Physical quantity estimation system, approximate function generating device, physical quantity estimation device, program, recording medium, and physical quantity estimation method

Abstract

To enable highly accurate estimation of a physical quantity value of composite materials.SOLUTION: Upon input of values of categorical variables consisting of digital variables associated with factors affecting a physical quantity value of a first composite material having an unknown physical quantity value, the physical quantity value of the first composite material is estimated using an approximate function that outputs the physical quantity value for the first composite material.SELECTED DRAWING: Figure 8

Description

[Technical Field]

[0001] The present invention relates to a physical quantity estimation system, an approximate function generating device, a physical quantity estimation device, a program, a recording medium, and a physical quantity estimation technique, and relates to a technique that is effective when applied to, for example, a technique for estimating the value of a physical quantity according to the blending ratio of a resin composite material. [Background technology]

[0002] Japanese Patent Application Laid-Open No. 2018-156689 (Patent Document 1) describes a technology for estimating the physical properties of a composite material using artificial intelligence. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-156689 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, composite materials have been developed that combine multiple types of resins and compounding agents to impart new performance to the properties of the resin itself. In this regard, the development of new composite materials requires material development while adjusting the composition ratio of each component until the composite material has the desired properties. This results in enormous costs for composite material development. Therefore, from the perspective of improving the efficiency of composite material development, it is desirable to be able to estimate to some extent the physical quantities of composite materials to be tested at the experimental planning stage. However, for example, composite materials for electrical wire coating materials contain many types of compounding agents, and the values ​​of the physical quantities can vary significantly depending on the compounding composition ratio. This makes it difficult to estimate the values ​​of the physical quantities of composite materials. For these reasons, a technology that can estimate the values ​​of the physical quantities of composite materials with high accuracy is desired. [Means for solving the problem]

[0005] A physical quantity estimation system according to one embodiment is a system for estimating a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials. The physical quantity estimation system includes: an approximation function generation unit that generates an approximation function that outputs a value of the physical quantity for a first composite material when a value of a first categorical variable, the approximation function being a digital variable associated with a factor that affects the value of the physical quantity of a first composite material whose value of the physical quantity is unknown, and a physical quantity estimation unit that estimates the value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximation function.

[0006] An approximate function generating device in one embodiment is an approximate function generating device that is a component of a physical quantity estimation system that estimates a value of a physical quantity for a composite material that includes, as constituent materials, two or more materials belonging to a plurality of different materials. The approximate function generating device includes an approximate function generating unit that generates an approximate function that outputs a value of a physical quantity for a first composite material when a value of a first categorical variable consisting of digital variables associated with factors that affect the value of the physical quantity of a first composite material whose physical quantity value is unknown is input.

[0007] In one embodiment, the program causes a computer to execute a process for estimating a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials. The program includes an approximation function generation process for generating an approximation function that outputs a value of the physical quantity for a first composite material when a value of a first categorical variable including digital variables associated with factors that affect the value of the physical quantity of a first composite material whose value of the physical quantity is unknown is input.

[0008] A physical quantity estimation device in one embodiment is a component of a physical quantity estimation system that estimates a value of a physical quantity for a composite material that includes, as constituent materials, two or more materials belonging to a plurality of different materials. The physical quantity estimation device includes a physical quantity estimation unit that estimates a value of a physical quantity for a first composite material based on a value of a first categorical variable, which is made up of digital variables associated with factors that affect the value of the physical quantity of a first composite material whose physical quantity value is unknown, and an approximation function. Here, the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable is input.

[0009] In one embodiment, the program causes a computer to execute a process for estimating a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials. The program includes a physical quantity estimation process for estimating a value of a physical quantity for a first composite material, the value of the physical quantity of which is unknown, based on a value of a first categorical variable composed of digital variables associated with factors that affect the value of the physical quantity of the first composite material, and an approximation function. Here, the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable is input.

[0010] A physical quantity estimation method according to one embodiment is a physical quantity estimation method in which a computer estimates a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials. The physical quantity estimation method includes an approximate function generation step in which, when a value of a first categorical variable including digital variables associated with factors that affect the value of the physical quantity of a first composite material whose physical quantity value is unknown is input, an approximate function generation unit of the computer generates an approximate function that outputs a value of the physical quantity for the first composite material, and a physical quantity estimation step in which a physical quantity estimation unit of the computer estimates the value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximate function. [Effects of the Invention]

[0011] According to one embodiment, the value of a physical quantity for a composite material can be estimated with high accuracy. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of a hardware configuration of a physical quantity estimation device. [Figure 2] 2 is a functional block diagram showing functions of the physical quantity estimation device according to the first embodiment. FIG. [Figure 3] FIG. 1 is a diagram illustrating machine learning for generating an approximate function. [Figure 4] 10 is a flowchart illustrating an operation for generating an approximate function. [Figure 5] 10 is a flowchart illustrating an operation of estimating a value of a physical quantity for a composite material to be evaluated. [Figure 6] FIG. 1 is a functional block diagram showing an example of a physical quantity estimation system configured from a physical quantity estimation device and an approximate function generation device. [Figure 7] FIG. 10 is a diagram showing a functional block configuration of a physical quantity estimation device according to a second embodiment. [Figure 8] FIG. 1 is a diagram illustrating machine learning for generating an approximate function. [Figure 9] 10 is a flowchart illustrating an operation for generating an approximate function. [Figure 10] 10 is a flowchart illustrating an operation of estimating a value of a physical quantity for a first composite material to be evaluated. [Figure 11] 10 is a table showing data combining blend data and physical quantity data in a specific example. [Figure 12] 10 is a table showing data obtained by combining synthesis related data and additional data in a specific example. [Figure 13] 1 is a table showing first blending data of a first composite material to be evaluated, the correspondence of which to the values ​​of physical quantities of which is unknown. [Figure 14] 10 is a table showing data including a first composite characteristic value, a first categorical variable, and a first irradiation dose in a specific example. [Figure 15] 10 is a table showing the estimation results of values ​​of physical quantities in a specific example. [Figure 16](a) is a graph showing the results of estimating the initial tensile strength of the first composite material using an approximation function that does not use categorical variables as input parameters, and (b) is a graph showing the results of estimating the initial tensile strength of the first composite material using an approximation function that uses categorical variables as input parameters. DETAILED DESCRIPTION OF THE INVENTION

[0013] In all the drawings for explaining the embodiments, the same components are generally designated by the same reference numerals, and repeated explanations thereof will be omitted. In addition, hatching may be used even in plan views to make the drawings easier to understand.

[0014] (Embodiment 1) The technical idea of ​​the first embodiment is a concept related to a physical quantity estimation system that estimates the value of a physical quantity corresponding to the blending ratio in a composite material obtained by combining multiple types of resins and compounding agents.

[0015] Here, the composite material may be, for example, a wire coating material containing a resin and compounding agents, and the physical quantity may be, for example, the elongation and tensile strength of the composite material.

[0016] Examples of resins include polyolefins such as high-density polyethylene, low-density polyethylene, and ethylene-acrylic acid copolymers, as well as elastomers such as chlorinated polyethylene. Examples of compounding agents include fillers such as talc, calcium carbonate, and silica, plasticizers, crosslinking agents, and stabilizers. However, the types and numbers of resins and compounding agents that make up the composite material are not limited.

[0017] The technical idea of ​​the present embodiment 1 is applicable not only to composite materials made by combining multiple types of resins and compounding agents, but also to composite materials made by combining multiple types of magnetic materials, and examples of physical quantities include magnetic susceptibility and magnetic field (magnetic field, magnetic flux density) strength.

[0018] <Description of Related Art> First, we will explain related technology related to a physical quantity estimation system that estimates the value of a physical quantity corresponding to a blending ratio. In this specification, the term "related technology" refers to technology that is not publicly known, but has problems that the inventors have discovered, and is a technology that is the premise of the present invention.

[0019] For example, a related technology can be considered as a physical quantity estimation system that, when the names of constituent materials that make up a composite material and the blending ratios of the constituent materials are input, estimates the values ​​of the physical quantities of the composite material based on an approximation function that outputs the values ​​of the physical quantities of the composite material. In this related technology, for example, data on the names of the constituent materials, the blending ratios of the constituent materials, and the values ​​of the physical quantities corresponding to these blending ratios are used as training data, and an approximation function is generated that takes the material names and blending ratios as inputs and the physical quantity values ​​as outputs.

[0020] However, in the related art, the estimation targets for the values ​​of physical quantities are limited to the constituent materials included in the training data used to generate the approximation function. In other words, if a constituent material that was not used to generate the approximation function is included in the composite material to be evaluated, the estimation accuracy of the values ​​of the physical quantities of this composite material decreases. This is because, in the related art, the input parameters of the approximation function are the names of the constituent materials, and therefore, it is not possible to combine the input parameters. This point will be explained in an easy-to-understand manner.

[0021] For example, suppose an approximate function for related technologies is generated using training data that associates the physical quantity value "100" with the material name "high-density polyethylene" and the physical quantity value "200" with the material name "low-density polyethylene."

[0022] In this case, for example, consider estimating the value of a physical quantity for a composite material that contains "high-density polyethylene" and "low-density polyethylene" as constituent materials in a 50:50 blend ratio using an approximation function generated by related technology.

[0023] First, in the related art, when input parameters for the constituent materials that make up a composite material are synthesized to obtain input parameters for the composite material, the calculation is "high density polyethylene" x 0.5 + "low density polyethylene" x 0.5, which is a calculation of "material name" x "numerical value," and therefore the calculation of synthesizing input parameters itself is meaningless.

[0024] However, the training data used is data associating the physical quantity value "100" with the material name "high-density polyethylene" and data associating the physical quantity value "200" with the material name "low-density polyethylene." From this, in this case, it is assumed that the approximation function generated by the related technology can estimate the physical quantity value for the composite material as "100" x 0.5 + "200" x 0.5 = "150" without performing the calculation of combining input parameters. In other words, it is believed that the related technology can estimate the physical quantity value with high accuracy for a composite material containing "high-density polyethylene" and "low-density polyethylene" used in the training data.

[0025] In contrast to this, for example, consider estimating the value of a physical quantity for a composite material that contains "polyolefin" and "high-density polyethylene" as constituent materials and has a blending ratio of the constituent materials of 70:30, using an approximation function generated by the related technology.

[0026] In this case too, first consider synthesizing the input parameters for the constituent materials that make up the composite material to obtain the input parameters for the composite material. This results in a calculation of "polyolefin" x 0.7 + "high-density polyethylene" x 0.3, which is "material name" x "number," so the calculation of synthesizing input parameters itself is meaningless.

[0027] Furthermore, in this case, the composite material contains "polyolefin," which is not included in the training data. As a result, it is difficult to grasp the value of the physical quantity for "polyolefin" using the approximation function generated by the related technology, and the value of the physical quantity for the composite material becomes "???" x 0.7 + "100" x 0.3, making it difficult to accurately estimate the value of the physical quantity for a composite material containing "polyolefin" and "high-density polyethylene."

[0028] This is because, in an approximation function that uses material names as input parameters, it is meaningless to perform a composite operation between input parameters, and this reduces the accuracy of estimating the values ​​of physical quantities for composite materials that include constituent materials not used in the training data.

[0029] From the above, there is room for improvement in the related art in terms of accurately estimating the values ​​of physical quantities for composite materials that include constituent materials that were not used to generate the approximation function.

[0030] Therefore, in the present embodiment 1, some improvements have been made to address the room for improvement that exists in the related art. The technical concept of the present embodiment 1 that incorporates these improvements will be described below.

[0031] <Basic Concept of First Embodiment> First, the present inventors have noticed that the essence of the problem lies in the fact that the related art uses input parameters, such as material names, which are difficult to perform synthesis calculations on, resulting in a decrease in the accuracy of estimating physical quantities for composite materials containing constituent materials not used in the training data.The present inventors have then discovered that, for example, if input parameters related to constituent materials that are easy to perform synthesis calculations on are used, the accuracy of estimating physical quantities for composite materials containing constituent materials not used in the training data may be improved.

[0032] In this regard, the basic idea is that if parameters that can be expressed numerically are used as input parameters related to the constituent materials, it becomes possible to perform synthesis calculations, and therefore it is possible to improve the accuracy of estimating the values ​​of physical quantities for composite materials that include constituent materials that are not used in the training data. This point will be explained in detail below.

[0033] For example, suppose an approximation function is generated using training data that associates a physical quantity value of "100" with an input parameter of "50" and data that associates a physical quantity value of "150" with an input parameter of "100."

[0034] In this regard, first consider the case where the constituent materials of a composite material include two constituent materials with an input parameter of "50" and another with an input parameter of "100," and the constituent materials are blended in a 50:50 ratio, and the value of the physical quantity for this composite material is estimated using the above-described approximation function. In this case, to obtain the input parameters for the composite material, the input parameters for the constituent materials are combined: "50" x 0.5 + "100" x 0.5 = "75," which is a "numerical value" x "numerical value" operation, making the input parameter combination easy to perform. This yields the input parameter "75" for the composite material. By inputting this input parameter "75" into the approximation function based on the basic concept, the value of the physical quantity for the composite material can be estimated with high accuracy. Therefore, according to the basic concept, it is possible to accurately estimate the value of the physical quantity for a composite material containing the constituent materials used in the training data.

[0035] Next, for example, consider estimating the value of a physical quantity for a composite material that includes, as its constituent materials, a constituent material with an input parameter of "50" and a constituent material with an input parameter of "75" and has a blending ratio of the constituent materials of 50:50, using the above-mentioned approximation function.

[0036] In this case, the composite material contains a constituent material with an input parameter of "75" that is not included in the training data. However, the basic concept uses parameters expressed as numerical values ​​as input parameters. Therefore, to obtain the input parameters for the composite material, the basic concept allows the input parameters for the constituent materials to be synthesized. Specifically, when synthesizing the input parameters for the constituent materials of the composite material, "50" x 0.5 + "75" x 0.5 = "62.5", which is a "numerical value" x "numerical value" operation, the input parameter synthesis operation can be easily performed. This results in the input parameter "62.5" for the composite material. By inputting this input parameter "62.5" into the approximation function in the basic concept, the physical quantity value for the composite material can be estimated. Therefore, according to the basic concept, the physical quantity value can be estimated with high accuracy even for composite materials containing new constituent materials not used in the training data. This is the result of the basic concept using input parameters that can be expressed as numerical values ​​as input parameters for the constituent materials, which are easy to synthesize. Thus, the essence of the basic idea is to use numerical values ​​that can be used for synthetic calculations as input parameters related to constituent materials.

[0037] Here, the inventors have focused on the characteristic values ​​of the constituent materials as input parameters relating to the constituent materials that can be expressed numerically.

[0038] In other words, the basic idea in this embodiment 1 is to estimate the value of a physical quantity for a composite material by using an approximation function generated based on the characteristic values ​​(numerical values) of the constituent materials that make up the composite material and the blending ratio of the constituent materials.

[0039] According to this basic concept, the following effects can be obtained by using an approximation function generated based on the characteristic values ​​of the constituent materials and the blending ratios of the constituent materials.

[0040] For example, in an approximation function generated based on the names and blending ratios of constituent materials, as in the related art, the input parameters are the names and blending ratios of constituent materials. Therefore, if a new constituent material that was not used to generate the approximation function is included in the composite material to be evaluated, the concept of combining the names of the constituent materials used to generate the approximation function with the names of the new constituent material becomes meaningless, resulting in a decrease in the accuracy of estimating the values ​​of physical quantities for this composite material. In other words, the approximation function generated by the related art narrows the range of composite materials for which the values ​​of physical quantities can be estimated with high accuracy.

[0041] In particular, in the related art, even if the names of new constituent materials (new material names) that were not used to generate the approximation function are known, if the values ​​of the corresponding physical quantities are not known, the approximation function generated by the related art cannot accurately estimate the physical quantities for the composite material to be evaluated. In other words, the approximation function generated by the related art can only accurately estimate the physical quantities for composite materials that include only the constituent materials used in the training data.

[0042] In contrast, the basic concept of the first embodiment is to generate an approximation function based on the characteristic values ​​of the constituent materials and the blending ratios of the constituent materials. In this case, even if the composite material to be evaluated contains a new constituent material that was not used to generate the approximation function, if the characteristic values ​​corresponding to this new constituent material are known, the values ​​of the physical quantities for the composite material can be estimated with high precision. This is because the characteristic values ​​of the constituent materials can be expressed numerically, making it possible to perform a synthesis operation.

[0043] Thus, the scope of application of the approximation function generated by the basic concept is broader than that of the approximation function generated by the related technology. This has great technical significance in that it allows for highly accurate estimation of physical quantities for composite materials, even when the composite material being evaluated contains a new constituent material that was not used in the training data. In other words, while the scope of application of the approximation function generated by the related technology is limited to the training data, the scope of application of the approximation function generated by the basic concept is not limited to the training data. Therefore, the basic concept can be considered an excellent technical concept. For example, according to the basic concept, by storing characteristic values ​​for new constituent materials that were not used to generate the approximation function in a database, it is possible to highly accurately estimate physical quantities for composite materials containing new constituent materials that were not considered when the approximation function was generated. Furthermore, by using the approximation function in the basic concept, it is possible to highly accurately estimate physical quantities for composite materials containing new constituent materials, even if the new constituent materials are not stored in the database, as long as the characteristic values ​​of these new constituent materials can be obtained by some means. This makes the scope of application of the approximation function generated by the basic concept significant.

[0044] Here, "characteristic values" refer to, for example, thermal properties, mechanical properties, physical properties, etc. For example, thermal properties include heat of fusion and melt flow rate. Physical properties include specific gravity. On the other hand, "physical quantities" are assumed to be elongation, tensile strength, etc.

[0045] In this specification, a "characteristic value" and a "value of a physical quantity" are clearly distinguished from each other. Specifically, a "characteristic value" is a parameter used to generate an approximation function and as an input to the approximation function. On the other hand, a "value of a physical quantity" is a value output from the approximation function, and is a target value estimated by the physical quantity estimation system in the first embodiment.

[0046] In the following, an example in which a physical quantity estimation system embodying this basic idea is configured from a single computer will be mainly described, but the physical quantity estimation system in the first embodiment can also be realized as a distributed system consisting of a plurality of computers.

[0047] <Configuration of the physical quantity estimation device> <<Hardware configuration>> First, the hardware configuration of the physical quantity estimation device according to the first embodiment will be described.

[0048] Fig. 1 is a diagram showing an example of a hardware configuration of a physical quantity estimation device 100 according to the first embodiment. Note that the configuration shown in Fig. 1 merely shows an example of the hardware configuration of the physical quantity estimation device 100, and the hardware configuration of the physical quantity estimation device 100 is not limited to the configuration shown in Fig. 1 and may be other configurations.

[0049] 1, a physical quantity estimation device 100 includes a CPU (Central Processing Unit) 101 that executes a program. The CPU 101 is electrically connected to, for example, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, and a hard disk drive 112 via a bus 113, and is configured to control these hardware devices.

[0050] The CPU 101 is also connected to input devices and output devices via a bus 113. Examples of input devices include a keyboard 105, a mouse 106, a communication board 107, and a scanner 111. Examples of output devices include a display 104, a communication board 107, and a printer 110. The CPU 101 may also be connected to, for example, a removable disk device 108 and a CD / DVD-ROM device 109.

[0051] The physical quantity estimation device 100 may be connected to, for example, a network. For example, when the physical quantity estimation device 100 is connected to other external devices via a network, a communication board 107 constituting a part of the physical quantity estimation device 100 is connected to a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet.

[0052] The RAM 103 is an example of a volatile memory, and the ROM 102, the removable disk device 108, the CD / DVD-ROM device 109, and the hard disk device 112 are examples of non-volatile memories. These volatile memories and non-volatile memories configure a storage device of the physical quantity estimation device 100.

[0053] The hard disk drive 112 stores, for example, an operating system (OS) 201, a program group 202, and a file group 203. The programs included in the program group 202 are executed by the CPU 101 using the operating system 201. The RAM 103 also temporarily stores at least some of the programs of the operating system 201 and application programs executed by the CPU 101, as well as various data required for processing by the CPU 101.

[0054] A BIOS (Basic Input Output System) program is stored in the ROM 102, and a boot program is stored in the hard disk drive 112. When the physical quantity estimation device 100 is started up, the BIOS program stored in the ROM 102 and the boot program stored in the hard disk drive 112 are executed, and the operating system 201 is started up by the BIOS program and the boot program.

[0055] The program group 202 stores programs that realize the functions of the physical quantity estimation device 100, and these programs are read and executed by the CPU 101. The file group 203 stores information, data, signal values, variable values, and parameters indicating the results of processing by the CPU 101 as each item of a file.

[0056] The files are recorded on a recording medium such as the hard disk drive 112 or memory. The information, data, signal values, variable values, and parameters recorded on the recording medium such as the hard disk drive 112 or memory are read by the CPU 101 into the main memory or cache memory and used for the operations of the CPU 101, such as extraction, search, reference, comparison, calculation, processing, editing, output, printing, and display. For example, during the operations of the CPU 101 described above, the information, data, signal values, variable values, and parameters are temporarily stored in the main memory, registers, cache memory, buffer memory, etc.

[0057] The functions of the physical quantity estimation apparatus 100 may be realized by firmware stored in the ROM 102, or may be realized by software alone, by hardware alone such as elements, devices, boards, and wiring, a combination of software and hardware, or even a combination of firmware and the like. The firmware and software are recorded as programs on a recording medium such as the hard disk drive 112, a removable disk, a CD-ROM, or a DVD-ROM. The programs are read and executed by the CPU 101. That is, the programs cause the computer to function as the physical quantity estimation apparatus 100.

[0058] As described above, the physical quantity estimation device 100 is a computer including the CPU 101 as a processing device, the hard disk drive 112 and memory as storage devices, the keyboard 105, mouse 106, and communication board 107 as input devices, and the display 104, printer 110, and communication board 107 as output devices. The functions of the physical quantity estimation device 100 are realized by using the processing device, the storage device, the input device, and the output device.

[0059] <<Function block configuration>> Next, the functional block configuration of the physical quantity estimation device 100 will be described.

[0060] FIG. 2 is a functional block diagram showing the functions of the physical quantity estimation device.

[0061] The physical quantity estimation device 100 includes an input unit 301, a characteristic value data extraction unit 302, a composite characteristic value calculation unit 303, a composite related data generation unit 304, an approximate function generation unit 305, a physical quantity estimation unit 306, an output unit 307, and a data storage unit 308.

[0062] The input unit 301 is configured to input characteristic value data. Here, "characteristic value data" refers to data that associates the material name with the characteristic value of each of a plurality of different materials. The characteristic value data input to the input unit 301 is stored in the data storage unit 308. This data storage unit 308 functions as a database that stores a plurality of pieces of characteristic value data.

[0063] The input unit 301 is also configured to input the composition data and physical quantity data of a composite material that contains, as constituent materials, two or more materials contained in a plurality of different materials. Here, "composition data" refers to data including the names and composition ratios of the constituent materials that make up the composite material, and is sometimes referred to as composition information. On the other hand, "physical quantity data" refers to data that indicates the values ​​of physical quantities in a composite material whose physical quantity values ​​are known, and is, for example, data obtained by experiment. The composition data and physical quantity data input to the input unit 301 are also stored in the data storage unit 308.

[0064] The characteristic value data extraction unit 302 is configured to extract characteristic value data corresponding to the constituent materials contained in the composite material from the plurality of characteristic value data stored in the data storage unit 308. For example, when the constituent materials contained in the composite material are "polyolefin" and "polyethylene," the characteristic value data extraction unit 302 is configured to extract characteristic value data corresponding to "polyolefin" and characteristic value data corresponding to "polyethylene" from the plurality of characteristic value data.

[0065] The composite characteristic value calculation unit 303 is configured to calculate the composite characteristic value of the composite material by performing a calculation to synthesize characteristic values ​​corresponding to the constituent materials that make up the composite material, based on the blending ratio contained in the blending data input to the input unit 301 and the characteristic values ​​contained in the characteristic value data extracted by the characteristic value data extraction unit 302.

[0066] For example, consider a composite material that includes two constituent materials with a characteristic value of "50" and one with a characteristic value of "75," with a blending ratio of the constituent materials of 50:50. In this case, the composite characteristic value calculation unit 303 performs a synthesis operation of "50" x 0.5 + "75" x 0.5 = "62.5" to calculate a composite characteristic value of "62.5."

[0067] The composite characteristic values ​​include, for example, the composite heat of fusion of the composite material, the composite melt flow rate of the composite material, and the like.

[0068] The synthesis related data generation unit 304 is configured to generate synthesis related data that associates the synthesis characteristic value calculated by the synthesis characteristic value calculation unit 303 with the value of the physical quantity for the composite material (the "physical quantity data" of the composite material). This synthesis related data is generated for the composite material input to the input unit 301, for which the corresponding physical quantity is known. For example, if the physical quantity value for the composite material in the above example is "150", the synthesis related data generation unit 304 generates synthesis related data that associates the synthesis characteristic value "62.5" with the physical quantity value "150". The generated synthesis related data is stored in the data storage unit 308.

[0069] The approximate function generation unit 305 has a function of generating an approximate function based on the synthesis associated data generated by the synthesis associated data generation unit 304. In other words, the approximate function generation unit 305 is configured to generate an approximate function that associates the synthesis characteristic value with the value of the physical quantity.

[0070] Specifically, as shown in FIG. 3, the approximation function generation unit 305 is configured to generate an approximation function using the synthesis related data as training data, with the synthesis characteristic value as the input and the value of the physical quantity as the output.

[0071] Here, an "approximation function" is defined as a function that, when a composite characteristic value is input, outputs a value of a physical quantity corresponding to the composite characteristic value. In other words, an "approximation function" is defined as a function that, when a composite characteristic value of a composite material whose correspondence with the value of a physical quantity is unknown is input, outputs a value of a physical quantity that is estimated to be realized by the composite material. In this way, an approximation function can be said to be a function used to estimate the value of a physical quantity for a composite material whose correspondence with the value of a physical quantity is unknown.

[0072] The physical quantity estimation unit 306 is configured to estimate the value of the physical quantity corresponding to the first composite material based on the first composite characteristic value calculated by the composite characteristic value calculation unit 303 based on the first blending ratio included in the first blending data of the first composite material and the characteristic value of the first characteristic value data extracted by the characteristic value data extraction unit 302, and the approximate function generated by the approximate function generation unit 305.

[0073] The term "first composite material" refers to a composite material containing two or more materials contained in a plurality of different materials as constituent materials, where the values ​​of the corresponding physical quantities are unknown, and represents the composite material to be evaluated. Here, the composition data of the first composite material is referred to as "first composition data," and the composition ratio contained in the composition data of the first composite material is referred to as "first composition ratio." Furthermore, the composite characteristic value of the first composite material is referred to as "first composite characteristic value," and the characteristic value data corresponding to the constituent materials contained in the first composite material, among the characteristic value data stored in the data storage unit 308, is referred to as "first characteristic value data."

[0074] For example, the first blending data is input to the physical quantity estimation device 100 from the input unit 301 , and the first characteristic value data is extracted by the characteristic value data extraction unit 302 .

[0075] The output unit 307 outputs the value of the physical quantity estimated by the physical quantity estimation unit 306 .

[0076] In this way, the physical quantity estimation device 100 is configured.

[0077] The constituent materials of the composite material may include, for example, a plurality of different types of resin, but may also include other constituent materials. For example, the constituent materials of the composite material may include additives, antioxidants, cross-linking aids, etc. Furthermore, one example of a resin is a cross-linked resin. Depending on the specific constituent materials of the composite material, additional functions are added to the physical quantity estimation device 100, and this point will be described below.

[0078] <<<When composite materials contain additives>>> When an additive is contained in the composite material, the composite characteristic value calculation unit 303 is configured to calculate the average inter-filler distance of the additive or the volume fraction of the additive based on the characteristic value of the additive, in addition to the above-mentioned functions. The composite characteristic value calculated by the composite characteristic value calculation unit 303 includes the average inter-filler distance of the additive or the volume fraction of the additive.

[0079] The average interparticle distance, typified by the average inter-filler distance, is calculated, for example, from the average particle diameter D50 using a theoretical formula, and the volume fraction is calculated from the specific gravity of the blended materials.

[0080] <<<When the composite material contains an antioxidant and a crosslinking coagent>>> When the composite material contains an antioxidant and a cross-linking coagent, the synthesis characteristic value calculation unit 303 is configured to, in addition to the above-mentioned functions, further calculate the number of reacted moles of the primary reactive group of the antioxidant, the number of reacted moles of the secondary reactive group of the antioxidant, and the number of reacted moles of the cross-linking coagent based on the characteristic value of the antioxidant and the characteristic value of the cross-linking coagent.The synthesis characteristic value calculated by the synthesis characteristic value calculation unit 303 includes the number of reacted moles of the primary reactive group of the antioxidant, the number of reacted moles of the secondary reactive group of the antioxidant, and the number of reacted moles of the cross-linking coagent.

[0081] <<<When the composite material contains cross-linked resin>>> When the composite material contains a cross-linked resin, the input unit 301 is configured to further input a radiation exposure dose for cross-linking the resin. The approximate function generation unit 305 is configured to generate an approximate function based on the synthesis-related data and the radiation exposure dose. In this case, the approximate function is generated as a function that takes a synthesis characteristic value and a radiation exposure dose as inputs and a physical quantity value as output. The physical quantity estimation unit 306 is configured to estimate a physical quantity value for the first composite material based on the first synthesis characteristic value, the first radiation exposure dose, and the approximate function. Here, the "first radiation exposure dose" represents the radiation exposure dose irradiated to the first composite material.

[0082] <Operation of the physical quantity estimation device> The physical quantity estimation device 100 in the first embodiment is configured as described above, and its operation will be described below. The operation of the physical quantity estimation device 100 includes an "operation for generating an approximate function" and an "operation for estimating the value of a physical quantity corresponding to a composite material to be evaluated." Therefore, these operations will be described below.

[0083] <<Approximation function generation operation>> FIG. 4 is a flowchart illustrating the operation of generating the approximation function.

[0084] 4, first, the input unit 301 inputs a plurality of characteristic value data in which the material name and the characteristic value of each of a plurality of different materials are associated with each other (S101).Then, the plurality of characteristic value data input to the input unit 301 is stored in the data storage unit 308 (S102).

[0085] Next, the input unit 301 inputs the blending data and physical quantity data of a composite material that contains two or more materials as constituent materials and for which the corresponding physical quantity values ​​are known (S103).

[0086] Thereafter, the characteristic value data extraction unit 302 extracts characteristic value data corresponding to the constituent materials contained in the composite material from the plurality of characteristic value data stored in the data storage unit 308 (S104). Next, the composite characteristic value calculation unit 303 calculates the composite characteristic value of the composite material by performing an operation to combine the characteristic values ​​of the characteristic value data extracted by the characteristic value data extraction unit based on the composition data input from the input unit 301 (S105).

[0087] Then, the synthesis related data generation unit 304 generates synthesis related data that associates the synthesis characteristic value calculated by the synthesis characteristic value calculation unit 303 with the physical quantity value (physical quantity data) for the composite material (S106). Thereafter, the synthesis related data generated by the synthesis related data generation unit 304 is stored in the data storage unit 308 (S107).

[0088] Next, the approximate function generation unit 305 generates an approximate function based on the synthesis related data generated by the synthesis related data generation unit 304 (S108). Specifically, the approximate function generation unit 305 uses the synthesis related data as training data to generate an approximate function that has synthesis characteristic values ​​as inputs and physical quantity values ​​as outputs (see FIG. 3).

[0089] Then, the approximate function generated by the approximate function generating unit 305 is stored in the data storage unit 308 (S109). In this manner, the operation of generating the approximate function is performed.

[0090] <<Estimation of the physical quantity value for the first composite material to be evaluated>> Next, an operation for estimating the value of the physical quantity for the first composite material to be evaluated will be described.

[0091] 5 is a flowchart illustrating the operation of estimating the value of the physical quantity for the first composite material to be evaluated. Note that the approximate function is already stored in the data storage unit 308.

[0092] In FIG. 5, first, the input unit 301 inputs the first blend data of the first composite material to be evaluated, the correspondence of which to the value of the physical quantity being unknown (S201).

[0093] Next, the characteristic value data extraction unit 302 extracts first characteristic value data corresponding to the constituent materials contained in the first composite material from the plurality of characteristic value data stored in the data storage unit 308 (S202).

[0094] Next, the composite characteristic value calculation unit 303 calculates the first composite characteristic value of the first composite material by performing an operation to combine the characteristic values ​​of the first characteristic value data extracted by the characteristic value data extraction unit 302 based on the first blending data input from the input unit 301 (S203).

[0095] Thereafter, the physical quantity estimation unit 306 estimates the value of the physical quantity for the first composite material by inputting the first composite characteristic value calculated by the composite characteristic value calculation unit 303 into an approximation function (S204). Then, the output unit 307 outputs the value of the physical quantity estimated by the physical quantity estimation unit 306 (S205). In this way, the physical quantity estimation device 100 can output the value of the physical quantity that is likely to be realized for the first composite material to be evaluated, whose correspondence with the value of the physical quantity is unknown.

[0096] <Physical quantity estimation program> The physical quantity estimation method performed by the above-described physical quantity estimation device 100 can be realized by a physical quantity estimation program that causes a computer to execute a physical quantity estimation process.

[0097] For example, in a physical quantity estimation device 100 including a computer shown in Fig. 1, the physical quantity estimation program according to the first embodiment can be introduced as one of the programs 202 stored in the hard disk drive 112. Then, by causing the computer that is the physical quantity estimation device 100 to execute this physical quantity estimation program, the physical quantity estimation method according to the first embodiment can be realized.

[0098] The physical quantity estimation program that causes a computer to execute each process for creating data related to the physical quantity estimation process can be recorded on a computer-readable recording medium and distributed. Examples of the recording medium include magnetic storage media such as hard disks and flexible disks, optical storage media such as CD-ROMs and DVD-ROMs, and hardware devices such as non-volatile memories such as ROMs and EEPROMs.

[0099] <Modification> In the first embodiment, as shown in FIG. 2 , an example has been described in which the physical quantity estimation system for estimating the value of a physical quantity for a composite material is configured from a single physical quantity estimation device 100. However, the physical quantity estimation system is not limited to this configuration and can also be configured from, for example, a distributed system.

[0100] FIG. 6 is a functional block diagram showing an example in which a physical quantity estimation system is configured from a physical quantity estimation device and an approximate function generation device.

[0101] As shown in FIG. 6, the physical quantity estimation system is composed of a physical quantity estimation device 400 and an approximate function generation device 500, and the physical quantity estimation device 400 and the approximate function generation device 500 are connected via a network 600, for example.

[0102] The physical quantity estimation device 400 includes an input unit 301A, a first characteristic value data extraction unit 302A, a first composite characteristic value calculation unit 303A, a physical quantity estimation unit 306, an output unit 307, a communication unit 309A, and a data storage unit 310A.

[0103] The approximate function generating device 500 has an input unit 301B, a characteristic value data extracting unit 302B, a composite characteristic value calculating unit 303B, a composite associated data generating unit 304, an approximate function generating unit 305, a communication unit 309B, and a data storage unit 310B.

[0104] The physical quantity estimation device 400 and the approximate function generating device 500 configured in this way are configured to be able to transmit and receive data via the communication units 309A and 309B via the network 600. Then, in the approximate function generating device 500, the above-mentioned "approximate function generating operation" is performed to generate an approximate function.

[0105] On the other hand, the physical quantity estimation device 400 outputs the first composite characteristic value calculated by the first composite characteristic value calculation unit 303A to the approximate function generation device 500. Thereafter, the approximate function generation device 500 inputs the first composite characteristic value into the approximate function, and outputs an output result from the approximate function, which is then input from the approximate function generation device 500 and stored in the data storage unit 310A.

[0106] Thereafter, the physical quantity estimation device 400 acquires the values ​​of the physical quantities for the composite material to be evaluated, based on the output results input from the approximate function generation device 500.

[0107] In this way, the physical quantity estimation system according to the first embodiment can also be constructed by a distributed system including the physical quantity estimation device 400 and the approximate function generation device 500.

[0108] (Embodiment 2) In the above-described first embodiment, for a first composite material whose physical quantity value is unknown, a first composite characteristic value of the first composite material is calculated based on the first compounding ratio of the first composite material and characteristic values ​​corresponding to the constituent materials contained in the first composite material, and this calculated first composite characteristic value is input into an approximation function generated by an approximation function generation unit, thereby estimating the output value output from the approximation function as the value of the physical quantity for the first composite material.

[0109] In this case, even if the first composite material contains a new constituent material that was not used in the training data, the value of the physical quantity for the first composite material can be estimated with high accuracy.

[0110] That is, even if the first composite material contains a new constituent material that was not used to generate the approximation function, if the characteristic value corresponding to this new constituent material is known, the value of the physical quantity for the first composite material can be estimated with high accuracy. This is because the characteristic values ​​of the constituent materials are expressed as numerical values, which allows for a synthetic calculation and makes it possible to calculate the first synthetic characteristic value (analog numerical value) for the first composite material.

[0111] Therefore, the technical idea of ​​the first embodiment has great technical significance in that it is possible to estimate the values ​​of physical quantities for the first composite material with high accuracy even when the first composite material to be evaluated includes a new constituent material that was not used in the training data.

[0112] As described above, the technical idea in the first embodiment focuses on the "characteristic values" that can be subjected to synthetic calculations as factors that affect the values ​​of the physical quantities of the first composite material, and by using the synthetic characteristic values ​​of the first composite material as input parameters (explanatory variables) of the approximation function, the output value from the approximation function is used as an estimated value of the physical quantity of the first composite material.

[0113] In this regard, factors that affect the values ​​of the physical quantities of the first composite material are not limited to the "characteristic values" that can be subjected to the above-described synthesis operation. That is, input parameters other than the "characteristic values" can also be considered as factors that affect the values ​​of the physical quantities of the first composite material.

[0114] Therefore, in the second embodiment, a technical idea of ​​estimating the value of the physical quantity for the first composite material with high accuracy by taking into consideration input parameters other than the "characteristic value" will be described.

[0115] <Basic Concept of the Second Embodiment> The basic idea of ​​the second embodiment is to estimate the value of a physical quantity of a first composite material by using an approximation function that outputs the value of a physical quantity for the first composite material when the value of a categorical variable made up of digital variables associated with factors that affect the value of the physical quantity of the first composite material, whose value of the physical quantity is unknown, is input. That is, the basic idea of ​​the second embodiment is to use digital numerical values ​​such as the value of a categorical variable as the input parameter of the approximation function, rather than analog numerical values ​​such as "characteristic values."

[0116] In other words, the basic idea of ​​the second embodiment is to generate an approximation function that outputs the value of the physical quantity for the first composite material when the value of a categorical variable made up of digital variables associated with factors that affect the value of the physical quantity of a first composite material, the value of which is unknown, is input, and to estimate the value of the physical quantity for the first composite material based on the value of the categorical variable and the approximation function.

[0117] This makes it possible to consider, for example, factors that affect the value of a physical quantity of the first composite material not only factors that are suitable for being expressed in analog numbers, such as "characteristic values," but also factors that are suitable for being expressed in digital numbers, such as the value of a categorical variable.

[0118] Among the factors that affect the value of the physical quantity of the first composite material, an example of a factor that is suitable for being expressed by a digital numerical value, such as a value of a categorical variable, will be described below.

[0119] For example, consider a material containing a resin and a flame retardant as the first composite material. The physical quantities of the first composite material are elongation and tensile strength. To improve elongation and tensile strength, a surface treatment is performed on the surface of the flame retardant mixed with the resin. Examples of such surface treatments include silane coupling treatment and fatty acid treatment. There are several types of materials that make up the flame retardant, such as magnesium hydroxide and aluminum hydroxide.

[0120] Therefore, the elongation and tensile strength of the first composite material are thought to be affected by the type of surface treatment performed on the flame retardant surface and the type of material that constitutes the flame retardant. In other words, the type of surface treatment performed on the flame retardant surface and the type of material that constitutes the flame retardant can be thought of as factors that affect the values ​​of the physical quantities of the first composite material.

[0121] From this, it is considered that by using the type of surface treatment performed on the surface of the flame retardant and the type of material that makes up the flame retardant as input parameters of the approximation function, factors that affect the values ​​of the physical quantities of the first composite material can be incorporated into the approximation function, and therefore it is possible to generate an approximation function that can output highly accurate estimates of the physical quantities.

[0122] In this regard, when the surface treatment performed on the surface of the flame retardant or the type of material constituting the flame retardant is used as an input parameter of the approximation function, it is suitable to employ categorical variables consisting of digital variables as the input parameters. This is because, for example, the categorical variables, which are digital variables, can be configured to include a first variable indicating whether or not the flame retardant has undergone a first surface treatment, a second variable indicating whether or not the flame retardant has undergone a second surface treatment, a third variable indicating whether or not the flame retardant has undergone a first material constituting the flame retardant, and a fourth variable indicating whether or not the flame retardant has undergone a second material constituting the flame retardant. By defining the first surface treatment as a silane coupling treatment and the second surface treatment as a fatty acid treatment, and by defining the first material as magnesium hydroxide and the second material as aluminum hydroxide, the type of surface treatment performed on the surface of the flame retardant or the type of material constituting the flame retardant can be used as an input parameter of the approximation function.

[0123] Specifically, when the value of the first digital variable is "1," it indicates that a silane coupling treatment has been performed as a surface treatment for the flame retardant, whereas when the value of the first digital variable is "0," it indicates that a silane coupling treatment has not been performed as a surface treatment for the flame retardant. Similarly, when the value of the second digital variable is "1," it indicates that a fatty acid treatment has been performed as a surface treatment for the flame retardant, whereas when the value of the second digital variable is "0," it indicates that a fatty acid treatment has not been performed as a surface treatment for the flame retardant. Furthermore, when the value of the third digital variable is "1," it indicates that the flame retardant material is magnesium hydroxide, whereas when the value of the third digital variable is "0," it indicates that the flame retardant material is not magnesium hydroxide. Similarly, when the value of the fourth digital variable is "1," it indicates that the flame retardant material is aluminum hydroxide, whereas when the value of the fourth digital variable is "0," it indicates that the flame retardant material is not aluminum hydroxide.

[0124] From the above, for example, the type of surface treatment performed on the surface of the flame retardant and the type of material constituting the flame retardant can be said to be factors that are suitable for being expressed by digital numerical values ​​such as the value of a categorical variable, among factors that affect the value of the physical quantity of the first composite material. Therefore, the basic idea of ​​the second embodiment, in which the value of a categorical variable made up of a digital variable is used as an input parameter, is useful for generating an approximation function that can output an estimated value of the physical quantity with high accuracy by using the type of surface treatment performed on the surface of the flame retardant and the type of material constituting the flame retardant as an input parameter.

[0125] <Embodying the basic idea> Next, a description will be given of an embodiment that embodies the basic idea of ​​the present embodiment 2. In the embodiment that embodies the basic idea of ​​the present embodiment 2, for example, the physical quantity estimation device 100 can also be used.

[0126] <<Configuration of the physical quantity estimation device>> <<<Hardware Configuration>>> The hardware configuration of the physical quantity estimation device 100 in the second embodiment is the same as, for example, the hardware configuration shown in Fig. 1. Note that the configuration shown in Fig. 1 merely shows one example of the hardware configuration of the physical quantity estimation device 100, and the hardware configuration of the physical quantity estimation device 100 is not limited to the configuration shown in Fig. 1 and may be other configurations.

[0127] <<<Function block configuration>>> 7 is a diagram showing a functional block configuration of a physical quantity estimation device 100 according to the second embodiment. In FIG. 7, the physical quantity estimation device 100 includes an input unit 301, an additional data generation unit 304A, an approximate function generation unit 305, a physical quantity estimation unit 306, an output unit 307, and a data storage unit 308.

[0128] The input unit 301 is configured to input values ​​of categorical variables, which are digital variables associated with factors that affect the values ​​of physical quantities of the composite material. For example, if the categorical variables include a first variable indicating whether or not the flame retardant is silane-coupling-treated, a second variable indicating whether or not the flame retardant is fatty acid-treated, a third variable indicating whether or not magnesium hydroxide is present in the flame retardant, and a fourth variable indicating whether or not aluminum hydroxide is present in the flame retardant, the values ​​of the first, second, third, and fourth variables are input to the input unit 301. The values ​​of the categorical variables input to the input unit 301 are stored in the data storage unit 308. The data storage unit 308 functions as a database that stores values ​​of multiple categorical variables.

[0129] The input unit 301 is also configured to input blend data and physical quantity data of a composite material that includes, as constituent materials, two or more materials contained in a plurality of different materials.

[0130] Here, "composition data" refers to data including the names and composition ratios of the constituent materials that make up the composite material, and is data called composition information. On the other hand, "physical quantity data" refers to data indicating the values ​​of physical quantities in a composite material whose physical quantity values ​​are known, and is, for example, data obtained by experiment. The composition data and physical quantity data input to the input unit 301 are also stored in the data storage unit 308.

[0131] The additional data generation unit 304A is configured to generate additional data that associates the values ​​of the categorical variables input to the input unit 301 and stored in the data storage unit 308 with the values ​​of the physical quantities for the composite material (the "physical quantity data" of the composite material).

[0132] This additional data is generated for the composite material input to the input unit 301 and for which the corresponding physical quantities are known.

[0133] The approximate function generating unit 305 has a function of generating an approximate function based on the values ​​of the categorical variables input to the input unit 301 and stored in the data storage unit 308. In other words, the approximate function generating unit 305 has a function of generating an approximate function that outputs the value of the physical quantity for the first composite material when the value of the first categorical variable for the first composite material, whose physical quantity value is unknown, is input. In other words, the approximate function generating unit 305 is configured to generate an approximate function that associates the value of the categorical variable with the value of the physical quantity.

[0134] Specifically, as shown in FIG. 8 , the approximation function generation unit 305 is configured to use the additional data as training data to generate an approximation function that takes categorical variable values ​​as input and physical quantity values ​​as output. Here, an "approximation function" is defined as a function that, when a categorical variable value is input, outputs a physical quantity value corresponding to the categorical variable value. That is, an "approximation function" is defined as a function that, when a first categorical variable value of a constituent material constituting a first composite material whose correspondence with the physical quantity value is unknown is input, outputs a physical quantity value that is estimated to be realized by the first composite material. In this way, an approximation function can be said to be a function used to estimate a physical quantity value for a first composite material whose correspondence with the physical quantity value is unknown.

[0135] The physical quantity estimation unit 306 is configured to estimate the value of a physical quantity corresponding to the first composite material based on the value of the first categorical variable of the first composite material and the approximate function generated by the approximate function generation unit 305. Note that the "first composite material" refers to a composite material that includes two or more materials contained in a plurality of different materials as constituent materials, and is a composite material to be evaluated, in which the values ​​of the corresponding physical quantities are unknown. Here, the categorical variable of the first composite material is referred to as the "first categorical variable."

[0136] The output unit 307 outputs the value of the physical quantity estimated by the physical quantity estimation unit 306 .

[0137] In this way, the physical quantity estimation device 100 is configured.

[0138] <<Operation of the physical quantity estimation device>> <<<Approximation Function Generation Operation>>> FIG. 9 is a flowchart illustrating the operation of generating the approximation function.

[0139] 9, first, the input unit 301 inputs the values ​​of categorical variables, which are digital variables associated with factors that affect the values ​​of physical quantities of a composite material (S301).Then, the values ​​of the categorical variables are stored in the data storage unit 308 (S302).

[0140] Next, the input unit 301 inputs the blending data and physical quantity data of a composite material that contains two or more materials as constituent materials and for which the corresponding physical quantity values ​​are known (S303).

[0141] Then, the additional data generating unit 304A generates additional data that associates the values ​​of the categorical variables of the composite material with the values ​​of the physical quantities (physical quantity data) for the composite material (S304).Then, the additional data generated by the additional data generating unit 304A is stored in the data storage unit 308 (S305).

[0142] Next, the approximate function generation unit 305 generates an approximate function based on the additional data generated by the additional data generation unit 304A (S306). Specifically, the approximate function generation unit 305 uses the additional data as training data to generate an approximate function whose input is a value of a categorical variable and whose output is a value of a physical quantity. The approximate function generated by the approximate function generation unit 305 is then stored in the data storage unit 308 (S307).

[0143] In this way, the operation of generating the approximation function is performed.

[0144] <<<<Estimation of the physical quantity value for the first composite material to be evaluated>>> Next, an operation for estimating the value of the physical quantity for the first composite material to be evaluated will be described.

[0145] 10 is a flowchart illustrating the operation of estimating the value of the physical quantity for the first composite material to be evaluated. The approximate function is already stored in the data storage unit 308.

[0146] In FIG. 10, first, the input unit 301 inputs the value of the first categorical variable of the first composite material to be evaluated, the correspondence of which to the value of the physical quantity being unknown (S401).

[0147] Next, the physical quantity estimation unit 306 estimates the value of the physical quantity for the first composite material by inputting the value of the first categorical variable to the approximation function (S402). Then, the output unit 307 outputs the value of the physical quantity estimated by the physical quantity estimation unit 306 (S403).

[0148] In this way, the physical quantity estimation device 100 can output the value of a physical quantity that is likely to be realized for the first composite material to be evaluated, the correspondence of which with the value of the physical quantity being unknown.

[0149] <Example> Next, a specific example in which the first and second embodiments are combined will be described.

[0150] In a specific example, categorical variables, composite property values, formulation information, and process condition values ​​are used as input parameters.

[0151] Fig. 11 is a table showing data combining formulation data and physical quantity data for this specific example. In Fig. 11, the formulation number is an ID number that identifies the composite material. In Fig. 11, the constituent materials that make up the composite material include a resin, a flame retardant (filler), an antioxidant, a lubricant, a colorant, and a cross-linking aid.

[0152] Examples of resins include resins with the material names Resin A, Resin B, Resin C, Resin D, Resin E, Resin F, and Resin G. Examples of flame retardants include flame retardants with the material names Flame Retardant H, Flame Retardant I, and Flame Retardant J. Examples of antioxidants include antioxidants with the material names Antioxidant K and Antioxidant L, and examples of lubricants include lubricants with the material names Lubricant M, Lubricant N, and Lubricant O. Examples of colorants include a colorant with the material name Colorant P, and examples of cross-linking aids include a cross-linking aid with the material name Cross-linking Aid Q.

[0153] 11, for example, the composite material identified by formulation number "ID1" contains, as constituent materials, resin B (20 parts by mass), resin C (50 parts by mass), resin E (30 parts by mass), flame retardant H (200 parts by mass), antioxidant K (1 part by mass), antioxidant L (2 parts by mass), lubricant M (1 part by mass), lubricant N (2 parts by mass), colorant P (2 parts by mass), and cross-linking aid Q (4 parts by mass). As such, it can be seen that the data shown in FIG. 11 includes formulation data (formulation information) that includes the names and blending ratios of the constituent materials that make up the composite material.

[0154] Furthermore, in Fig. 11, for example, it is shown that the composite material identified by the formulation number "ID1" has a tensile strength of "8.3347" as a physical quantity. In other words, the data shown in Fig. 11 also includes physical quantity data indicating the values ​​of physical quantities for composite materials whose physical quantity values ​​are known. From the above, it can be seen that Fig. 11 lists combinations of formulation data and physical quantity data for composite materials whose physical quantity values ​​are known.

[0155] Next, in this specific example, the data shown in FIG. 12 is generated based on the data shown in FIG. 11, which includes the formulation data and physical quantity data. The data shown in FIG. 12 is composed of synthesis-related data, additional data, and supplemental data. Here, the synthesis-related data is data that associates synthesis characteristic values ​​with physical quantity values ​​(physical quantity data) for the composite material. The supplemental data is data that associates categorical variable values ​​with physical quantity values ​​(physical quantity data) for the composite material, and the supplemental data is data that associates irradiation doses as process condition values ​​with physical quantity values ​​(physical quantity data) for the composite material.

[0156] First, the synthesis-related data included in the data shown in FIG. 12 will be described.

[0157] The composite characteristic value included in the composite-related data is calculated by performing an operation to combine the characteristic values ​​of the characteristic value data based on the blending ratio included in the blending data in the data shown in Figure 11 and characteristic value data (not shown). Here, the characteristic value data refers to data that associates the material name and the characteristic value of each of a plurality of different materials, and this characteristic value data is assumed to be acquired in advance. For example, when focusing on Resin A shown in Figure 11, the characteristic value data can be said to be data that associates the material name Resin A with the characteristic value of Resin A.

[0158] Here, the composite characteristic value does not necessarily have to be calculated using the characteristic values ​​for all of the constituent materials that make up the composite material, but may be calculated using only the characteristic values ​​for some of the constituent materials that make up the composite material (limited to constituent materials that are related).

[0159] The composite characteristic value will be specifically described below.

[0160] 12, the composite characteristic value of this specific example includes five types of composite characteristic values, which will be described below.

[0161] (1) Filler volume ratio The filler volume ratio indicates the ratio of the volume of the filler (flame retardant) to the volume of the resin (base polymer), and is a parameter that indicates the proportion of the filler added to the resin. For example, the composite characteristic value related to the filler volume ratio is related to the resin and the filler. For this reason, a calculation is performed to calculate the composite characteristic value based on the characteristic values ​​of each of the resins (resins A to G) shown in FIG. 11 and each of the flame retardants (flame retardants H to J) shown in FIG. 11, among the constituent materials that make up the composite material, and the blending ratios shown in FIG. 11.

[0162] (2) Amount of maleic anhydride modification The maleic anhydride modification amount is a parameter that represents the amount of maleic anhydride (MAH) contained in a composite material. Maleic anhydride has the function of bonding resin and filler, and the amount of maleic anhydride is thought to affect the elongation and tensile strength of the resin composition, so it is adopted as a parameter. For example, the composite characteristic value related to the maleic anhydride modification amount is related to the resin. For this reason, calculations are performed to calculate the composite characteristic value based on the characteristic values ​​of each of the resins (resins A to G) shown in Figure 11 among the constituent materials that make up the composite material, and the blending ratios shown in Figure 11.

[0163] (3) Crystal Amount The crystallinity is a parameter that represents the amount of crystalline resin contained in a composite material. Since the hardness of a composite material changes depending on the amount of crystalline resin, it is believed that the amount of crystalline resin affects the elongation and tensile strength of the resin composition, and therefore it is adopted as a parameter. For example, the composite characteristic value related to the crystallinity is related to the resin. For this reason, calculations are performed to calculate the composite characteristic value based on the characteristic values ​​of each of the resins (resins A to G) shown in Figure 11 among the constituent materials that make up the composite material, and the blending ratios shown in Figure 11.

[0164] (4) Amount of vinyl acetate groups The amount of vinyl acetate groups is a parameter that represents the amount of vinyl acetate groups contained in a composite material. Since the hardness of a composite material changes depending on the amount of vinyl acetate groups, it is believed that the amount of vinyl acetate groups affects the elongation and tensile strength of a resin composition, and so it is adopted as a parameter. For example, the composite characteristic value related to the amount of crystallinity is related to the resin. For this reason, calculations are performed to calculate the composite characteristic value based on the characteristic values ​​of each of the resins (resins A to G) shown in Figure 11 among the constituent materials that make up the composite material, and the blending ratios shown in Figure 11.

[0165] (5) Filler surface area The filler surface area is used as a parameter that represents the particle size of fillers used as flame retardants or flame retardant auxiliaries. The particle size of fillers is considered to affect the elongation and tensile strength of resin compositions, and is therefore adopted as a parameter. For example, the composite characteristic value related to the filler surface area is related to the flame retardant. For this reason, calculations are performed to calculate the composite characteristic value based on the characteristic values ​​of each of the flame retardants (flame retardants H to J) shown in Figure 11 among the constituent materials that make up the composite material, and the blending ratios shown in Figure 11.

[0166] Next, the additional data included in the data shown in FIG. 12 will be described.

[0167] The additional data includes categorical variables, whose values ​​are input based on the composition data included in the data shown in FIG.

[0168] Categorical variables are digital variables, and four types of categorical variables are used in the additional data. Specifically, the categorical variable "CAT1" indicates the type of surface treatment of the flame retardant, and when the variable value is "1," it indicates that the surface treatment of the flame retardant is a silane coupling treatment, while when the variable value is "0," it indicates that the silane coupling treatment has not been applied.

[0169] The categorical variable "CAT2" indicates the type of surface treatment of the flame retardant. A variable value of "1" indicates that the surface treatment of the flame retardant is a fatty acid treatment, while a variable value of "0" indicates that the surface treatment is not a fatty acid treatment.

[0170] The categorical variable "CAT3" indicates the components of the flame retardant, and when the variable value is "1", it indicates that the flame retardant components contain magnesium hydroxide, while when the variable value is "0", it indicates that the flame retardant components do not contain magnesium hydroxide.

[0171] The categorical variable "CAT4" indicates the components of the flame retardant, and when the variable value is "1", it indicates that the flame retardant contains aluminum hydroxide, while when the variable value is "0", it indicates that the flame retardant does not contain aluminum hydroxide.

[0172] For example, in Fig. 12, the composite material identified by the compounding number "ID1" has a categorical variable "CAT1" of "1," a categorical variable "CAT2" of "0," a categorical variable "CAT3" of "1," and a categorical variable "CAT4" of "0." This shows that the composite material identified by the compounding number "ID1" contains magnesium hydroxide as a component of the flame retardant, which is a constituent material, and that a silane coupling treatment has been applied as a surface treatment of the flame retardant.

[0173] Further, the additional data included in the data shown in FIG. 12 will be described.

[0174] The additional data includes the irradiation dose as a process parameter value. This irradiation dose represents the amount of radiation used in the process of cross-linking the resin contained in the composite material. For example, if the irradiation dose is "0," it means that the process of cross-linking the resin by irradiation was not performed in the first place.

[0175] In this way, the data shown in FIG. 12 is constructed.

[0176] Next, an approximation function is generated based on the formulation data included in FIG. 11 and the data shown in FIG. 12 (synthesis-related data, additional data, and additional data). Specifically, the approximation function is generated by performing machine learning using the formulation data included in FIG. 11 and the data shown in FIG. 12 as training data, with formulation information, synthesis characteristic values, categorical variable values, and irradiation dose values ​​as inputs and physical quantity values ​​as outputs. In this specific example, the approximation function is generated using formulation information including material names and blending ratios (formulation data included in FIG. 11) as training data, along with the data shown in FIG. 12. In this case, an approximation function is generated in which formulation information, synthesis characteristic values, categorical variable values, and irradiation dose values ​​are inputs, and physical quantity values ​​are output.

[0177] When generating an approximation function, instead of using all of the formulation information, composite characteristic values, categorical variable values, and dose values ​​as input, the approximation function may be generated by performing machine learning using the formulation information, composite characteristic values, and categorical variable values ​​as inputs and the physical quantity values ​​as output. In this case, an approximation function is generated using the formulation information, composite characteristic values, and categorical variable values ​​as inputs and the physical quantity values ​​as output. Also, the approximation function may be generated by performing machine learning using the categorical variable values ​​and process condition values ​​(dose values) as inputs and the physical quantity values ​​as output. In this case, an approximation function is generated using the categorical variable values ​​and process condition values ​​as inputs and the physical quantity values ​​as output.

[0178] Furthermore, an approximation function may be generated by performing machine learning in which categorical variable values ​​are used as inputs and physical quantity values ​​are used as outputs. In this case, an approximation function is generated in which categorical variable values ​​are used as inputs and physical quantity values ​​are used as outputs.

[0179] Next, a description will be given of estimating the value of the physical quantity for the first composite material to be evaluated based on the approximation function generated as described above.

[0180] Fig. 13 is a table showing first blending data for a first composite material to be evaluated, the correspondence of which to physical quantities is unknown. In Fig. 13, the blending number is an ID number that identifies the first composite material. In Fig. 13, the constituent materials that make up the first composite material include a resin, a flame retardant (filler), an antioxidant, a lubricant, a colorant, and a cross-linking aid.

[0181] Examples of resins include resins with the material names Resin A, Resin D, Resin F, and Resin G. Examples of flame retardants include a flame retardant with the material name Flame Retardant I. Examples of antioxidants include antioxidants with the material names Antioxidant K and Antioxidant L, and examples of lubricants include lubricants with the material names Lubricant M and Lubricant O. Examples of colorants include a colorant with the material name Colorant P, and examples of cross-linking aids include a cross-linking aid with the material name Cross-linking Aid Q.

[0182] 13, for example, the first composite material identified by the formulation number "ID100" contains, as constituent materials, resin A (45 parts by mass), resin D (40 parts by mass), resin F (15 parts by mass), flame retardant I (160 parts by mass), antioxidant K (1 part by mass), antioxidant L (2 parts by mass), lubricant M (1 part by mass), lubricant O (2 parts by mass), colorant P (2 parts by mass), and cross-linking aid Q (4 parts by mass). As such, it can be seen that the data shown in FIG. 13 is first formulation data (formulation information) that includes the names and formulation ratios of the constituent materials that make up the first composite material.

[0183] Next, in this specific example, the data shown in Fig. 14 is generated based on the first blending data shown in Fig. 13. The data shown in Fig. 14 is composed of a first composite characteristic value, a value of a first categorical variable, and a value of a first irradiation dose.

[0184] In this specific example, a first composite characteristic value of the first composite material is calculated based on the first blending data shown in FIG. 13 and first characteristic value data (not shown). Specifically, the first composite characteristic value of the first composite material is calculated based on first blending ratios of the constituent materials included in the first composite material and characteristic values ​​corresponding to the constituent materials included in the first composite material. For example, the first composite characteristic value is calculated by performing a calculation to combine characteristic values ​​of the first characteristic value data based on the first blending ratios of the first blending data shown in FIG. 13 and first characteristic value data (not shown) corresponding to the constituent materials included in the first composite material. Note that the first characteristic value data refers to data that associates the material names of the constituent materials included in the first composite material with the characteristic values ​​of the constituent materials, and this first characteristic value data is assumed to be acquired in advance. For example, when focusing on resin D shown in FIG. 13, the first characteristic value data is data that associates the material name "resin D" with the characteristic values ​​of resin D.

[0185] Furthermore, the value of the first categorical variable is input based on the first blending data shown in Fig. 13. Similarly, the value of the first irradiation dose is also input based on the first blending data shown in Fig. 13. Here, the value of the first categorical variable is the value of the categorical variable for the first composite material, and the value of the first irradiation dose is the value of the irradiation dose for the first composite material.

[0186] For example, the first composite material identified by the formulation number "ID100" has a filler volume ratio of "0.6", a maleic anhydride modification amount of "0.3", a crystalline amount of "27", a vinyl acetate group amount of "32", and a filler surface area of ​​"643". Furthermore, the first composite material identified by the formulation number "ID100" has the first categorical variables "CAT1" of "1", "CAT2" of "0", "CAT3" of "0", and "CAT4" of "1", and the first irradiation dose of "0".

[0187] Next, the material name and first blending ratio included in the first blending data shown in FIG. 13, and the first composite characteristic value, first categorical variable value, and first irradiation dose value shown in FIG. 14 are input into an approximation function to estimate the physical quantity value for the first composite material. As a result, the estimated physical quantity values ​​are output as shown in the table of FIG. 15. For example, in FIG. 15, it can be seen that a value (estimated value) of "13.15" is output for the tensile strength of the first composite material identified by blending number "ID100."

[0188] In this way, according to this example, it is possible to output the value of a physical quantity that is likely to be realized for the first composite material to be evaluated, the correspondence of which with the value of the physical quantity being unknown.

[0189] In particular, in this specific example, not only categorical variables but also composition information including the names and composition ratios of constituent materials, the first composite characteristic value, and the first irradiation dose (process condition value) are used as input parameters of the approximation function. Therefore, according to this specific example, the number of types of input parameters of the approximation function increases, and as a result, the estimation accuracy of the physical quantity value can be improved.

[0190] For example, when the input parameter is "x" and the output parameter is "y," the approximation function is expressed by a function "f" of y = f(x). In this case, when generating an approximation function using machine learning, generally, increasing the number of types of input parameter "x" often leads to obtaining a more accurate approximation function. For this reason, in this specific example, not only categorical variables but also the first composite characteristic value, compounding information including "material name" and "compound ratio," and the first irradiation dose (process condition value) are used as the input parameter "x." As a result, this specific example has more types of input parameters than when the input parameters are only categorical variables. As a result, this specific example can generate a more accurate approximation function, thereby improving the estimation accuracy of the physical quantity value.

[0191] <Verification of effectiveness> Hereinafter, a description will be given of the verification result that, according to the second embodiment, it is possible to estimate with high accuracy the value of a physical quantity corresponding to a composite material whose correspondence with the value of a physical quantity is unknown.

[0192] Figure 16(a) is a graph showing the results of estimating the initial tensile strength of the first composite material using an approximation function that does not use categorical variables as input parameters. In Figure 16(a), the horizontal axis shows the measured values, while the vertical axis shows the predicted values. As shown in Figure 16(a), the coefficient of determination, R 2 The value is "0.8357".

[0193] In contrast, Figure 16(b) is a graph showing the results of estimating the initial tensile strength of the first composite material using an approximation function that uses categorical variables as input parameters. In Figure 16(b), the horizontal axis shows the measured values, while the vertical axis shows the predicted values. As shown in Figure 16(b), the coefficient of determination, R 2 The value is "0.8722".

[0194] In this case, considering that the larger the coefficient of determination, the closer the predicted value is to the actual measured value, it can be seen that estimating the initial tensile strength of the first composite material using an approximation function that uses categorical variables as input parameters improves the accuracy of estimating the initial tensile strength compared to estimating the initial tensile strength of the first composite material using an approximation function that does not use categorical variables as input parameters.

[0195] 16(a) and 16(b) support the idea that the value of a physical quantity (for example, the value of initial tensile strength) corresponding to a first composite material whose correspondence with a physical quantity value is unknown can be estimated with high accuracy according to the technical idea of ​​the present embodiment 2. In other words, the verification results of Fig. 16(a) and 16(b) demonstrate that the technical idea of ​​the present embodiment 2, of estimating the initial tensile strength of a first composite material using an approximation function that uses categorical variables as input parameters, is a useful technical idea in that it can estimate with high accuracy the value of a physical quantity corresponding to a first composite material whose correspondence with a physical quantity value is unknown.

[0196] The invention made by the inventor has been specifically described above based on the embodiments thereof, but it goes without saying that the present invention is not limited to the above-described embodiments and can be modified in various ways without departing from the spirit of the invention. [Explanation of symbols]

[0197] 100 Physical quantity estimation device 101 CPU 102 ROM 103 RAM 104 Display 105 keyboard 106 Mouse 107 Communication Board 108 Removable disk device 109 CD / DVD-ROM device 110 Printer 111 Scanner 112 Hard disk drive 113 Bus 201 Operating Systems 202 Programs 203 files 301 Input section 301A input section 301B Input section 302 Characteristic value data extraction unit 302A First characteristic value data extraction unit 302B Characteristic value data extraction unit 303 Composite characteristic value calculation unit 303A First composite characteristic value calculation unit 303B Composite characteristic value calculation unit 304 Synthesis-related data generation unit 304A Additional data generation unit 305 Approximation Function Generator 306 Physical quantity estimation section 307 Output section 308 Data Storage Unit 309A Communication Department 309B Communication Department 310A Data storage unit 310B Data storage unit 400 Physical quantity estimation device 500 Approximation Function Generator

Claims

1. A physical quantity estimation system that estimates a value of a physical quantity for a composite material that includes, as constituent materials, two or more materials belonging to a plurality of different materials, an approximate function generating unit that, when a value of a first categorical variable is input, the value of the first categorical variable is made up of a digital variable associated with a factor that influences the value of the physical quantity of a first composite material whose value of the physical quantity is unknown, generates an approximate function that outputs the value of the physical quantity for the first composite material; a physical quantity estimating unit that estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximation function; Equipped with the first composite material includes a flame retardant; The first categorical variable is a first variable indicating whether or not the flame retardant has undergone a first surface treatment; A second variable indicating the presence or absence of a second surface treatment of the flame retardant; a third variable indicating the presence or absence of a first material that constitutes the flame retardant; a fourth variable indicating the presence or absence of a second material that constitutes the flame retardant; A physical quantity estimation system including:

2. 2. The physical quantity estimation system according to claim 1, the first surface treatment is a silane coupling treatment, the second surface treatment is a fatty acid treatment, the first material is magnesium hydroxide; The physical quantity estimation system, wherein the second material is aluminum hydroxide.

3. 2. The physical quantity estimation system according to claim 1, the physical quantity estimation system includes a composite characteristic value calculation unit that calculates a first composite characteristic value of the first composite material based on first blending ratios of constituent materials included in the first composite material and first characteristic values ​​corresponding to the constituent materials included in the first composite material; the approximation function generation unit generates an approximation function that receives the first composite characteristic value and the value of the first categorical variable as input and outputs a value of the physical quantity for the first composite material; The physical quantity estimation unit estimates a value of the physical quantity for the first composite material based on the first composite characteristic value, the value of the first categorical variable, and the approximation function.

4. A physical quantity estimation system for estimating a value of a physical quantity for a composite material containing two or more materials belonging to a plurality of different materials as constituent materials, comprising: an approximate function generating unit that, when a value of a first categorical variable is input, the value of the first categorical variable is made up of a digital variable associated with a factor that influences the value of the physical quantity of a first composite material whose value of the physical quantity is unknown, generates an approximate function that outputs the value of the physical quantity for the first composite material; a physical quantity estimating unit that estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximation function; Equipped with the approximation function generation unit receives a value of the first categorical variable and a first process condition value as input and generates an approximation function that outputs a value of the physical quantity for the first composite material; the physical quantity estimating unit estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable, the first process condition value, and the approximation function; The physical quantity estimation system, wherein the first process condition value is a value of a radiation dose in a crosslinking treatment of a resin.

5. 5. The physical quantity estimation system according to claim 1, A physical quantity estimation system, wherein the physical quantity is elongation or tensile strength.

6. A program for causing a computer to execute a process of estimating a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials, the program comprising: an approximate function generation process for generating an approximate function that outputs a value of a physical quantity for a first composite material when a value of a first categorical variable, the first categorical variable being a digital variable associated with a factor that influences the value of the physical quantity of the first composite material, is input; the first composite material includes a flame retardant; The first categorical variable is a first variable indicating whether or not the flame retardant has undergone a first surface treatment; A second variable indicating the presence or absence of a second surface treatment of the flame retardant; a third variable indicating the presence or absence of a first material that constitutes the flame retardant; a fourth variable indicating the presence or absence of a second material that constitutes the flame retardant; Including, the program.

7. A computer-readable recording medium on which the program according to claim 6 is recorded.

8. A physical quantity estimation device that is a component of a physical quantity estimation system that estimates a value of a physical quantity for a composite material that includes, as constituent materials, two or more materials belonging to a plurality of different material groups, comprising: a physical quantity estimating unit that estimates a value of a physical quantity of a first composite material, the value of the physical quantity of which is unknown, based on a value of a first categorical variable that is made up of digital variables associated with factors that affect the value of the physical quantity of the first composite material, and an approximation function; the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable is input, the first composite material includes a flame retardant; The first categorical variable is a first variable indicating whether or not the flame retardant has undergone a first surface treatment; A second variable indicating the presence or absence of a second surface treatment of the flame retardant; a third variable indicating the presence or absence of a first material that constitutes the flame retardant; a fourth variable indicating the presence or absence of a second material that constitutes the flame retardant; A physical quantity estimation device comprising:

9. 9. The physical quantity estimation device according to claim 8, a composite characteristic value calculation unit that calculates a first composite characteristic value of the first composite material based on a first blending ratio of constituent materials included in the first composite material and a first characteristic value corresponding to the constituent materials included in the first composite material; the physical quantity estimating unit estimates a value of the physical quantity for the first composite material based on the first composite characteristic value, the value of the first categorical variable, and an approximation function; The physical quantity estimation device, wherein the approximation function is a function that outputs the value of the physical quantity for the first composite material when the first composite characteristic value and the value of the first categorical variable are input.

10. A physical quantity estimation device that is a component of a physical quantity estimation system that estimates a value of a physical quantity for a composite material that includes two or more materials belonging to a plurality of different materials as constituent materials, comprising: a physical quantity estimating unit that estimates a value of a physical quantity of a first composite material, the value of the physical quantity of which is unknown, based on a value of a first categorical variable that is made up of digital variables associated with factors that affect the value of the physical quantity of the first composite material, and an approximation function; the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable is input, the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable and a first process condition value are input; the physical quantity estimating unit estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable, the first process condition value, and the approximation function; the first process condition value is a value of radiation exposure dose in a crosslinking treatment of a resin; Physical quantity estimation device.

11. A program for causing a computer to execute a process of estimating a value of a physical quantity for a composite material including, as constituent materials, two or more materials belonging to a plurality of different materials, the program comprising: a physical quantity estimation process for estimating a value of a physical quantity of a first composite material, the value of the physical quantity of which is unknown, based on a value of a first categorical variable including digital variables associated with factors that affect the value of the physical quantity of the first composite material and an approximation function; the approximation function is a function that outputs a value of the physical quantity for the first composite material when a value of the first categorical variable is input, the first composite material includes a flame retardant; The first categorical variable is a first variable indicating whether or not the flame retardant has undergone a first surface treatment; A second variable indicating the presence or absence of a second surface treatment of the flame retardant; a third variable indicating the presence or absence of a first material that constitutes the flame retardant; a fourth variable indicating the presence or absence of a second material that constitutes the flame retardant; Including, the program.

12. A computer-readable recording medium on which the program according to claim 11 is recorded.

13. A physical quantity estimation method in which a computer estimates a value of a physical quantity for a composite material including two or more materials belonging to a plurality of different material groups as constituent materials, the method comprising: an approximate function generating step in which, when a value of a first categorical variable consisting of a digital variable associated with a factor that influences the value of a physical quantity of a first composite material whose value is unknown, an approximate function generating unit of a computer generates an approximate function that outputs a value of the physical quantity for the first composite material; a physical quantity estimating step in which a physical quantity estimating unit of a computer estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximation function; Equipped with the first composite material includes a flame retardant; The first categorical variable is a first variable indicating whether or not the flame retardant has undergone a first surface treatment; A second variable indicating the presence or absence of a second surface treatment of the flame retardant; a third variable indicating the presence or absence of a first material that constitutes the flame retardant; a fourth variable indicating the presence or absence of a second material that constitutes the flame retardant; A physical quantity estimation method, including:

14. The physical quantity estimation method according to claim 13, The physical quantity estimation method includes a composite characteristic value calculation step in which a composite characteristic value calculation unit of a computer calculates a first composite characteristic value of the first composite material based on first blending ratios of constituent materials included in the first composite material and first characteristic values ​​corresponding to the constituent materials included in the first composite material; In the approximation function generating step, the approximation function generating unit of the computer receives the first composite characteristic value and the value of the first categorical variable and generates an approximation function that outputs a value of the physical quantity for the first composite material; a physical quantity estimation unit of a computer estimating a value of the physical quantity for the first composite material based on the first composite characteristic value, the value of the first categorical variable, and the approximation function, in the physical quantity estimation step.

15. A physical quantity estimation method in which a computer estimates a value of a physical quantity for a composite material containing two or more materials belonging to a plurality of different materials as constituent materials, comprising: an approximate function generating step in which, when a value of a first categorical variable consisting of a digital variable associated with a factor that influences the value of a physical quantity of a first composite material whose value is unknown, an approximate function generating unit of a computer generates an approximate function that outputs a value of the physical quantity for the first composite material; a physical quantity estimating step in which a physical quantity estimating unit of a computer estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable and the approximation function; Equipped with In the approximation function generating step, an approximation function generating unit of a computer receives a value of the first categorical variable and a first process condition value as input and generates an approximation function that outputs a value of the physical quantity for the first composite material; In the physical quantity estimation step, a physical quantity estimation unit of a computer estimates a value of the physical quantity for the first composite material based on the value of the first categorical variable, the first process condition value, and the approximation function; the first process condition value is a value of radiation exposure dose in a crosslinking treatment of a resin; Physical quantity estimation method.

Images