Trained model generation method, composition condition setting method, trained model generation program, composition condition setting program, training device, composition condition setting device, method for manufacturing polyester resin film, system for manufacturing polyester resin film, and polyester resin film

Abstract

To provide a trained model generation method capable of efficiently setting a composition condition of a resin film, a composition condition setting method, a trained model generation program, a composition condition setting program, a training device, a composition condition setting device, a method for manufacturing a resin film, a device for manufacturing a resin film and a resin film.SOLUTION: A trained model generation method according to the present invention causes a computer to generate a trained model by learning using learning data with composition conditions including the physical properties and composition ratio of a thermoplastic resin constituting a resin film as explanatory variables and the properties of the resin film as objective variables.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a trained model generating method, a blending condition setting method, a trained model generating program, a blending condition setting program, a learning device, a blending condition setting device, a resin film manufacturing method, a resin film manufacturing system, and a resin film. [Background technology]

[0002] The resin film is a film that is excellent in heat resistance, flame retardancy, chemical resistance, electrical insulation, moist heat resistance, mechanical strength, dimensional stability, etc. Such a resin film is produced, for example, by biaxial stretching in which resin chips are melted, stretched in one direction, and then stretched in a direction perpendicular to the one direction (see, for example, Patent Documents 1 and 2). This biaxial stretching produces a film with high strength in the longitudinal and transverse directions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2001-287266 A [Patent Document 2] JP 2011-148186 A Summary of the Invention [Problem to be solved by the invention]

[0004] In order to obtain a resin film with the desired physical properties, the above-mentioned resin films have been designed by engineers through extensive trial and error, with the blending ratios and other blending conditions being designed, and there has been a demand for making such design more efficient.

[0005] The present invention has been made in consideration of the above, and aims to provide a trained model generation method, a blending condition setting method, a trained model generation program, a blending condition setting program, a learning device, a blending condition setting device, a resin film manufacturing method, a resin film manufacturing system, and a resin film, which can efficiently set blending conditions for a resin film. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the trained model generation method of the present invention generates a trained model by having a computer learn using training data in which the blending conditions, including the physical properties and blending ratio of the thermoplastic resin that constitutes a resin film, are used as explanatory variables, and the physical properties of the resin film are used as objective variables.

[0007] In addition, in the trained model generation method according to the present invention, in the above invention, the physical properties of the thermoplastic resin include the intrinsic viscosity and solution haze of the thermoplastic resin.

[0008] In addition, in the trained model generation method of the present invention, in the above invention, the physical properties of the resin film include the intrinsic viscosity and film haze of the resin film.

[0009] In addition, in the trained model generation method according to the present invention, in the above invention, the thermoplastic resin includes recycled resin.

[0010] In addition, in the trained model generation method according to the present invention, in the above invention, the thermoplastic resin is a polyester resin.

[0011] In addition, in the trained model generation method of the present invention, in the above invention, the resin film is a biaxially oriented polyester film.

[0012] In addition, the mixing condition setting method of the present invention involves a computer inputting the physical properties of the target resin film into a search section including a trained model generated by learning using learning data in which mixing conditions including the physical properties and mixing ratio of the thermoplastic resin constituting the resin film are explanatory variables and the physical properties of the resin film are objective variables, and setting the mixing conditions based on the output results of the search section.

[0013] In addition, in the above-mentioned invention, the step of setting the blending conditions of the present invention is such that, when a plurality of blending conditions are present in the output result, a blending condition having a large proportion of recycled resin is selected from among the blending conditions.

[0014] In the blending condition setting method according to the present invention, the physical properties of the thermoplastic resin include the intrinsic viscosity and solution haze of the thermoplastic resin.

[0015] In the blending condition setting method according to the present invention, in the above invention, the physical properties of the resin film include an intrinsic viscosity and a film haze of the resin film.

[0016] In the blending condition setting method according to the present invention, in the above-mentioned invention, the thermoplastic resin includes a recycled resin.

[0017] In the blending condition setting method according to the present invention, in the above-mentioned invention, the thermoplastic resin is a polyester resin.

[0018] In the blending condition setting method according to the present invention, the resin film is a biaxially oriented polyester film.

[0019] In addition, the trained model generation program of the present invention causes a computer to execute a trained model generation step of generating a trained model by learning using training data in which the blending conditions, including the physical properties and blending ratio of the thermoplastic resin constituting a resin film, are explanatory variables, and the physical properties of the resin film are objective variables.

[0020] In addition, the mixing condition setting program of the present invention causes a computer to execute a mixing condition setting step of inputting the physical properties of the target resin film into a search section including a trained model generated by learning using learning data in which mixing conditions including the physical properties and mixing ratio of the thermoplastic resin constituting the resin film are used as explanatory variables and the physical properties of the resin film are used as objective variables, and setting the mixing conditions based on the output results of the search section.

[0021] In addition, the learning device of the present invention is equipped with a learning unit that generates a trained model by learning using learning data in which the physical properties and blending conditions including the blending ratio of the thermoplastic resin that constitutes the resin film are explanatory variables, and the physical properties of the resin film are objective variables.

[0022] In addition, the mixing condition setting device of the present invention has a trained model generated by learning using learning data in which mixing conditions including the physical properties and mixing ratio of the thermoplastic resin constituting the resin film are explanatory variables and the physical properties of the resin film are objective variables, and is equipped with a search unit that inputs the physical properties of the target resin film into the trained model to search for mixing conditions suitable for the physical properties, and a setting unit that sets the mixing conditions based on the output results of the learning search unit.

[0023] In addition, the method for producing a resin film according to the present invention produces a resin film in accordance with the blending conditions of the thermoplastic resin set by the blending condition setting method according to the above-mentioned invention.

[0024] In addition, a resin film manufacturing system according to the present invention includes a blending condition setting device according to the above invention, and a film manufacturing device that manufactures a resin film in accordance with the blending conditions of the thermoplastic resin set by the blending condition setting device.

[0025] The resin film according to the present invention is produced by mixing thermoplastic resins according to the blending conditions set by the blending condition setting method according to the above-mentioned invention, and forming the mixture into a sheet. Effect of the Invention

[0026] According to the present invention, the compounding conditions for the resin film can be set efficiently. [Brief description of the drawings]

[0027] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of a blending condition setting system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram for explaining the flow of a blending condition setting process performed by the blending condition setting system according to one embodiment of the present invention. [Diagram 3] FIG. 3 is a diagram for explaining an example of a production method by biaxial stretching. [Figure 4] FIG. 4 is a block diagram showing the configuration of a learning device provided in a blending condition setting system according to an embodiment of the present invention. [Diagram 5] FIG. 5 is a block diagram showing the configuration of a blending condition setting device provided in a blending condition setting system according to one embodiment of the present invention. [Figure 6] FIG. 6 is a flowchart showing an outline of the learning process performed by the learning device according to an embodiment of the present invention. [Figure 7] FIG. 7 is a flowchart showing an outline of a blending condition setting process performed by a blending condition setting device according to one embodiment of the present invention. [Figure 8] FIG. 8 is a flowchart showing an outline of a blending condition setting process performed by a blending condition setting device according to a modified embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] Hereinafter, an embodiment of the compounding condition setting system according to the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to this embodiment.

[0029] (Embodiment) 1 is a diagram showing a schematic configuration of a blending condition setting system according to an embodiment of the present invention. The blending condition setting system 1 includes a learning device 2 that creates learning data and generates a trained model trained using the created learning data, a blending condition setting device 3 that sets blending conditions that give the physical properties of a resin film desired by a user using the trained model generated by the learning device 2, a display device 4 that displays information including the setting results of the blending condition setting device 3, and an input device 5.

[0030] The blending conditions set by the blending condition setting device 3 include the types of raw materials (resins) constituting the resin film and their blending ratios.

[0031] Examples of the resin constituting the resin film include thermoplastic resins. Examples of the thermoplastic resin include polyester resins. Thermoplastic resins include new resins that have not been subjected to processing such as hot melt molding or heat treatment, and recycled resins that have been subjected to processing such as hot melt molding or heat treatment. Recycled resins can be used, for example, from process waste materials generated when a product is manufactured, or from discarded or collected products. The form of the resin is not limited, and it is used in the form of melt-extruded pellets or compressed flakes.

[0032] 2 is a diagram for explaining the flow of a blending condition setting process performed by a blending condition setting system according to an embodiment of the present invention. The learning device 2 generates a trained model 100 by learning using the learning data LD. The blending condition setting device 3 inputs physical property conditions IP indicating the desired physical properties into the trained model 100 to obtain blending conditions (predicted conditions), and sets and outputs blending conditions OP that satisfy the physical properties (predictions) of the resin film. Alternatively, the blending condition setting device 3 inputs physical property conditions IP indicating the desired physical properties to the trained model 100 to obtain blending conditions (prediction conditions), and outputs the obtained one or more blending conditions OP.

[0033] Here, an example of a method for producing a resin film will be described with reference to Fig. 3. Fig. 3 is a diagram for explaining an example of a production method by biaxial stretching. In Fig. 3, the longitudinal direction of the film to which the resin is sent in the treatment process is the X-axis direction, the width direction of the resin film (the same as the rotation axis of the roll that sends it to the next process) is the Y-axis direction, and the height direction perpendicular to the X-axis direction and the Y-axis direction is the Z-axis direction.

[0034] The resin film manufacturing apparatus 200 includes a manufacturing unit 201 and a control unit 202 . The blending condition setting device 3 and the production device 200 constitute a resin film production system. The production device 200 is not limited to a production unit that produces a resin film by biaxial stretching, such as the production unit 201 shown in FIG.

[0035] The manufacturing section 201 includes a vacuum drying section 211 that removes moisture from the pellets (resin), a storage section 212 that stores the pellets after vacuum drying, an extrusion section 213 that melts and extrudes the pellets sent from the storage section 212, a filtration filter 214 that filters the molten resin sent from the extrusion section 213, a die 215 that forms the filtered molten resin into a sheet, a casting drum 216 that wraps the sheet-like resin from the die 215 around and cools and solidifies it, a first stretching section 217 that stretches the sheet-like resin in the X-axis direction, a second stretching section 218 that stretches in the Y-axis direction perpendicular to the stretching direction by the first stretching section 217, a transfer conveying section 219 that conveys the biaxially stretched film that has passed through the second stretching section 218 while cooling it, and a winding section 220 that winds up the stretched resin sent from the transfer conveying section 219.

[0036] The extrusion section 213 mixes and melts the pellets and forces them through a die 215 . The casting drum 216 rotates about an axis in the Y-axis direction, cools and solidifies the resin, and sends the sheet-like resin in the film longitudinal direction (X-axis direction).

[0037] The first stretching section 217 stretches the sheet-like resin sent from the casting drum 216 in the film longitudinal direction (X-axis direction) using a plurality of rolls while heating as necessary, to form a uniaxially stretched film.

[0038] The second stretching section 218 stretches the uniaxially stretched film (221) sent from the first stretching section 217 in a direction perpendicular to the longitudinal direction of the film using clips while heating it as necessary. Here, it stretches in the Y-axis direction (film width direction / roll rotation axis direction) to form a biaxially stretched film.

[0039] The winding section 220 is a roll that winds up the biaxially stretched film after the stretching process in the second stretching section 218 via the transfer conveying section 219. Through this series of processes, a biaxially stretched resin film stretched in two perpendicular directions is produced by mixing, melting, and stretching a plurality of raw resins into a sheet shape. Since the biaxially stretched resin film is stretched in different directions, it exhibits high isotropy compared to a uniaxially stretched film, and exhibits, for example, excellent dimensional stability.

[0040] The control unit 202 controls the operation of the production unit 201. For example, when the production conditions for biaxial stretching, such as the temperature and rotation speed of the rolls, are set in the blending condition setting device 3, the control unit 202 acquires the blending conditions and drives the production unit 201 according to the production conditions. The control unit 202 is a computer configured using one or more hardware such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field Programmable Gate Array), and a memory in which various programs and the like are pre-installed.

[0041] Next, the configuration of the learning device 2 will be described with reference to Fig. 4. The learning device 2 is electrically connected to a blending condition setting device 3. Fig. 4 is a block diagram showing the configuration of a learning device provided in a blending condition setting system according to an embodiment of the present invention. The learning device 2 has a learning data generating unit 21, a learning unit 22, a control unit 23, and a storage unit 24.

[0042] The learning data generating unit 21 generates, from the data stored in the storage unit 24, data in which the blending conditions consisting of the types and physical properties of the multiple raw materials constituting the resin film and the blending ratio of the raw materials correspond to the physical properties of the resin film manufactured under the blending conditions, as learning data. In other words, the learning data is data on a resin film whose physical properties are known. The learning data generating unit 21 may extract data according to the conditions input via the input device 5 to generate the learning data. The learning data generating unit 21 generates learning data in which the blending conditions including the physical properties and blending ratio of the thermoplastic resin constituting the resin film are explanatory variables, and the physical properties of the resin film corresponding to the blending conditions are objective variables. In this case, the type, physical properties, and mixing ratio of the raw materials, which are the blending conditions, may be quantified or visualized. In addition, a plurality of these blending conditions may be combined and quantified or visualized to be expressed as one blending condition. For example, if there are 40 combinations of ingredient types and blending ratios, a number between 1 and 40 can be obtained by assigning a number corresponding to each combination, and this number can be quantified as a blending condition related to ingredient types and blending ratios. Using the above-mentioned representation makes it possible to reduce explanatory variables in the generated learning data and reduce multicollinearity, leading to the construction of a highly accurate trained model. The physical properties of the resin film may be expressed numerically or as an image. When the resin film has a plurality of physical properties, these physical properties may be combined and expressed as one physical property of the resin film. The experimental data, which is stored in the memory unit 24 and contains a mixture of compounding conditions and physical properties, is divided into explanatory variables (x1, x2, ...) and a response variable (y) in the learning data generating unit 21. At this time, there may be multiple types of compounding conditions used as explanatory variables, and each compounding condition is associated with a physical property. Note that multiple compounding conditions may be collectively treated as one. Also, the explanatory variables and the response variable may be stored separately in advance in the memory unit.

[0043] Here, the known blending ratio of a resin film refers to data accumulated in the past that expresses the composition ratio of raw materials in a resin film in terms of weight ratio, and includes the resin ratio and additive ratio as necessary.

[0044] The physical properties used as learning data include the physical properties of the raw materials and the physical properties of the resin film. The physical properties of the raw materials include intrinsic viscosity, solution haze (turbidity), and color tone. The physical properties of the resin film include intrinsic viscosity, film haze (turbidity), color tone, thickness, and mechanical strength. When the resin is manufactured using biaxial stretching, the mechanical strength includes the strength in each stretching direction. In addition, in the case of recycled resin, the contents of processing performed in the past (heating conditions, etc.) may be included as physical properties. In this case, even if a new resin and a recycled resin are the same product, they may have different physical properties such as intrinsic viscosity, solution haze (turbidity), and color tone. In particular, recycled resins that have been repeatedly recycled may have relatively large differences in physical properties such as intrinsic viscosity, film haze (turbidity), and color tone compared to new resins.

[0045] The raw material for resin films is a mixture of multiple resins depending on the desired physical properties. For example, even when a film is made using polyester resin, there are different types of raw materials for the polyester resin, such as polyethylene terephthalate (PET), polyethylene naphthalate (PEN), polytrimethylen terephthalate (PTT), polybutylene terephthalate (PBT), etc. Even if it is the same polyester resin, the physical properties will differ depending on whether it is recycled or not.

[0046] An example of raw material parameters will now be described with reference to Table 1. Table 1 shows an example of the physical properties (intrinsic viscosity, solution haze (turbidity), color tone (b value)) of polyester resin raw materials and whether they can be recycled. In Table 1, No. 1 and No. 2 show the physical properties of new resins, and No. 3 to No. 7 show the physical properties of recycled resins. As shown in Table 1, even if it is the same polyester resin, the physical properties will be different if the type is different. [Table 1]

[0047] The learning unit 22 performs learning using the learning data to generate a trained model. A known learning method can be adopted for the learning performed by the learning unit 22. Examples of statistical models adopted for learning include a simple linear regression model, Ridge regression, Lasso regression, Elastic Net regression, general additive model, random forest regression, rule fit regression, gradient boosting tree, extra tree, support vector regression, Gaussian process regression, k-nearest neighbor regression, kernel ridge regression, and neural network.

[0048] For example, when the learning unit 22 generates a trained model by learning using regularization, the learning unit 22 provides multiple candidate values ​​for hyperparameters of the trained model, executes learning for each of the provided candidate values ​​of the hyperparameters, generates a trained model for the objective variable (physical properties of the resin film), and stores the trained model in the storage unit 24. After that, the learning unit 22 calculates prediction errors by cross validation or hold-out validation using the learning data for the models obtained by learning using each candidate value, and selects a trained model that provides the smallest prediction error. Note that the hyperparameters referred to here are parameters that are set in advance by the learning unit 22 to perform learning, and include, for example, regularization coefficients. In addition, the hyperparameters in the case of a trained model using a neural network also include the number of layers of the neural network.

[0049] The control unit 23 comprehensively controls the operation of the learning device 2 .

[0050] The storage unit 24 stores various programs for operating the learning device 2, and data including various parameters necessary for the operation of the learning device 2. The various programs include a learning data generation program that generates learning data for generating a trained model, and a trained model generation program that learns using the learning data to generate a trained model. The various parameters include hyperparameters, parameters acquired by the learning unit 22 through learning, and the like. The storage unit 24 also stores data for constituting the learning data (for example, the above-mentioned blending conditions and physical properties).

[0051] The storage unit 24 is composed of a ROM (Read Only Memory) in which various programs and the like are pre-installed, a RAM (Random Access Memory) for storing calculation parameters and data for each process, a HDD (Hard Disk Drive), an SSD (Solid State Drive), etc.

[0052] The various programs can be widely distributed by recording them on computer-readable recording media such as HDDs, flash memories, CD-ROMs, DVD-ROMs, Blu-ray (registered trademark), etc. The communication network referred to here is configured using, for example, an existing public line network, a LAN (Local Area Network), a WAN (Wide Area Network), etc., and may be wired or wireless.

[0053] The learning device 2 having the above-described functional configuration is a computer configured using one or more pieces of hardware such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field Programmable Gate Array).

[0054] Next, the blending condition setting device 3 will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the configuration of the blending condition setting device provided in the blending condition setting system according to one embodiment of the present invention. The blending condition setting device 3 is electrically connected to the learning device 2 and the display device 4. The blending condition setting device 3 has a setting unit 31, a search unit 32, a control unit 33, and a memory unit 34.

[0055] The blending condition setting device 3 uses the physical properties to be predicted and the trained model acquired from the learning device 2 to set blending conditions including the types of raw materials and their blending ratios suitable for the conditions.

[0056] The setting unit 31 inputs the set and input physical properties to the search unit 32 including a trained model, and sets the candidate blending conditions output from the search unit 32 as the blending conditions. The blending conditions set at this time may be the most suitable blending condition among a plurality of blending conditions that satisfy the set physical property conditions, or may be all blending conditions that satisfy the physical property conditions.

[0057] The search unit 32 extracts optimal blending conditions by searching for blending condition candidates using the trained model based on the physical properties input from the setting unit 31, and outputs the optimal blending conditions to the setting unit 31. Here, searching for blending condition candidates using the trained model refers to inputting blending condition candidates generated based on a search algorithm described below into the trained model, and extracting optimal blending conditions for achieving the physical properties input from the setting unit 31 from the physical properties of the resin film output from the trained model.

[0058] Here, the optimal blending conditions are those in which the target physical property is at its most preferable value, and in the present embodiment, for example, in the case of strength, this is synonymous with maximizing or bringing the physical property closest to the set value. If there is a preferable range, the physical property falls within that range. In addition, if the set conditions include multiple types of physical properties, candidate blending conditions are extracted according to the difference between the respective physical property values, the priority assigned to each physical property, and the like.

[0059] Examples of search algorithms for obtaining optimal blending conditions include a grid search method that selects blending conditions from a trained model that satisfy the target range of the physical properties of the target resin film, or a random search method that determines an upper limit of the number of searches in advance and randomly extracts blending conditions to obtain blending conditions that maximize / minimize the physical properties. In addition, a Bayesian optimization method can be used as a search method in which a confidence interval represented by the average physical property value ± predicted error, which takes into account the predicted error of the physical properties, is selected and evaluated near the extreme values ​​of the accumulated data, and the search is repeated. In addition, a genetic algorithm selection method can be used as a search method in which blending conditions close to the target physical properties are selected and the search for blending conditions is repeated while changing some of the blending conditions. Here, when a search algorithm that requires a starting point before searching, such as the Bayesian optimization method or the genetic algorithm selection method, may be performed, as a starting point, in addition to data generated by grid search and random plotting, learning data used to generate the trained model may be used.

[0060] The control unit 33 controls the overall operation of the blending condition setting device 3. The control unit 33 has a display control unit 331 that displays the setting result of the setting unit 31 on the display device 4. The display control unit 331 may display information such as raw materials, the raw materials, and predicted physical properties on the display device 4 in addition to the setting result.

[0061] The storage unit 34 stores various programs for operating the blending condition setting device 3, and data including various parameters necessary for the operation of the blending condition setting device 3. The various programs include a blending condition setting program executed using a trained model. The storage unit 34 may also store a trained model. In this case, the trained model may be updated in synchronization with the learning device 2. The storage unit 34 is configured using a ROM in which various programs are pre-installed, and a RAM, HDD, SSD, etc. that store calculation parameters and data for each process.

[0062] The various programs can be recorded in computer-readable recording media such as HDD, flash memory, CD-ROM, DVD-ROM, Blu-ray (registered trademark), etc., and widely distributed. The blending condition setting device 3 can also acquire the various programs via a communication network. The communication network referred to here is, for example, configured using an existing public line network, LAN, WAN, etc., and may be wired or wireless.

[0063] The blending condition setting device 3 having the above-mentioned functional configuration is a computer configured using one or more pieces of hardware such as a CPU, a GPU, an ASIC, and an FPGA.

[0064] The display device 4 is a display made of liquid crystal or organic EL (Electro Luminescence), and is electrically connected to the blending condition setting device 3. The display device 4 acquires and displays display data output from the blending condition setting device 3 under the control of the display control unit 331. The display device 4 may have an audio output function such as a speaker.

[0065] The input device 5 receives input of various information including information such as set mechanical property values ​​related to the process of setting the blending conditions, and outputs the received information to the learning device 2 and the blending condition setting device 3. The input device 5 is configured using a user interface such as a keyboard, a mouse, a microphone, and a touch panel.

[0066] Next, the flow of the learning process performed by the learning device 2 will be described with reference to FIG. 6. FIG. 6 is a flowchart showing an outline of the learning process performed by the learning device according to one embodiment of the present invention. First, the learning device 2 generates a data set to be used for learning with reference to the storage unit 24 (step S11). Here, the learning data generation unit 21 generates a data set that pairs the blending conditions including the types, physical properties, and blending ratios of the raw materials in the resin film with the physical properties of the resin film manufactured under those blending conditions. This data set is used as learning data for generating a trained model. The learning data generation unit 21 generates learning data for each resin film.

[0067] The learning unit 22 generates a trained model by executing machine learning using the learning data generated in step S11 (step S12). The learning unit 22 performs learning using the blending conditions including the physical properties and blending ratio of the thermoplastic resin constituting the resin film as explanatory variables and the physical properties of the resin film as objective variables to generate a trained model.

[0068] Thereafter, the blending conditions, which are the optimum raw material types and blending ratios of the resin film suitable for the physical properties to be set, are set in the blending condition setting device 3. Fig. 7 is a flowchart showing an outline of the blending condition setting process performed by the blending condition setting device according to one embodiment of the present invention.

[0069] The setting unit 31 acquires the trained model from the learning device 2, and inputs the physical properties of the target resin film to the search unit 32 (step S21). The search unit 32 receives the set physical properties for the physical properties treated as the objective variables during learning, and outputs the blending conditions. When the physical properties of the target resin film are input to the search unit in this way, blending conditions (prediction conditions) suitable for the physical properties are output. The target physical properties input at this time are based on, for example, information input by the user via the input unit of the blending condition setting device 3. For example, a blending condition using raw materials A and B with a blending ratio of A:B=○○(%):△△%(%) is set and output. At this time, the ratio of recycled resin to the total amount of raw materials (recycle rate) may be displayed. The trained model may output the blending condition in a digitized or visualized form, and the setting unit 31 etc. may convert it to express the blending condition.

[0070] The setting unit 31 sets the blending conditions based on the prediction result of the search unit 32 (step S22). In this embodiment, when there are multiple blending conditions for the target physical property, the setting unit 31 may set one optimal blending condition that is closest to the target physical property, may set a blending condition that satisfies the target physical property or its allowable setting range, or may select and set the top several blending conditions that satisfy the target physical property. For example, when a priority is set for each type of physical property, the blending conditions are preferentially selected based on the physical property with the highest priority and the condition with the smallest difference between the target physical property.

[0071] When the display control unit 331 acquires the setting result from the setting unit 31, the display control unit 331 outputs the setting result to the display device 4 and performs display control to display the setting result on the display device 4. The display device 4 displays the blending conditions including the types of raw materials of the optimal resin film predicted to exhibit the target physical properties and their blending ratios.

[0072] Thereafter, for example, raw materials are prepared according to the blending conditions set by the above-mentioned setting method, and a resin film is produced using the above-mentioned production apparatus 200.

[0073] In the embodiment described above, the type and physical properties of raw materials and their blending ratios are used as explanatory variables, and the target physical properties are used as objective variables to generate a trained model, whereby blending conditions for a resin film having target physical properties are set by inputting the target physical properties. According to the embodiment, the blending conditions for a resin film can be set efficiently.

[0074] In addition, in the embodiment, since it is possible to search for blending conditions including recycled resins as well as new resins as raw materials for the resin film and set blending conditions including the recycled resins, it is possible to improve the recycling rate of raw materials in the manufacturing process. In this case, the priority of recycled resins may be set higher than the priority of new resins when selecting raw materials.

[0075] In the embodiment, the objective variables are described as the physical properties of the resin film, and the explanatory variables are the physical properties and blending conditions of the raw materials. However, in addition to these, the objective variables may further include spectroscopic intensity, process condition values ​​during manufacturing (e.g., stretching ratio, etc.), and the like, and may further include measurement condition values.

[0076] In this case, the spectral intensity refers to the intensity of the spectrum at each wavelength obtained by spectral measurement of the resin film, and examples of the spectral intensity include spectral measurements using light sources in each wavelength region, such as infrared light, near-infrared light, visible light, ultraviolet light, and X-rays.

[0077] The process condition values ​​refer to control parameters for producing a resin film, and include, for example, production conditions such as temperature when biaxial stretching is used, the feed speed of the resin (the rotation speed of the roll), the distance between clips in the film width direction, etc. In addition, when isotropy or the like is specified as the target physical property, the necessity of biaxial stretching, etc. may be included in the compounding conditions.

[0078] In addition, it may include any of the physical values ​​or properties inherent to each raw material of the resin film and values ​​that can be calculated from the blending conditions thereof, and physical quantities such as molecular weight, glass transition point, melting point, etc. Here, the physical quantities inherent to each raw material can be calculated from the amount of specific functional groups or the number of partial structures that each raw material has, or the chemical structure.

[0079] In addition, when a contribution derived from the chemical structure of the resin components contained in the resin film is expected, the accuracy of the trained model can be expected to be further improved by using as explanatory variables not only the component blending ratio but also physical quantities including the amount of specific functional groups or the number of partial structures and related values ​​calculated based on the chemical structural formula of the component, or molecular weights that can be calculated from the chemical structure of each component, or physical values ​​including glass transition point and melting point.

[0080] (Modification) Next, a modified example of the embodiment will be described with reference to FIG. 8. In the modified example, the compounding condition setting process is different from the above-mentioned embodiment. The process and system configuration other than the compounding condition setting process are the same as the embodiment, so the description will be omitted.

[0081] 8 is a flowchart showing an outline of a blending condition setting process performed by a blending condition setting device according to a modified embodiment of the present invention. The setting unit 31 acquires a trained model from the learning device 2 in the same manner as in step S21, and inputs the target physical properties to the search unit 32 (step S31). When the target physical properties of the resin film are input to the search unit 32, blending conditions (prediction conditions) suitable for the physical properties are output.

[0082] The setting unit 31 judges whether the combination conditions output by the trained model are multiple (step S32). If the setting unit 31 judges that the combination conditions are not multiple (step S32: No), the process proceeds to step S34. On the other hand, if the setting unit 31 judges that the combination conditions are multiple (step S32: Yes), the process proceeds to step S33.

[0083] In step S33, the setting unit 31 calculates the recycle rate for each blending condition and selects the blending condition with the highest recycle rate. The setting unit 31, for example, calculates the ratio of recycled resin in the raw materials to be blended, and sets this as the recycle rate. The ratio is calculated, for example, by adding up the blending rate or mass% of the recycled resin. After calculating the recycle rate, the setting unit 31 proceeds to step S34.

[0084] In step S34, the setting unit 31 sets the compounding condition. In this modification, if there is one compounding condition in step S32, the setting unit 31 sets the compounding condition, and if a compounding condition is selected in step S33, the setting unit 31 sets the selected compounding condition.

[0085] Thereafter, when the display control unit 331 acquires the setting result from the setting unit 31, the display control unit 331 outputs the setting result to the display device 4 and performs display control to display the setting result on the display device 4. The display device 4 displays the types of raw materials of the optimal resin film that are predicted to exhibit the physical properties of the target resin film, and the blending conditions including the blending ratios thereof.

[0086] Thereafter, for example, raw materials are prepared according to the blending conditions set by the above-mentioned setting method, and a resin film is produced using the above-mentioned production apparatus 200.

[0087] In the above-described modified example, as in the embodiment, the type and physical properties of the raw materials and their blending ratio are used as explanatory variables, and the physical properties of the resin film are used as objective variables to generate a trained model for setting blending conditions for a resin film having target physical properties. According to this modified example, blending conditions for a resin film can be set efficiently.

[0088] In addition, in the modified example, the compounding conditions are set so that the proportion or amount of recycled resin used as the raw material for the resin film is high, thereby improving the recycling rate of raw materials in the production process.

[0089] (Other embodiments) Although the embodiment for carrying out the present invention has been described above, the present invention should not be limited to the above-mentioned embodiment. For example, the compounding condition setting device may have the function of a learning unit. In this case, the compounding condition setting device not only sets the compounding conditions to be set, but also sequentially updates the learned model. [Explanation of symbols]

[0090] 1. Mixing condition setting system 2 Learning device 3 Mixing condition setting device 4 Display device 5 Input Devices 21 Learning data generation unit 22 Learning Department 23, 33, 202 Control section 24, 34 Storage section 31 Setting section 32 Search Department 200 Manufacturing equipment 201 Manufacturing Department 331 Display control unit

Claims

1. The computer A trained model is generated by training using training data in which the physical properties and blending conditions including the blending ratio of the thermoplastic resin constituting the resin film are explanatory variables, and the physical properties of the resin film are objective variables. How to generate trained models.

2. The physical properties of the thermoplastic resin include the intrinsic viscosity and solution haze of the thermoplastic resin. The trained model generating method according to claim 1 .

3. The physical properties of the resin film include the intrinsic viscosity, film haze, and mechanical properties of the resin film. The trained model generating method according to claim 1 .

4. The thermoplastic resin includes a recycled resin. The trained model generating method according to claim 1 .

5. The thermoplastic resin is a polyester resin. The trained model generating method according to claim 1 .

6. The resin film is a biaxially oriented polyester film. The trained model generating method according to claim 1 .

7. The computer The physical properties of the target resin film are input to a search unit including a trained model generated by training using training data in which the blending conditions, including the physical properties and blending ratio of the thermoplastic resin constituting the resin film, are used as explanatory variables, and the physical properties of the resin film are used as objective variables; Set the blending conditions based on the output result of the search unit. How to set compounding conditions.

8. In the step of setting the blending conditions, when a plurality of blending conditions are present in the output result, a blending condition having a large proportion of recycled resin is selected from among the blending conditions. The method for setting blending conditions according to claim 7.

9. On the computer, A trained model generation step of generating a trained model by learning using training data having blending conditions including the physical properties and blending ratio of the thermoplastic resin constituting the resin film as explanatory variables and the physical properties of the resin film as objective variables; A trained model generation program that executes the above.

10. On the computer, A blending condition setting step of inputting the physical properties of the target resin film into a search unit including a trained model generated by learning using learning data in which blending conditions including the physical properties and blending ratio of the thermoplastic resin constituting the resin film are explanatory variables and the physical properties of the resin film are objective variables, and setting the blending conditions based on the output result of the search unit; A program for setting compounding conditions.

11. A learning unit that generates a trained model by learning using training data in which the physical properties and blending conditions including the blending ratio of the thermoplastic resin constituting the resin film are explanatory variables and the physical properties of the resin film are objective variables; A learning device comprising:

12. A search unit that has a trained model generated by learning using training data in which the physical properties of the target resin film and blending conditions including the blending ratio of the thermoplastic resin constituting the resin film are used as explanatory variables and the physical properties of the resin film are used as objective variables, and that inputs the physical properties of the target resin film into the trained model to search for blending conditions suitable for the physical properties; A setting unit that sets a combination condition based on the output result of the search unit; A blending condition setting device comprising:

13. A resin film is produced according to the blending conditions of the thermoplastic resin set by the blending condition setting method according to claim 7. A method for producing a resin film.

14. The blending condition setting device according to claim 12, a film manufacturing device that manufactures a resin film in accordance with the blending conditions of the thermoplastic resin set by the blending condition setting device; A resin film manufacturing system comprising:

15. The thermoplastic resins are mixed according to the blending conditions of the thermoplastic resins set by the blending condition setting method according to claim 7, and the mixture is molded into a sheet shape. Resin film.

Images