Method for generating a material property prediction model, apparatus for generating a material property prediction model, method for predicting material properties, and apparatus for predicting material properties

Abstract

This technology provides a standardized process for generating features, thereby improving user convenience. [Solution] The method for generating a physical property prediction model comprises: a data mart generation step of generating a data mart that includes the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound; a base calculation generation step of generating a base calculation table that describes the materials and the calculation processing applied to the materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; a training data generation step of generating a training data mart consisting of at least one of the feature quantities calculated by the base calculation step and the data included in the data mart; and a training step of training a learning-type calculation model that predicts the physical properties of a rubber compound based on the training data mart.

Description

Technical Field

[0001] The present invention relates to a method for generating a physical property prediction model, an apparatus for generating a physical property prediction model, a physical property prediction method, and an apparatus for predicting physical properties in a rubber formulation.

Background Art

[0002] For example, a rubber formulation used for a tire or the like mounted on a vehicle is a composite material in which a polymer, which is a rubber material as a main raw material, is added with a reinforcing agent and various chemicals. Rubber formulations are formulated based on various materials according to their uses, and those having different physical properties have been developed.

[0003] Patent Document 1 discloses a conventional physical property prediction system. The physical property prediction system includes a prediction device, an information terminal, and a database. The performance prediction unit of the prediction device predicts the value of the physical properties of the rubber to be predicted based on the material information regarding a plurality of materials constituting the rubber to be predicted. The display processing unit of the information terminal associates the predicted value predicted by the performance prediction unit with the feature amount of a specific material among the plurality of materials and displays the same on the display unit.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When extracting the feature amounts of the materials used in the formulation of a rubber formulation to predict the physical properties, the feature amounts have conventionally been derived by experience and knowledge, and there has been a problem that the prediction of the physical properties is complicated. Further, when generating a large number of feature amounts for predicting the physical properties, a high-level data processing ability regarding the materials is required, and there has been a concern that the convenience in performing the physical property prediction is reduced.

[0006] This invention has been made in view of the above circumstances, and its purpose is to provide a method for generating a material property prediction model, a material property prediction model generation apparatus, a material property prediction method, and a material property prediction apparatus that can improve user convenience by standardizing the computational processing process for generating feature quantities. [Means for solving the problem]

[0007] One aspect of the present invention is a method for generating a physical property prediction model. The method for generating a physical property prediction model comprises: a data mart generation step of generating a data mart that includes the blending amounts of a plurality of materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the plurality of materials, and the physical properties of the rubber compound; a base calculation generation step of generating a base calculation table that describes the materials and the calculation processing applied to the materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; a learning data generation step of generating a learning data mart consisting of at least one of the feature quantities calculated by the base calculation step and the data included in the data mart; and a learning step of training a learning-type calculation model that predicts the physical properties of a rubber compound based on the learning data mart.

[0008] Another aspect of the present invention is a physical property prediction model generation device. The physical property prediction model generation device comprises: a data mart generation unit that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound; a base calculation unit that generates a base calculation table describing the materials and the calculation processing applied to the materials, and calculates feature quantities based on the calculation processing by the base calculation table; a learning data generation unit that adds the feature quantities calculated by the base calculation unit to the data mart to generate a learning data mart; and a learning processing unit that trains a learning-type calculation model for predicting the physical properties of a rubber compound based on the learning data mart.

[0009] Another aspect of the present invention is a method for predicting physical properties. The method for predicting physical properties comprises: a data mart generation step of generating a data mart that includes the blending amounts of a plurality of materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the plurality of materials; a base calculation generation step of generating a base calculation table that describes the materials and the calculation processing applied to the materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; and a physical property prediction step of inputting at least one of the feature quantities calculated by the base calculation step and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound.

[0010] Another aspect of the present invention is a physical property prediction device. The physical property prediction device comprises: a data mart generation unit that generates a data mart including the blending amounts of a plurality of materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the materials; a base calculation unit that generates a base calculation table describing the materials and the calculation processing applied to the materials, and calculates feature quantities based on the calculation processing by the base calculation table; and a physical property prediction processing unit that inputs at least one of the feature quantities calculated by the base calculation unit and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound. [Effects of the Invention]

[0011] According to the present invention, the process of computation for generating feature quantities can be standardized, thereby improving user convenience. [Brief explanation of the drawing]

[0012] [Figure 1] This is a block diagram showing the functional configuration of the physical property prediction model generation device according to Embodiment 1. [Figure 2] This diagram illustrates the relationship between mixing time and mixing temperature in the mixing process of each material in a rubber compound. [Figure 3] This is a schematic diagram illustrating the condensation reaction between the silanol groups of silica particles and the silane agent. [Figure 4] This diagram shows an example of setting the temperature T2 and mixing time t2 in the second mixing process. [Figure 5] This graph illustrates the impact of the second mixing process on tire fuel efficiency. [Figure 6] Figure 6(a) is a diagram showing an example of a base calculation table, and Figure 6(b) is a diagram showing an example of a feature calculated by the base calculation table. [Figure 7] Figure 7(a) is a diagram showing an example of a material group table that specifies the correspondence between material groups and material target numbers, and Figure 7(b) is a diagram showing an example of a material category table that specifies the correspondence between material target numbers and material categories. [Figure 8] Figure 8(a) is a diagram showing an example of an analysis group table that specifies the correspondence between numerical analysis groups and analysis target numbers, and Figure 8(b) is a diagram showing an example of an analysis category table that specifies the correspondence between analysis target numbers and numerical analysis categories. [Figure 9] Figure 9(a) is a diagram showing an example of a composite calculation table, and Figure 9(b) is a diagram showing an example of a feature calculated by the composite calculation table. [Figure 10] This is a flowchart showing the steps involved in generating the computational model. [Figure 11] This flowchart shows the procedure for calculating features based on a base calculation table. [Figure 12] This flowchart shows the procedure for calculating features based on a composite calculation table. [Figure 13] This is a block diagram showing the functional configuration of the physical property prediction device according to Embodiment 2. [Figure 14] This is a flowchart showing the procedure for predicting material properties. [Figure 15] This is a block diagram showing the functional configuration of the formulation prediction device according to Embodiment 3. [Figure 16] This is a flowchart showing the procedure for the formulation prediction process.

Best Mode for Carrying Out the Invention

[0013] Hereinafter, the present invention will be described based on preferred embodiments with reference to FIGS. 1 to 16. The same or equivalent components and members shown in each drawing are denoted by the same reference numerals, and repeated explanations will be omitted as appropriate. In addition, the dimensions of the members in each drawing are appropriately enlarged or reduced for easy understanding. Also, a part of the members that are not important for explaining the embodiments in each drawing is omitted from the display.

[0014] (Embodiment 1) FIG. 1 is a block diagram showing the functional configuration of a physical property prediction model generation device 100 according to Embodiment 1. The physical property prediction model generation device 100 includes a storage unit 10, an operation unit 31, a display unit 32, and an arithmetic processing unit 4 and generates an arithmetic model for predicting the physical properties of a rubber composition used in, for example, tires. The physical property prediction model generation device 100 is an information processing device such as a PC (personal computer). Each part in the physical property prediction model generation device 100 can be realized hardware-wise by an electronic processing circuit and mechanical parts including a computer CPU and software-wise by a computer program or the like. Here, functional blocks realized by their cooperation are depicted. Therefore, it is understood by those skilled in the art that these functional blocks can be realized in various forms by combinations of hardware and software.

[0015] The storage unit 10 is a storage device constituted by, for example, an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, or the like. In the storage unit 10, a data mart 11 used for predicting the physical properties of a rubber composition, a table 21 used for arithmetic operations, a computer program executed by the arithmetic processing unit 40, and data used for executing the computer program are stored.

[0016] The data mart 11 includes formulation data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 corresponding to each of the multiple rubber compound. In the data mart 11, for example, identification information such as a sequential number is assigned to each of the multiple rubber compound, and the formulation, physical properties, and raw material properties corresponding to each identification information are included in the formulation data 12, physical property data 13, and raw material data 14.

[0017] Compounding data 12 is a set of data showing the proportions of each material in multiple rubber compoundings. Compounding data 12 includes the names and proportions of the main rubber materials, reinforcing agents, and various chemicals corresponding to each of the multiple rubber compoundings. Examples of rubber materials include natural rubber (NR), butadiene rubber (BR), styrene-butadiene rubber (SBR), and isobutylene-isoprene rubber (IIR). Examples of reinforcing agents (fillers) include carbon black and silica. Examples of various chemicals include sulfur, wax, and silanes. The proportions are expressed as volume, weight, and their ratios. Silanes are also called silane coupling agents.

[0018] The physical property data 13 consists of data for each of the multiple rubber compound, such as hardness Hs, tensile stress S, loss tangent tanδ, abrasion resistance, rebound elasticity, rolling resistance coefficient, and fuel efficiency index. The raw material data 14 consists of data for each of the multiple rubber compound, such as property values ​​and categorical variables of the materials used. Property values ​​include, for example, DBP (Dibutyl Phthalate) absorption and carbon surface area, while categorical variables include, for example, the ASTM grade of carbon.

[0019] The mixing condition data 15 is data on the conditions in the mixing process of each material of the rubber compound. The mixing process is also called the kneading process because it involves mixing and kneading each material of the rubber compound. The mixing process can be considered as part of the various subsequent processing processes. Therefore, the mixing condition data 15 can be considered as part of the processing condition data 16 described later, and may be considered as being included in the processing condition data 16.

[0020] Figure 2 is a diagram illustrating the relationship between mixing time and mixing temperature in the mixing process of each material in a rubber compound. In Figure 2, the horizontal axis represents mixing time, and the vertical axis represents mixing temperature. In the mixing process of a rubber compound, each material is introduced into the chamber of a mixer and mixed together. The mixer is, for example, an internal mixer. An internal mixer is also called a Banbury mixer. The mixing temperature represents the temperature inside the chamber of the mixer.

[0021] The mixing process includes two steps: a first mixing step and a second mixing step. The first mixing step is the process of uniformly mixing each material, such as rubber material, reinforcing material, and various chemicals, by kneading them as they are sequentially introduced into the chamber of the mixer. Depending on the order, timing, and mixing time of each material introduced into the mixer in the first mixing step, as well as the type of mixer, the uniformity of each material in the mixture after the completion of the first mixing step changes, and thus the physical properties of the rubber compound change. The mixing condition data 15 may include the above-mentioned conditions in the first mixing step. The material introduced into the chamber of the mixer and undergoing the mixing process is referred to as the mixture.

[0022] In the first mixing step, the temperature inside the mixer chamber decreases and increases as mixing progresses, starting from the initial temperature To at the beginning of mixing. The temperature inside the chamber decreases as the preheated mixer chamber cools down after the materials are added, and then increases due to friction and chemical reactions caused by kneading. In the first mixing step, the mixture is mixed for a predetermined mixing time t1, reaching a final temperature T1. The temperature inside the chamber and the temperature of the mixture at the end of the first mixing step can be considered to be approximately the same.

[0023] The second mixing step is a subsequent step following the first mixing step, and its purpose is to promote the condensation reaction between silica and the silane agent. In the first mixing step, silica, used as a reinforcing material, is crushed into fine particles and dispersed within the mixture. The condensation reaction between silica and the silane agent in the second mixing step further increases the dispersibility within the mixture, which is known to lead to improved fuel efficiency in vehicles equipped with tires made of rubber compounds, for example.

[0024] Figure 3 is a schematic diagram illustrating the condensation reaction between the silanol groups of silica particles and the silane agent. In the second mixing step, the condensation reaction between silica and the silane agent replaces the hydrogen atoms (H) of the silanol groups on the surface of the silica particles with hydrophobic molecules of the silane agent (silane coupling agent). As the silica surface becomes more hydrophobic, its affinity for rubber increases, and the dispersibility of silica in the mixture is improved.

[0025] Returning to Figure 2, the second mixing step involves mixing the mixture for a predetermined mixing time t2 while maintaining the mixture at a predetermined set temperature T2. It is preferable that the temperature inside the mixer chamber and the temperature of the mixture be controlled to be approximately the same. The set temperature T2 is an important condition for promoting the condensation reaction between silica and the silane agent, so strictly speaking, it is preferable to specify it as the temperature of the mixture, but it may also be specified as the temperature inside the chamber, assuming that the temperature inside the chamber and the temperature of the mixture are equivalent in the second mixing step. The set temperature T2 is set, for example, in the range of 120°C or higher and 160°C or lower. It is more preferable that the set temperature T2 be set in the range of 130°C or higher and 160°C or lower. The mixing time t2 is set, for example, in the range of 30 seconds or higher and 360 seconds or lower. In practice, the temperature of the mixture in the second mixing step is controlled within a predetermined temperature range including the set temperature T2 (e.g., within ±3°C of the set temperature T2). If there is a difference between the end temperature T1 of the first mixing step and the set temperature T2 of the second mixing step, a transition period is provided to change the temperature of the mixture to the set temperature T2.

[0026] Figure 4 is a diagram showing examples of setting the temperature T2 and mixing time t2 in the second mixing step. In Figure 4, examples are shown where the setting temperature T2 is set in the range of 130°C or higher and 160°C or lower, and the mixing time t2 is set in the range of 30 seconds or higher and 360 seconds or lower. For example, the setting temperature T2 may be set to 150°C and the mixing time t2 to 90 seconds. Note that the setting temperature T2 and mixing time t2 in the second mixing step are not limited to the examples shown above.

[0027] Figure 5 is a graph illustrating the effect of the second mixing process on tire fuel efficiency. In Figure 5, the horizontal axis represents the mixing time t2 in the second mixing process, and the vertical axis represents the fuel efficiency index. The fuel efficiency index is expressed using, for example, the rolling resistance coefficient, and the larger the fuel efficiency index, the greater the energy loss and the worse the fuel efficiency. Figure 5 shows graphs of the fuel efficiency index when the set temperature T2 is 140°C, 150°C, and 160°C. As shown in Figure 5, the fuel efficiency index changes according to the mixing time t2 for each set temperature T2. The fuel efficiency index may be, for example, the value of the rolling resistance coefficient, or the ratio value of the rolling resistance coefficient to a reference value.

[0028] The dispersibility of silica in the mixture during the second mixing process changes depending on conditions such as the set temperature T2, mixing time t2, and type of mixer, which in turn changes the physical properties of the rubber compound (e.g., fuel efficiency). The mixing condition data 15 shall include all of the above-mentioned conditions in the second mixing process.

[0029] In practice, the temperature of the mixture during the second mixing step is controlled to remain within a predetermined temperature range, including the set temperature T2. Therefore, the mixing condition data 15 may include the lower and upper temperature limits of the predetermined temperature range as conditions for the second mixing step.

[0030] The processing condition data 16 is a data set that includes conditions such as time, temperature, name of the machine used during processing, and name of the processing method for each processing step such as molding and vulcanization of the mixed rubber compound. The data may be in the form of numerical variables or categorical variables. The data mart 11 may acquire compounding data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 of multiple rubber compound products from an external device 90. The external device 90 is, for example, an information processing device such as a PC, and has a storage device that stores compounding data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 of multiple rubber compound products.

[0031] Table 21 includes the base calculation table 22, material group table 23, material category table 24, analysis group table 25, analysis category table 26, and composite calculation table 27 used by the calculation processing unit 40. These tables will be described later.

[0032] The operation unit 31 has operable input devices such as a touch panel, switches, keyboard, and mouse device, and accepts user input. The operation unit 31 accepts user input in the generation of rubber compound property prediction models, property prediction, and compound prediction.

[0033] The display unit 32 has a display device such as a liquid crystal display and displays a screen for receiving various data and user inputs during the generation process of the rubber compound property prediction model. The display unit 32 also displays a screen for receiving various data and user inputs during the rubber compound property prediction and formulation prediction.

[0034] The arithmetic processing unit 40 includes a data mart generation unit 41, a base arithmetic unit 42, a composite arithmetic unit 43, a learning data generation unit 44, a physical property prediction processing unit 45, and a learning processing unit 46. The arithmetic processing unit 40 is an electronic circuit that performs arithmetic processing, such as a CPU, and functions by reading and executing computer programs and data stored in the storage unit 10. The data mart generation unit 41, base arithmetic unit 42, composite arithmetic unit 43, learning data generation unit 44, physical property prediction processing unit 45, and learning processing unit 46 in the arithmetic processing unit 40 may be constructed as a plurality of program modules formed by computer programs.

[0035] The data mart generation unit 41 acquires compounding data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 of multiple rubber compounding materials from an external device 90 to generate a data mart 11. The data mart generation unit 41 may also set all or part of a database of compounding, physical properties, raw material properties and categorical variables of multiple rubber compounding materials, as well as mixing conditions and processing conditions, which are stored in the storage unit 10 in advance, as the data mart 11 to be used for generating a physical property prediction model. The data mart generation unit 41 may also generate the data mart 11 by receiving user input via the operation unit 31 to specify the rubber compounding materials to be included in the data mart 11.

[0036] The base calculation unit 42 generates a base calculation table 22 that describes the materials used in the compounding of the rubber compound and the calculation processing performed on those materials. The base calculation unit 42 calculates feature quantities based on the calculation processing performed using the generated base calculation table 22.

[0037] Figure 6(a) is a diagram showing an example of the base calculation table 22, and Figure 6(b) is a diagram showing an example of the feature quantities calculated by the base calculation table 22. As shown in Figure 6(a), the base calculation table 22 consists of an action number, a material group, a numerical analysis group, and an action description.

[0038] In the base calculation table 22 generated by the base calculation unit 42, for example, for action number A1, material group G1 is specified as numerical analysis group SG1, and the action content is specified as calculating a weighted average value W_avg based on the blending amount. For action number A2, etc., the action content is specified as calculating a sum value SUM by addition. For action number A4, the action content is specified as performing clustering by principal component analysis (PCA) and extracting principal components. The action content in the base calculation table 22 includes arithmetic operations, weighted averages, principal component analysis, and special numerical analysis calculations such as t-distribution type stochastic nearest neighbor embedding (t-SNE).

[0039] The base calculation unit 42 calculates the feature quantities shown in Figure 6(b) by performing calculation processing according to the base calculation table 22 shown in Figure 6(a). Figure 7(a) is a diagram showing an example of a material group table 23 that specifies the correspondence between material groups and material target numbers, and Figure 7(b) is a diagram showing an example of a material category table 24 that specifies the correspondence between material target numbers and material categories. Figure 8(a) is a diagram showing an example of an analysis group table 25 that specifies the correspondence between numerical analysis groups and analysis target numbers, and Figure 8(b) is a diagram showing an example of an analysis category table 26 that specifies the correspondence between analysis target numbers and numerical analysis categories.

[0040] As shown in Figure 7(a), material group G1 is associated with material target number M1. Material group G4 is associated with material target numbers M4 and M5. As shown in Figure 7(b), material classifications and material categories are associated with material target numbers. For example, material target number M1 is associated with carbon (material category), which is a reinforcing material (material classification). Material target number M2 is associated with carbon and silica, which are reinforcing materials. Material target number M3 is associated with oil, material target number M4 is associated with SBR rubber, and material target number M5 is associated with BR rubber. In addition to the material classifications and material categories shown in Figure 7(b), further subdivided classifications and categories may be created. Alternatively, material classifications and material categories may be identified by symbols, and a master table may be created for the materials corresponding to each symbol.

[0041] As shown in Figure 8(a), analyte number B1 is associated with numerical analysis group SG1, and analyte number B2 is associated with numerical analysis group SG2. As shown in Figure 8(b), the DBP absorption amount, which indicates the degree of carbon particle linkage and aggregation, is associated with analyte number B1 as a numerical analysis category. The numerical analysis categories associated with analyte number B2 are the amount of cis-1,4 bonds in the butadiene unit portion of SBR or BR (denoted as Cis%), the amount of trans-1,4 bonds in the butadiene unit portion of SBR or BR (denoted as Trans%), the styrene content in SBR (denoted as St%), and the amount of 1,2-vinyl bonds in the butadiene unit portion of SBR or BR (denoted as Vinyl%).

[0042] The calculation process in the base calculation unit 42 will be explained using action number A1 as an example. Returning to Figure 6(a), in action number A1, material group G1 is specified as material target number M1 (see Figure 7(a)), which corresponds to the reinforcing carbon (see Figure 7(b)). In action number A1, numerical analysis group SG1 is specified as analysis target number B1 (see Figure 8(a)), which corresponds to DBP absorption amount (see Figure 8(b)). The action content in action number A1 is to calculate the weighted average value W_avg based on the blending amount. As shown in Figure 6(b), the base calculation unit 42 calculates the weighted average value W_avg based on the blending amount for the DBP absorption amount of various carbons used in the rubber compound as a feature quantity through the calculation of action number A1.

[0043] The blending amounts of each type of carbon are included in the blending data 12 of the data mart 11. The DBP absorption amounts of each type of carbon are included in the raw material data 14 of the data mart 11. The base calculation unit 42 reads the necessary data from the data mart 11 and performs calculation processing in the base calculation table.

[0044] The base calculation unit 42 generates a base calculation table 22 describing the calculation process based on user input specifying the materials used in the rubber compound formulation and the calculation process applied to those materials, and stores it in the storage unit 10. The base calculation unit 42 also generates a material group table 23, a material category table 24, an analysis group table 25, and an analysis category table 26 based on user input specifying material groups, etc., and stores them in the storage unit 10. The base calculation table 22, material group table 23, material category table 24, analysis group table 25, and analysis category table 26 may be generated based on user input from the operation unit 31, or they may be generated using pre-prepared tables. The administrator of the physical property prediction model generation device 100 may also prepare an electronic file containing the base calculation table 22 and other tables in advance and store it in the storage unit 10. Note that the operator performing the processing related to the physical property prediction model, as well as the administrator of the physical property prediction model generation device 100, may be considered a user.

[0045] When a user adds a new feature, the base calculation unit 42 sequentially adds the new action number to the base calculation table 22 and updates the base calculation table 22 based on user input specifying the material group, numerical analysis group, and action content. The base calculation unit 42 updates the material group table 23, material category table 24, analysis group table 25, and analysis category table 26 based on user input specifying information related to the new action number.

[0046] The material group table 23 and the material category table 24 function as auxiliary tables that supplement the material information in the base calculation table 22. Similarly, the analysis group table 25 and the analysis category table 26 function as auxiliary tables that supplement the information related to the numerical analysis.

[0047] The composite calculation unit 43 selects at least two feature quantities calculated by the base calculation unit 42 and generates a composite calculation table 27 that describes the calculation process. The composite calculation unit 43 calculates feature quantities based on the calculation process using the generated composite calculation table 27. Based on user input specifying the calculation process by selecting at least two feature quantities calculated by the base calculation unit 42, the composite calculation unit 43 generates a composite calculation table 27 that describes the calculation process and stores it in the storage unit 10. The composite calculation table 27 may be generated based on user input from the operation unit 31, or it may be generated using a pre-prepared table. Alternatively, the administrator of the physical property prediction model generation device 100 may prepare an electronic file containing the composite calculation table 27 in advance and store it in the storage unit 10.

[0048] Figure 9(a) is a diagram showing an example of a composite calculation table 27, and Figure 9(b) is a diagram showing an example of a feature calculated by the composite calculation table 27. As shown in Figure 9(a), the composite calculation table 27 consists of an action number, an action number in the base calculation table 22, and an action description.

[0049] In the composite calculation table 27 generated by the composite calculation unit 43, for example, action number AM1 is specified as action numbers A2 and A3 in the base calculation table 22, and the action content is a subtraction operation. The action content in the composite calculation table 27 is an arithmetic operation on at least two of the feature quantities calculated by the base calculation table 22.

[0050] The composite calculation unit 43 calculates the feature quantities shown in Figure 9(b) by performing calculations using the composite calculation table 27 shown in Figure 9(a).

[0051] As shown in Figure 9(b), action number AM1 yields a feature value obtained by subtracting the total amount of oil from the total amount of filler. This value tends to correlate highly with rubber hardness. Action number AM2 yields a feature value obtained by dividing the total amount of oil by the total amount of filler. This value also tends to correlate highly with rubber hardness. Generally, rubber hardness is thought to be determined by the balance between oil and filler.

[0052] Action number AM3 yields a feature value that is the sum of the total filler amount and the total oil amount. This sum tends to correlate highly with fuel efficiency. Generally, fuel efficiency is determined by the energy loss components in the rubber compound, and oil and filler are considered to be energy loss components.

[0053] Action number AM4 yields a feature value obtained by multiplying the total filler amount by the amount of DBP absorbed by carbon. This product of the total filler amount and the amount of DBP absorbed by carbon tends to correlate highly with wear resistance. Generally, wear resistance depends on the reinforcing properties of the filler, and it is believed that the reinforcing properties of the filler can be represented by multiplying the total filler amount and the amount of DBP absorbed by carbon.

[0054] The training data generation unit 44 generates a training data mart consisting of at least one of the features calculated by the base calculation unit 42 and the features calculated by the composite calculation unit 43, and the data contained in the data mart 11. The training data mart may include at least one of the features calculated by the base calculation unit 42 and not include any features calculated by the composite calculation unit 43. The training data mart may not include any features calculated by the base calculation unit 42 and may include at least one of the features calculated by the composite calculation unit 43. The training data mart may include at least one of the features calculated by the base calculation unit 42 and at least one of the features calculated by the composite calculation unit 43.

[0055] The learning data generation unit 44 generates a learning data mart that includes some or all of the multiple rubber compounds included in the data mart 11. The rubber compounds included in the learning data mart may be pre-set, or they may be selected by user input received by the operation unit 31. The learning data generation unit 44 also generates a learning data mart that includes some or all of the compounding data 12 and physical property data 13. The learning data mart may also include some or all of the raw material data 14. The learning data mart may also include some or all of the mixing condition data 15 and processing condition data 16.

[0056] The learning data generation unit 44 may include pre-set data from among the formulation data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 in the learning data mart. Alternatively, the learning data generation unit 44 may receive user input via the operation unit 31 and select the data from among the formulation data 12, physical property data 13, raw material data 14, mixing condition data 15, and processing condition data 16 to include in the learning data mart.

[0057] The physical property prediction processing unit 45 inputs data other than the physical property data 13 in the learning data mart generated by the learning data generation unit 44 as explanatory variables into a learning-type computational model 45a to predict the physical properties of the rubber compound. In the physical property prediction processing unit 45, the explanatory variables that are input data to the computational model 45a are the compounding data 12, the feature quantities calculated by the base computation unit 42 and the composite computation unit 43, the raw material data 14, the mixing condition data 15, and the processing condition data 16. The computational model 45a is a random forest type learning model, which is an ensemble learning algorithm using decision trees.

[0058] The learning processing unit 46 trains the computational model 45a based on the learning data mart generated by the learning data generation unit 44. The learning processing unit 46 compares the estimated physical properties of the rubber compound, which are output data from the computational model 45a, with the known physical property data 13, which are training data, and trains the computational model 45a. The computational model 45a may be, for example, a generalized linear regression model, a DNN (Deep Neural Network) model, a gradient boosting decision tree model, etc. Known validation methods such as random data sampling and cross-validation can be used to validate the computational model 45a.

[0059] Next, the operation of the physical property prediction model generation device 100 will be described. Figure 10 is a flowchart showing the procedure for generating the calculation model 45a. The data mart generation unit 41 of the calculation processing unit 40 generates a data mart 11 to be used for training the calculation model 45a (S1). The data mart 11 includes at least formulation data 12, physical property data 13, and raw material data 14. In addition to the formulation data 12, physical property data 13, and raw material data 14, the data mart 11 may also include mixing condition data 15 and processing condition data 16.

[0060] The base calculation unit 42 generates a base calculation table 22 that describes the materials of the rubber compound and the calculation processing for those materials (S2). In step S2, along with generating the base calculation table 22, the base calculation unit 42 generates a material group table 23, a material category table 24, an analysis group table 25, and an analysis category table 26.

[0061] The base calculation unit 42 calculates feature quantities based on the calculations performed by the base calculation table 22 (S3). In step S3, the base calculation unit 42 refers to the material group table 23, the material category table 24, the analysis group table 25, and the analysis category table 26, and performs the calculations performed by the base calculation table 22.

[0062] The composite calculation unit 43 selects at least two of the feature quantities calculated by the base calculation unit 42 and generates a composite calculation table 27 that describes the calculation process (S4). The composite calculation unit 43 calculates feature quantities based on the calculation process performed by the base calculation table 22 (S5).

[0063] The training data generation unit 44 generates a training data mart consisting of at least one of the feature quantities calculated by the base calculation unit 42 and the composite calculation unit 43, as well as data included in the data mart 11 (S6). The training data mart includes formulation data 12, physical property data 13, and raw material data 14. The training data mart may also include mixing condition data 15 and processing condition data 16.

[0064] The learning processing unit 46 trains a learning-type computational model 45a that predicts the physical properties of the rubber compound based on the training data mart (S7), and then terminates the process. The learning processing unit 46 compares the estimated values ​​of the physical properties of the rubber compound calculated by the computational model 45a with the known physical property data 13 used as training data, and trains the computational model 45a.

[0065] Figure 11 is a flowchart showing the procedure for calculating features based on the base calculation table 22. The base calculation unit 42 selects one unexecuted action number in the base calculation table 22 (S11). Based on the material group in the selected action number, the base calculation unit 42 refers to the material group table 23 and the material category table 24 and extracts data from the formulation data 12 (S12).

[0066] The base calculation unit 42 determines whether or not there is a numerical analysis group corresponding to the action number in the base calculation table 22 (S13). If it is determined in step S13 that there is no numerical analysis group (S13: NO), the base calculation unit 42 executes the action content in the base calculation table 22 and calculates the feature quantities (S14).

[0067] If it is determined in step S13 that a numerical analysis group exists (S13: YES), the base calculation unit 42 refers to the analysis group table 25 and the analysis category table 26 and extracts data such as property values ​​from the raw material data 14 (S15). After step S15, the base calculation unit 42 proceeds to step S14 and executes the action contents in the base calculation table 22 to calculate feature quantities.

[0068] After step S14, the base calculation unit 42 determines whether or not it has performed all action numbers (S16). If it determines in step S16 that it has not performed all action numbers (S16: NO), the base calculation unit 42 returns to step S11 and repeats the process. If it determines in step S16 that it has performed all action numbers (S16: YES), the base calculation unit 42 terminates the process.

[0069] Figure 12 is a flowchart showing the procedure for calculating features based on the composite calculation table 27. The composite calculation unit 43 selects one unexecuted action number in the composite calculation table 27 (S21). The composite calculation unit 43 extracts the feature of the action number in the base calculation table 22 that corresponds to the selected action number (S22). The composite calculation unit 43 executes the action content in the composite calculation table 27 on the feature extracted in step S22 and calculates the feature (S23).

[0070] After step S23, the composite calculation unit 43 determines whether or not it has performed the actions for all action numbers (S24). If it determines in step S24 that it has not performed the actions for all action numbers (S24: NO), the composite calculation unit 43 returns to step S21 and repeats the process. If it determines in step S24 that it has performed the actions for all action numbers (S24: YES), the composite calculation unit 43 terminates the process.

[0071] The physical property prediction model generation method in this embodiment generates a data mart 11 in a data mart generation step, which includes the blending amounts of multiple materials used in the production of the rubber compound, the property values ​​of the materials, and the physical properties of the rubber compound. The physical property prediction model generation method generates a base calculation table 22 in a base calculation generation step, which describes the materials and the calculation processes applied to the materials. The physical property prediction model generation method calculates feature quantities based on the calculation processes in the base calculation table 22 in a base calculation step.

[0072] The material property prediction model generation method generates a training data mart consisting of at least one feature calculated in the base calculation step and data contained in the data mart 11 in the training data generation step. In the training step, the material property prediction model generation method trains a learning-type calculation model 45a that predicts the material properties of rubber compounds based on the training data mart. This material property prediction model generation method improves user convenience by standardizing the calculation process for generating feature quantities.

[0073] The method for generating a physical property prediction model generates a data mart containing the mixing conditions in a mixing process in which multiple materials are mixed, through a data mart generation step. The conditions in the mixing process of each material, such as rubber material, reinforcing material, and various chemicals used in the production of rubber compound, contribute to the dispersibility of each material in the rubber compound and affect the properties of the rubber compound. The method for generating a physical property prediction model can generate a computational model 45a with high estimation accuracy that takes the mixing conditions into account by including the mixing conditions in the data mart 11 and training the computational model 45a.

[0074] The method for generating a physical property prediction model includes, as mixing conditions, the set temperature T2 and mixing time t2 in the second mixing step described above, which promote the condensation reaction of silica and silane. As shown in Figure 5, the set temperature T2 and mixing time t2 in the second mixing step affect the fuel efficiency performance of a vehicle equipped with the tire when the rubber compound is a tire. The method for generating a physical property prediction model can generate a calculation model 45a that considers the fuel efficiency performance of a tire, for example, by generating a data mart 11 that includes the set temperature T2 and mixing time t2 in the second mixing step as mixing conditions. Here, it is preferable that the method for generating a physical property prediction model includes physical property values ​​such as the rolling resistance coefficient and the low fuel consumption performance index as physical properties of the rubber compound in the data mart 11.

[0075] The method for generating a physical property prediction model may also include the type of mixer as a mixing condition. Various types of mixers, such as Banbury mixers, are used, and the mixing performance, such as the volume of the mixture to be mixed, the mixing time, and the uniformity of the resulting mixture, differs depending on the type and model number of the individual mixer. The method for generating a physical property prediction model can generate a calculation model 45a that takes the type of mixer into account by generating a data mart 11 that includes the type of mixer (type and model number, etc.) as a mixing condition.

[0076] The method for generating a physical property prediction model sets the set temperature T2 to a value between 120°C and 160°C. Setting the set temperature T2 to a value between 120°C and 160°C is appropriate as a condition for the condensation reaction of silane and silane agent in the second mixing step described above. By setting the set temperature T2 to a value between 120°C and 160°C, the method for generating a physical property prediction model can generate a calculation model 45a that takes into account conditions suitable for promoting the condensation reaction of silane and silane agent.

[0077] In the material property prediction model generation method, the base calculation table 22 includes at least one of the four basic arithmetic operations. This allows the material property prediction model generation method to generate feature quantities for rubber compounds by specifying an arithmetic operation in the base calculation table 22.

[0078] In the method for generating a physical property prediction model, the data mart 11 includes data on processing conditions for the rubber compound. This allows the physical property prediction model generation method to train the computational model 45a while reflecting the influence of the processing condition data 16.

[0079] The material property prediction model generation method further generates a composite calculation table 27 in which at least two of the features calculated in the base calculation step are selected and the calculation process is described, through a composite calculation generation step. The material property prediction model generation method calculates features based on the calculation process in the composite calculation table 27 through a composite calculation step. The material property prediction model generation method adds at least one of the features calculated in the composite calculation step to the training data mart through a training data generation step. As a result, the material property prediction model generation method can standardize the calculation process of the compositely calculated features and further improve user convenience.

[0080] In the material property prediction model generation method, the composite calculation table 27 includes at least one of the four basic arithmetic operations. This allows the material property prediction model generation method to generate complex features in rubber compounds by specifying an arithmetic operation in the composite calculation table 27.

[0081] In the material property prediction model generation method, the base calculation table 22 performs calculations within a material group containing multiple materials. This allows the material property prediction model generation method to generate features that take into account the overall blending amount and property values ​​of carbon materials, for example, when multiple carbon materials are blended.

[0082] The actions specified in the base calculation table 22 are not limited to arithmetic operations, but may also include numerical analyses such as DBP absorption, Cis%, Trans%, St%, and Vinyl%, as described above.

[0083] Furthermore, in the method for generating material property prediction models, the computational model 45a can use, for example, a random forest model, a gradient boosting decision tree model, and a generalized linear regression model. This allows the material property prediction model generation method to construct computational models that utilize the characteristics of each model.

[0084] (Embodiment 2) Figure 13 is a block diagram showing the functional configuration of the physical property prediction device 110 according to Embodiment 2. The physical property prediction device 110 has the same configuration as the physical property prediction model generation device 100 in Embodiment 1, but with the learning data generation unit 44 and the learning processing unit 46 removed. In addition, the calculation model 45a in the physical property prediction processing unit 45 of the physical property prediction device 110 uses the calculation model that has been learned by the physical property prediction model generation device 100.

[0085] The data mart generation unit 41 of the physical property prediction device 110 generates a data mart 11 consisting of formulation data 12, raw material data 14, mixing condition data 15, and processing condition data 16 for a new rubber compound whose physical properties are to be predicted. Since the data mart 11 generated here is not used to train the calculation model 45a, it is sufficient to have the formulation data 12, raw material data 14, mixing condition data 15, and processing condition data 16, and does not need to include the physical property data 13.

[0086] The base calculation unit 42 of the material property prediction device 110 generates a base calculation table 22, similar to Embodiment 1, and calculates feature quantities based on the calculations performed by the base calculation table 22. During the calculations performed by the base calculation table 22, the material group table 23, material category table 24, analysis group table 25, and analysis category table 26 are referenced. The composite calculation unit 43 generates a composite calculation table 27, similar to Embodiment 1, and calculates feature quantities based on the calculations performed by the composite calculation table 27.

[0087] The physical property prediction processing unit 45 uses at least one feature quantity calculated for the new rubber compound by the base calculation unit 42 and the composite calculation unit 43, as well as the compounding data 12, raw material data 14, mixing condition data 15, and processing condition data 16 of the new rubber compound, as explanatory variables. The physical property prediction processing unit 45 inputs the data used as explanatory variables into the trained calculation model 45a and predicts the physical properties.

[0088] The explanatory variables used by the physical property prediction processing unit 45 as input to the learned calculation model 45a during physical property prediction are the same as the explanatory variables used during the training of the calculation model 45a in the above-described embodiment 1. The physical property prediction processing unit 45 may also store the physical properties predicted for the new rubber compound by the calculation model 45a in the storage unit 10 as physical property data 13.

[0089] Next, the operation of the physical property prediction device 110 will be described. Figure 14 is a flowchart showing the procedure for the physical property prediction process. The data mart generation unit 41 of the calculation processing unit 40 generates a data mart 11 for the new rubber compound (S31). The processes from step S32 to step S35 are equivalent to the processes from step S2 to step S5 in Figure 10, and are omitted for brevity. In addition, the calculation processes in steps S33 and S35 are equivalent to the calculation processes described in Figures 11 and 12.

[0090] The physical property prediction processing unit 45 predicts the physical properties of the new rubber compound using the computational model 45a with the feature quantities calculated in steps S33 and S35 (S36), and then terminates the process.

[0091] In this embodiment, the physical property prediction method generates a data mart 11 in a data mart generation step, which includes the blending amounts and material property values ​​of multiple materials used in the production of a rubber compound. The physical property prediction method generates a base calculation table 22 in a base calculation generation step, which describes the materials and the calculation processes applied to them. The physical property prediction method calculates feature quantities based on the calculation processes in the base calculation table 22 in a base calculation step.

[0092] The physical property prediction method predicts the physical properties of a rubber compound by inputting at least one of the features calculated in the base calculation step and the data contained in the data mart 11 into a trained calculation model 45a in the physical property prediction step. This physical property prediction method improves user convenience by standardizing the calculation process for generating features.

[0093] The physical property prediction method generates a data mart 11 containing the mixing conditions in a mixing process in which multiple materials are mixed, in a data mart generation step, thereby allowing the physical properties of the rubber compound to be predicted based on a calculation model 45a that takes the mixing conditions into account. The mixing conditions should preferably include in the data mart 11 the set temperature T2, mixing time t2, and type of mixer in the second mixing process described above, which promotes the condensation reaction of silica and silane agents. Furthermore, the set temperature T2 should preferably be set to a value between 120°C and 160°C, which is suitable for promoting the condensation reaction of silane and silane agents.

[0094] The physical property prediction method further generates a composite calculation table 27 in a composite calculation generation step, selecting at least two of the features calculated in the base calculation step and describing the calculation process. The physical property prediction method calculates features based on the calculation process in the composite calculation table 27 in a composite calculation step. The physical property prediction method predicts the physical properties of the rubber compound by inputting at least one of the features calculated in the composite calculation step and the data contained in the data mart 11 into a trained calculation model 45a. This allows the physical property prediction method to standardize the calculation process of the compositely calculated features and further improve user convenience.

[0095] (Embodiment 3) Figure 15 is a block diagram showing the functional configuration of the formulation prediction device 120 according to Embodiment 3. The formulation prediction device 120 includes a formulation prediction processing unit 47. The formulation prediction processing unit 47 has a calculation model 45a that has been learned by the physical property prediction model generation device 100.

[0096] The data mart generation unit 41 in the formulation prediction device 120 generates a data mart 11 based on constraints related to the rubber compound for which the formulation is to be predicted. The data mart 11 includes constraints related to formulation data 12, raw material data 14, mixing condition data 15, and processing condition data 16 related to the rubber compound.

[0097] The base calculation unit 42, similar to Embodiment 1, generates a base calculation table 22 and has the function of calculating feature quantities based on the calculations performed by the base calculation table 22. During the calculations performed by the base calculation table 22, the material group table 23, material category table 24, analysis group table 25, and analysis category table 26 are referenced. The composite calculation unit 43, similar to Embodiment 1, generates a composite calculation table 27 and has the function of calculating feature quantities based on the calculations performed by the composite calculation table 27.

[0098] The formulation prediction processing unit 47 uses the computation model 45a to predict the formulation of a rubber compound as an inverse problem using a genetic algorithm method, based on the target physical properties and constraints regarding the amount of materials used in the rubber compound, raw material data, mixing condition data, and processing condition data. Alternatively, the formulation prediction processing unit 47 may also predict the formulation of a rubber compound as an inverse problem using known optimization methods, such as gradient descent. The formulation prediction processing unit 47 may also predict a rubber compound that satisfies the physical properties and the compounding cost by adding a target compounding cost in addition to the target physical properties. In this case, the computation model 45a outputs the compounding cost, and the compounding cost as physical property data is pre-learned as training data. For example, by including the cost of each material in the raw material data 14, and calculating the compounding cost by taking a weighted average using the amount of material used and the cost of the material, and registering it in the physical property data 13, the compounding cost can be treated in the same way as physical properties.

[0099] The formulation prediction processing unit 47 may add the formulation data, raw material data, mixing condition data, and processing condition data of the rubber compound assumed in the prediction process to the data mart 11, calculate feature quantities using the base calculation unit 42 and the composite calculation unit 43, and reflect them in the formulation prediction.

[0100] Figure 16 is a flowchart showing the procedure for the formulation prediction process. The formulation prediction processing unit 47 obtains the physical properties of the target rubber compound (S41) and the constraints of the rubber compound (S42). Using a trained computation model 45a, the formulation prediction processing unit 47 predicts the formulation of the rubber compound as an inverse problem using an optimization method based on the target physical properties and the constraints regarding the amount of material to be blended and the material properties in the rubber compound (S43), and then terminates the process. Note that the constraints may include at least one of the mixing conditions and processing conditions. The formulation prediction processing unit 47 may also be configured to predict, for a rubber compound having the target physical properties, the formulation (material ratio), the property values ​​and categorical variables of the raw materials, and at least one of the mixing conditions and processing conditions.

[0101] In this embodiment, the formulation prediction method generates a base calculation table 22 that describes materials and calculation processes applied to those materials in a base calculation generation step. The formulation prediction method calculates feature quantities based on the calculation processes in the base calculation table 22 in a base calculation step. In the formulation prediction step, the formulation prediction method uses a learned calculation model in which at least one of the feature quantities calculated in the base calculation step is added as an explanatory variable to predict the formulation of the rubber compound using an optimization method based on the target physical properties and constraints on the amount of material used and the property values ​​of the material in the rubber compound. This formulation prediction method improves user convenience by standardizing the calculation process for generating feature quantities and makes it possible to predict the formulation of a rubber compound that will obtain the target physical properties.

[0102] The formulation prediction method can predict the formulation of a rubber compound based on a calculation model 45a that takes into account the mixing conditions in a mixing process in which multiple materials are mixed. The mixing conditions should include in the data mart 11 the set temperature T2, mixing time t2, and type of mixer in the second mixing process described above, which promotes the condensation reaction of silica and silane agents. The set temperature T2 should be set to a value between 120°C and 160°C, which is suitable for promoting the condensation reaction of silane and silane agents. The formulation prediction method may also predict the formulation of the rubber compound by imposing constraints on the mixing conditions.

[0103] The formulation prediction method further generates a composite calculation table 27 in a composite calculation generation step, which selects at least two of the features calculated in the base calculation step and describes the calculation process. The formulation prediction method calculates features based on the calculation process in the composite calculation table 27 in a composite calculation step. The formulation prediction method predicts the rubber compound formulation in a formulation prediction step, which uses a learned calculation model in which at least one of the features calculated in the composite calculation step is added as an explanatory variable. As a result, the formulation prediction method can further improve user convenience by standardizing the calculation process of the compositely calculated features.

[0104] The technical ideas embodied in the above embodiments can be generalized to include the technical ideas described in the following items.

[0105] The first item is a method for generating a physical property prediction model, comprising: a data mart generation step of generating a data mart that includes the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound; a base calculation generation step of generating a base calculation table that describes the materials and the calculation processing applied to the materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; a training data generation step of generating a training data mart consisting of at least one of the feature quantities calculated by the base calculation step and the data included in the data mart; and a training step of training a learning-type calculation model that predicts the physical properties of a rubber compound based on the training data mart.

[0106] The second item is a method for generating a physical property prediction model as described in the first item, wherein the mixing conditions include the set temperature and mixing time in the step of promoting the condensation reaction of silica and silane agent.

[0107] The third item is the method for generating a physical property prediction model as described in item 2, which further includes the type of mixer as the mixing conditions.

[0108] The fourth item is a method for generating a physical property prediction model described in any one of the second or third items, wherein the set temperature is set to a value between 120°C and 160°C.

[0109] The fifth item is a method for generating a physical property prediction model described in any one of the first to fourth items, in which the base calculation table includes at least one of the four basic arithmetic operations.

[0110] The sixth item further comprises a composite calculation generation step of selecting at least two of the features calculated by the base calculation step and generating a composite calculation table that describes the calculation process, and a composite calculation step of calculating features based on the calculation process by the composite calculation table, wherein the training data generation step adds at least one of the features calculated by the composite calculation step to the training data mart, and is a method for generating a physical property prediction model according to any one of the first to fifth items.

[0111] The seventh item is a method for generating a physical property prediction model as described in item 6, wherein the composite calculation table includes at least one of the four basic arithmetic operations.

[0112] The eighth item is a method for generating a physical property prediction model described in any one of the first to seventh items, in which the base calculation table performs calculations within a material group that includes multiple materials.

[0113] The ninth item comprises a data mart generation unit that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound; a base calculation unit that generates a base calculation table describing the materials and the calculation processing applied to the materials, and calculates feature quantities based on the calculation processing performed by the base calculation table; and a training data generation unit that adds the feature quantities calculated by the base calculation unit to the data mart to generate a training data mart. This is a physical property prediction model generation device comprising a learning processing unit that trains a learning-type computational model for predicting the physical properties of rubber compound based on the learning data mart.

[0114] The tenth item is a physical property prediction method comprising: a data mart generation step of generating a data mart that includes the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the multiple materials; a base calculation generation step of generating a base calculation table that describes the materials and the calculation processing applied to the materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; and a physical property prediction step of inputting at least one of the feature quantities calculated by the base calculation step and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound.

[0115] The 11th item is a physical property prediction device comprising: a data mart generation unit that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the materials; a base calculation unit that generates a base calculation table describing the materials and calculation processing for the materials, and calculates feature quantities based on the calculation processing by the base calculation table; and a physical property prediction processing unit that inputs at least one of the feature quantities calculated by the base calculation unit and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound.

[0116] The 12th item is a property prediction program that causes a computer to perform the following steps: a data mart generation step that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the materials; a base calculation generation step that generates a base calculation table describing the materials and the calculation processing applied to the materials; a base calculation step that calculates feature quantities based on the calculation processing performed by the base calculation table; and a property prediction step that inputs at least one of the feature quantities calculated by the base calculation step and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound.

[0117] The 13th item is a formulation prediction method comprising: a base calculation generation step of generating a base calculation table that describes materials and calculation processing for said materials; a base calculation step of calculating feature quantities based on the calculation processing by the base calculation table; and a formulation prediction step of using a calculation model that has been trained with at least one of the feature quantities calculated by the base calculation step added as an explanatory variable, to predict the formulation of a rubber compound by an optimization method based on the target physical properties and constraints on the amount of said materials in the rubber compound, the property values ​​of said materials, and the mixing conditions in the process of mixing said materials.

[0118] The 14th item is a formulation prediction method comprising: a base calculation unit that generates a base calculation table describing materials and calculation processing for said materials, and calculates feature quantities based on the calculation processing by the base calculation table; and a formulation prediction processing unit that uses a calculation model learned by adding at least one of the feature quantities calculated by the base calculation unit as an explanatory variable, and predicts the formulation of a rubber compound by an optimization method based on the target physical properties and constraints regarding the amount of said materials in the rubber compound, the property values ​​of said materials, and the mixing conditions in the process of mixing said materials.

[0119] The 15th item is a formulation prediction program that causes a computer to execute the following steps: a base calculation generation step that generates a base calculation table describing materials and calculation processes applied to said materials; a base calculation step that calculates feature quantities based on the calculation processes performed by the base calculation table; and a formulation prediction step that uses a learned calculation model in which at least one of the feature quantities calculated by the base calculation step is added as an explanatory variable, and predicts the formulation of a rubber compound by an optimization method based on the target physical properties and constraints regarding the amount of said materials in the rubber compound, the property values ​​of said materials, and the mixing conditions in the process of mixing said materials.

[0120] The embodiments of the present invention have been described above. These embodiments are illustrative, and it will be understood by those skilled in the art that various modifications and changes are possible within the scope of the claims of the present invention, and that such modifications and changes are also within the scope of the claims of the present invention. Accordingly, the descriptions and drawings herein should be treated as illustrative rather than limiting. [Explanation of Symbols]

[0121] 11 Data marts, 22 Base calculation tables, 27 Compound calculation tables, 41 Data mart generation unit, 42 Base calculation unit, 43 Complex calculation unit, 44 Training data generation unit, 45 Physical property prediction processing unit, 45a Computation model, 46 Learning processing unit, 47 Formulation prediction processing unit, 100 Physical property prediction model generation device, 110 Physical property prediction device, 120 Formulation prediction device.

Claims

1. A data mart generation step that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound, A base calculation generation step that generates a base calculation table describing the material and the calculation process applied to the material, A base calculation step that calculates feature quantities based on the calculation process using the base calculation table, A training data generation step that generates a training data mart consisting of at least one of the features calculated by the base calculation step and the data included in the data mart, A learning step in which a learning-type computational model for predicting the physical properties of rubber compound is trained based on the learning data mart, A method for generating a material property prediction model that includes the following features.

2. The method for generating a physical property prediction model according to claim 1, wherein the mixing conditions include a set temperature and mixing time in a step that promotes the condensation reaction of silica and a silane agent.

3. The method for generating a physical property prediction model according to claim 2, wherein the mixing conditions further include the type of mixer.

4. The method for generating a physical property prediction model according to claim 2, wherein the set temperature is set to a value of 120°C or higher and 160°C or lower.

5. The method for generating a physical property prediction model according to claim 1, wherein the base calculation table includes at least one of the four basic arithmetic operations.

6. A composite calculation generation step that generates a composite calculation table describing the calculation process by selecting at least two of the feature quantities calculated in the base calculation step, The system further comprises a complex calculation step of calculating feature quantities based on the calculation process performed by the complex calculation table, The method for generating a physical property prediction model according to claim 1, wherein the training data generation step adds at least one of the features calculated by the composite calculation step to the training data mart.

7. The method for generating a physical property prediction model according to claim 6, wherein the composite calculation table includes at least one of the four basic arithmetic operations.

8. The method for generating a physical property prediction model according to any one of claims 1 to 7, wherein the base calculation table performs calculations within a material group that includes multiple materials.

9. A data mart generation unit that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, the mixing conditions in the process of mixing the multiple materials, and the physical properties of the rubber compound, A base calculation unit generates a base calculation table describing the material and the calculation process applied to the material, and calculates feature quantities based on the calculation process performed by the base calculation table, A training data generation unit generates a training data mart by adding the feature quantities calculated by the base calculation unit to the data mart, A learning processing unit that trains a learning-type computational model for predicting the physical properties of rubber compound based on the learning data mart, A physical property prediction model generation device equipped with the following features.

10. A data mart generation step that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the multiple materials, A base calculation generation step that generates a base calculation table describing the material and the calculation process applied to the material, A base calculation step that calculates feature quantities based on the calculation process using the base calculation table, A property prediction step in which at least one of the features calculated by the base calculation step and the data contained in the data mart are input into a trained calculation model to predict the physical properties of the rubber compound, A method for predicting material properties, comprising the following features.

11. A data mart generation unit that generates a data mart including the blending amounts of multiple materials used in the production of a rubber compound, the property values ​​of the materials, and the mixing conditions in the process of mixing the materials, A base calculation unit generates a base calculation table describing the material and the calculation process applied to the material, and calculates feature quantities based on the calculation process performed by the base calculation table, A property prediction processing unit that inputs at least one of the feature quantities calculated by the base calculation unit and the data contained in the data mart into a trained calculation model to predict the physical properties of the rubber compound, A physical property prediction device equipped with the following features.

Images