosure aims to continuously produce molded articles having a desired quality. [Means for solving the problem]

[0011] To solve the above problems, an information processing device according to one aspect of the present disclosure includes: an identification unit that identifies each polymer fed into each hopper of an extruder used in the manufacture of a molded product manufactured by blending multiple polymers; a quality prediction unit that predicts the quality of the molded product using a quality prediction model in which the quality of the molded product is the objective variable and the blending ratio when blending the multiple polymers identified by the identification unit is at least one of the explanatory variables; and an optimization calculation unit that optimizes the blending ratio so that the quality of the molded product predicted by the quality prediction unit falls within a preset target range, wherein at least one of the polymers fed into each hopper is a multiple polymer. The system is provided in lots of several units, and the quality prediction unit predicts the quality for each polymer combination in each lot, the optimization calculation unit optimizes the blending ratio so that the predicted quality for the combination falls within the target range, and further comprises an alignment unit that arranges the combinations so that the variation in the blending ratio of the combinations optimized by the optimization calculation unit is minimized, and a planning unit that formulates a production plan for the molded products, the planning unit calculates the production volume of the molded products that can be produced with the target combinations in the order of the combinations arranged by the alignment unit, and determines the combinations to be used in the production plan up to the combinations whose production volume satisfies predetermined conditions.

[0012] To solve the above problems, an information processing method according to one aspect of the present disclosure is an information processing method performed by one or more information processing devices, comprising: an identification step of identifying each polymer to be fed into each hopper of an extruder used in the manufacture of a molded article manufactured by compounding multiple polymers; a quality prediction step of predicting the quality of the molded article using a quality prediction model in which the quality of the molded article is the objective variable and the compounding ratio when compounding the multiple polymers identified in the identification step is included as at least one explanatory variable; and an optimization calculation step of optimizing the compounding ratio so that the quality of the molded article predicted in the quality prediction step falls within a preset target range, wherein at least The polymer is prepared in multiple lots, and the quality prediction step predicts the quality for each polymer combination for each lot, the optimization calculation step optimizes the blending ratio so that the predicted quality for the combination falls within the target range, and further includes an alignment step in which the combinations are arranged so that the variation in the blending ratio of the combination optimized in the optimization calculation step is small, and a planning step in which a production plan for the molded product is formulated, wherein in the planning step, the production volume of the molded product that can be produced with the target combination is calculated in the order of the combinations arranged in the alignment step, and the combinations up to the combination whose production volume satisfies predetermined conditions are determined to be used in the production plan.

[0013] Each aspect of the information processing device described herein may be implemented by a computer. In this case, an information processing program that enables the computer to implement the information processing device by operating the computer as each part (software element) of the information processing device, and a computer-readable recording medium on which the program is recorded, also fall within the scope of this disclosure. [Effects of the Invention]

[0014] According to one aspect of this disclosure, it is possible to continuously produce molded articles having a desired quality. [Brief explanation of the drawing]

[0015] [Figure 1] FIG. 1 is a diagram illustrating an outline of an information processing system according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a block diagram showing an example of the main configuration of an information processing apparatus according to an embodiment of the present disclosure. [Figure 3] FIG. 3 is a schematic diagram showing an example of the flow of each data according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of permutation of combinations. [Figure 5] FIG. 5 is a diagram illustrating an example of a production plan. [Figure 6] FIG. 6 is a diagram illustrating an example of lot switching. [Figure 7] FIG. 7 is a flowchart showing an example of processing executed by the information processing apparatus according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS

[0016] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same or substantially the same configurations are denoted by the same reference numerals, and repeated description thereof will be omitted.

[0017] In the present disclosure, the phrases "based on" or "in accordance with" do not mean "based only on" or "in accordance only with" unless otherwise explicitly stated. The phrase "based on" means both "based only on" and "based at least on". Similarly, the phrase "in accordance with" means both "in accordance only with" and "in accordance at least with".

[0018] Application Example of Information Processing System First, an application example of the information processing system 100 according to the present embodiment will be described with reference to FIG. 1. FIG. 1 illustrates an aspect in which the information processing system 100 according to the present embodiment is applied to extrusion molding using an extruder 90. As shown in FIG. 1, the information processing system 100 includes an extruder 90, an information processing apparatus 1, and an information processing apparatus 2. In the following, after describing extrusion molding which is an example of the application target, the information processing apparatus 1 and the information processing apparatus 2 will be described.

[0019] The extruder 90 shown as an example includes a plurality of hoppers (hoppers 92a, 92b, 92c, ...), a side feeder 93, a barrel 94, a screw 91 housed inside the barrel 94, and a die head 95. The extruder 90 may be a single-screw extruder including one screw, or a twin-screw extruder including two screws. In the following description, unless otherwise specified, the extruder 90 is described as a twin-screw extruder. In addition, when it is not necessary to distinguish between the two screws, the two screws are collectively described as the screw 91.

[0020] An example of a molded article manufactured by such an extruder 90 is pellets (resin molded articles) used in the manufacture of plastic products and the like. Pellets are molded by blending a plurality of raw materials (polymers). The polymer is not particularly limited, but as an example, it may be the biodegradable polymer described above. In addition, all of the respective polymers to be blended may be biodegradable polymers, or among the respective polymers to be blended, some polymers may be biodegradable polymers. In the following description, unless otherwise specified, a molded article manufactured by the extruder 90 is described as a "pellet", and a raw material used for the "pellet" is described as a "polymer". Furthermore, each polymer is described as a biodegradable polymer.

[0021] Barrel 94 is equipped with a cylinder (not shown) having a shape formed by combining two cylinders, and a heater (not shown) for melting the polymer. The polymer is fed into the cylinder from a plurality of hoppers (hoppers 92a, 92b, 92c, ...) located at the top of barrel 94. The polymer fed in from the plurality of hoppers (hoppers 92a, 92b, 92c, ...) is melted by the heat of the heater.

[0022] Each polymer is stored in a container (containers 97a, 97b, and 97c), and is removed from the container and placed into the corresponding hopper. Such containers are also known as flexible containers (FIBCs).

[0023] The screws 91 are housed in a cylinder in a meshed state and rotate in the same direction under the torque of a motor (not shown). This makes it possible to knead the polymer. In addition, predetermined additives are introduced from the side feeder 93 and kneaded with the polymer.

[0024] The polymer and additives fed into the extruder 90 are melted and mixed, processed into a specific shape (pellet shape), and extruded from the die head 95. The cooling process and other steps after extrusion from the die head 95 are omitted from this explanation.

[0025] As explained above, in the manufacturing process using the extruder 90, each polymer is melted and kneaded with predetermined additives to form pellets. The polymers are classified into predetermined types based on their molecular weight and functional group composition, and pellets are usually produced by blending 2 to 4 types of polymers. By changing the combination and ratio (blending ratio) of the polymers blended, the melting characteristics and physical properties after molding of the pellets can be manipulated. The manufactured pellets are classified into predetermined grades according to their application. For each grade, a standard formulation is set that defines the combination and blending ratio of polymers to reproduce the quality.

[0026] As mentioned above, each polymer exemplified as a biodegradable polymer (particularly polyhydroxyalkanoates) relies on a biochemical production process, resulting in differences in physical properties between batches even for polymers produced in the same manner. Therefore, even when each polymer is blended according to a standard formulation, the desired quality may not be obtained, meaning the quality may deviate from the specifications. To resolve this problem, one could adjust the blending ratio while monitoring the changeover between batches, but as already stated, this is practically difficult. Therefore, in order to guarantee pellet quality, it is necessary to stop production at the time of batch changeover, which leads to a decrease in productivity. In this embodiment, the following configuration is adopted: (1) Pellet quality is predicted using a quality prediction model; (2) The blending ratio of each polymer is optimized using the quality prediction results; (3) The combination of each polymer is rearranged so that the fluctuation in the blending ratio before and after batch changeover is minimized; (4) The amount of pellets that can be produced with the target combination is calculated in the order of the rearranged combinations; and (5) A pellet production plan is formulated using the calculation results.

[0027] With this configuration, when the polymer batch being fed into each hopper (hoppers 92a, 92b, 92c, ...) changes, the optimized blending ratio is automatically applied to the new batch. This eliminates the need for the operator to monitor batch changes and adjust the blending ratio. This reduces the operator's workload and contributes to increased productivity. Furthermore, since the blending ratio for each combination is pre-optimized, there is no need to perform quality evaluation again when batches change. Thus, with this embodiment, the work of monitoring batch changes and adjusting the blending ratio is eliminated, and there is no need to interrupt production when batches change. This makes it possible to continuously produce pellets of the desired quality, thereby improving productivity.

[0028] Regarding (1) above, the information processing device 1 shown in Figure 1 generates a quality prediction model using machine learning with training data. The information processing device 2 uses this quality prediction model to predict the quality of pellets from prediction data. The details of the information processing device 1, the information processing device 2, the quality prediction model, and (1) to (5) above will be explained below.

[0029] (Example configuration of information processing device 1 and information processing device 2) Next, we will describe the information processing device 1 and the information processing device 2 with reference to Figure 2. Figure 2 is a block diagram showing an example configuration of the information processing device 1 and the information processing device 2.

[0030] As shown in Figure 2, the information processing device 1 comprises a control unit 10 that centrally controls all parts of the information processing device 1, and a storage unit 11 that stores various data used by the information processing device 1. The information processing device 1 also comprises a communication unit 12 for the information processing device 1 to communicate with other devices, an input unit 13 that receives input of various data to the information processing device 1, and an output unit 14 for the information processing device 1 to output various data. The control unit 10 also includes a training data acquisition unit 101 and a learning unit 102. The storage unit 11 stores training data 111.

[0031] The information processing device 1 may be configured as a general-purpose computer. When the information processing device 1 is configured as a general-purpose computer, the control unit 10 may be configured to include a processor, ROM (Read Only Memory), RAM (Random Access Memory), etc. The processor can read programs from ROM and execute various programs using RAM as a working area. The storage unit 11 may be configured as an HDD (Hard Disk Drive) or SSD (Solid State Drive), etc. Furthermore, the storage unit 11 does not necessarily have to be provided in the information processing device 1. In this case, for example, the storage unit 11 may be provided on an external server. Such an external server may be a physical server or a cloud server. When the storage unit 11 is provided on an external server, the information processing device 1 can access the storage unit 11 via a communication network such as a wireless LAN (Local Area Network). Thus, this embodiment includes both cases in which the information processing device 1 is physically connected to the storage unit 11 and cases in which the information processing device 1 is not physically connected to the storage unit 11.

[0032] The input unit 13 is typically a keyboard or mouse, but is not limited to these; any configuration capable of inputting various types of data is acceptable. For example, the input unit 13 may be a microphone or a touch panel. The output unit 14 is typically a display, but is not limited to this; any configuration capable of outputting various types of data is acceptable. For example, the output unit 14 may be a speaker or a warning light.

[0033] The training data 111 stored in the memory unit 11 will now be described. The training data 111 is labeled data used in machine learning. Machine learning is a method that learns the features contained in input data and generates a "model" that predicts the result corresponding to newly input data. The quality prediction model 211, which will be described later, is a trained model generated by machine learning.

[0034] Training data 111 is generated by associating input data with correct answer data and stored in the memory unit 11. Examples of "input data" here include data showing the blending ratio of each polymer, data showing the physical properties of each polymer, and data showing the operating conditions of the extruder 90.

[0035] (Composition ratio of each polymer) "The blending ratio of each polymer" refers to the ratio in which each type of polymer should be blended when manufacturing pellets according to the grade. As mentioned above, such blending ratios are determined by the standard formulation. However, as already stated, due to differences in physical properties between lots, the desired quality may not be obtained even if each polymer is blended according to the standard formulation. Therefore, it is necessary to adjust the blending ratio according to the lot, i.e., according to the physical properties. In this embodiment, the blending ratio is the subject of optimization calculations.

[0036] (Physical properties of each polymer) The physical properties included in "physical property conditions" are not particularly limited, but may include, for example, molecular weight data, thermal stability, thermal decomposition temperature, and melt flow rate (MFR) of each polymer to be blended. Molecular weight data may include number-average molecular weight (Mn), weight-average molecular weight (Mw), molecular weight distribution (Mw / Mn), etc. The melt flow rate is a well-known indicator for evaluating the fluidity of resins. Furthermore, "thermal stability" as used here refers to the degree of molecular weight reduction due to processing at a specified temperature and pressure for a specified time, and the unit used is %.

[0037] Furthermore, the "physical property conditions" may include the content of repeating units of a predetermined functional group possessed by each polymer to be blended. The "physical property conditions" only need to include at least one of these data (physical property values ​​that show physical properties as quantitative values). Of course, the "physical property conditions" may include all of these data.

[0038] Physical properties are parameters that affect the quality of pellets, and even with the same type of polymer, the values ​​can differ from lot to lot.

[0039] (Operating conditions for extruder 90) The "operating conditions of the extruder 90" may include "various setting values ​​set for the extruder 90" and / or "measured values ​​which are data actually measured for said setting values." Examples of the various operating conditions set for the extruder 90 include the temperature at the tip of the extruder 90, the pressure at the tip of the extruder 90, the polymer feeding rate into the extruder 90, and the screw rotation speed of the extruder 90. These values ​​are measured by temperature sensors, pressure sensors, speed sensors, etc., installed in the extruder 90 and are treated as measured values.

[0040] Next, an example of "correct data" will be explained. Correct data is data that indicates the quality of pellets produced using "data showing the blending ratio of each polymer," "data showing the physical properties of each polymer," and "data showing the operating conditions of the extruder 90" as input data. The "quality of the pellets" is not particularly limited, but for example, it may be defined by the melt flow rate.

[0041] Training data 111 is generated by associating the input data and correct answer data described above, and is stored in the storage unit 11.

[0042] The training data acquisition unit 101 acquires training data 111 by referring to the storage unit 11. The training data acquisition unit 101 outputs the acquired training data 111 to the learning unit 102.

[0043] The learning unit 102 generates a quality prediction model 211 for predicting pellet quality from prediction data by machine learning using the training data 111 acquired from the training data acquisition unit 101. The quality prediction model 211 is a computational model with "blending ratio of each polymer," "physical property conditions of each polymer," and "operating conditions of the extruder 90" as explanatory variables, and "pellet quality" as the objective variable. The machine learning algorithm is not particularly limited. For example, the learning unit 102 may generate the quality prediction model 211 using a neural network, or it may generate the quality prediction model 211 using support vector regression, random forest, etc.

[0044] The quality prediction model 211 generated by the learning unit 102 is transmitted to the information processing device 2 and stored in the storage unit 21 of the information processing device 2. Alternatively, the quality prediction model 211 generated by the learning unit 102 may be stored in the storage unit 11.

[0045] Next, the information processing device 2 will be described. The information processing device 2 includes a control unit 20 that controls all parts of the information processing device 2, and a storage unit 21 that stores various data used by the information processing device 2. The information processing device 2 also includes a communication unit 22 for the information processing device 2 to communicate with other devices, an input unit 23 that receives input of various data to the information processing device 2, and an output unit 24 for the information processing device 2 to output various data. The control unit 20 also includes a identification unit 201, a prediction data acquisition unit 202, a quality prediction unit 203, an optimization calculation unit 204, an alignment unit 205, a planning unit 206, and an output control unit 207. The storage unit 21 stores the quality prediction model 211 generated by the information processing device 1.

[0046] The information processing device 2 may also be configured as a general-purpose computer, similar to the information processing device 1. When the information processing device 2 is configured as a general-purpose computer, the control unit 20, storage unit 21, communication unit 22, input unit 23, and output unit 24 may have the same configuration as the control unit 10, storage unit 11, communication unit 12, input unit 13, and output unit 14 of the information processing device 1. That is, the storage unit 21 may also be provided on an external server instead of being provided on the information processing device 2. This embodiment includes both cases where the information processing device 2 is physically connected to the storage unit 21 and cases where the information processing device 2 is not physically connected to the storage unit 21.

[0047] Before actually manufacturing pellets, the identification unit 201 identifies the polymers (multiple polymers) to be used in the manufacture of the target pellets as information necessary to formulate a production plan for the pellets to be manufactured. Hereinafter, the pellets to be manufactured may be referred to as "pellets P". For example, the polymers used in the manufacture of "pellets P" will be "polymer X", "polymer Y", and "polymer Z". That is, pellet P described as an example is a molded product manufactured by blending three polymers (polymers X, Y, and Z). The method of identification is not particularly limited, but for example, the identification unit 201 may identify polypolymers X, Y, and Z as the polymers necessary for the manufacture of pellet P by referring to a standard formula stored in the memory unit 21. Note that the operator may also specify the pellets to be manufactured. That is, the identification unit 201 may identify the polymers necessary for the manufacture of the pellets specified by the operator.

[0048] The prediction data acquisition unit 202 acquires input data to be input into the quality prediction model 211. The input data referred to here corresponds to the "prediction data" described in Figure 1. Examples of input data include the "data indicating the blending ratio of each polymer," the "data indicating the physical properties of each polymer," and the "data indicating the operating conditions of the extruder 90." Each polymer is a polymer identified by the identification unit 201 (for example, polymers X, Y, and Z). There are no particular limitations on how this data is acquired, but regarding the blending ratio, the prediction data acquisition unit 202 may acquire it by referring to a standard formula recorded in the storage unit 21. Regarding the physical properties, the prediction data acquisition unit 202 may acquire it by referring to measurement results measured for each lot. Such measurement results may be recorded in the storage unit 21. Regarding the operating conditions, the prediction data acquisition unit 202 may acquire setting values ​​entered by the operator via the input unit 23 or setting values ​​set in the PLC (Programmable Logic Controller) as operating conditions. The prediction data acquisition unit 202 outputs the acquired data to the quality prediction unit 203. The data acquired by the prediction data acquisition unit 202 is data used to predict the quality of the pellets.

[0049] The quality prediction unit 203 uses a quality prediction model 211, generated by learning the relationship between the blending ratio of each polymer, the physical properties of each polymer, the operating conditions of the extruder 90, and the quality of the pellets, to predict the quality of the pellets from the data acquired by the prediction data acquisition unit 202. Specifically, the quality prediction unit 203 can predict the quality of the pellets by inputting the blending ratio, physical properties, and operating conditions acquired by the prediction data acquisition unit 202 into the quality prediction model 211.

[0050] The quality prediction unit 203 predicts the quality of pellets for all combinations of polymers (polymers X, Y, and Z) for each lot. For example, let's assume that there are two lots of polymer X, three lots of polymer Y, and four lots of polymer Z. In this case, there are 2 × 3 × 4 = 24 possible combinations of polymers for each lot. The quality prediction unit 203 predicts the quality of pellets for all of these 24 combinations. The pellet quality for each of the 24 combinations predicted by the quality prediction unit 203 is output to the optimization calculation unit 204.

[0051] The optimization calculation unit 204 optimizes the blending ratio based on the quality predicted by the quality prediction unit 203 (24 in total). Specifically, the optimization calculation unit 204 optimizes the blending ratio so that the predicted quality falls within the target range for all 24 combinations. In other words, in the case of the 24 combinations shown as an example, there will be 24 possible optimized blending ratios. Any well-known optimization method can be used for the optimization calculation. Well-known optimization methods include genetic algorithms, grid search, random search, and Bayesian optimization. The optimization calculation unit 204 can search for a blending ratio that yields the desired quality by repeatedly performing the optimization calculation. The calculation results from the optimization calculation unit 204 are output to the sorting unit 205.

[0052] The alignment unit 205 arranges or rearranges the combinations so that the variation in the mixing ratios of all combinations, optimized by the optimization calculation unit 204, is minimized. The details of this rearrangement will be explained in detail in Figure 4 below.

[0053] The planning unit 206 formulates a pellet production plan according to the blending ratios of all combinations. Specifically, the planning unit 206 calculates the amount of pellets that can be produced for each combination in the order of the combinations arranged by the alignment unit 205. The planning unit 206 determines that the combinations up to the combination whose production volume meets predetermined conditions will be used in the production plan. The planning unit 206 outputs information regarding the formulated production plan to the output control unit 207.

[0054] The output control unit 207 causes the output unit 24 to output information related to the production plan formulated by the planning unit 206. The mode of output is arbitrary; for example, the output control unit 207 may output information related to the production plan in at least one of the following modes: display output, audio output, and printed output. The device that outputs information related to the production plan may also be an external device to the information processing device 2. With such output, the operator can grasp the optimized production plan. When the operator inputs the information necessary for the optimized production plan into the PLC, pellet manufacturing begins. According to this embodiment, when a lot is switched during manufacturing, the optimized blending ratio is automatically applied to the new lot, eliminating the need for the operator to monitor the lot switch and adjust the blending ratio. Furthermore, since the blending ratio for each combination is optimized in advance, there is no need to perform quality evaluation again when a lot is switched. Thus, according to this embodiment, the work of adjusting the blending ratio while monitoring the changeover between lots becomes unnecessary, and there is no need to stop production at the time of lot changeover. As a result, it becomes possible to continuously produce pellets with the desired quality, and productivity is improved.

[0055] (An example of data flow when formulating a production plan) Next, referring to Figure 3, we will explain an example of the data flow when formulating a production plan, that is, before the actual production of pellets.

[0056] As shown in Figure 3, the quality prediction model 211 is inputted with "data showing the blending ratio of each polymer" shown in block 40, "data showing the physical property conditions of each polymer" shown in block 41, and "data showing the operating conditions of the extruder 90" shown in block 42.

[0057] As shown in Block 43, the quality prediction model 211 predicts the quality of the pellets based on the blending ratio, physical properties, and operating conditions. The prediction result is output, for example, as the melt flow rate. The evaluation of the predicted quality is determined to see if it falls within a preset target range (see Block 44). If it is determined that the predicted quality does not fall within the target range, the optimization calculation unit 204 optimizes the blending ratio so that the quality falls within the target range. An example of the "target range" here is the range of specifications required for each grade of pellets, which is preset. The optimization calculation unit 204 optimizes the blending ratio for all combinations of polymers for each lot (24 combinations in the example above). Then, the planning unit 206 formulates a pellet production plan according to the blending ratios of all combinations (see Block 45).

[0058] Thus, the blending ratio, physical properties, and operating conditions are explanatory variables of the quality prediction model 211, and the pellet quality is the dependent variable of the quality prediction model 211. Note that Figure 3 illustrates a configuration in which the quality prediction model 211 includes three data points—blending ratio, physical properties, and operating conditions—as explanatory variables, but it is not limited to this configuration. The dependent variable of the quality prediction model 211 only needs to include the blending ratio; physical properties and operating conditions do not necessarily need to be included as dependent variables.

[0059] (Combination sorting) Next, with reference to Figure 4, the sorting of combinations performed by the sorting unit 205 will be explained. As described above, the sorting unit 205 sorts or rearranges the combinations so that the variation in the blending ratios of all combinations, which have been optimized by the optimization calculation unit 204, is minimized. Combinations A, B, and C shown in Figure 4 represent the types of polymers used in the pellets to be manufactured (pellets P) and their blending ratios. As described above, the types of polymers used in pellets P are polymers X, Y, and Z, which are illustrated in Figure 4. The numerical values ​​shown in Figure 4 represent the optimized blending ratios. Specifically, the optimized blending ratio in combination A is polymer X:polymer Y:polymer Z = 30:50:20. The optimized blending ratio in combination B is polymer X:polymer Y:polymer Z = 10:80:10. The optimized blending ratio in combination C is polymer X:polymer Y:polymer Z = 20:40:40. Even if the type of polymer used is the same, the reason for the different blending ratios is, as mentioned above, that each polymer, exemplified as a biodegradable polymer (especially polyhydroxyalkanoates), relies on a biochemical production process, resulting in differences in physical properties between batches even for polymers produced in the same manner. Although not shown in the diagram, in combination A and combination B, combination A and combination C, and combination B and combination C, at least one of polymers X, Y, and Z is from a different batch.

[0060] Assuming that the production of pellet P is started in the order of combinations A, B, and C, as shown in Figure 4, for combinations A to C optimized by the optimization calculation unit 204, in this case, pellet P is initially produced with the blending ratio of combination A. When the remaining amount of any of the polymer lots X, Y, and Z runs out, the lot of the target polymer is switched to another lot. The blending ratio after the switch is shown in combination B. As production progresses, when the remaining amount of any of the polymer lots X, Y, and Z runs out again, the lot of the target polymer is switched to another lot. The blending ratio after the switch is shown in combination C.

[0061] Here, we focus on the magnitude of the change in the mixing ratio. When switching from combination A to combination B, the mixing ratio of polymer X changes from 30 to 10. The mixing ratio of polymer Y changes from 50 to 80. The mixing ratio of polymer Z changes from 20 to 10. In other words, the magnitude of the change in the mixing ratio of polymer X is 20. The magnitude of the change in the mixing ratio of polymer Y is 30. The magnitude of the change in the mixing ratio of polymer Z is 10.

[0062] When switching from combination B to combination C, the mixing ratio of polymer X changes from 10 to 20. The mixing ratio of polymer Y changes from 80 to 40. The mixing ratio of polymer Z changes from 10 to 40. In other words, the magnitude of the change in the mixing ratio of polymer X is 10. The magnitude of the change in the mixing ratio of polymer Y is 40. The magnitude of the change in the mixing ratio of polymer Z is 30.

[0063] Thus, the largest variation in the blending ratio occurs when switching from combination B to combination C, at which point polymer Y is "40". Large variations in the blending ratio may adversely affect quality. Therefore, it is preferable for the variation in the blending ratio to be small. Accordingly, in this embodiment, the alignment unit 205 is configured to rearrange combinations A to C in a way that minimizes the variation in the blending ratio. As shown in Figure 4, there are six candidate arrangements for combinations A to C: "ABC", "ACB", "BAC", "BCA", "CBA", and "CAB".

[0064] Of the six candidates, the alignment unit 205 excludes the candidates containing "BC" or "CB" because, as mentioned above, they contain "40," which represents the largest variation in the blending ratio. The remaining candidates, "BAC" or "CAB," can eliminate "40," thus suppressing the magnitude of the blending ratio variation. There is no particular limitation on which of "BAC" or "CAB" to adopt; either may be used. The alignment unit 205 may, for example, adopt a rule prioritizing alphabetical order if the combination names include letters. In this case, "BAC" would be adopted. Figure 4 illustrates the case where "BAC" is adopted. As shown in Figure 4, by rearranging the order of "ABC" (manufacturing order) to "BAC," even the value with the largest variation in the blending ratio remains at "30." Therefore, manufacturing using this rearranged production plan can suppress the magnitude of the blending ratio variation, thereby suppressing quality variation and enabling the production of pellets with stable quality. Note that, in addition to letters, numbers may be used in the combination names. Thus, when the alignment unit 205 arranges the combinations in such a way that the variation in the mixing ratio of the combinations is small, and multiple candidates arise, it may use predetermined information (alphabetical information, numerical information, etc.) to determine the order to be used in the production plan from among the multiple candidates.

[0065] As another example, the alignment unit 205 may select a candidate lot from "BAC" or "CAB" that can be used consecutively due to the remaining quantity. Such continuous use increases the likelihood that the lot can be used until the remaining quantity is depleted. This improves storage operations, as the lot can be used until the remaining quantity is depleted, whereas previously, intermittent use resulted in lots with low remaining quantity taking up storage space.

[0066] (Lot changes during production planning and actual manufacturing) Next, with reference to Figures 5 and 6, an example of lot changeover in production planning and actual manufacturing will be explained. Combination DGM shown in Figure 5 indicates that lot D is used for polymer X, lot G is used for polymer Y, and lot M is used for polymer Z. Lots D, G, and M are illustrated in Figure 6. Combination EGM indicates that lot E is used for polymer X, lot G is used for polymer Y, and lot M is used for polymer Z. Combination EHM indicates that lot E is used for polymer X, lot H is used for polymer Y, and lot M is used for polymer Z.

[0067] Pellet P is manufactured in the order of DGM, EGM, and EHM. This order is determined by the alignment unit 205. The planning unit 206 calculates the amount of pellet P that can be produced for the target combination (not shown) in the order of the combinations arranged by the alignment unit 205. The amount of polymer required for the production amount of combination DGM is exemplified as "60". Based on this "60", the amount of each polymer to be fed into each hopper is determined according to the optimized blending ratio. In combination DGM, the amount of polymer X fed into hopper 92a is "30". The amount of polymer Y fed into hopper 92b is "25". The amount of polymer Z fed into hopper 92c is "5". The same applies to combinations EGM and EHM.

[0068] The planning unit 206 repeatedly performs these calculations until the production volume meets the target volume, and determines the combinations that meet the target volume as the combinations to be used in the production plan.

[0069] The devised production plan may be entered into the PLC by the operator. The PLC starts manufacturing pellets P according to the entered production plan. An example of actual manufacturing is shown in Figure 6. As shown in Figure 6, the PLC, following the initial combination DGM, puts "30" units of polymer X from lot D into hopper 92a, "25" units of polymer Y from lot G into hopper 92b, and "5" units of polymer Z from lot M into hopper 92c. When the remaining amount in lot D is depleted, the lot of polymer X switches from D to E, that is, the combination switches from DGM to EGM. In the example shown in Figure 6, this is the first lot switch.

[0070] The change in mixing ratio due to lot changes is automatically applied by the PLC. As a result, in the EGM combination, the PLC puts "65" units of polymer X from lot E into hopper 92a, "46" units of polymer Y from lot G into hopper 92b, and "20" units of polymer Z from lot M into hopper 92c. When the remaining amount in lot G is depleted, the lot of polymer Y switches from G to H, meaning the combination switches from EGM to EHM. In the example shown in Figure 6, this is the second lot change.

[0071] Similar to the first switchover, the PLC automatically applies the change in the blending ratio during the second switchover. This means the PLC automatically loads 152 units of polymer X from lot E into hopper 92a, 125 units of polymer Y from lot H into hopper 92b, and 27 units of polymer Z from lot M into hopper 92c for the EHM combination. Until the pellet P production reaches the target amount, the lot switchover and blending ratio change are automatically applied each time a lot is empty. With this configuration, when a lot is switched, the optimized blending ratio is automatically applied to the new lot, eliminating the need for the operator to monitor the lot switchover and adjust the blending ratio. Furthermore, since the blending ratio for each combination is pre-optimized, there is no need to re-evaluate the quality when a lot is switched. Thus, according to this embodiment, the work of adjusting the blending ratio while monitoring lot changes is eliminated, and there is no need to stop production at the time of lot change. As a result, it becomes possible to continuously produce pellets with the desired quality, improving productivity. Furthermore, since the manufacturing order (combination order) is arranged to minimize fluctuations in the blending ratio, the magnitude of fluctuations in the blending ratio during manufacturing can be suppressed, and quality fluctuations can be suppressed. This makes it possible to continuously produce pellets with stable quality.

[0072] Furthermore, as shown in lot M of Figure 6, there may be polymers for which there is only one lot during manufacturing. Therefore, within each polymer lot, there may be polymers for which the lot number does not change.

[0073] (Process flow) Next, with reference to Figure 7, the flow of processing performed by the information processing device 2 will be explained. Figure 7 is a flowchart showing an example of processing performed by the information processing device 2.

[0074] In step S101, the identification unit 201 of the information processing device 2 identifies the polymers to be used in the manufacture of the target pellets as information necessary to formulate a production plan for the pellets to be manufactured, before actually manufacturing the pellets. As mentioned above, if the pellets to be manufactured are "pellets P", the identified polymers will be polymers X, Y, and Z. An example of the identification method has already been explained, so the explanation will be omitted here.

[0075] In step S102, the prediction data acquisition unit 202 of the information processing device 2 acquires prediction data, which is input data to be input to the quality prediction model 211. Specifically, the prediction data acquisition unit 202 acquires data indicating the blending ratio of each polymer identified in the processing of step S101, data indicating the physical property conditions of each polymer, and data indicating the operating conditions of the extruder 90 as prediction data.

[0076] In step S103, the quality prediction unit 203 of the information processing device 2 uses a quality prediction model 211, which was generated by learning the relationship between "the blending ratio of each polymer," "the physical properties of each polymer," and "the operating conditions of the extruder 90," and "the quality of the pellets," to predict the quality of the pellets from the data acquired by the prediction data acquisition unit 202.

[0077] The process proceeds to step S104, where it is determined whether the quality predicted in step S103 (e.g., melt flow rate) meets the termination condition. If it is determined that the quality meets the termination condition (YES in step S104), the process proceeds to step S106. On the other hand, if it is determined that the quality does not meet the termination condition (NO in step S104), the process proceeds to step S105. The termination condition can be set arbitrarily. For example, the termination condition may be set to the melt flow rate falling within the target range.

[0078] In step S105, the optimization calculation unit 204 of the information processing device 2 updates the blending ratio parameters, and then the process returns to step S103. The method for updating the blending ratio parameters can be predetermined. The processes from steps S103 to S105 are repeatedly executed until the termination condition is met (determined as YES in step S104). Furthermore, the processes from steps S103 to S105 are executed for all combinations of each polymer for each lot (24 combinations in the example above).

[0079] In step S106, the alignment unit 205 of the information processing device 2 arranges or rearranges the combinations so that the variation in the mixing ratio of all optimized combinations is small (see Figure 4).

[0080] In step S107, the planning unit 206 of the information processing device 2 formulates a pellet production plan according to the blending ratios of all combinations. Specifically, the planning unit 206 calculates the amount of pellets that can be produced for each combination in the order of the combinations listed in the process of step S106. The planning unit 206 determines that the combinations up to the combinations whose production volume satisfies predetermined conditions will be used in the production plan.

[0081] In step S108, the output control unit 207 of the information processing device 2 outputs information regarding the production plan formulated in step S107 to the output unit 24. This output allows the operator to understand the optimized production plan. The operator inputs the information necessary for the optimized production plan into the PLC, and pellet production begins.

[0082] As described above, the information processing method according to this embodiment includes: an identification step (S101) in which each polymer is fed into each hopper of an extruder 90 used in the manufacture of a molded product manufactured by blending multiple polymers; a quality prediction step (S103) in which the quality of the molded product is the objective variable and the blending ratio when blending the multiple polymers identified in the identification step is included as at least one explanatory variable; and an optimization calculation step (S105) in which the blending ratio is optimized so that the quality of the molded product predicted in the quality prediction step falls within a predetermined target range. Of the polymers fed into each hopper, at least one polymer is prepared in multiple lots. In the quality prediction step, the quality is predicted for all combinations of each polymer for each lot. In the optimization calculation step, the blending ratio is optimized so that the predicted quality for all combinations falls within the target range. The information processing method according to this embodiment further includes an alignment step (S106) in which combinations are arranged in such a way that the variation in the blending ratio of all combinations optimized in the optimization calculation step is minimized, and a planning step (S107) in which a production plan for molded products is formulated. In the planning step, the production volume of molded products that can be produced with the target combinations is calculated in the order of the combinations arranged in the alignment step, and combinations up to the combination whose production volume satisfies predetermined conditions are determined to be used in the production plan.

[0083] Note that the processing flow shown in the flowchart in Figure 7 is just one example, and steps may be deleted, new steps added, or the processing order rearranged as long as it does not deviate from the main point.

[0084] (Effects and Benefits) As described above, the following effects and advantages can be obtained according to this embodiment.

[0085] The information processing device 2 includes: an identification unit 201 that identifies each polymer to be fed into each hopper (hopper 92a, 92b, 92c, ...) of an extruder 90 used to manufacture molded products by blending multiple polymers; a quality prediction unit 203 that predicts the quality of the molded product using a quality prediction model 211 that includes the blending ratio of the multiple polymers identified by the identification unit 201 as at least one of the explanatory variables, with the quality of the molded product as the objective variable; and an optimization calculation unit 204 that optimizes the blending ratio so that the quality of the molded product predicted by the quality prediction unit 203 falls within a preset target range. Of the polymers fed into each hopper, at least one polymer is prepared in multiple lots. The quality prediction unit 203 predicts the quality for all combinations of each polymer for each lot. The optimization calculation unit 204 optimizes the blending ratio so that the predicted quality for all combinations falls within the target range. The information processing device 2 further includes an alignment unit 205 that arranges combinations so that the variation in the mixing ratio of all combinations is small, as optimized by the optimization calculation unit 204, and a planning unit 206 that formulates a production plan for molded products. The planning unit 206 calculates the production volume of molded products that can be produced with the target combinations in the order of the combinations arranged by the alignment unit 205, and determines the combinations to be used in the production plan up to the combinations whose production volume satisfies predetermined conditions.

[0086] As mentioned above, each polymer, exemplified as a biodegradable polymer (especially polyhydroxyalkanoates), relies on a biochemical production process, resulting in differences in physical properties between batches even when polymers are produced similarly. Therefore, even when each polymer is blended according to a standard formulation, the desired quality may not be achieved, meaning the quality may deviate from specifications. To resolve this problem, one could adjust the blending ratio while monitoring the changeover between batches, but as already stated, this is practically difficult. Therefore, in order to guarantee pellet quality, production must be stopped at the time of batch changeover, leading to a decrease in productivity. In this respect, using the production plan formulated with the above configuration, when a batch changes, the optimized blending ratio is automatically applied to the new batch, eliminating the need for operators to monitor the batch changeover and adjust the blending ratio.

[0087] Furthermore, since the mixing ratios for each combination are pre-optimized, there is no need to re-evaluate the quality when a new batch is produced. Thus, with the above configuration, the work of adjusting the mixing ratio while monitoring batch changes is unnecessary, and there is no need to stop production when a batch changes, making it possible to continuously produce pellets of the desired quality and improving productivity. In addition, with the above configuration, the manufacturing order (combination order) is arranged to minimize fluctuations in the mixing ratio, so the magnitude of fluctuations in the mixing ratio during manufacturing can be suppressed, and quality fluctuations can be suppressed. This makes it possible to continuously produce pellets of stable quality.

[0088] Furthermore, conventionally, lots that were used intermittently and had low remaining quantities became difficult to use and took up storage space. However, with the above configuration, lots with low remaining quantities can be used until they are completely depleted, according to the mixing ratio and required amount (see Figure 5), thus contributing to improved storage operations.

[0089] Furthermore, if multiple candidates arise when the alignment unit 205 arranges the combinations in a way that minimizes fluctuations in the mixing ratio of the combinations, it may use predetermined information (e.g., alphabetical information, numerical information, etc.) to determine the order to be used in the production plan from among the multiple candidates.

[0090] According to the above configuration, production plans can be formulated efficiently.

[0091] Furthermore, at least one of the multiple polymers may be the biodegradable polymer described above. The biodegradable polymer may be a polyhydroxyalkanoate in particular. In this case, the biodegradable polymer is a polymer derived from microorganisms, in which microorganisms take up a substrate (e.g., sugars, fatty acids, etc.) and synthesize the biodegradable polymer through metabolic processes. The synthesized polymer is extracted from the microorganisms and purified by removing impurities. A biodegradable polymer is obtained through such a biochemical process. Therefore, if the polymer is a polyhydroxyalkanoate, it can be said that the polymer is a polymer extracted from microorganisms. Note that all of the multiple polymers described in this embodiment may be polymers extracted from microorganisms. Also, the type of one or more polymers in this embodiment is not limited as long as they are polymers extracted from microorganisms, and therefore is not limited to polyhydroxyalkanoates.

[0092] Polyhydroxyalkanoates have excellent biodegradability and can help solve environmental problems caused by discarded plastics. Particularly preferred is poly(3-hydroxyalkanoate) (hereinafter sometimes referred to as P3HA). More specifically, P3HA preferably contains 3-hydroxybutyrate (3HB) units. P3HA containing 3HB units is preferably selected from the group consisting of poly(3-hydroxybutyrate) (P3HB), poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (P3HB3HV), poly(3-hydroxybutyrate-co-3-hydroxyhexanoate) (P3HB3HH), poly(3-hydroxybutyrate-co-3-hydroxyvalerate-co-3-hydroxyhexanoate) (P3HB3HV3HH), poly(3-hydroxybutyrate-co-4-hydroxybutyrate) (P3HB4HB), poly(3-hydroxybutyrate-co-3-hydroxyoctanoate), and poly(3-hydroxybutyrate-co-3-hydroxydecanoate). P3HA may contain only one type or two or more types.

[0093] Furthermore, the explanatory variables may also include physical property conditions related to physical property values ​​that show the physical properties of the polymer as quantitative values, and the operating conditions of the extruder 90.

[0094] As shown in the configuration above, the accuracy of quality prediction is improved by adding physical properties and operating conditions that affect the quality to the objective variables of the quality prediction model 211 for predicting pellet quality.

[0095] [Other Embodiments] The entity executing each process described in the above embodiments is arbitrary and not limited to the examples above. In other words, the same functions as information processing devices 1 and 2 can be realized by multiple information processing devices that can communicate with each other. For example, the processing of each step shown in Figure 7 may be divided and executed by multiple information processing devices. Furthermore, an information processing device that combines the functions of information processing device 1 and information processing device 2 is also included in the scope of this disclosure.

[0096] Furthermore, the method for manufacturing molded articles (e.g., pellets) described in the above-described embodiment may include a step of manufacturing the molded articles in accordance with the production plan formulated by the information processing device 2.

[0097] Furthermore, in the above-described embodiment, it was explained that "the quality prediction unit 203 predicts the quality for all combinations of polymers for each lot," but this disclosure is not limited to this, and predicting the quality for "all" combinations is not mandatory. Similarly, in the above-described embodiment, it was explained that "the optimization calculation unit 204 optimizes the blending ratio so that the predicted quality for all combinations falls within the target range," but this configuration also does not need to address "all" combinations. Likewise, in the above-described embodiment, it was explained that "the alignment unit 205 arranges the combinations so that the variation in the blending ratio of all optimized combinations is small," but this configuration also does not need to address "all" combinations.

[0098] This disclosure is also applicable to cases where, in the case of a polymer, multiple lots exist, and one or more lots (e.g., Y lots, where X > Y) are used from among multiple lots (e.g., X lots).

[0099] Furthermore, the lot used for the combination may be a pre-prepared lot. In other words, this disclosure is also applicable to each polymer combination for each pre-prepared lot.

[0100] [Examples of implementation using software] The functions of the information processing devices 1 and 2 (hereinafter simply referred to as "devices") are programs (information processing programs) that cause the devices to function as computers, and these programs can be implemented by programs that cause each control block of the devices (especially each part included in control unit 10 and control unit 20) to function as a computer.

[0101] In this case, the above-mentioned device comprises a computer having at least one device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. The computer executes the program, thereby realizing each of the functions described in each embodiment.

[0102] The program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0103] Furthermore, some or all of the functions of each control block can be implemented by logic circuits. For example, an integrated circuit in which logic circuits functioning as each control block are formed is also included in the scope of this disclosure. In addition, it is also possible to implement the functions of each control block using, for example, a quantum computer.

[0104] Furthermore, each process described in each embodiment may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the above-mentioned device, or it may operate on another device (for example, an edge computer or a cloud server).

[0105] This disclosure is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this disclosure. [Explanation of symbols]

[0106] 100 Information Processing Systems 1, 2 Information Processing Devices 10, 20 Control Unit 101 Training Data Acquisition Unit 102 Learning Department 201 Specific section 202 Data acquisition unit for prediction 203 Quality Forecasting Department 204 Optimization Calculation Unit 205 Alignment section 206 Planning Department 207 Output Control Unit 211 Quality Prediction Model 90 Extruder

Claims

1. An identification unit that identifies each polymer fed into each hopper of an extruder used in the manufacture of molded products made by blending multiple polymers, A quality prediction unit predicts the quality of the molded product using a quality prediction model in which the quality of the molded product is the objective variable and the blending ratio of the multiple polymers identified by the identification unit is included as at least one of the explanatory variables. The system includes an optimization calculation unit that optimizes the blending ratio so that the quality of the molded product predicted by the quality prediction unit falls within a preset target range, Of the polymers that are fed into each of the aforementioned hoppers, at least one polymer is prepared in multiple lots. The quality prediction unit predicts the quality for each polymer combination for each lot, The optimization calculation unit optimizes the blending ratio so that the predicted quality for the combination falls within the target range. moreover, An alignment unit that arranges the combinations so that the variation in the mixing ratio of the combinations optimized by the optimization calculation unit becomes small, The system comprises a planning unit for formulating a production plan for the molded products, The aforementioned planning department, The production volume of the molded product that can be produced with the target combination is calculated in the order of the combinations arranged by the alignment unit. The combinations up to the point where the aforementioned production volume satisfies the predetermined conditions are determined to be used in the production plan. Information processing device.

2. The quality prediction unit predicts the quality for each polymer combination for each prepared lot. The information processing apparatus according to claim 1.

3. The quality prediction unit predicts the quality for all combinations of polymers for each lot, The optimization calculation unit optimizes the blending ratio so that the predicted quality for all combinations falls within the target range. The alignment unit arranges the combinations so that the variation in the blending ratio of all combinations, optimized by the optimization calculation unit, is minimized. The information processing apparatus according to claim 1.

4. When the alignment unit arranges the combinations in such a way that the variation in the mixing ratio of the combinations is small, if multiple candidates are generated, it uses predetermined information to determine the order in which to be used in the production plan from among the multiple candidates. The information processing apparatus according to claim 1.

5. At least one of the aforementioned plurality of polymers is a polymer extracted from a microorganism. The information processing apparatus according to any one of claims 1 to 4.

6. The explanatory variables further include property conditions relating to property values ​​that show the physical properties of the polymer as quantitative values, and the operating conditions of the extruder. The information processing apparatus according to any one of claims 1 to 4.

7. An information processing method performed by one or more information processing devices, A process that identifies each polymer to be fed into each hopper of an extruder used in the manufacture of molded products made by blending multiple polymers, A quality prediction step in which the quality of the molded product is used as the objective variable, and the quality of the molded product is predicted using a quality prediction model that includes, at least, the blending ratio of the multiple polymers identified in the specific step as an explanatory variable, The optimization calculation step includes optimizing the compounding ratio so that the quality of the molded product predicted in the quality prediction step falls within a predetermined target range, Of the polymers that are fed into each of the aforementioned hoppers, at least one polymer is prepared in multiple lots. In the quality prediction step, the quality is predicted for each polymer combination for each lot. In the optimization calculation step, the blending ratio is optimized so that the predicted quality for the combination falls within the target range. moreover, A sorting step in which the combinations are arranged such that the variation in the mixing ratio of the combinations optimized in the optimization calculation step is reduced, This includes a planning step of formulating a production plan for the molded product, In the aforementioned planning step, In the order of the combinations arranged in the aforementioned alignment step, the production volume of the molded product that can be produced with the target combination is calculated. The combinations up to the point where the aforementioned production volume satisfies the predetermined conditions are determined to be used in the production plan. Information processing methods.

8. An information processing program for causing a computer to function as an information processing device according to claim 1, wherein the computer functions as the identification unit, the quality prediction unit, the optimization calculation unit, the alignment unit, and the planning unit.

9. The process includes manufacturing the molded product in accordance with the production plan formulated by the information processing device described in claim 1, A method for manufacturing molded products.

Images